1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
|
;;; GNU Guix --- Functional package management for GNU
;;; Copyright © 2014, 2015, 2016 Ricardo Wurmus <rekado@elephly.net>
;;; Copyright © 2015, 2016 Ben Woodcroft <donttrustben@gmail.com>
;;; Copyright © 2015, 2016 Pjotr Prins <pjotr.guix@thebird.nl>
;;; Copyright © 2015 Andreas Enge <andreas@enge.fr>
;;; Copyright © 2016 Roel Janssen <roel@gnu.org>
;;; Copyright © 2016 Efraim Flashner <efraim@flashner.co.il>
;;;
;;; This file is part of GNU Guix.
;;;
;;; GNU Guix is free software; you can redistribute it and/or modify it
;;; under the terms of the GNU General Public License as published by
;;; the Free Software Foundation; either version 3 of the License, or (at
;;; your option) any later version.
;;;
;;; GNU Guix is distributed in the hope that it will be useful, but
;;; WITHOUT ANY WARRANTY; without even the implied warranty of
;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
;;; GNU General Public License for more details.
;;;
;;; You should have received a copy of the GNU General Public License
;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
(define-module (gnu packages bioinformatics)
#:use-module ((guix licenses) #:prefix license:)
#:use-module (guix packages)
#:use-module (guix utils)
#:use-module (guix download)
#:use-module (guix git-download)
#:use-module (guix build-system ant)
#:use-module (guix build-system gnu)
#:use-module (guix build-system cmake)
#:use-module (guix build-system perl)
#:use-module (guix build-system python)
#:use-module (guix build-system r)
#:use-module (guix build-system ruby)
#:use-module (guix build-system trivial)
#:use-module (gnu packages)
#:use-module (gnu packages autotools)
#:use-module (gnu packages algebra)
#:use-module (gnu packages base)
#:use-module (gnu packages bison)
#:use-module (gnu packages boost)
#:use-module (gnu packages compression)
#:use-module (gnu packages cpio)
#:use-module (gnu packages curl)
#:use-module (gnu packages documentation)
#:use-module (gnu packages datastructures)
#:use-module (gnu packages file)
#:use-module (gnu packages gawk)
#:use-module (gnu packages gcc)
#:use-module (gnu packages java)
#:use-module (gnu packages linux)
#:use-module (gnu packages machine-learning)
#:use-module (gnu packages maths)
#:use-module (gnu packages mpi)
#:use-module (gnu packages ncurses)
#:use-module (gnu packages pcre)
#:use-module (gnu packages perl)
#:use-module (gnu packages pkg-config)
#:use-module (gnu packages popt)
#:use-module (gnu packages protobuf)
#:use-module (gnu packages python)
#:use-module (gnu packages ruby)
#:use-module (gnu packages statistics)
#:use-module (gnu packages tbb)
#:use-module (gnu packages textutils)
#:use-module (gnu packages time)
#:use-module (gnu packages tls)
#:use-module (gnu packages vim)
#:use-module (gnu packages web)
#:use-module (gnu packages xml)
#:use-module (gnu packages zip)
#:use-module (srfi srfi-1))
(define-public aragorn
(package
(name "aragorn")
(version "1.2.36")
(source (origin
(method url-fetch)
(uri (string-append
"http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
version ".tgz"))
(sha256
(base32
"1dg7jlz1qpqy88igjxd6ncs11ccsirb36qv1z01a0np4i4jh61mb"))))
(build-system gnu-build-system)
(arguments
`(#:tests? #f ; there are no tests
#:phases
(modify-phases %standard-phases
(delete 'configure)
(replace 'build
(lambda _
(zero? (system* "gcc"
"-O3"
"-ffast-math"
"-finline-functions"
"-o"
"aragorn"
(string-append "aragorn" ,version ".c")))))
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let* ((out (assoc-ref outputs "out"))
(bin (string-append out "/bin"))
(man (string-append out "/share/man/man1")))
(mkdir-p bin)
(copy-file "aragorn"
(string-append bin "/aragorn"))
(mkdir-p man)
(copy-file "aragorn.1"
(string-append man "/aragorn.1")))
#t)))))
(home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
(synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
(description
"Aragorn identifies transfer RNA, mitochondrial RNA and
transfer-messenger RNA from nucleotide sequences, based on homology to known
tRNA consensus sequences and RNA structure. It also outputs the secondary
structure of the predicted RNA.")
(license license:gpl2)))
(define-public bamtools
(package
(name "bamtools")
(version "2.3.0")
(source (origin
(method url-fetch)
(uri (string-append
"https://github.com/pezmaster31/bamtools/archive/v"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"1brry29bw2xr2l9pqn240rkqwayg85b8qq78zk2zs6nlspk4d018"))))
(build-system cmake-build-system)
(arguments
`(#:tests? #f ;no "check" target
#:phases
(modify-phases %standard-phases
(add-before
'configure 'set-ldflags
(lambda* (#:key outputs #:allow-other-keys)
(setenv "LDFLAGS"
(string-append
"-Wl,-rpath="
(assoc-ref outputs "out") "/lib/bamtools")))))))
(inputs `(("zlib" ,zlib)))
(home-page "https://github.com/pezmaster31/bamtools")
(synopsis "C++ API and command-line toolkit for working with BAM data")
(description
"BamTools provides both a C++ API and a command-line toolkit for handling
BAM files.")
(license license:expat)))
(define-public bedops
(package
(name "bedops")
(version "2.4.14")
(source (origin
(method url-fetch)
(uri (string-append "https://github.com/bedops/bedops/archive/v"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"1kqbac547wyqma81cyky9n7mkgikjpsfd3nnmcm6hpqwanqgh10v"))))
(build-system gnu-build-system)
(arguments
'(#:tests? #f
#:make-flags (list (string-append "BINDIR=" %output "/bin"))
#:phases
(alist-cons-after
'unpack 'unpack-tarballs
(lambda _
;; FIXME: Bedops includes tarballs of minimally patched upstream
;; libraries jansson, zlib, and bzip2. We cannot just use stock
;; libraries because at least one of the libraries (zlib) is
;; patched to add a C++ function definition (deflateInit2cpp).
;; Until the Bedops developers offer a way to link against system
;; libraries we have to build the in-tree copies of these three
;; libraries.
;; See upstream discussion:
;; https://github.com/bedops/bedops/issues/124
;; Unpack the tarballs to benefit from shebang patching.
(with-directory-excursion "third-party"
(and (zero? (system* "tar" "xvf" "jansson-2.6.tar.bz2"))
(zero? (system* "tar" "xvf" "zlib-1.2.7.tar.bz2"))
(zero? (system* "tar" "xvf" "bzip2-1.0.6.tar.bz2"))))
;; Disable unpacking of tarballs in Makefile.
(substitute* "system.mk/Makefile.linux"
(("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
(("\\./configure") "CONFIG_SHELL=bash ./configure"))
(substitute* "third-party/zlib-1.2.7/Makefile.in"
(("^SHELL=.*$") "SHELL=bash\n")))
(alist-delete 'configure %standard-phases))))
(home-page "https://github.com/bedops/bedops")
(synopsis "Tools for high-performance genomic feature operations")
(description
"BEDOPS is a suite of tools to address common questions raised in genomic
studies---mostly with regard to overlap and proximity relationships between
data sets. It aims to be scalable and flexible, facilitating the efficient
and accurate analysis and management of large-scale genomic data.
BEDOPS provides tools that perform highly efficient and scalable Boolean and
other set operations, statistical calculations, archiving, conversion and
other management of genomic data of arbitrary scale. Tasks can be easily
split by chromosome for distributing whole-genome analyses across a
computational cluster.")
(license license:gpl2+)))
(define-public bedtools
(package
(name "bedtools")
(version "2.25.0")
(source (origin
(method url-fetch)
(uri (string-append "https://github.com/arq5x/bedtools2/archive/v"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"1ywcy3yfwzhl905b51l0ffjia55h75vv3mw5xkvib04pp6pj548m"))))
(build-system gnu-build-system)
(native-inputs `(("python" ,python-2)))
(inputs `(("samtools" ,samtools)
("zlib" ,zlib)))
(arguments
'(#:test-target "test"
#:phases
(modify-phases %standard-phases
(delete 'configure)
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
(for-each (lambda (file)
(install-file file bin))
(find-files "bin" ".*")))
#t)))))
(home-page "https://github.com/arq5x/bedtools2")
(synopsis "Tools for genome analysis and arithmetic")
(description
"Collectively, the bedtools utilities are a swiss-army knife of tools for
a wide-range of genomics analysis tasks. The most widely-used tools enable
genome arithmetic: that is, set theory on the genome. For example, bedtools
allows one to intersect, merge, count, complement, and shuffle genomic
intervals from multiple files in widely-used genomic file formats such as BAM,
BED, GFF/GTF, VCF.")
(license license:gpl2)))
(define-public bioawk
(package
(name "bioawk")
(version "1.0")
(source (origin
(method url-fetch)
(uri (string-append "https://github.com/lh3/bioawk/archive/v"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
(build-system gnu-build-system)
(inputs
`(("zlib" ,zlib)))
(native-inputs
`(("bison" ,bison)))
(arguments
`(#:tests? #f ; There are no tests to run.
;; Bison must generate files, before other targets can build.
#:parallel-build? #f
#:phases
(modify-phases %standard-phases
(delete 'configure) ; There is no configure phase.
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let* ((out (assoc-ref outputs "out"))
(bin (string-append out "/bin"))
(man (string-append out "/share/man/man1")))
(mkdir-p man)
(copy-file "awk.1" (string-append man "/bioawk.1"))
(install-file "bioawk" bin)))))))
(home-page "https://github.com/lh3/bioawk")
(synopsis "AWK with bioinformatics extensions")
(description "Bioawk is an extension to Brian Kernighan's awk, adding the
support of several common biological data formats, including optionally gzip'ed
BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
also adds a few built-in functions and a command line option to use TAB as the
input/output delimiter. When the new functionality is not used, bioawk is
intended to behave exactly the same as the original BWK awk.")
(license license:x11)))
(define-public python2-pybedtools
(package
(name "python2-pybedtools")
(version "0.6.9")
(source (origin
(method url-fetch)
(uri (string-append
"https://pypi.python.org/packages/source/p/pybedtools/pybedtools-"
version ".tar.gz"))
(sha256
(base32
"1ldzdxw1p4y3g2ignmggsdypvqkcwqwzhdha4rbgpih048z5p4an"))))
(build-system python-build-system)
(arguments `(#:python ,python-2)) ; no Python 3 support
(inputs
`(("python-cython" ,python2-cython)
("python-matplotlib" ,python2-matplotlib)))
(propagated-inputs
`(("bedtools" ,bedtools)
("samtools" ,samtools)))
(native-inputs
`(("python-pyyaml" ,python2-pyyaml)
("python-nose" ,python2-nose)
("python-setuptools" ,python2-setuptools)))
(home-page "https://pythonhosted.org/pybedtools/")
(synopsis "Python wrapper for BEDtools programs")
(description
"pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
which are widely used for genomic interval manipulation or \"genome algebra\".
pybedtools extends BEDTools by offering feature-level manipulations from with
Python.")
(license license:gpl2+)))
(define-public bioperl-minimal
(let* ((inputs `(("perl-module-build" ,perl-module-build)
("perl-data-stag" ,perl-data-stag)
("perl-libwww" ,perl-libwww)
("perl-uri" ,perl-uri)))
(transitive-inputs
(map (compose package-name cadr)
(delete-duplicates
(concatenate
(map (compose package-transitive-target-inputs cadr) inputs))))))
(package
(name "bioperl-minimal")
(version "1.6.924")
(source
(origin
(method url-fetch)
(uri (string-append "mirror://cpan/authors/id/C/CJ/CJFIELDS/BioPerl-"
version ".tar.gz"))
(sha256
(base32
"1l3npcvvvwjlhkna9dndpfv1hklhrgva013kw96m0n1wpd37ask1"))))
(build-system perl-build-system)
(arguments
`(#:phases
(modify-phases %standard-phases
(add-after
'install 'wrap-programs
(lambda* (#:key outputs #:allow-other-keys)
;; Make sure all executables in "bin" find the required Perl
;; modules at runtime. As the PERL5LIB variable contains also
;; the paths of native inputs, we pick the transitive target
;; inputs from %build-inputs.
(let* ((out (assoc-ref outputs "out"))
(bin (string-append out "/bin/"))
(path (string-join
(cons (string-append out "/lib/perl5/site_perl")
(map (lambda (name)
(assoc-ref %build-inputs name))
',transitive-inputs))
":")))
(for-each (lambda (file)
(wrap-program file
`("PERL5LIB" ":" prefix (,path))))
(find-files bin "\\.pl$"))
#t))))))
(inputs inputs)
(native-inputs
`(("perl-test-most" ,perl-test-most)))
(home-page "http://search.cpan.org/dist/BioPerl")
(synopsis "Bioinformatics toolkit")
(description
"BioPerl is the product of a community effort to produce Perl code which
is useful in biology. Examples include Sequence objects, Alignment objects
and database searching objects. These objects not only do what they are
advertised to do in the documentation, but they also interact - Alignment
objects are made from the Sequence objects, Sequence objects have access to
Annotation and SeqFeature objects and databases, Blast objects can be
converted to Alignment objects, and so on. This means that the objects
provide a coordinated and extensible framework to do computational biology.")
(license (package-license perl)))))
(define-public python-biopython
(package
(name "python-biopython")
(version "1.66")
(source (origin
(method url-fetch)
;; use PyPi rather than biopython.org to ease updating
(uri (pypi-uri "biopython" version))
(sha256
(base32
"1gdv92593klimg22icf5j9by7xiq86jnwzkpz4abaa05ylkdf6hp"))))
(build-system python-build-system)
(inputs
`(("python-numpy" ,python-numpy)))
(native-inputs
`(("python-setuptools" ,python2-setuptools)))
(home-page "http://biopython.org/")
(synopsis "Tools for biological computation in Python")
(description
"Biopython is a set of tools for biological computation including parsers
for bioinformatics files into Python data structures; interfaces to common
bioinformatics programs; a standard sequence class and tools for performing
common operations on them; code to perform data classification; code for
dealing with alignments; code making it easy to split up parallelizable tasks
into separate processes; and more.")
(license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
(define-public python2-biopython
(package (inherit (package-with-python2 python-biopython))
(inputs
`(("python2-numpy" ,python2-numpy)))))
(define-public blast+
(package
(name "blast+")
(version "2.2.31")
(source (origin
(method url-fetch)
(uri (string-append
"ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
version "/ncbi-blast-" version "+-src.tar.gz"))
(sha256
(base32
"19gq6as4k1jrgsd26158ads6h7v4jca3h4r5dzg1y0m6ya50x5ph"))
(modules '((guix build utils)))
(snippet
'(begin
;; Remove bundled bzip2 and zlib
(delete-file-recursively "c++/src/util/compress/bzip2")
(delete-file-recursively "c++/src/util/compress/zlib")
(substitute* "c++/src/util/compress/Makefile.in"
(("bzip2 zlib api") "api"))
;; Remove useless msbuild directory
(delete-file-recursively
"c++/src/build-system/project_tree_builder/msbuild")
#t))))
(build-system gnu-build-system)
(arguments
`(;; There are three(!) tests for this massive library, and all fail with
;; "unparsable timing stats".
;; ERR [127] -- [util/regexp] test_pcre.sh (unparsable timing stats)
;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
#:tests? #f
#:out-of-source? #t
#:parallel-build? #f ; not supported
#:phases
(modify-phases %standard-phases
(add-before
'configure 'set-HOME
;; $HOME needs to be set at some point during the configure phase
(lambda _ (setenv "HOME" "/tmp") #t))
(add-after
'unpack 'enter-dir
(lambda _ (chdir "c++") #t))
(add-after
'enter-dir 'fix-build-system
(lambda _
(define (which* cmd)
(cond ((string=? cmd "date")
;; make call to "date" deterministic
"date -d @0")
((which cmd)
=> identity)
(else
(format (current-error-port)
"WARNING: Unable to find absolute path for ~s~%"
cmd)
#f)))
;; Rewrite hardcoded paths to various tools
(substitute* (append '("src/build-system/configure.ac"
"src/build-system/configure"
"scripts/common/impl/if_diff.sh"
"scripts/common/impl/run_with_lock.sh"
"src/build-system/Makefile.configurables.real"
"src/build-system/Makefile.in.top"
"src/build-system/Makefile.meta.gmake=no"
"src/build-system/Makefile.meta.in"
"src/build-system/Makefile.meta_l"
"src/build-system/Makefile.meta_p"
"src/build-system/Makefile.meta_r"
"src/build-system/Makefile.mk.in"
"src/build-system/Makefile.requirements"
"src/build-system/Makefile.rules_with_autodep.in")
(find-files "scripts/common/check" "\\.sh$"))
(("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
(or (which* cmd) all)))
(substitute* (find-files "src/build-system" "^config.*")
(("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
(("^PATH=.*") ""))
;; rewrite "/var/tmp" in check script
(substitute* "scripts/common/check/check_make_unix.sh"
(("/var/tmp") "/tmp"))
;; do not reset PATH
(substitute* (find-files "scripts/common/impl/" "\\.sh$")
(("^ *PATH=.*") "")
(("action=/bin/") "action=")
(("export PATH") ":"))
#t))
(replace
'configure
(lambda* (#:key inputs outputs #:allow-other-keys)
(let ((out (assoc-ref outputs "out"))
(lib (string-append (assoc-ref outputs "lib") "/lib"))
(include (string-append (assoc-ref outputs "include")
"/include/ncbi-tools++")))
;; The 'configure' script doesn't recognize things like
;; '--enable-fast-install'.
(zero? (system* "./configure.orig"
(string-append "--with-build-root=" (getcwd) "/build")
(string-append "--prefix=" out)
(string-append "--libdir=" lib)
(string-append "--includedir=" include)
(string-append "--with-bz2="
(assoc-ref inputs "bzip2"))
(string-append "--with-z="
(assoc-ref inputs "zlib"))
;; Each library is built twice by default, once
;; with "-static" in its name, and again
;; without.
"--without-static"
"--with-dll"))))))))
(outputs '("out" ; 19 MB
"lib" ; 203 MB
"include")) ; 32 MB
(inputs
`(("bzip2" ,bzip2)
("zlib" ,zlib)))
(native-inputs
`(("cpio" ,cpio)))
(home-page "http://blast.ncbi.nlm.nih.gov")
(synopsis "Basic local alignment search tool")
(description
"BLAST is a popular method of performing a DNA or protein sequence
similarity search, using heuristics to produce results quickly. It also
calculates an “expect value” that estimates how many matches would have
occurred at a given score by chance, which can aid a user in judging how much
confidence to have in an alignment.")
;; Most of the sources are in the public domain, with the following
;; exceptions:
;; * Expat:
;; * ./c++/include/util/bitset/
;; * ./c++/src/html/ncbi_menu*.js
;; * Boost license:
;; * ./c++/include/util/impl/floating_point_comparison.hpp
;; * LGPL 2+:
;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
;; * ASL 2.0:
;; * ./c++/src/corelib/teamcity_*
(license (list license:public-domain
license:expat
license:boost1.0
license:lgpl2.0+
license:asl2.0))))
(define-public bless
(package
(name "bless")
(version "1p02")
(source (origin
(method url-fetch)
(uri (string-append "mirror://sourceforge/bless-ec/bless.v"
version ".tgz"))
(sha256
(base32
"0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
(modules '((guix build utils)))
(snippet
`(begin
;; Remove bundled boost, pigz, zlib, and .git directory
;; FIXME: also remove bundled sources for murmurhash3 and
;; kmc once packaged.
(delete-file-recursively "boost")
(delete-file-recursively "pigz")
(delete-file-recursively "google-sparsehash")
(delete-file-recursively "zlib")
(delete-file-recursively ".git")
#t))))
(build-system gnu-build-system)
(arguments
'(#:tests? #f ;no "check" target
#:make-flags
(list (string-append "ZLIB="
(assoc-ref %build-inputs "zlib")
"/lib/libz.a")
(string-append "LDFLAGS="
(string-join '("-lboost_filesystem"
"-lboost_system"
"-lboost_iostreams"
"-lz"
"-fopenmp"
"-std=c++11"))))
#:phases
(modify-phases %standard-phases
(add-after 'unpack 'do-not-build-bundled-pigz
(lambda* (#:key inputs outputs #:allow-other-keys)
(substitute* "Makefile"
(("cd pigz/pigz-2.3.3; make") ""))
#t))
(add-after 'unpack 'patch-paths-to-executables
(lambda* (#:key inputs outputs #:allow-other-keys)
(substitute* "parse_args.cpp"
(("kmc_binary = .*")
(string-append "kmc_binary = \""
(assoc-ref outputs "out")
"/bin/kmc\";"))
(("pigz_binary = .*")
(string-append "pigz_binary = \""
(assoc-ref inputs "pigz")
"/bin/pigz\";")))
#t))
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
(for-each (lambda (file)
(install-file file bin))
'("bless" "kmc/bin/kmc"))
#t)))
(delete 'configure))))
(native-inputs
`(("perl" ,perl)))
(inputs
`(("openmpi" ,openmpi)
("boost" ,boost)
("sparsehash" ,sparsehash)
("pigz" ,pigz)
("zlib" ,zlib)))
(supported-systems '("x86_64-linux"))
(home-page "http://sourceforge.net/p/bless-ec/wiki/Home/")
(synopsis "Bloom-filter-based error correction tool for NGS reads")
(description
"@dfn{Bloom-filter-based error correction solution for high-throughput
sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
correction tool for genomic reads produced by @dfn{Next-generation
sequencing} (NGS). BLESS produces accurate correction results with much less
memory compared with previous solutions and is also able to tolerate a higher
false-positive rate. BLESS can extend reads like DNA assemblers to correct
errors at the end of reads.")
(license license:gpl3+)))
(define-public bowtie
(package
(name "bowtie")
(version "2.2.6")
(source (origin
(method url-fetch)
(uri (string-append "https://github.com/BenLangmead/bowtie2/archive/v"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"1ssfvymxfrap6f9pf86s9bvsbqdgka4abr2r7j3mgr4w1l289m86"))
(modules '((guix build utils)))
(snippet
'(substitute* "Makefile"
;; replace BUILD_HOST and BUILD_TIME for deterministic build
(("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
(("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
(build-system gnu-build-system)
(inputs `(("perl" ,perl)
("perl-clone" ,perl-clone)
("perl-test-deep" ,perl-test-deep)
("perl-test-simple" ,perl-test-simple)
("python" ,python-2)
("tbb" ,tbb)))
(arguments
'(#:make-flags
(list "allall"
"WITH_TBB=1"
(string-append "prefix=" (assoc-ref %outputs "out")))
#:phases
(alist-delete
'configure
(alist-replace
'check
(lambda* (#:key outputs #:allow-other-keys)
(system* "perl"
"scripts/test/simple_tests.pl"
"--bowtie2=./bowtie2"
"--bowtie2-build=./bowtie2-build"))
%standard-phases))))
(home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
(synopsis "Fast and sensitive nucleotide sequence read aligner")
(description
"Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
reads to long reference sequences. It is particularly good at aligning reads
of about 50 up to 100s or 1,000s of characters, and particularly good at
aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
genome with an FM Index to keep its memory footprint small: for the human
genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
gapped, local, and paired-end alignment modes.")
(supported-systems '("x86_64-linux"))
(license license:gpl3+)))
(define-public tophat
(package
(name "tophat")
(version "2.1.0")
(source (origin
(method url-fetch)
(uri (string-append
"http://ccb.jhu.edu/software/tophat/downloads/tophat-"
version ".tar.gz"))
(sha256
(base32
"168zlzykq622zbgkh90a90f1bdgsxkscq2zxzbj8brq80hbjpyp7"))
(patches (search-patches "tophat-build-with-later-seqan.patch"))
(modules '((guix build utils)))
(snippet
'(begin
;; Remove bundled SeqAn and samtools
(delete-file-recursively "src/SeqAn-1.3")
(delete-file-recursively "src/samtools-0.1.18")
#t))))
(build-system gnu-build-system)
(arguments
'(#:parallel-build? #f ; not supported
#:phases
(modify-phases %standard-phases
(add-after 'unpack 'use-system-samtools
(lambda* (#:key inputs #:allow-other-keys)
(substitute* "src/Makefile.in"
(("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
(("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
(("SAMPROG = samtools_0\\.1\\.18") "")
(("\\$\\(samtools_0_1_18_SOURCES\\)") "")
(("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
(substitute* '("src/common.cpp"
"src/tophat.py")
(("samtools_0.1.18") (which "samtools")))
(substitute* '("src/common.h"
"src/bam2fastx.cpp")
(("#include \"bam.h\"") "#include <samtools/bam.h>")
(("#include \"sam.h\"") "#include <samtools/sam.h>"))
(substitute* '("src/bwt_map.h"
"src/map2gtf.h"
"src/align_status.h")
(("#include <bam.h>") "#include <samtools/bam.h>")
(("#include <sam.h>") "#include <samtools/sam.h>"))
#t)))))
(inputs
`(("boost" ,boost)
("bowtie" ,bowtie)
("samtools" ,samtools-0.1)
("ncurses" ,ncurses)
("python" ,python-2)
("perl" ,perl)
("zlib" ,zlib)
("seqan" ,seqan)))
(home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
(synopsis "Spliced read mapper for RNA-Seq data")
(description
"TopHat is a fast splice junction mapper for nucleotide sequence
reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
mammalian-sized genomes using the ultra high-throughput short read
aligner Bowtie, and then analyzes the mapping results to identify
splice junctions between exons.")
;; TopHat is released under the Boost Software License, Version 1.0
;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
(license license:boost1.0)))
(define-public bwa
(package
(name "bwa")
(version "0.7.12")
(source (origin
(method url-fetch)
(uri (string-append "mirror://sourceforge/bio-bwa/bwa-"
version ".tar.bz2"))
(sha256
(base32
"1330dpqncv0px3pbhjzz1gwgg39kkcv2r9qp2xs0sixf8z8wl7bh"))))
(build-system gnu-build-system)
(arguments
'(#:tests? #f ;no "check" target
#:phases
(alist-replace
'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append
(assoc-ref outputs "out") "/bin"))
(doc (string-append
(assoc-ref outputs "out") "/share/doc/bwa"))
(man (string-append
(assoc-ref outputs "out") "/share/man/man1")))
(mkdir-p bin)
(mkdir-p doc)
(mkdir-p man)
(install-file "bwa" bin)
(install-file "README.md" doc)
(install-file "bwa.1" man)))
;; no "configure" script
(alist-delete 'configure %standard-phases))))
(inputs `(("zlib" ,zlib)))
;; Non-portable SSE instructions are used so building fails on platforms
;; other than x86_64.
(supported-systems '("x86_64-linux"))
(home-page "http://bio-bwa.sourceforge.net/")
(synopsis "Burrows-Wheeler sequence aligner")
(description
"BWA is a software package for mapping low-divergent sequences against a
large reference genome, such as the human genome. It consists of three
algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
designed for Illumina sequence reads up to 100bp, while the rest two for
longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
features such as long-read support and split alignment, but BWA-MEM, which is
the latest, is generally recommended for high-quality queries as it is faster
and more accurate. BWA-MEM also has better performance than BWA-backtrack for
70-100bp Illumina reads.")
(license license:gpl3+)))
(define-public bwa-pssm
(package (inherit bwa)
(name "bwa-pssm")
(version "0.5.11")
(source (origin
(method url-fetch)
(uri (string-append "https://github.com/pkerpedjiev/bwa-pssm/"
"archive/" version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"02p7mpbs4mlxmn84g2x4ghak638vbj4lqix2ipx5g84pz9bhdavg"))))
(build-system gnu-build-system)
(inputs
`(("gdsl" ,gdsl)
("zlib" ,zlib)
("perl" ,perl)))
(home-page "http://bwa-pssm.binf.ku.dk/")
(synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
(description
"BWA-PSSM is a probabilistic short genomic sequence read aligner based on
the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
existing aligners it is fast and sensitive. Unlike most other aligners,
however, it is also adaptible in the sense that one can direct the alignment
based on known biases within the data set. It is coded as a modification of
the original BWA alignment program and shares the genome index structure as
well as many of the command line options.")
(license license:gpl3+)))
(define-public python2-bx-python
(package
(name "python2-bx-python")
(version "0.7.2")
(source (origin
(method url-fetch)
(uri (string-append
"https://pypi.python.org/packages/source/b/bx-python/bx-python-"
version ".tar.gz"))
(sha256
(base32
"0ld49idhc5zjdvbhvjq1a2qmpjj7h5v58rqr25dzmfq7g34b50xh"))
(modules '((guix build utils)))
(snippet
'(substitute* "setup.py"
;; remove dependency on outdated "distribute" module
(("^from distribute_setup import use_setuptools") "")
(("^use_setuptools\\(\\)") "")))))
(build-system python-build-system)
(arguments
`(#:tests? #f ;tests fail because test data are not included
#:python ,python-2))
(inputs
`(("python-numpy" ,python2-numpy)
("zlib" ,zlib)))
(native-inputs
`(("python-nose" ,python2-nose)
("python-setuptools" ,python2-setuptools)))
(home-page "http://bitbucket.org/james_taylor/bx-python/")
(synopsis "Tools for manipulating biological data")
(description
"bx-python provides tools for manipulating biological data, particularly
multiple sequence alignments.")
(license license:expat)))
(define-public python-pysam
(package
(name "python-pysam")
(version "0.8.4")
(source (origin
(method url-fetch)
(uri (pypi-uri "pysam" version))
(sha256
(base32
"1slx5mb94mzm5qzk52q270sab0sar95j67w1g1k452nz3s9j7krh"))))
(build-system python-build-system)
(arguments
`(#:tests? #f ; tests are excluded in the manifest
#:phases
(alist-cons-before
'build 'set-flags
(lambda _
(setenv "LDFLAGS" "-lncurses")
(setenv "CFLAGS" "-D_CURSES_LIB=1"))
%standard-phases)))
(inputs
`(("ncurses" ,ncurses)
("zlib" ,zlib)))
(native-inputs
`(("python-cython" ,python-cython)
("python-setuptools" ,python-setuptools)))
(home-page "https://github.com/pysam-developers/pysam")
(synopsis "Python bindings to the SAMtools C API")
(description
"Pysam is a Python module for reading and manipulating files in the
SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
also includes an interface for tabix.")
(license license:expat)))
(define-public python2-pysam
(package-with-python2 python-pysam))
(define-public python-twobitreader
(package
(name "python-twobitreader")
(version "3.1.2")
(source (origin
(method url-fetch)
(uri (pypi-uri "twobitreader" version))
(sha256
(base32
"0y408fp6psqzwxpcpqn0wp7fr41dwz8d54wpj6j261fj5q8vs169"))))
(properties `((python2-variant . ,(delay python2-twobitreader))))
(build-system python-build-system)
(native-inputs
`(("python-sphinx" ,python-sphinx)))
(home-page "https://github.com/benjschiller/twobitreader")
(synopsis "Python library for reading .2bit files")
(description
"twobitreader is a Python library for reading .2bit files as used by the
UCSC genome browser.")
(license license:artistic2.0)))
(define-public python2-twobitreader
(let ((base (package-with-python2 (strip-python2-variant python-twobitreader))))
(package
(inherit base)
(native-inputs `(("python2-setuptools" ,python2-setuptools)
,@(package-native-inputs base))))))
(define-public python-plastid
(package
(name "python-plastid")
(version "0.4.5")
(source (origin
(method url-fetch)
(uri (pypi-uri "plastid" version))
(sha256
(base32
"1nhxw8a5gn9as58i2ih52c5cjwj48ik418pzsjwph3s66mmy9yvq"))))
(properties `((python2-variant . ,(delay python2-plastid))))
(build-system python-build-system)
(arguments
;; Some test files are not included.
`(#:tests? #f))
(propagated-inputs
`(("python-numpy" ,python-numpy)
("python-scipy" ,python-scipy)
("python-pandas" ,python-pandas)
("python-pysam" ,python-pysam)
("python-matplotlib" ,python-matplotlib)
("python-biopython" ,python-biopython)
("python-twobitreader" ,python-twobitreader)))
(native-inputs
`(("python-cython" ,python-cython)
("python-nose" ,python-nose)))
(home-page "https://github.com/joshuagryphon/plastid")
(synopsis "Python library for genomic analysis")
(description
"plastid is a Python library for genomic analysis – in particular,
high-throughput sequencing data – with an emphasis on simplicity.")
(license license:bsd-3)))
(define-public python2-plastid
(let ((base (package-with-python2 (strip-python2-variant python-plastid))))
(package
(inherit base)
;; setuptools is required at runtime
(propagated-inputs `(("python2-setuptools" ,python2-setuptools)
,@(package-propagated-inputs base))))))
(define-public cd-hit
(package
(name "cd-hit")
(version "4.6.5")
(source (origin
(method url-fetch)
(uri (string-append "https://github.com/weizhongli/cdhit"
"/releases/download/V" version
"/cd-hit-v" version "-2016-0304.tar.gz"))
(sha256
(base32
"15db0hq38yyifwqx9b6l34z14jcq576dmjavhj8a426c18lvnhp3"))))
(build-system gnu-build-system)
(arguments
`(#:tests? #f ; there are no tests
#:make-flags
;; Executables are copied directly to the PREFIX.
(list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin"))
#:phases
(modify-phases %standard-phases
;; No "configure" script
(delete 'configure)
;; Remove sources of non-determinism
(add-after 'unpack 'be-timeless
(lambda _
(substitute* "cdhit-utility.c++"
((" \\(built on \" __DATE__ \"\\)") ""))
(substitute* "cdhit-common.c++"
(("__DATE__") "\"0\"")
(("\", %s, \" __TIME__ \"\\\\n\", date") ""))
#t))
;; The "install" target does not create the target directory
(add-before 'install 'create-target-dir
(lambda* (#:key outputs #:allow-other-keys)
(mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
#t)))))
(inputs
`(("perl" ,perl)))
(home-page "http://weizhongli-lab.org/cd-hit/")
(synopsis "Cluster and compare protein or nucleotide sequences")
(description
"CD-HIT is a program for clustering and comparing protein or nucleotide
sequences. CD-HIT is designed to be fast and handle extremely large
databases.")
;; The manual says: "It can be copied under the GNU General Public License
;; version 2 (GPLv2)."
(license license:gpl2)))
(define-public clipper
(package
(name "clipper")
(version "0.3.0")
(source (origin
(method url-fetch)
(uri (string-append
"https://github.com/YeoLab/clipper/archive/"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"1q7jpimsqln7ic44i8v2rx2haj5wvik8hc1s2syd31zcn0xk1iyq"))
(modules '((guix build utils)))
(snippet
;; remove unnecessary setup dependency
'(substitute* "setup.py"
(("setup_requires = .*") "")))))
(build-system python-build-system)
(arguments `(#:python ,python-2)) ; only Python 2 is supported
(inputs
`(("htseq" ,htseq)
("python-pybedtools" ,python2-pybedtools)
("python-cython" ,python2-cython)
("python-scikit-learn" ,python2-scikit-learn)
("python-matplotlib" ,python2-matplotlib)
("python-pysam" ,python2-pysam)
("python-numpy" ,python2-numpy)
("python-scipy" ,python2-scipy)))
(native-inputs
`(("python-mock" ,python2-mock) ; for tests
("python-pytz" ,python2-pytz) ; for tests
("python-setuptools" ,python2-setuptools)))
(home-page "https://github.com/YeoLab/clipper")
(synopsis "CLIP peak enrichment recognition")
(description
"CLIPper is a tool to define peaks in CLIP-seq datasets.")
(license license:gpl2)))
(define-public codingquarry
(package
(name "codingquarry")
(version "2.0")
(source (origin
(method url-fetch)
(uri (string-append
"mirror://sourceforge/codingquarry/CodingQuarry_v"
version ".tar.gz"))
(sha256
(base32
"0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
(build-system gnu-build-system)
(arguments
'(#:tests? #f ; no "check" target
#:phases
(modify-phases %standard-phases
(delete 'configure)
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let* ((out (assoc-ref outputs "out"))
(bin (string-append out "/bin"))
(doc (string-append out "/share/doc/codingquarry")))
(install-file "INSTRUCTIONS.pdf" doc)
(copy-recursively "QuarryFiles"
(string-append out "/QuarryFiles"))
(install-file "CodingQuarry" bin)
(install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin)))))))
(inputs `(("openmpi" ,openmpi)))
(native-search-paths
(list (search-path-specification
(variable "QUARRY_PATH")
(files '("QuarryFiles")))))
(native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
(synopsis "Fungal gene predictor")
(description "CodingQuarry is a highly accurate, self-training GHMM fungal
gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
(home-page "https://sourceforge.net/projects/codingquarry/")
(license license:gpl3+)))
(define-public couger
(package
(name "couger")
(version "1.8.2")
(source (origin
(method url-fetch)
(uri (string-append
"http://couger.oit.duke.edu/static/assets/COUGER"
version ".zip"))
(sha256
(base32
"04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
(build-system gnu-build-system)
(arguments
`(#:tests? #f
#:phases
(modify-phases %standard-phases
(delete 'configure)
(delete 'build)
(replace
'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((out (assoc-ref outputs "out")))
(copy-recursively "src" (string-append out "/src"))
(mkdir (string-append out "/bin"))
;; Add "src" directory to module lookup path.
(substitute* "couger"
(("from argparse")
(string-append "import sys\nsys.path.append(\""
out "\")\nfrom argparse")))
(copy-file "couger" (string-append out "/bin/couger")))
#t))
(add-after
'install 'wrap-program
(lambda* (#:key inputs outputs #:allow-other-keys)
;; Make sure 'couger' runs with the correct PYTHONPATH.
(let* ((out (assoc-ref outputs "out"))
(path (getenv "PYTHONPATH")))
(wrap-program (string-append out "/bin/couger")
`("PYTHONPATH" ":" prefix (,path))))
#t)))))
(inputs
`(("python" ,python-2)
("python2-pillow" ,python2-pillow)
("python2-numpy" ,python2-numpy)
("python2-scipy" ,python2-scipy)
("python2-matplotlib" ,python2-matplotlib)))
(propagated-inputs
`(("r" ,r)
("libsvm" ,libsvm)
("randomjungle" ,randomjungle)))
(native-inputs
`(("unzip" ,unzip)))
(home-page "http://couger.oit.duke.edu")
(synopsis "Identify co-factors in sets of genomic regions")
(description
"COUGER can be applied to any two sets of genomic regions bound by
paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
putative co-factors that provide specificity to each TF. The framework
determines the genomic targets uniquely-bound by each TF, and identifies a
small set of co-factors that best explain the in vivo binding differences
between the two TFs.
COUGER uses classification algorithms (support vector machines and random
forests) with features that reflect the DNA binding specificities of putative
co-factors. The features are generated either from high-throughput TF-DNA
binding data (from protein binding microarray experiments), or from large
collections of DNA motifs.")
(license license:gpl3+)))
(define-public clustal-omega
(package
(name "clustal-omega")
(version "1.2.1")
(source (origin
(method url-fetch)
(uri (string-append
"http://www.clustal.org/omega/clustal-omega-"
version ".tar.gz"))
(sha256
(base32
"02ibkx0m0iwz8nscg998bh41gg251y56cgh86bvyrii5m8kjgwqf"))))
(build-system gnu-build-system)
(inputs
`(("argtable" ,argtable)))
(home-page "http://www.clustal.org/omega/")
(synopsis "Multiple sequence aligner for protein and DNA/RNA")
(description
"Clustal-Omega is a general purpose multiple sequence alignment (MSA)
program for protein and DNA/RNA. It produces high quality MSAs and is capable
of handling data-sets of hundreds of thousands of sequences in reasonable
time.")
(license license:gpl2+)))
(define-public crossmap
(package
(name "crossmap")
(version "0.2.1")
(source (origin
(method url-fetch)
(uri (string-append "mirror://sourceforge/crossmap/CrossMap-"
version ".tar.gz"))
(sha256
(base32
"07y179f63d7qnzdvkqcziwk9bs3k4zhp81q392fp1hwszjdvy22f"))
;; This patch has been sent upstream already and is available
;; for download from Sourceforge, but it has not been merged.
(patches (search-patches "crossmap-allow-system-pysam.patch"))
(modules '((guix build utils)))
;; remove bundled copy of pysam
(snippet
'(delete-file-recursively "lib/pysam"))))
(build-system python-build-system)
(arguments
`(#:python ,python-2
#:phases
(alist-cons-after
'unpack 'set-env
(lambda _ (setenv "CROSSMAP_USE_SYSTEM_PYSAM" "1"))
%standard-phases)))
(inputs
`(("python-numpy" ,python2-numpy)
("python-pysam" ,python2-pysam)
("zlib" ,zlib)))
(native-inputs
`(("python-cython" ,python2-cython)
("python-nose" ,python2-nose)
("python-setuptools" ,python2-setuptools)))
(home-page "http://crossmap.sourceforge.net/")
(synopsis "Convert genome coordinates between assemblies")
(description
"CrossMap is a program for conversion of genome coordinates or annotation
files between different genome assemblies. It supports most commonly used
file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
(license license:gpl2+)))
(define-public cufflinks
(package
(name "cufflinks")
(version "2.2.1")
(source (origin
(method url-fetch)
(uri (string-append "http://cole-trapnell-lab.github.io/"
"cufflinks/assets/downloads/cufflinks-"
version ".tar.gz"))
(sha256
(base32
"1bnm10p8m7zq4qiipjhjqb24csiqdm1pwc8c795z253r2xk6ncg8"))))
(build-system gnu-build-system)
(arguments
`(#:make-flags
(list
;; The includes for "eigen" are located in a subdirectory.
(string-append "EIGEN_CPPFLAGS="
"-I" (assoc-ref %build-inputs "eigen")
"/include/eigen3/")
;; Cufflinks must be linked with various boost libraries.
(string-append "LDFLAGS="
(string-join '("-lboost_system"
"-lboost_serialization"
"-lboost_thread"))))
#:phases
(modify-phases %standard-phases
(add-after 'unpack 'fix-search-for-bam
(lambda _
(substitute* '("ax_bam.m4"
"configure"
"src/hits.h")
(("<bam/sam\\.h>") "<samtools/sam.h>")
(("<bam/bam\\.h>") "<samtools/bam.h>")
(("<bam/version\\.hpp>") "<samtools/version.h>"))
#t)))
#:configure-flags
(list (string-append "--with-bam="
(assoc-ref %build-inputs "samtools")))))
(inputs
`(("eigen" ,eigen)
("samtools" ,samtools-0.1)
("htslib" ,htslib)
("boost" ,boost)
("python" ,python-2)
("zlib" ,zlib)))
(home-page "http://cole-trapnell-lab.github.io/cufflinks/")
(synopsis "Transcriptome assembly and RNA-Seq expression analysis")
(description
"Cufflinks assembles RNA transcripts, estimates their abundances,
and tests for differential expression and regulation in RNA-Seq
samples. It accepts aligned RNA-Seq reads and assembles the
alignments into a parsimonious set of transcripts. Cufflinks then
estimates the relative abundances of these transcripts based on how
many reads support each one, taking into account biases in library
preparation protocols.")
(license license:boost1.0)))
(define-public cutadapt
(package
(name "cutadapt")
(version "1.8")
(source (origin
(method url-fetch)
(uri (string-append
"https://github.com/marcelm/cutadapt/archive/v"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"161bp87y6gd6r5bmvjpn2b1k942i3fizfpa139f0jn6jv1wcp5h5"))))
(build-system python-build-system)
(arguments
;; tests must be run after install
`(#:phases (alist-cons-after
'install 'check
(lambda* (#:key inputs outputs #:allow-other-keys)
(setenv "PYTHONPATH"
(string-append
(getenv "PYTHONPATH")
":" (assoc-ref outputs "out")
"/lib/python"
(string-take (string-take-right
(assoc-ref inputs "python") 5) 3)
"/site-packages"))
(zero? (system* "nosetests" "-P" "tests")))
(alist-delete 'check %standard-phases))))
(native-inputs
`(("python-cython" ,python-cython)
("python-nose" ,python-nose)
("python-setuptools" ,python-setuptools)))
(home-page "https://code.google.com/p/cutadapt/")
(synopsis "Remove adapter sequences from nucleotide sequencing reads")
(description
"Cutadapt finds and removes adapter sequences, primers, poly-A tails and
other types of unwanted sequence from high-throughput sequencing reads.")
(license license:expat)))
(define-public libbigwig
(package
(name "libbigwig")
(version "0.1.4")
(source (origin
(method url-fetch)
(uri (string-append "https://github.com/dpryan79/libBigWig/"
"archive/" version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"098rjh35pi4a9q83n8wiwvyzykjqj6l8q189p1xgfw4ghywdlvw1"))))
(build-system gnu-build-system)
(arguments
`(#:test-target "test"
#:make-flags
(list "CC=gcc"
(string-append "prefix=" (assoc-ref %outputs "out")))
#:phases
(modify-phases %standard-phases
(delete 'configure)
(add-before 'check 'disable-curl-test
(lambda _
(substitute* "Makefile"
(("./test/testRemote.*") ""))
#t))
;; This has been fixed with the upstream commit 4ff6959cd8a0, but
;; there has not yet been a release containing this change.
(add-before 'install 'create-target-dirs
(lambda* (#:key outputs #:allow-other-keys)
(let ((out (assoc-ref outputs "out")))
(mkdir-p (string-append out "/lib"))
(mkdir-p (string-append out "/include"))
#t))))))
(inputs
`(("zlib" ,zlib)
("curl" ,curl)))
(native-inputs
`(("doxygen" ,doxygen)))
(home-page "https://github.com/dpryan79/libBigWig")
(synopsis "C library for handling bigWig files")
(description
"This package provides a C library for parsing local and remote BigWig
files.")
(license license:expat)))
(define-public python-pybigwig
(package
(name "python-pybigwig")
(version "0.2.5")
(source (origin
(method url-fetch)
(uri (pypi-uri "pyBigWig" version))
(sha256
(base32
"0yrpdxg3y0sny25x4w22lv1k47jzccqjmg7j4bp0hywklvp0hg7d"))
(modules '((guix build utils)))
(snippet
'(begin
;; Delete bundled libBigWig sources
(delete-file-recursively "libBigWig")))))
(build-system python-build-system)
(arguments
`(#:phases
(modify-phases %standard-phases
(add-after 'unpack 'link-with-libBigWig
(lambda* (#:key inputs #:allow-other-keys)
(substitute* "setup.py"
(("libs=\\[") "libs=[\"BigWig\", "))
#t)))))
(inputs
`(("libbigwig" ,libbigwig)
("zlib" ,zlib)
("curl" ,curl)))
(home-page "https://github.com/dpryan79/pyBigWig")
(synopsis "Access bigWig files in Python using libBigWig")
(description
"This package provides Python bindings to the libBigWig library for
accessing bigWig files.")
(license license:expat)))
(define-public python2-pybigwig
(let ((pybigwig (package-with-python2 python-pybigwig)))
(package (inherit pybigwig)
(native-inputs
`(("python-setuptools" ,python2-setuptools))))))
(define-public deeptools
(package
(name "deeptools")
(version "2.1.1")
(source (origin
(method url-fetch)
(uri (string-append "https://github.com/fidelram/deepTools/"
"archive/" version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"1nmfin0zjdby3vay3r4flvz94dr6qjhj41ax4yz3vx13j6wz8izd"))))
(build-system python-build-system)
(arguments
`(#:python ,python-2))
(inputs
`(("python-scipy" ,python2-scipy)
("python-numpy" ,python2-numpy)
("python-numpydoc" ,python2-numpydoc)
("python-matplotlib" ,python2-matplotlib)
("python-bx-python" ,python2-bx-python)
("python-pysam" ,python2-pysam)
("python-pybigwig" ,python2-pybigwig)))
(native-inputs
`(("python-mock" ,python2-mock) ;for tests
("python-pytz" ,python2-pytz) ;for tests
("python-setuptools" ,python2-setuptools)))
(home-page "https://github.com/fidelram/deepTools")
(synopsis "Tools for normalizing and visualizing deep-sequencing data")
(description
"DeepTools addresses the challenge of handling the large amounts of data
that are now routinely generated from DNA sequencing centers. To do so,
deepTools contains useful modules to process the mapped reads data to create
coverage files in standard bedGraph and bigWig file formats. By doing so,
deepTools allows the creation of normalized coverage files or the comparison
between two files (for example, treatment and control). Finally, using such
normalized and standardized files, multiple visualizations can be created to
identify enrichments with functional annotations of the genome.")
(license license:gpl3+)))
(define-public diamond
(package
(name "diamond")
(version "0.7.9")
(source (origin
(method url-fetch)
(uri (string-append
"https://github.com/bbuchfink/diamond/archive/v"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"0hfkcfv9f76h5brbyw9fyvmc0l9cmbsxrcdqk0fa9xv82zj47p15"))
(snippet '(begin
(delete-file "bin/diamond")
#t))))
(build-system gnu-build-system)
(arguments
'(#:tests? #f ;no "check" target
#:phases
(modify-phases %standard-phases
(add-after 'unpack 'enter-source-dir
(lambda _
(chdir "src")
#t))
(delete 'configure)
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append (assoc-ref outputs "out")
"/bin")))
(mkdir-p bin)
(copy-file "../bin/diamond"
(string-append bin "/diamond"))
#t))))))
(native-inputs
`(("bc" ,bc)))
(inputs
`(("boost" ,boost)
("zlib" ,zlib)))
(home-page "https://github.com/bbuchfink/diamond")
(synopsis "Accelerated BLAST compatible local sequence aligner")
(description
"DIAMOND is a BLAST-compatible local aligner for mapping protein and
translated DNA query sequences against a protein reference database (BLASTP
and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
reads at a typical sensitivity of 90-99% relative to BLAST depending on the
data and settings.")
;; diamond fails to build on other platforms
;; https://github.com/bbuchfink/diamond/issues/18
(supported-systems '("x86_64-linux"))
(license (license:non-copyleft "file://src/COPYING"
"See src/COPYING in the distribution."))))
(define-public edirect
(package
(name "edirect")
(version "4.10")
(source (origin
(method url-fetch)
(uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/"
"versions/2016-05-03/edirect.tar.gz"))
(sha256
(base32
"15zsprak5yh8c1yrz4r1knmb5s8qcmdid4xdhkh3lqcv64l60hli"))))
(build-system perl-build-system)
(arguments
`(#:tests? #f ;no "check" target
#:phases
(modify-phases %standard-phases
(delete 'configure)
(delete 'build)
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((target (string-append (assoc-ref outputs "out")
"/bin")))
(mkdir-p target)
(copy-file "edirect.pl"
(string-append target "/edirect.pl"))
#t)))
(add-after
'install 'wrap-program
(lambda* (#:key inputs outputs #:allow-other-keys)
;; Make sure 'edirect.pl' finds all perl inputs at runtime.
(let* ((out (assoc-ref outputs "out"))
(path (getenv "PERL5LIB")))
(wrap-program (string-append out "/bin/edirect.pl")
`("PERL5LIB" ":" prefix (,path)))))))))
(inputs
`(("perl-html-parser" ,perl-html-parser)
("perl-encode-locale" ,perl-encode-locale)
("perl-file-listing" ,perl-file-listing)
("perl-html-tagset" ,perl-html-tagset)
("perl-html-tree" ,perl-html-tree)
("perl-http-cookies" ,perl-http-cookies)
("perl-http-date" ,perl-http-date)
("perl-http-message" ,perl-http-message)
("perl-http-negotiate" ,perl-http-negotiate)
("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
("perl-net-http" ,perl-net-http)
("perl-uri" ,perl-uri)
("perl-www-robotrules" ,perl-www-robotrules)
("perl" ,perl)))
(home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
(synopsis "Tools for accessing the NCBI's set of databases")
(description
"Entrez Direct (EDirect) is a method for accessing the National Center
for Biotechnology Information's (NCBI) set of interconnected
databases (publication, sequence, structure, gene, variation, expression,
etc.) from a terminal. Functions take search terms from command-line
arguments. Individual operations are combined to build multi-step queries.
Record retrieval and formatting normally complete the process.
EDirect also provides an argument-driven function that simplifies the
extraction of data from document summaries or other results that are returned
in structured XML format. This can eliminate the need for writing custom
software to answer ad hoc questions.")
(license license:public-domain)))
(define-public express
(package
(name "express")
(version "1.5.1")
(source (origin
(method url-fetch)
(uri
(string-append
"http://bio.math.berkeley.edu/eXpress/downloads/express-"
version "/express-" version "-src.tgz"))
(sha256
(base32
"03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
(build-system cmake-build-system)
(arguments
`(#:tests? #f ;no "check" target
#:phases
(alist-cons-after
'unpack 'use-shared-boost-libs-and-set-bamtools-paths
(lambda* (#:key inputs #:allow-other-keys)
(substitute* "CMakeLists.txt"
(("set\\(Boost_USE_STATIC_LIBS ON\\)")
"set(Boost_USE_STATIC_LIBS OFF)")
(("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
(string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
(substitute* "src/CMakeLists.txt"
(("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
(string-append (assoc-ref inputs "bamtools") "/lib/bamtools")))
#t)
%standard-phases)))
(inputs
`(("boost" ,boost)
("bamtools" ,bamtools)
("protobuf" ,protobuf)
("zlib" ,zlib)))
(home-page "http://bio.math.berkeley.edu/eXpress")
(synopsis "Streaming quantification for high-throughput genomic sequencing")
(description
"eXpress is a streaming tool for quantifying the abundances of a set of
target sequences from sampled subsequences. Example applications include
transcript-level RNA-Seq quantification, allele-specific/haplotype expression
analysis (from RNA-Seq), transcription factor binding quantification in
ChIP-Seq, and analysis of metagenomic data.")
(license license:artistic2.0)))
(define-public express-beta-diversity
(package
(name "express-beta-diversity")
(version "1.0.7")
(source (origin
(method url-fetch)
(uri
(string-append
"https://github.com/dparks1134/ExpressBetaDiversity/archive/v"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"1djvdlmqvjf6h0zq7w36y8cl5cli6rgj86x65znl48agnwmzxfxr"))))
(build-system gnu-build-system)
(arguments
`(#:phases
(modify-phases %standard-phases
(delete 'configure)
(add-before 'build 'enter-source (lambda _ (chdir "source") #t))
(replace 'check
(lambda _ (zero? (system* "../bin/ExpressBetaDiversity"
"-u"))))
(add-after 'check 'exit-source (lambda _ (chdir "..") #t))
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append (assoc-ref outputs "out")
"/bin")))
(mkdir-p bin)
(copy-file "scripts/convertToEBD.py"
(string-append bin "/convertToEBD.py"))
(copy-file "bin/ExpressBetaDiversity"
(string-append bin "/ExpressBetaDiversity"))
#t))))))
(inputs
`(("python" ,python-2)))
(home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
(synopsis "Taxon- and phylogenetic-based beta diversity measures")
(description
"Express Beta Diversity (EBD) calculates ecological beta diversity
(dissimilarity) measures between biological communities. EBD implements a
variety of diversity measures including those that make use of phylogenetic
similarity of community members.")
(license license:gpl3+)))
(define-public fasttree
(package
(name "fasttree")
(version "2.1.8")
(source (origin
(method url-fetch)
(uri (string-append
"http://www.microbesonline.org/fasttree/FastTree-"
version ".c"))
(sha256
(base32
"0dzqc9vr9iiiw21y159xfjl2z90vw0y7r4x6456pcaxiy5hd2wmi"))))
(build-system gnu-build-system)
(arguments
`(#:tests? #f ; no "check" target
#:phases
(modify-phases %standard-phases
(delete 'unpack)
(delete 'configure)
(replace 'build
(lambda* (#:key source #:allow-other-keys)
(and (zero? (system* "gcc"
"-O3"
"-finline-functions"
"-funroll-loops"
"-Wall"
"-o"
"FastTree"
source
"-lm"))
(zero? (system* "gcc"
"-DOPENMP"
"-fopenmp"
"-O3"
"-finline-functions"
"-funroll-loops"
"-Wall"
"-o"
"FastTreeMP"
source
"-lm")))))
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append (assoc-ref outputs "out")
"/bin")))
(mkdir-p bin)
(copy-file "FastTree"
(string-append bin "/FastTree"))
(copy-file "FastTreeMP"
(string-append bin "/FastTreeMP"))
#t))))))
(home-page "http://www.microbesonline.org/fasttree")
(synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
(description
"FastTree can handle alignments with up to a million of sequences in a
reasonable amount of time and memory. For large alignments, FastTree is
100-1,000 times faster than PhyML 3.0 or RAxML 7.")
(license license:gpl2+)))
(define-public fastx-toolkit
(package
(name "fastx-toolkit")
(version "0.0.14")
(source (origin
(method url-fetch)
(uri
(string-append
"https://github.com/agordon/fastx_toolkit/releases/download/"
version "/fastx_toolkit-" version ".tar.bz2"))
(sha256
(base32
"01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
(build-system gnu-build-system)
(inputs
`(("libgtextutils" ,libgtextutils)))
(native-inputs
`(("pkg-config" ,pkg-config)))
(home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
(synopsis "Tools for FASTA/FASTQ file preprocessing")
(description
"The FASTX-Toolkit is a collection of command line tools for Short-Reads
FASTA/FASTQ files preprocessing.
Next-Generation sequencing machines usually produce FASTA or FASTQ files,
containing multiple short-reads sequences. The main processing of such
FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
is sometimes more productive to preprocess the files before mapping the
sequences to the genome---manipulating the sequences to produce better mapping
results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
(license license:agpl3+)))
(define-public flexbar
(package
(name "flexbar")
(version "2.5")
(source (origin
(method url-fetch)
(uri
(string-append "mirror://sourceforge/flexbar/"
version "/flexbar_v" version "_src.tgz"))
(sha256
(base32
"13jaykc3y1x8y5nn9j8ljnb79s5y51kyxz46hdmvvjj6qhyympmf"))))
(build-system cmake-build-system)
(arguments
`(#:configure-flags (list
(string-append "-DFLEXBAR_BINARY_DIR="
(assoc-ref %outputs "out")
"/bin/"))
#:phases
(alist-replace
'check
(lambda* (#:key outputs #:allow-other-keys)
(setenv "PATH" (string-append
(assoc-ref outputs "out") "/bin:"
(getenv "PATH")))
(chdir "../flexbar_v2.5_src/test")
(zero? (system* "bash" "flexbar_validate.sh")))
(alist-delete 'install %standard-phases))))
(inputs
`(("tbb" ,tbb)
("zlib" ,zlib)))
(native-inputs
`(("pkg-config" ,pkg-config)
("seqan" ,seqan)))
(home-page "http://flexbar.sourceforge.net")
(synopsis "Barcode and adapter removal tool for sequencing platforms")
(description
"Flexbar preprocesses high-throughput nucleotide sequencing data
efficiently. It demultiplexes barcoded runs and removes adapter sequences.
Moreover, trimming and filtering features are provided. Flexbar increases
read mapping rates and improves genome and transcriptome assemblies. It
supports next-generation sequencing data in fasta/q and csfasta/q format from
Illumina, Roche 454, and the SOLiD platform.")
(license license:gpl3)))
(define-public fraggenescan
(package
(name "fraggenescan")
(version "1.20")
(source
(origin
(method url-fetch)
(uri
(string-append "mirror://sourceforge/fraggenescan/"
"FragGeneScan" version ".tar.gz"))
(sha256
(base32 "1zzigqmvqvjyqv4945kv6nc5ah2xxm1nxgrlsnbzav3f5c0n0pyj"))))
(build-system gnu-build-system)
(arguments
`(#:phases
(modify-phases %standard-phases
(delete 'configure)
(add-before 'build 'patch-paths
(lambda* (#:key outputs #:allow-other-keys)
(let* ((out (string-append (assoc-ref outputs "out")))
(share (string-append out "/share/fraggenescan/")))
(substitute* "run_FragGeneScan.pl"
(("system\\(\"rm")
(string-append "system(\"" (which "rm")))
(("system\\(\"mv")
(string-append "system(\"" (which "mv")))
;; This script and other programs expect the training files
;; to be in the non-standard location bin/train/XXX. Change
;; this to be share/fraggenescan/train/XXX instead.
(("^\\$train.file = \\$dir.*")
(string-append "$train_file = \""
share
"train/\".$FGS_train_file;")))
(substitute* "run_hmm.c"
(("^ strcat\\(train_dir, \\\"train/\\\"\\);")
(string-append " strcpy(train_dir, \"" share "/train/\");")))
(substitute* "post_process.pl"
(("^my \\$dir = substr.*")
(string-append "my $dir = \"" share "\";"))))
#t))
(replace 'build
(lambda _ (and (zero? (system* "make" "clean"))
(zero? (system* "make" "fgs")))))
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let* ((out (string-append (assoc-ref outputs "out")))
(bin (string-append out "/bin/"))
(share (string-append out "/share/fraggenescan/train")))
(install-file "run_FragGeneScan.pl" bin)
(install-file "FragGeneScan" bin)
(install-file "FGS_gff.py" bin)
(install-file "post_process.pl" bin)
(copy-recursively "train" share))))
(delete 'check)
(add-after 'install 'post-install-check
;; In lieu of 'make check', run one of the examples and check the
;; output files gets created.
(lambda* (#:key outputs #:allow-other-keys)
(let* ((out (string-append (assoc-ref outputs "out")))
(bin (string-append out "/bin/")))
(and (zero? (system* (string-append bin "run_FragGeneScan.pl")
"-genome=./example/NC_000913.fna"
"-out=./test2"
"-complete=1"
"-train=complete"))
(file-exists? "test2.faa")
(file-exists? "test2.ffn")
(file-exists? "test2.gff")
(file-exists? "test2.out"))))))))
(inputs
`(("perl" ,perl)
("python" ,python-2))) ;not compatible with python 3.
(home-page "https://sourceforge.net/projects/fraggenescan/")
(synopsis "Finds potentially fragmented genes in short reads")
(description
"FragGeneScan is a program for predicting bacterial and archaeal genes in
short and error-prone DNA sequencing reads. It can also be applied to predict
genes in incomplete assemblies or complete genomes.")
;; GPL3+ according to private correspondense with the authors.
(license license:gpl3+)))
(define-public fxtract
(let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
(package
(name "fxtract")
(version "2.3")
(source
(origin
(method url-fetch)
(uri (string-append
"https://github.com/ctSkennerton/fxtract/archive/"
version ".tar.gz"))
(file-name (string-append "ctstennerton-util-"
(string-take util-commit 7)
"-checkout"))
(sha256
(base32
"0275cfdhis8517hm01is62062swmi06fxzifq7mr3knbbxjlaiwj"))))
(build-system gnu-build-system)
(arguments
`(#:make-flags (list
(string-append "PREFIX=" (assoc-ref %outputs "out"))
"CC=gcc")
#:test-target "fxtract_test"
#:phases
(modify-phases %standard-phases
(delete 'configure)
(add-before 'build 'copy-util
(lambda* (#:key inputs #:allow-other-keys)
(rmdir "util")
(copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
#t))
;; Do not use make install as this requires additional dependencies.
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let* ((out (assoc-ref outputs "out"))
(bin (string-append out"/bin")))
(install-file "fxtract" bin)
#t))))))
(inputs
`(("pcre" ,pcre)
("zlib" ,zlib)))
(native-inputs
;; ctskennerton-util is licensed under GPL2.
`(("ctskennerton-util"
,(origin
(method git-fetch)
(uri (git-reference
(url "https://github.com/ctSkennerton/util.git")
(commit util-commit)))
(file-name (string-append
"ctstennerton-util-" util-commit "-checkout"))
(sha256
(base32
"0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
(home-page "https://github.com/ctSkennerton/fxtract")
(synopsis "Extract sequences from FASTA and FASTQ files")
(description
"Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
or FASTQ) file given a subsequence. It uses a simple substring search for
basic tasks but can change to using POSIX regular expressions, PCRE, hash
lookups or multi-pattern searching as required. By default fxtract looks in
the sequence of each record but can also be told to look in the header,
comment or quality sections.")
(license license:expat))))
(define-public grit
(package
(name "grit")
(version "2.0.2")
(source (origin
(method url-fetch)
(uri (string-append
"https://github.com/nboley/grit/archive/"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"157in84dj70wimbind3x7sy1whs3h57qfgcnj2s6lrd38fbrb7mj"))))
(build-system python-build-system)
(arguments
`(#:python ,python-2
#:phases
(alist-cons-after
'unpack 'generate-from-cython-sources
(lambda* (#:key inputs outputs #:allow-other-keys)
;; Delete these C files to force fresh generation from pyx sources.
(delete-file "grit/sparsify_support_fns.c")
(delete-file "grit/call_peaks_support_fns.c")
(substitute* "setup.py"
(("Cython.Setup") "Cython.Build")
;; Add numpy include path to fix compilation
(("pyx\", \\]")
(string-append "pyx\", ], include_dirs = ['"
(assoc-ref inputs "python-numpy")
"/lib/python2.7/site-packages/numpy/core/include/"
"']"))) #t)
%standard-phases)))
(inputs
`(("python-scipy" ,python2-scipy)
("python-numpy" ,python2-numpy)
("python-pysam" ,python2-pysam)
("python-networkx" ,python2-networkx)))
(native-inputs
`(("python-cython" ,python2-cython)
("python-setuptools" ,python2-setuptools)))
(home-page "http://grit-bio.org")
(synopsis "Tool for integrative analysis of RNA-seq type assays")
(description
"GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
full length transcript models. When none of these data sources are available,
GRIT can be run by providing a candidate set of TES or TSS sites. In
addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
also be run in quantification mode, where it uses a provided GTF file and just
estimates transcript expression.")
(license license:gpl3+)))
(define-public hisat
(package
(name "hisat")
(version "0.1.4")
(source (origin
(method url-fetch)
(uri (string-append
"http://ccb.jhu.edu/software/hisat/downloads/hisat-"
version "-beta-source.zip"))
(sha256
(base32
"1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
(build-system gnu-build-system)
(arguments
`(#:tests? #f ;no check target
#:make-flags '("allall"
;; Disable unsupported `popcnt' instructions on
;; architectures other than x86_64
,@(if (string-prefix? "x86_64"
(or (%current-target-system)
(%current-system)))
'()
'("POPCNT_CAPABILITY=0")))
#:phases
(alist-cons-after
'unpack 'patch-sources
(lambda _
;; XXX Cannot use snippet because zip files are not supported
(substitute* "Makefile"
(("^CC = .*$") "CC = gcc")
(("^CPP = .*$") "CPP = g++")
;; replace BUILD_HOST and BUILD_TIME for deterministic build
(("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
(("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
(substitute* '("hisat-build" "hisat-inspect")
(("/usr/bin/env") (which "env"))))
(alist-replace
'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append (assoc-ref outputs "out") "/bi/")))
(for-each (lambda (file)
(install-file file bin))
(find-files
"."
"hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))))
(alist-delete 'configure %standard-phases)))))
(native-inputs
`(("unzip" ,unzip)))
(inputs
`(("perl" ,perl)
("python" ,python)
("zlib" ,zlib)))
;; Non-portable SSE instructions are used so building fails on platforms
;; other than x86_64.
(supported-systems '("x86_64-linux"))
(home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
(synopsis "Hierarchical indexing for spliced alignment of transcripts")
(description
"HISAT is a fast and sensitive spliced alignment program for mapping
RNA-seq reads. In addition to one global FM index that represents a whole
genome, HISAT uses a large set of small FM indexes that collectively cover the
whole genome. These small indexes (called local indexes) combined with
several alignment strategies enable effective alignment of RNA-seq reads, in
particular, reads spanning multiple exons.")
(license license:gpl3+)))
(define-public hmmer
(package
(name "hmmer")
(version "3.1b2")
(source (origin
(method url-fetch)
(uri (string-append
"http://eddylab.org/software/hmmer"
(version-prefix version 1) "/"
version "/hmmer-" version ".tar.gz"))
(sha256
(base32
"0djmgc0pfli0jilfx8hql1axhwhqxqb8rxg2r5rg07aw73sfs5nx"))))
(build-system gnu-build-system)
(native-inputs `(("perl" ,perl)))
(home-page "http://hmmer.org/")
(synopsis "Biosequence analysis using profile hidden Markov models")
(description
"HMMER is used for searching sequence databases for homologs of protein
sequences, and for making protein sequence alignments. It implements methods
using probabilistic models called profile hidden Markov models (profile
HMMs).")
(license (list license:gpl3+
;; The bundled library 'easel' is distributed
;; under The Janelia Farm Software License.
(license:non-copyleft
"file://easel/LICENSE"
"See easel/LICENSE in the distribution.")))))
(define-public htseq
(package
(name "htseq")
(version "0.6.1")
(source (origin
(method url-fetch)
(uri (string-append
"https://pypi.python.org/packages/source/H/HTSeq/HTSeq-"
version ".tar.gz"))
(sha256
(base32
"1i85ppf2j2lj12m0x690qq5nn17xxk23pbbx2c83r8ayb5wngzwv"))))
(build-system python-build-system)
(arguments `(#:python ,python-2)) ; only Python 2 is supported
;; Numpy needs to be propagated when htseq is used as a Python library.
(propagated-inputs
`(("python-numpy" ,python2-numpy)))
(inputs
`(("python-pysam" ,python2-pysam)))
(native-inputs
`(("python-setuptools" ,python2-setuptools)))
(home-page "http://www-huber.embl.de/users/anders/HTSeq/")
(synopsis "Analysing high-throughput sequencing data with Python")
(description
"HTSeq is a Python package that provides infrastructure to process data
from high-throughput sequencing assays.")
(license license:gpl3+)))
(define-public java-htsjdk
(package
(name "java-htsjdk")
(version "1.129")
(source (origin
(method url-fetch)
(uri (string-append
"https://github.com/samtools/htsjdk/archive/"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"0asdk9b8jx2ij7yd6apg9qx03li8q7z3ml0qy2r2qczkra79y6fw"))
(modules '((guix build utils)))
;; remove build dependency on git
(snippet '(substitute* "build.xml"
(("failifexecutionfails=\"true\"")
"failifexecutionfails=\"false\"")))))
(build-system ant-build-system)
(arguments
`(#:tests? #f ; test require Internet access
#:make-flags
(list (string-append "-Ddist=" (assoc-ref %outputs "out")
"/share/java/htsjdk/"))
#:build-target "all"
#:phases
(modify-phases %standard-phases
;; The build phase also installs the jars
(delete 'install))))
(home-page "http://samtools.github.io/htsjdk/")
(synopsis "Java API for high-throughput sequencing data (HTS) formats")
(description
"HTSJDK is an implementation of a unified Java library for accessing
common file formats, such as SAM and VCF, used for high-throughput
sequencing (HTS) data. There are also an number of useful utilities for
manipulating HTS data.")
(license license:expat)))
(define-public htslib
(package
(name "htslib")
(version "1.2.1")
(source (origin
(method url-fetch)
(uri (string-append
"https://github.com/samtools/htslib/releases/download/"
version "/htslib-" version ".tar.bz2"))
(sha256
(base32
"1c32ssscbnjwfw3dra140fq7riarp2x990qxybh34nr1p5r17nxx"))))
(build-system gnu-build-system)
(arguments
`(#:phases
(modify-phases %standard-phases
(add-after
'unpack 'patch-tests
(lambda _
(substitute* "test/test.pl"
(("/bin/bash") (which "bash")))
#t)))))
(inputs
`(("zlib" ,zlib)))
(native-inputs
`(("perl" ,perl)))
(home-page "http://www.htslib.org")
(synopsis "C library for reading/writing high-throughput sequencing data")
(description
"HTSlib is a C library for reading/writing high-throughput sequencing
data. It also provides the bgzip, htsfile, and tabix utilities.")
;; Files under cram/ are released under the modified BSD license;
;; the rest is released under the Expat license
(license (list license:expat license:bsd-3))))
(define-public idr
(package
(name "idr")
(version "2.0.0")
(source (origin
(method url-fetch)
(uri (string-append
"https://github.com/nboley/idr/archive/"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"1k3x44biak00aiv3hpm1yd6nn4hhp7n0qnbs3zh2q9sw7qr1qj5r"))))
(build-system python-build-system)
(arguments
`(#:phases
(modify-phases %standard-phases
(add-after
'install 'wrap-program
(lambda* (#:key inputs outputs #:allow-other-keys)
(let* ((out (assoc-ref outputs "out"))
(python-version (string-take (string-take-right
(assoc-ref inputs "python") 5) 3))
(path (string-join
(map (lambda (name)
(string-append (assoc-ref inputs name)
"/lib/python" python-version
"/site-packages"))
'("python-scipy"
"python-numpy"
"python-matplotlib"))
":")))
(wrap-program (string-append out "/bin/idr")
`("PYTHONPATH" ":" prefix (,path))))
#t)))))
(inputs
`(("python-scipy" ,python-scipy)
("python-numpy" ,python-numpy)
("python-matplotlib" ,python-matplotlib)))
(native-inputs
`(("python-cython" ,python-cython)
("python-setuptools" ,python-setuptools)))
(home-page "https://github.com/nboley/idr")
(synopsis "Tool to measure the irreproducible discovery rate (IDR)")
(description
"The IDR (Irreproducible Discovery Rate) framework is a unified approach
to measure the reproducibility of findings identified from replicate
experiments and provide highly stable thresholds based on reproducibility.")
(license license:gpl3+)))
(define-public jellyfish
(package
(name "jellyfish")
(version "2.2.4")
(source (origin
(method url-fetch)
(uri (string-append "https://github.com/gmarcais/Jellyfish/"
"releases/download/v" version
"/jellyfish-" version ".tar.gz"))
(sha256
(base32
"0a6xnynqy2ibfbfz86b9g2m2dgm7f1469pmymkpam333gi3p26nk"))))
(build-system gnu-build-system)
(outputs '("out" ;for library
"ruby" ;for Ruby bindings
"python")) ;for Python bindings
(arguments
`(#:configure-flags
(list (string-append "--enable-ruby-binding="
(assoc-ref %outputs "ruby"))
(string-append "--enable-python-binding="
(assoc-ref %outputs "python")))
#:phases
(modify-phases %standard-phases
(add-before 'check 'set-SHELL-variable
(lambda _
;; generator_manager.hpp either uses /bin/sh or $SHELL
;; to run tests.
(setenv "SHELL" (which "bash"))
#t)))))
(native-inputs
`(("bc" ,bc)
("time" ,time)
("ruby" ,ruby)
("python" ,python-2)))
(synopsis "Tool for fast counting of k-mers in DNA")
(description
"Jellyfish is a tool for fast, memory-efficient counting of k-mers in
DNA. A k-mer is a substring of length k, and counting the occurrences of all
such substrings is a central step in many analyses of DNA sequence. Jellyfish
is a command-line program that reads FASTA and multi-FASTA files containing
DNA sequences. It outputs its k-mer counts in a binary format, which can be
translated into a human-readable text format using the @code{jellyfish dump}
command, or queried for specific k-mers with @code{jellyfish query}.")
(home-page "http://www.genome.umd.edu/jellyfish.html")
;; The combined work is published under the GPLv3 or later. Individual
;; files such as lib/jsoncpp.cpp are released under the Expat license.
(license (list license:gpl3+ license:expat))))
(define-public macs
(package
(name "macs")
(version "2.1.0.20151222")
(source (origin
(method url-fetch)
(uri (pypi-uri "MACS2" version))
(sha256
(base32
"1r2hcz6irhcq7lwbafjks98jbn34hv05avgbdjnp6w6mlfjkf8x5"))))
(build-system python-build-system)
(arguments
`(#:python ,python-2 ; only compatible with Python 2.7
#:tests? #f)) ; no test target
(inputs
`(("python-numpy" ,python2-numpy)))
(native-inputs
`(("python-setuptools" ,python2-setuptools)))
(home-page "http://github.com/taoliu/MACS/")
(synopsis "Model based analysis for ChIP-Seq data")
(description
"MACS is an implementation of a ChIP-Seq analysis algorithm for
identifying transcript factor binding sites named Model-based Analysis of
ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
the significance of enriched ChIP regions and it improves the spatial
resolution of binding sites through combining the information of both
sequencing tag position and orientation.")
(license license:bsd-3)))
(define-public mafft
(package
(name "mafft")
(version "7.267")
(source (origin
(method url-fetch)
(uri (string-append
"http://mafft.cbrc.jp/alignment/software/mafft-" version
"-without-extensions-src.tgz"))
(file-name (string-append name "-" version ".tgz"))
(sha256
(base32
"1xl6xq1rfxkws0svrlhyqxhhwbv6r77jwblsdpcyiwzsscw6wlk0"))))
(build-system gnu-build-system)
(arguments
`(#:tests? #f ; no automated tests, though there are tests in the read me
#:make-flags (let ((out (assoc-ref %outputs "out")))
(list (string-append "PREFIX=" out)
(string-append "BINDIR="
(string-append out "/bin"))))
#:phases
(modify-phases %standard-phases
(add-after 'unpack 'enter-dir
(lambda _ (chdir "core") #t))
(add-after 'enter-dir 'patch-makefile
(lambda _
;; on advice from the MAFFT authors, there is no need to
;; distribute mafft-profile, mafft-distance, or
;; mafft-homologs.rb as they are too "specialised".
(substitute* "Makefile"
;; remove mafft-homologs.rb from SCRIPTS
(("^SCRIPTS = mafft mafft-homologs.rb")
"SCRIPTS = mafft")
;; remove mafft-homologs from MANPAGES
(("^MANPAGES = mafft.1 mafft-homologs.1")
"MANPAGES = mafft.1")
;; remove mafft-distance from PROGS
(("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
"PROGS = dvtditr dndfast7 dndblast sextet5")
;; remove mafft-profile from PROGS
(("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
"splittbfast disttbfast tbfast f2cl mccaskillwrap")
(("^rm -f mafft-profile mafft-profile.exe") "#")
(("^rm -f mafft-distance mafft-distance.exe") ")#")
;; do not install MAN pages in libexec folder
(("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
\\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
#t))
(add-after 'enter-dir 'patch-paths
(lambda* (#:key inputs #:allow-other-keys)
(substitute* '("pairash.c"
"mafft.tmpl")
(("perl") (which "perl"))
(("([\"`| ])awk" _ prefix)
(string-append prefix (which "awk")))
(("grep") (which "grep")))
#t))
(delete 'configure))))
(inputs
`(("perl" ,perl)
("gawk" ,gawk)
("grep" ,grep)))
(propagated-inputs
`(("coreutils" ,coreutils)))
(home-page "http://mafft.cbrc.jp/alignment/software/")
(synopsis "Multiple sequence alignment program")
(description
"MAFFT offers a range of multiple alignment methods for nucleotide and
protein sequences. For instance, it offers L-INS-i (accurate; for alignment
of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
sequences).")
(license (license:non-copyleft
"http://mafft.cbrc.jp/alignment/software/license.txt"
"BSD-3 with different formatting"))))
(define-public metabat
(package
(name "metabat")
(version "0.26.1")
(source (origin
(method url-fetch)
(uri (string-append
"https://bitbucket.org/berkeleylab/metabat/get/"
version ".tar.bz2"))
(file-name (string-append name "-" version ".tar.bz2"))
(sha256
(base32
"0vgrhbaxg4dkxyax2kbigak7w0arhqvw0szwp6gd9wmyilc44kfa"))))
(build-system gnu-build-system)
(arguments
`(#:phases
(modify-phases %standard-phases
(add-after 'unpack 'fix-includes
(lambda _
(substitute* "SConstruct"
(("/include/bam/bam.h")
"/include/samtools/bam.h"))
(substitute* "src/BamUtils.h"
(("^#include \"bam/bam\\.h\"")
"#include \"samtools/bam.h\"")
(("^#include \"bam/sam\\.h\"")
"#include \"samtools/sam.h\""))
(substitute* "src/KseqReader.h"
(("^#include \"bam/kseq\\.h\"")
"#include \"samtools/kseq.h\""))
#t))
(add-after 'unpack 'fix-scons
(lambda _
(substitute* "SConstruct" ; Do not distribute README
(("^env\\.Install\\(idir_prefix, 'README\\.md'\\)")
""))
#t))
(delete 'configure)
(replace 'build
(lambda* (#:key inputs outputs #:allow-other-keys)
(mkdir (assoc-ref outputs "out"))
(zero? (system* "scons"
(string-append
"PREFIX="
(assoc-ref outputs "out"))
(string-append
"HTSLIB_DIR="
(assoc-ref inputs "htslib"))
(string-append
"SAMTOOLS_DIR="
(assoc-ref inputs "samtools"))
(string-append
"BOOST_ROOT="
(assoc-ref inputs "boost"))
"install"))))
;; check and install carried out during build phase
(delete 'check)
(delete 'install))))
(inputs
`(("zlib" ,zlib)
("perl" ,perl)
("samtools" ,samtools)
("htslib" ,htslib)
("boost" ,boost)))
(native-inputs
`(("scons" ,scons)))
(home-page "https://bitbucket.org/berkeleylab/metabat")
(synopsis
"Reconstruction of single genomes from complex microbial communities")
(description
"Grouping large genomic fragments assembled from shotgun metagenomic
sequences to deconvolute complex microbial communities, or metagenome binning,
enables the study of individual organisms and their interactions. MetaBAT is
an automated metagenome binning software, which integrates empirical
probabilistic distances of genome abundance and tetranucleotide frequency.")
(license (license:non-copyleft "file://license.txt"
"See license.txt in the distribution."))))
(define-public miso
(package
(name "miso")
(version "0.5.3")
(source (origin
(method url-fetch)
(uri (string-append
"https://pypi.python.org/packages/source/m/misopy/misopy-"
version ".tar.gz"))
(sha256
(base32
"0x446867az8ir0z8c1vjqffkp0ma37wm4sylixnkhgawllzx8v5w"))
(modules '((guix build utils)))
(snippet
'(substitute* "setup.py"
;; Use setuptools, or else the executables are not
;; installed.
(("distutils.core") "setuptools")
;; use "gcc" instead of "cc" for compilation
(("^defines")
"cc.set_executables(
compiler='gcc',
compiler_so='gcc',
linker_exe='gcc',
linker_so='gcc -shared'); defines")))))
(build-system python-build-system)
(arguments
`(#:python ,python-2 ; only Python 2 is supported
#:tests? #f)) ; no "test" target
(inputs
`(("samtools" ,samtools)
("python-numpy" ,python2-numpy)
("python-pysam" ,python2-pysam)
("python-scipy" ,python2-scipy)
("python-matplotlib" ,python2-matplotlib)))
(native-inputs
`(("python-mock" ,python2-mock) ;for tests
("python-pytz" ,python2-pytz) ;for tests
("python-setuptools" ,python2-setuptools)))
(home-page "http://genes.mit.edu/burgelab/miso/index.html")
(synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
(description
"MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
the expression level of alternatively spliced genes from RNA-Seq data, and
identifies differentially regulated isoforms or exons across samples. By
modeling the generative process by which reads are produced from isoforms in
RNA-Seq, the MISO model uses Bayesian inference to compute the probability
that a read originated from a particular isoform.")
(license license:gpl2)))
(define-public muscle
(package
(name "muscle")
(version "3.8.1551")
(source (origin
(method url-fetch/tarbomb)
(file-name (string-append name "-" version))
(uri (string-append
"http://www.drive5.com/muscle/muscle_src_"
version ".tar.gz"))
(sha256
(base32
"0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
(build-system gnu-build-system)
(arguments
`(#:make-flags (list "LDLIBS = -lm")
#:phases
(modify-phases %standard-phases
(delete 'configure)
(replace 'check
;; There are no tests, so just test if it runs.
(lambda _ (zero? (system* "./muscle" "-version"))))
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let* ((out (assoc-ref outputs "out"))
(bin (string-append out "/bin")))
(install-file "muscle" bin)))))))
(home-page "http://www.drive5.com/muscle")
(synopsis "Multiple sequence alignment program")
(description
"MUSCLE aims to be a fast and accurate multiple sequence alignment
program for nucleotide and protein sequences.")
;; License information found in 'muscle -h' and usage.cpp.
(license license:public-domain)))
(define-public orfm
(package
(name "orfm")
(version "0.5.3")
(source (origin
(method url-fetch)
(uri (string-append
"https://github.com/wwood/OrfM/releases/download/v"
version "/orfm-" version ".tar.gz"))
(sha256
(base32
"0vb6d771gl4mix8bwx919x5ayy9pkj44n7ki336nz3rz2rx4c7gk"))))
(build-system gnu-build-system)
(inputs `(("zlib" ,zlib)))
(native-inputs
`(("ruby-bio-commandeer" ,ruby-bio-commandeer)
("ruby-rspec" ,ruby-rspec)
("ruby" ,ruby)))
(synopsis "Simple and not slow open reading frame (ORF) caller")
(description
"An ORF caller finds stretches of DNA that, when translated, are not
interrupted by stop codons. OrfM finds and prints these ORFs.")
(home-page "https://github.com/wwood/OrfM")
(license license:lgpl3+)))
(define-public python2-pbcore
(package
(name "python2-pbcore")
(version "1.2.8")
(source (origin
(method url-fetch)
(uri (pypi-uri "pbcore" version))
(sha256
(base32
"02pfn5raa3zf739672bg0dkx7z3j2c4nx7vmpfjqy5b12jrqpymk"))))
(build-system python-build-system)
(arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
(inputs
`(("python-cython" ,python2-cython)
("python-numpy" ,python2-numpy)
("python-pysam" ,python2-pysam)
("python-h5py" ,python2-h5py)))
(native-inputs
`(("python-docutils" ,python2-docutils)
("python-nose" ,python2-nose)
("python-setuptools" ,python2-setuptools)
("python-sphinx" ,python2-sphinx)))
(home-page "http://pacificbiosciences.github.io/pbcore/")
(synopsis "Library for reading and writing PacBio data files")
(description
"The pbcore package provides Python APIs for interacting with PacBio data
files and writing bioinformatics applications.")
(license license:bsd-3)))
(define-public python2-warpedlmm
(package
(name "python2-warpedlmm")
(version "0.21")
(source
(origin
(method url-fetch)
(uri (string-append
"https://pypi.python.org/packages/source/W/WarpedLMM/WarpedLMM-"
version ".zip"))
(sha256
(base32
"1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
(build-system python-build-system)
(arguments
`(#:python ,python-2 ; requires Python 2.7
#:phases
(modify-phases %standard-phases
(add-after
'install 'remove-bin-directory
(lambda* (#:key outputs #:allow-other-keys)
;; The "bin" directory only contains wrappers for running
;; the module tests. They are not needed after the
;; "check" phase.
(delete-file-recursively
(string-append (assoc-ref outputs "out") "/bin"))
#t)))))
(propagated-inputs
`(("python-scipy" ,python2-scipy)
("python-numpy" ,python2-numpy)
("python-matplotlib" ,python2-matplotlib)
("python-fastlmm" ,python2-fastlmm)
("python-pandas" ,python2-pandas)
("python-pysnptools" ,python2-pysnptools)))
(native-inputs
`(("python-setuptools" ,python2-setuptools)
("python-mock" ,python2-mock)
("python-nose" ,python2-nose)
("unzip" ,unzip)))
(home-page "https://github.com/PMBio/warpedLMM")
(synopsis "Implementation of warped linear mixed models")
(description
"WarpedLMM is a Python implementation of the warped linear mixed model,
which automatically learns an optimal warping function (or transformation) for
the phenotype as it models the data.")
(license license:asl2.0)))
(define-public pbtranscript-tofu
(let ((commit "8f5467fe6"))
(package
(name "pbtranscript-tofu")
(version (string-append "2.2.3." commit))
(source (origin
(method git-fetch)
(uri (git-reference
(url "https://github.com/PacificBiosciences/cDNA_primer.git")
(commit commit)))
(file-name (string-append name "-" version "-checkout"))
(sha256
(base32
"1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
(modules '((guix build utils)))
(snippet
'(begin
;; remove bundled Cython sources
(delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
#t))))
(build-system python-build-system)
(arguments
`(#:python ,python-2
;; With standard flags, the install phase attempts to create a zip'd
;; egg file, and fails with an error: 'ZIP does not support timestamps
;; before 1980'
#:configure-flags '("--single-version-externally-managed"
"--record=pbtranscript-tofu.txt")
#:phases
(modify-phases %standard-phases
(add-after 'unpack 'enter-directory
(lambda _
(chdir "pbtranscript-tofu/pbtranscript/")
#t))
;; With setuptools version 18.0 and later this setup.py hack causes
;; a build error, so we disable it.
(add-after 'enter-directory 'patch-setuppy
(lambda _
(substitute* "setup.py"
(("if 'setuptools.extension' in sys.modules:")
"if False:"))
#t)))))
(inputs
`(("python-numpy" ,python2-numpy)
("python-bx-python" ,python2-bx-python)
("python-networkx" ,python2-networkx)
("python-scipy" ,python2-scipy)
("python-pbcore" ,python2-pbcore)
("python-h5py" ,python2-h5py)))
(native-inputs
`(("python-cython" ,python2-cython)
("python-nose" ,python2-nose)
("python-setuptools" ,python2-setuptools)))
(home-page "https://github.com/PacificBiosciences/cDNA_primer")
(synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
(description
"pbtranscript-tofu contains scripts to analyze transcriptome data
generated using the PacBio Iso-Seq protocol.")
(license license:bsd-3))))
(define-public pyicoteo
(package
(name "pyicoteo")
(version "2.0.7")
(source
(origin
(method url-fetch)
(uri (string-append "https://bitbucket.org/regulatorygenomicsupf/"
"pyicoteo/get/v" version ".tar.bz2"))
(file-name (string-append name "-" version ".tar.bz2"))
(sha256
(base32
"0d6087f29xp8wxwlj111c3sylli98n0l8ry58c51ixzq0zfm50wa"))))
(build-system python-build-system)
(arguments
`(#:python ,python-2 ; does not work with Python 3
#:tests? #f)) ; there are no tests
(inputs
`(("python2-matplotlib" ,python2-matplotlib)))
(home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
(synopsis "Analyze high-throughput genetic sequencing data")
(description
"Pyicoteo is a suite of tools for the analysis of high-throughput genetic
sequencing data. It works with genomic coordinates. There are currently six
different command-line tools:
@enumerate
@item pyicoregion: for generating exploratory regions automatically;
@item pyicoenrich: for differential enrichment between two conditions;
@item pyicoclip: for calling CLIP-Seq peaks without a control;
@item pyicos: for genomic coordinates manipulation;
@item pyicoller: for peak calling on punctuated ChIP-Seq;
@item pyicount: to count how many reads from N experiment files overlap in a
region file;
@item pyicotrocol: to combine operations from pyicoteo.
@end enumerate\n")
(license license:gpl3+)))
(define-public prodigal
(package
(name "prodigal")
(version "2.6.3")
(source (origin
(method url-fetch)
(uri (string-append
"https://github.com/hyattpd/Prodigal/archive/v"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"17srxkqd3jc77xk15pfbgg1a9xahqg7337w95mrsia7mpza4l2c9"))))
(build-system gnu-build-system)
(arguments
`(#:tests? #f ;no check target
#:make-flags (list (string-append "INSTALLDIR="
(assoc-ref %outputs "out")
"/bin"))
#:phases
(modify-phases %standard-phases
(delete 'configure))))
(home-page "http://prodigal.ornl.gov")
(synopsis "Protein-coding gene prediction for Archaea and Bacteria")
(description
"Prodigal runs smoothly on finished genomes, draft genomes, and
metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
format. It runs quickly, in an unsupervised fashion, handles gaps, handles
partial genes, and identifies translation initiation sites.")
(license license:gpl3+)))
(define-public rsem
(package
(name "rsem")
(version "1.2.20")
(source
(origin
(method url-fetch)
(uri
(string-append "http://deweylab.biostat.wisc.edu/rsem/src/rsem-"
version ".tar.gz"))
(sha256
(base32 "0nzdc0j0hjllhsd5f2xli95dafm3nawskigs140xzvjk67xh0r9q"))
(patches (search-patches "rsem-makefile.patch"))
(modules '((guix build utils)))
(snippet
'(begin
;; remove bundled copy of boost
(delete-file-recursively "boost")
#t))))
(build-system gnu-build-system)
(arguments
`(#:tests? #f ;no "check" target
#:phases
(modify-phases %standard-phases
;; No "configure" script.
;; Do not build bundled samtools library.
(replace 'configure
(lambda _
(substitute* "Makefile"
(("^all : sam/libbam.a") "all : "))
#t))
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let* ((out (string-append (assoc-ref outputs "out")))
(bin (string-append out "/bin/"))
(perl (string-append out "/lib/perl5/site_perl")))
(mkdir-p bin)
(mkdir-p perl)
(for-each (lambda (file)
(copy-file file
(string-append bin (basename file))))
(find-files "." "rsem-.*"))
(copy-file "rsem_perl_utils.pm"
(string-append perl "/rsem_perl_utils.pm")))
#t))
(add-after
'install 'wrap-program
(lambda* (#:key outputs #:allow-other-keys)
(let ((out (assoc-ref outputs "out")))
(for-each (lambda (prog)
(wrap-program (string-append out "/bin/" prog)
`("PERL5LIB" ":" prefix
(,(string-append out "/lib/perl5/site_perl")))))
'("rsem-plot-transcript-wiggles"
"rsem-calculate-expression"
"rsem-generate-ngvector"
"rsem-run-ebseq"
"rsem-prepare-reference")))
#t)))))
(inputs
`(("boost" ,boost)
("ncurses" ,ncurses)
("r" ,r)
("perl" ,perl)
("samtools" ,samtools-0.1)
("zlib" ,zlib)))
(home-page "http://deweylab.biostat.wisc.edu/rsem/")
(synopsis "Estimate gene expression levels from RNA-Seq data")
(description
"RSEM is a software package for estimating gene and isoform expression
levels from RNA-Seq data. The RSEM package provides a user-friendly
interface, supports threads for parallel computation of the EM algorithm,
single-end and paired-end read data, quality scores, variable-length reads and
RSPD estimation. In addition, it provides posterior mean and 95% credibility
interval estimates for expression levels. For visualization, it can generate
BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
(license license:gpl3+)))
(define-public rseqc
(package
(name "rseqc")
(version "2.6.1")
(source
(origin
(method url-fetch)
(uri
(string-append "mirror://sourceforge/rseqc/"
version "/RSeQC-" version ".tar.gz"))
(sha256
(base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
(modules '((guix build utils)))
(snippet
'(begin
;; remove bundled copy of pysam
(delete-file-recursively "lib/pysam")
(substitute* "setup.py"
;; remove dependency on outdated "distribute" module
(("^from distribute_setup import use_setuptools") "")
(("^use_setuptools\\(\\)") "")
;; do not use bundled copy of pysam
(("^have_pysam = False") "have_pysam = True"))))))
(build-system python-build-system)
(arguments `(#:python ,python-2))
(inputs
`(("python-cython" ,python2-cython)
("python-pysam" ,python2-pysam)
("python-numpy" ,python2-numpy)
("python-setuptools" ,python2-setuptools)
("zlib" ,zlib)))
(native-inputs
`(("python-nose" ,python2-nose)))
(home-page "http://rseqc.sourceforge.net/")
(synopsis "RNA-seq quality control package")
(description
"RSeQC provides a number of modules that can comprehensively evaluate
high throughput sequence data, especially RNA-seq data. Some basic modules
inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
while RNA-seq specific modules evaluate sequencing saturation, mapped reads
distribution, coverage uniformity, strand specificity, etc.")
(license license:gpl3+)))
(define-public samtools
(package
(name "samtools")
(version "1.3.1")
(source
(origin
(method url-fetch)
(uri
(string-append "mirror://sourceforge/samtools/"
version "/samtools-" version ".tar.bz2"))
(sha256
(base32
"0znnnxc467jbf1as2dpskrjhfh8mbll760j6w6rdkwlwbqsp8gbc"))))
(build-system gnu-build-system)
(arguments
`(#:modules ((ice-9 ftw)
(ice-9 regex)
(guix build gnu-build-system)
(guix build utils))
#:make-flags (list (string-append "prefix=" (assoc-ref %outputs "out")))
#:configure-flags (list "--with-ncurses")
#:phases
(alist-cons-after
'unpack 'patch-tests
(lambda _
(substitute* "test/test.pl"
;; The test script calls out to /bin/bash
(("/bin/bash") (which "bash")))
#t)
(alist-cons-after
'install 'install-library
(lambda* (#:key outputs #:allow-other-keys)
(let ((lib (string-append (assoc-ref outputs "out") "/lib")))
(install-file "libbam.a" lib)))
(alist-cons-after
'install 'install-headers
(lambda* (#:key outputs #:allow-other-keys)
(let ((include (string-append (assoc-ref outputs "out")
"/include/samtools/")))
(for-each (lambda (file)
(install-file file include))
(scandir "." (lambda (name) (string-match "\\.h$" name))))
#t))
%standard-phases)))))
(native-inputs `(("pkg-config" ,pkg-config)))
(inputs `(("ncurses" ,ncurses)
("perl" ,perl)
("python" ,python)
("zlib" ,zlib)))
(home-page "http://samtools.sourceforge.net")
(synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
(description
"Samtools implements various utilities for post-processing nucleotide
sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
variant calling (in conjunction with bcftools), and a simple alignment
viewer.")
(license license:expat)))
(define-public samtools-0.1
;; This is the most recent version of the 0.1 line of samtools. The input
;; and output formats differ greatly from that used and produced by samtools
;; 1.x and is still used in many bioinformatics pipelines.
(package (inherit samtools)
(version "0.1.19")
(source
(origin
(method url-fetch)
(uri
(string-append "mirror://sourceforge/samtools/"
version "/samtools-" version ".tar.bz2"))
(sha256
(base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
(arguments
`(#:tests? #f ;no "check" target
,@(substitute-keyword-arguments (package-arguments samtools)
((#:make-flags flags)
`(cons "LIBCURSES=-lncurses" ,flags))
((#:phases phases)
`(modify-phases ,phases
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append
(assoc-ref outputs "out") "/bin")))
(mkdir-p bin)
(copy-file "samtools"
(string-append bin "/samtools")))))
(delete 'patch-tests)
(delete 'configure))))))))
(define-public mosaik
(let ((commit "5c25216d"))
(package
(name "mosaik")
(version "2.2.30")
(source (origin
;; There are no release tarballs nor tags.
(method git-fetch)
(uri (git-reference
(url "https://github.com/wanpinglee/MOSAIK.git")
(commit commit)))
(file-name (string-append name "-" version))
(sha256
(base32
"17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
(build-system gnu-build-system)
(arguments
`(#:tests? #f ; no tests
#:make-flags (list "CC=gcc")
#:phases
(modify-phases %standard-phases
(replace 'configure
(lambda _ (chdir "src") #t))
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append (assoc-ref outputs "out")
"/bin")))
(mkdir-p bin)
(copy-recursively "../bin" bin)
#t))))))
(inputs
`(("perl" ,perl)
("zlib" ,zlib)))
(supported-systems '("x86_64-linux"))
(home-page "https://code.google.com/p/mosaik-aligner/")
(synopsis "Map nucleotide sequence reads to reference genomes")
(description
"MOSAIK is a program for mapping second and third-generation sequencing
reads to a reference genome. MOSAIK can align reads generated by all the
major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
;; MOSAIK is released under the GPLv2+ with the exception of third-party
;; code released into the public domain:
;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
;; 2. MD5 implementation - RSA Data Security, RFC 1321
(license (list license:gpl2+ license:public-domain)))))
(define-public ngs-sdk
(package
(name "ngs-sdk")
(version "1.2.3")
(source
(origin
(method url-fetch)
(uri
(string-append "https://github.com/ncbi/ngs/archive/"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"15074fdi94c6pjy83hhk22r86kfvzpaz2i07h3rqg9yy6x3w0pk2"))))
(build-system gnu-build-system)
(arguments
`(#:parallel-build? #f ; not supported
#:tests? #f ; no "check" target
#:phases
(alist-replace
'configure
(lambda* (#:key outputs #:allow-other-keys)
(let ((out (assoc-ref outputs "out")))
;; The 'configure' script doesn't recognize things like
;; '--enable-fast-install'.
(zero? (system* "./configure"
(string-append "--build-prefix=" (getcwd) "/build")
(string-append "--prefix=" out)))))
(alist-cons-after
'unpack 'enter-dir
(lambda _ (chdir "ngs-sdk") #t)
%standard-phases))))
(native-inputs `(("perl" ,perl)))
;; According to the test
;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
;; in ngs-sdk/setup/konfigure.perl
(supported-systems '("i686-linux" "x86_64-linux"))
(home-page "https://github.com/ncbi/ngs")
(synopsis "API for accessing Next Generation Sequencing data")
(description
"NGS is a domain-specific API for accessing reads, alignments and pileups
produced from Next Generation Sequencing. The API itself is independent from
any particular back-end implementation, and supports use of multiple back-ends
simultaneously.")
(license license:public-domain)))
(define-public java-ngs
(package (inherit ngs-sdk)
(name "java-ngs")
(arguments
`(,@(substitute-keyword-arguments
`(#:modules ((guix build gnu-build-system)
(guix build utils)
(srfi srfi-1)
(srfi srfi-26))
,@(package-arguments ngs-sdk))
((#:phases phases)
`(modify-phases ,phases
(replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
(inputs
`(("jdk" ,icedtea "jdk")
("ngs-sdk" ,ngs-sdk)))
(synopsis "Java bindings for NGS SDK")))
(define-public ncbi-vdb
(package
(name "ncbi-vdb")
(version "2.5.7")
(source
(origin
(method url-fetch)
(uri
(string-append "https://github.com/ncbi/ncbi-vdb/archive/"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"0hay5hy8ynva3mi5wbn4wmq1q23qwxc3aqzbb86hg3x4f1r73270"))))
(build-system gnu-build-system)
(arguments
`(#:parallel-build? #f ; not supported
#:tests? #f ; no "check" target
#:phases
(alist-replace
'configure
(lambda* (#:key inputs outputs #:allow-other-keys)
(let ((out (assoc-ref outputs "out")))
;; Override include path for libmagic
(substitute* "setup/package.prl"
(("name => 'magic', Include => '/usr/include'")
(string-append "name=> 'magic', Include => '"
(assoc-ref inputs "libmagic")
"/include" "'")))
;; Install kdf5 library (needed by sra-tools)
(substitute* "build/Makefile.install"
(("LIBRARIES_TO_INSTALL =")
"LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
;; The 'configure' script doesn't recognize things like
;; '--enable-fast-install'.
(zero? (system*
"./configure"
(string-append "--build-prefix=" (getcwd) "/build")
(string-append "--prefix=" (assoc-ref outputs "out"))
(string-append "--debug")
(string-append "--with-xml2-prefix="
(assoc-ref inputs "libxml2"))
(string-append "--with-ngs-sdk-prefix="
(assoc-ref inputs "ngs-sdk"))
(string-append "--with-ngs-java-prefix="
(assoc-ref inputs "java-ngs"))
(string-append "--with-hdf5-prefix="
(assoc-ref inputs "hdf5"))))))
(alist-cons-after
'install 'install-interfaces
(lambda* (#:key outputs #:allow-other-keys)
;; Install interface libraries. On i686 the interface libraries
;; are installed to "linux/gcc/i386", so we need to use the Linux
;; architecture name ("i386") instead of the target system prefix
;; ("i686").
(mkdir (string-append (assoc-ref outputs "out") "/ilib"))
(copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
,(system->linux-architecture
(or (%current-target-system)
(%current-system)))
"/rel/ilib")
(string-append (assoc-ref outputs "out")
"/ilib"))
;; Install interface headers
(copy-recursively "interfaces"
(string-append (assoc-ref outputs "out")
"/include")))
%standard-phases))))
(inputs
`(("libxml2" ,libxml2)
("ngs-sdk" ,ngs-sdk)
("java-ngs" ,java-ngs)
("libmagic" ,file)
("hdf5" ,hdf5)))
(native-inputs `(("perl" ,perl)))
(home-page "https://github.com/ncbi/ncbi-vdb")
(synopsis "Database engine for genetic information")
(description
"The NCBI-VDB library implements a highly compressed columnar data
warehousing engine that is most often used to store genetic information.
Databases are stored in a portable image within the file system, and can be
accessed/downloaded on demand across HTTP.")
(license license:public-domain)))
(define-public plink
(package
(name "plink")
(version "1.07")
(source
(origin
(method url-fetch)
(uri (string-append
"http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
version "-src.zip"))
(sha256
(base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
(patches (search-patches "plink-1.07-unclobber-i.patch"))))
(build-system gnu-build-system)
(arguments
'(#:tests? #f ;no "check" target
#:make-flags (list (string-append "LIB_LAPACK="
(assoc-ref %build-inputs "lapack")
"/lib/liblapack.so")
"WITH_LAPACK=1"
"FORCE_DYNAMIC=1"
;; disable phoning home
"WITH_WEBCHECK=")
#:phases
(modify-phases %standard-phases
;; no "configure" script
(delete 'configure)
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append (assoc-ref outputs "out")
"/bin/")))
(install-file "plink" bin)
#t))))))
(inputs
`(("zlib" ,zlib)
("lapack" ,lapack)))
(native-inputs
`(("unzip" ,unzip)))
(home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
(synopsis "Whole genome association analysis toolset")
(description
"PLINK is a whole genome association analysis toolset, designed to
perform a range of basic, large-scale analyses in a computationally efficient
manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
so there is no support for steps prior to this (e.g. study design and
planning, generating genotype or CNV calls from raw data). Through
integration with gPLINK and Haploview, there is some support for the
subsequent visualization, annotation and storage of results.")
;; Code is released under GPLv2, except for fisher.h, which is under
;; LGPLv2.1+
(license (list license:gpl2 license:lgpl2.1+))))
(define-public smithlab-cpp
(let ((revision "1")
(commit "728a097"))
(package
(name "smithlab-cpp")
(version (string-append "0." revision "." commit))
(source (origin
(method git-fetch)
(uri (git-reference
(url "https://github.com/smithlabcode/smithlab_cpp.git")
(commit commit)))
(file-name (string-append name "-" version "-checkout"))
(sha256
(base32
"0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
(build-system gnu-build-system)
(arguments
`(#:modules ((guix build gnu-build-system)
(guix build utils)
(srfi srfi-26))
#:tests? #f ;no "check" target
#:phases
(modify-phases %standard-phases
(add-after 'unpack 'use-samtools-headers
(lambda _
(substitute* '("SAM.cpp"
"SAM.hpp")
(("sam.h") "samtools/sam.h"))
#t))
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let* ((out (assoc-ref outputs "out"))
(lib (string-append out "/lib"))
(include (string-append out "/include/smithlab-cpp")))
(mkdir-p lib)
(mkdir-p include)
(for-each (cut install-file <> lib)
(find-files "." "\\.o$"))
(for-each (cut install-file <> include)
(find-files "." "\\.hpp$")))
#t))
(delete 'configure))))
(inputs
`(("samtools" ,samtools-0.1)
("zlib" ,zlib)))
(home-page "https://github.com/smithlabcode/smithlab_cpp")
(synopsis "C++ helper library for functions used in Smith lab projects")
(description
"Smithlab CPP is a C++ library that includes functions used in many of
the Smith lab bioinformatics projects, such as a wrapper around Samtools data
structures, classes for genomic regions, mapped sequencing reads, etc.")
(license license:gpl3+))))
(define-public preseq
(package
(name "preseq")
(version "2.0")
(source (origin
(method url-fetch)
(uri (string-append "https://github.com/smithlabcode/"
"preseq/archive/v" version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32 "08r684l50pnxjpvmhzjgqq56yv9rfw90k8vx0nsrnrzk8mf9hsdq"))
(modules '((guix build utils)))
(snippet
;; Remove bundled samtools.
'(delete-file-recursively "samtools"))))
(build-system gnu-build-system)
(arguments
`(#:tests? #f ;no "check" target
#:phases
(modify-phases %standard-phases
(delete 'configure))
#:make-flags
(list (string-append "PREFIX="
(assoc-ref %outputs "out"))
(string-append "LIBBAM="
(assoc-ref %build-inputs "samtools")
"/lib/libbam.a")
(string-append "SMITHLAB_CPP="
(assoc-ref %build-inputs "smithlab-cpp")
"/lib")
"PROGS=preseq"
"INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
(inputs
`(("gsl" ,gsl)
("samtools" ,samtools-0.1)
("smithlab-cpp" ,smithlab-cpp)
("zlib" ,zlib)))
(home-page "http://smithlabresearch.org/software/preseq/")
(synopsis "Program for analyzing library complexity")
(description
"The preseq package is aimed at predicting and estimating the complexity
of a genomic sequencing library, equivalent to predicting and estimating the
number of redundant reads from a given sequencing depth and how many will be
expected from additional sequencing using an initial sequencing experiment.
The estimates can then be used to examine the utility of further sequencing,
optimize the sequencing depth, or to screen multiple libraries to avoid low
complexity samples.")
(license license:gpl3+)))
(define-public sra-tools
(package
(name "sra-tools")
(version "2.5.7")
(source
(origin
(method url-fetch)
(uri
(string-append "https://github.com/ncbi/sra-tools/archive/"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"0q93qg744x787d08qmjmdafki1wkbvkdwynayjnjd454gkd26jl5"))))
(build-system gnu-build-system)
(arguments
`(#:parallel-build? #f ; not supported
#:tests? #f ; no "check" target
#:phases
(alist-replace
'configure
(lambda* (#:key inputs outputs #:allow-other-keys)
;; The build system expects a directory containing the sources and
;; raw build output of ncbi-vdb, including files that are not
;; installed. Since we are building against an installed version of
;; ncbi-vdb, the following modifications are needed.
(substitute* "setup/konfigure.perl"
;; Make the configure script look for the "ilib" directory of
;; "ncbi-vdb" without first checking for the existence of a
;; matching library in its "lib" directory.
(("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
"my $f = File::Spec->catdir($ilibdir, $ilib);")
;; Look for interface libraries in ncbi-vdb's "ilib" directory.
(("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
"my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
;; The 'configure' script doesn't recognize things like
;; '--enable-fast-install'.
(zero? (system*
"./configure"
(string-append "--build-prefix=" (getcwd) "/build")
(string-append "--prefix=" (assoc-ref outputs "out"))
(string-append "--debug")
(string-append "--with-fuse-prefix="
(assoc-ref inputs "fuse"))
(string-append "--with-magic-prefix="
(assoc-ref inputs "libmagic"))
;; TODO: building with libxml2 fails with linker errors
;; (string-append "--with-xml2-prefix="
;; (assoc-ref inputs "libxml2"))
(string-append "--with-ncbi-vdb-sources="
(assoc-ref inputs "ncbi-vdb"))
(string-append "--with-ncbi-vdb-build="
(assoc-ref inputs "ncbi-vdb"))
(string-append "--with-ngs-sdk-prefix="
(assoc-ref inputs "ngs-sdk"))
(string-append "--with-hdf5-prefix="
(assoc-ref inputs "hdf5")))))
%standard-phases)))
(native-inputs `(("perl" ,perl)))
(inputs
`(("ngs-sdk" ,ngs-sdk)
("ncbi-vdb" ,ncbi-vdb)
("libmagic" ,file)
("fuse" ,fuse)
("hdf5" ,hdf5)
("zlib" ,zlib)))
(home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
(synopsis "Tools and libraries for reading and writing sequencing data")
(description
"The SRA Toolkit from NCBI is a collection of tools and libraries for
reading of sequencing files from the Sequence Read Archive (SRA) database and
writing files into the .sra format.")
(license license:public-domain)))
(define-public seqan
(package
(name "seqan")
(version "1.4.2")
(source (origin
(method url-fetch)
(uri (string-append "http://packages.seqan.de/seqan-library/"
"seqan-library-" version ".tar.bz2"))
(sha256
(base32
"05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
;; makes sense to split the outputs.
(outputs '("out" "doc"))
(build-system trivial-build-system)
(arguments
`(#:modules ((guix build utils))
#:builder
(begin
(use-modules (guix build utils))
(let ((tar (assoc-ref %build-inputs "tar"))
(bzip (assoc-ref %build-inputs "bzip2"))
(out (assoc-ref %outputs "out"))
(doc (assoc-ref %outputs "doc")))
(setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
(system* "tar" "xvf" (assoc-ref %build-inputs "source"))
(chdir (string-append "seqan-library-" ,version))
(copy-recursively "include" (string-append out "/include"))
(copy-recursively "share" (string-append doc "/share"))))))
(native-inputs
`(("source" ,source)
("tar" ,tar)
("bzip2" ,bzip2)))
(home-page "http://www.seqan.de")
(synopsis "Library for nucleotide sequence analysis")
(description
"SeqAn is a C++ library of efficient algorithms and data structures for
the analysis of sequences with the focus on biological data. It contains
algorithms and data structures for string representation and their
manipulation, online and indexed string search, efficient I/O of
bioinformatics file formats, sequence alignment, and more.")
(license license:bsd-3)))
(define-public seqmagick
(package
(name "seqmagick")
(version "0.6.1")
(source
(origin
(method url-fetch)
(uri (string-append
"https://pypi.python.org/packages/source/s/seqmagick/seqmagick-"
version ".tar.gz"))
(sha256
(base32
"0cgn477n74gsl4qdaakrrhi953kcsd4q3ivk2lr18x74s3g4ma1d"))))
(build-system python-build-system)
(arguments
;; python2 only, see https://github.com/fhcrc/seqmagick/issues/56
`(#:python ,python-2
#:phases
(modify-phases %standard-phases
;; Current test in setup.py does not work as of 0.6.1,
;; so use nose to run tests instead for now. See
;; https://github.com/fhcrc/seqmagick/issues/55
(replace 'check (lambda _ (zero? (system* "nosetests")))))))
(inputs
`(("python-biopython" ,python2-biopython)))
(native-inputs
`(("python-setuptools" ,python2-setuptools)
("python-nose" ,python2-nose)))
(home-page "http://github.com/fhcrc/seqmagick")
(synopsis "Tools for converting and modifying sequence files")
(description
"Bioinformaticians often have to convert sequence files between formats
and do little manipulations on them, and it's not worth writing scripts for
that. Seqmagick is a utility to expose the file format conversion in
BioPython in a convenient way. Instead of having a big mess of scripts, there
is one that takes arguments.")
(license license:gpl3)))
(define-public snap-aligner
(package
(name "snap-aligner")
(version "1.0beta.18")
(source (origin
(method url-fetch)
(uri (string-append
"https://github.com/amplab/snap/archive/v"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"1vnsjwv007k1fl1q7d681kbwn6bc66cgw6h16hym6gvyy71qv2ly"))))
(build-system gnu-build-system)
(arguments
'(#:phases
(modify-phases %standard-phases
(delete 'configure)
(replace 'check (lambda _ (zero? (system* "./unit_tests"))))
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let* ((out (assoc-ref outputs "out"))
(bin (string-append out "/bin")))
(mkdir-p bin)
(install-file "snap-aligner" bin)
(install-file "SNAPCommand" bin)
#t))))))
(native-inputs
`(("zlib" ,zlib)))
(home-page "http://snap.cs.berkeley.edu/")
(synopsis "Short read DNA sequence aligner")
(description
"SNAP is a fast and accurate aligner for short DNA reads. It is
optimized for modern read lengths of 100 bases or higher, and takes advantage
of these reads to align data quickly through a hash-based indexing scheme.")
(license license:asl2.0)))
(define-public sortmerna
(package
(name "sortmerna")
(version "2.1")
(source
(origin
(method url-fetch)
(uri (string-append
"https://github.com/biocore/sortmerna/archive/"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"1mc5cf1c7xh0h7xb11vh7gqgzx0qvrfa606cb8ixlfg3f2av58s4"))))
(build-system gnu-build-system)
(outputs '("out" ;for binaries
"db")) ;for sequence databases
(arguments
`(#:phases
(modify-phases %standard-phases
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let* ((out (assoc-ref outputs "out"))
(bin (string-append out "/bin"))
(db (assoc-ref outputs "db"))
(share
(string-append db "/share/sortmerna/rRNA_databases")))
(install-file "sortmerna" bin)
(install-file "indexdb_rna" bin)
(for-each (lambda (file)
(install-file file share))
(find-files "rRNA_databases" ".*fasta"))
#t))))))
(home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
(synopsis "Biological sequence analysis tool for NGS reads")
(description
"SortMeRNA is a biological sequence analysis tool for filtering, mapping
and operational taxonomic unit (OTU) picking of next generation
sequencing (NGS) reads. The core algorithm is based on approximate seeds and
allows for fast and sensitive analyses of nucleotide sequences. The main
application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
(license license:lgpl3)))
(define-public star
(package
(name "star")
(version "2.5.1b")
(source (origin
(method url-fetch)
(uri (string-append "https://github.com/alexdobin/STAR/archive/"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"0wzcfhkg10apnh0y73xlarfa79xxwxdizicbdl11wb48awk44iq4"))
(modules '((guix build utils)))
(snippet
'(begin
(substitute* "source/Makefile"
(("/bin/rm") "rm"))
;; Remove pre-built binaries and bundled htslib sources.
(delete-file-recursively "bin/MacOSX_x86_64")
(delete-file-recursively "bin/Linux_x86_64")
(delete-file-recursively "source/htslib")
#t))))
(build-system gnu-build-system)
(arguments
'(#:tests? #f ;no check target
#:make-flags '("STAR")
#:phases
(modify-phases %standard-phases
(add-after 'unpack 'enter-source-dir
(lambda _ (chdir "source") #t))
(add-after 'enter-source-dir 'do-not-use-bundled-htslib
(lambda _
(substitute* "Makefile"
(("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
_ prefix) prefix))
(substitute* '("BAMfunctions.cpp"
"signalFromBAM.h"
"bam_cat.h"
"bam_cat.c"
"STAR.cpp"
"bamRemoveDuplicates.cpp")
(("#include \"htslib/([^\"]+\\.h)\"" _ header)
(string-append "#include <" header ">")))
(substitute* "IncludeDefine.h"
(("\"htslib/(htslib/[^\"]+.h)\"" _ header)
(string-append "<" header ">")))
#t))
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
(install-file "STAR" bin))
#t))
(delete 'configure))))
(native-inputs
`(("vim" ,vim))) ; for xxd
(inputs
`(("htslib" ,htslib)
("zlib" ,zlib)))
(home-page "https://github.com/alexdobin/STAR")
(synopsis "Universal RNA-seq aligner")
(description
"The Spliced Transcripts Alignment to a Reference (STAR) software is
based on a previously undescribed RNA-seq alignment algorithm that uses
sequential maximum mappable seed search in uncompressed suffix arrays followed
by seed clustering and stitching procedure. In addition to unbiased de novo
detection of canonical junctions, STAR can discover non-canonical splices and
chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
sequences.")
;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
(license license:gpl3+)))
(define-public subread
(package
(name "subread")
(version "1.4.6-p2")
(source (origin
(method url-fetch)
(uri (string-append
"mirror://sourceforge/subread/subread-"
version "-source.tar.gz"))
(sha256
(base32
"06sv9mpcsdj6p68y15d6gi70lca3lxmzk0dn61hg0kfsa7rxmsr3"))))
(build-system gnu-build-system)
(arguments
`(#:tests? #f ;no "check" target
;; The CC and CCFLAGS variables are set to contain a lot of x86_64
;; optimizations by default, so we override these flags such that x86_64
;; flags are only added when the build target is an x86_64 system.
#:make-flags
(list (let ((system ,(or (%current-target-system)
(%current-system)))
(flags '("-ggdb" "-fomit-frame-pointer"
"-ffast-math" "-funroll-loops"
"-fmessage-length=0"
"-O9" "-Wall" "-DMAKE_FOR_EXON"
"-DMAKE_STANDALONE"
"-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
(flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
(if (string-prefix? "x86_64" system)
(string-append "CCFLAGS=" (string-join (append flags flags64)))
(string-append "CCFLAGS=" (string-join flags))))
"-f" "Makefile.Linux"
"CC=gcc ${CCFLAGS}")
#:phases
(alist-cons-after
'unpack 'enter-dir
(lambda _ (chdir "src") #t)
(alist-replace
'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
(mkdir-p bin)
(copy-recursively "../bin" bin)))
;; no "configure" script
(alist-delete 'configure %standard-phases)))))
(inputs `(("zlib" ,zlib)))
(home-page "http://bioinf.wehi.edu.au/subread-package/")
(synopsis "Tool kit for processing next-gen sequencing data")
(description
"The subread package contains the following tools: subread aligner, a
general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
features; exactSNP: a SNP caller that discovers SNPs by testing signals
against local background noises.")
(license license:gpl3+)))
(define-public stringtie
(package
(name "stringtie")
(version "1.2.1")
(source (origin
(method url-fetch)
(uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
"stringtie-" version ".tar.gz"))
(sha256
(base32
"1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
(modules '((guix build utils)))
(snippet
'(begin
(delete-file-recursively "samtools-0.1.18")
#t))))
(build-system gnu-build-system)
(arguments
`(#:tests? #f ;no test suite
#:phases
(modify-phases %standard-phases
;; no configure script
(delete 'configure)
(add-before 'build 'use-system-samtools
(lambda _
(substitute* "Makefile"
(("stringtie: \\$\\{BAM\\}/libbam\\.a")
"stringtie: "))
(substitute* '("gclib/GBam.h"
"gclib/GBam.cpp")
(("#include \"(bam|sam|kstring).h\"" _ header)
(string-append "#include <samtools/" header ".h>")))
#t))
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
(install-file "stringtie" bin)
#t))))))
(inputs
`(("samtools" ,samtools-0.1)
("zlib" ,zlib)))
(home-page "http://ccb.jhu.edu/software/stringtie/")
(synopsis "Transcript assembly and quantification for RNA-Seq data")
(description
"StringTie is a fast and efficient assembler of RNA-Seq sequence
alignments into potential transcripts. It uses a novel network flow algorithm
as well as an optional de novo assembly step to assemble and quantitate
full-length transcripts representing multiple splice variants for each gene
locus. Its input can include not only the alignments of raw reads used by
other transcript assemblers, but also alignments of longer sequences that have
been assembled from those reads. To identify differentially expressed genes
between experiments, StringTie's output can be processed either by the
Cuffdiff or Ballgown programs.")
(license license:artistic2.0)))
(define-public vcftools
(package
(name "vcftools")
(version "0.1.14")
(source (origin
(method url-fetch)
(uri (string-append
"https://github.com/vcftools/vcftools/releases/download/v"
version "/vcftools-" version ".tar.gz"))
(sha256
(base32
"10l5c07z9p4i9pr4gl54b2c9h6ndhqlbq1rashg2zcgwkbfrkmvn"))))
(build-system gnu-build-system)
(arguments
`(#:tests? #f ; no "check" target
#:make-flags (list
"CFLAGS=-O2" ; override "-m64" flag
(string-append "PREFIX=" (assoc-ref %outputs "out"))
(string-append "MANDIR=" (assoc-ref %outputs "out")
"/share/man/man1"))))
(native-inputs
`(("pkg-config" ,pkg-config)))
(inputs
`(("perl" ,perl)
("zlib" ,zlib)))
(home-page "https://vcftools.github.io/")
(synopsis "Tools for working with VCF files")
(description
"VCFtools is a program package designed for working with VCF files, such
as those generated by the 1000 Genomes Project. The aim of VCFtools is to
provide easily accessible methods for working with complex genetic variation
data in the form of VCF files.")
;; The license is declared as LGPLv3 in the README and
;; at https://vcftools.github.io/license.html
(license license:lgpl3)))
(define-public vsearch
(package
(name "vsearch")
(version "1.10.0")
(source
(origin
(method url-fetch)
(uri (string-append
"https://github.com/torognes/vsearch/archive/v"
version ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32
"1i3bad7gnn2y3a1yfixzshd99xdkjc8w5bxzgifpysc6jiljwvb5"))
(modules '((guix build utils)))
(snippet
'(begin
;; Remove bundled cityhash and '-mtune=native'.
(substitute* "src/Makefile.am"
(("^AM_CXXFLAGS=-I\\$\\{srcdir\\}/cityhash \
-O3 -mtune=native -Wall -Wsign-compare")
(string-append "AM_CXXFLAGS=-lcityhash"
" -O3 -Wall -Wsign-compare"))
(("^__top_builddir__bin_vsearch_SOURCES = city.h \\\\")
"__top_builddir__bin_vsearch_SOURCES = \\")
(("^city.h \\\\") "\\")
(("^citycrc.h \\\\") "\\")
(("^libcityhash_a.*") "")
(("noinst_LIBRARIES = libcpu_sse2.a libcpu_ssse3.a \
libcityhash.a")
"noinst_LIBRARIES = libcpu_sse2.a libcpu_ssse3.a")
(("__top_builddir__bin_vsearch_LDADD = libcpu_ssse3.a \
libcpu_sse2.a libcityhash.a")
"__top_builddir__bin_vsearch_LDADD = libcpu_ssse3.a \
libcpu_sse2.a -lcityhash"))
(substitute* "src/vsearch.h"
(("^\\#include \"city.h\"") "#include <city.h>")
(("^\\#include \"citycrc.h\"") "#include <citycrc.h>"))
(delete-file "src/city.h")
(delete-file "src/citycrc.h")
(delete-file "src/city.cc")
#t))))
(build-system gnu-build-system)
(arguments
`(#:phases
(modify-phases %standard-phases
(add-before 'configure 'autogen
(lambda _ (zero? (system* "autoreconf" "-vif")))))))
(inputs
`(("zlib" ,zlib)
("bzip2" ,bzip2)
("cityhash" ,cityhash)))
(native-inputs
`(("autoconf" ,autoconf)
("automake" ,automake)))
(synopsis "Sequence search tools for metagenomics")
(description
"VSEARCH supports DNA sequence searching, clustering, chimera detection,
dereplication, pairwise alignment, shuffling, subsampling, sorting and
masking. The tool takes advantage of parallelism in the form of SIMD
vectorization as well as multiple threads to perform accurate alignments at
high speed. VSEARCH uses an optimal global aligner (full dynamic programming
Needleman-Wunsch).")
(home-page "https://github.com/torognes/vsearch")
;; vsearch uses non-portable SSE intrinsics so building fails on other
;; platforms.
(supported-systems '("x86_64-linux"))
;; Dual licensed; also includes public domain source.
(license (list license:gpl3 license:bsd-2))))
(define-public bio-locus
(package
(name "bio-locus")
(version "0.0.7")
(source
(origin
(method url-fetch)
(uri (rubygems-uri "bio-locus" version))
(sha256
(base32
"02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
(build-system ruby-build-system)
(native-inputs
`(("ruby-rspec" ,ruby-rspec)))
(synopsis "Tool for fast querying of genome locations")
(description
"Bio-locus is a tabix-like tool for fast querying of genome
locations. Many file formats in bioinformatics contain records that
start with a chromosome name and a position for a SNP, or a start-end
position for indels. Bio-locus allows users to store this chr+pos or
chr+pos+alt information in a database.")
(home-page "https://github.com/pjotrp/bio-locus")
(license license:expat)))
(define-public bio-blastxmlparser
(package
(name "bio-blastxmlparser")
(version "2.0.4")
(source (origin
(method url-fetch)
(uri (rubygems-uri "bio-blastxmlparser" version))
(sha256
(base32
"1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
(build-system ruby-build-system)
(propagated-inputs
`(("ruby-bio-logger" ,ruby-bio-logger)
("ruby-nokogiri" ,ruby-nokogiri)))
(inputs
`(("ruby-rspec" ,ruby-rspec)))
(synopsis "Fast big data BLAST XML parser and library")
(description
"Very fast parallel big-data BLAST XML file parser which can be used as
command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
(home-page "http://github.com/pjotrp/blastxmlparser")
(license license:expat)))
(define-public bioruby
(package
(name "bioruby")
(version "1.5.0")
(source
(origin
(method url-fetch)
(uri (rubygems-uri "bio" version))
(sha256
(base32
"01k2fyjl5fpx4zn8g6gqiqvsg2j1fgixrs9p03vzxckynxdq3wmc"))))
(build-system ruby-build-system)
(propagated-inputs
`(("ruby-libxml" ,ruby-libxml)))
(native-inputs
`(("which" ,which))) ; required for test phase
(arguments
`(#:phases
(modify-phases %standard-phases
(add-before 'build 'patch-test-command
(lambda _
(substitute* '("test/functional/bio/test_command.rb")
(("/bin/sh") (which "sh")))
(substitute* '("test/functional/bio/test_command.rb")
(("/bin/ls") (which "ls")))
(substitute* '("test/functional/bio/test_command.rb")
(("which") (which "which")))
(substitute* '("test/functional/bio/test_command.rb",
"test/data/command/echoarg2.sh")
(("/bin/echo") (which "echo")))
#t)))))
(synopsis "Ruby library, shell and utilities for bioinformatics")
(description "BioRuby comes with a comprehensive set of Ruby development
tools and libraries for bioinformatics and molecular biology. BioRuby has
components for sequence analysis, pathway analysis, protein modelling and
phylogenetic analysis; it supports many widely used data formats and provides
easy access to databases, external programs and public web services, including
BLAST, KEGG, GenBank, MEDLINE and GO.")
(home-page "http://bioruby.org/")
;; Code is released under Ruby license, except for setup
;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
(license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
(define-public r-acsnminer
(package
(name "r-acsnminer")
(version "0.16.01.29")
(source (origin
(method url-fetch)
(uri (cran-uri "ACSNMineR" version))
(sha256
(base32
"1b1243wkncanm1blkqzicjgzb576vzcg4iwinsgn2xqr7f264amf"))))
(properties `((upstream-name . "ACSNMineR")))
(build-system r-build-system)
(propagated-inputs
`(("r-ggplot2" ,r-ggplot2)
("r-gridextra" ,r-gridextra)))
(home-page "http://cran.r-project.org/web/packages/ACSNMineR")
(synopsis "Gene enrichment analysis")
(description
"This package provides tools to compute and represent gene set enrichment
or depletion from your data based on pre-saved maps from the @dfn{Atlas of
Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
enrichment can be run with hypergeometric test or Fisher exact test, and can
use multiple corrections. Visualization of data can be done either by
barplots or heatmaps.")
(license license:gpl2+)))
(define-public r-biocgenerics
(package
(name "r-biocgenerics")
(version "0.18.0")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "BiocGenerics" version))
(sha256
(base32
"1jjp48vbph09w5bmc7368gjjywsa1lmzfybpiwlypr60b51vlkp6"))))
(properties
`((upstream-name . "BiocGenerics")))
(build-system r-build-system)
(home-page "http://bioconductor.org/packages/BiocGenerics")
(synopsis "S4 generic functions for Bioconductor")
(description
"This package provides S4 generic functions needed by many Bioconductor
packages.")
(license license:artistic2.0)))
(define-public r-dnacopy
(package
(name "r-dnacopy")
(version "1.46.0")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "DNAcopy" version))
(sha256
(base32
"0vwv2mndfjpcjp4sybg75abc7xnx8zyw8zjk717k6xh8c33ymcip"))))
(properties
`((upstream-name . "DNAcopy")))
(build-system r-build-system)
(inputs
`(("gfortran" ,gfortran)))
(home-page "https://bioconductor.org/packages/DNAcopy")
(synopsis "Implementation of a circular binary segmentation algorithm")
(description "This package implements the circular binary segmentation (CBS)
algorithm to segment DNA copy number data and identify genomic regions with
abnormal copy number.")
(license license:gpl2+)))
(define-public r-s4vectors
(package
(name "r-s4vectors")
(version "0.10.0")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "S4Vectors" version))
(sha256
(base32
"1mi6lf6pnb9l657igy0vj4yz03yawbr2jhk22l757fzbjc7n9q3b"))))
(properties
`((upstream-name . "S4Vectors")))
(build-system r-build-system)
(propagated-inputs
`(("r-biocgenerics" ,r-biocgenerics)))
(home-page "http://bioconductor.org/packages/S4Vectors")
(synopsis "S4 implementation of vectors and lists")
(description
"The S4Vectors package defines the @code{Vector} and @code{List} virtual
classes and a set of generic functions that extend the semantic of ordinary
vectors and lists in R. Package developers can easily implement vector-like
or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
In addition, a few low-level concrete subclasses of general interest (e.g.
@code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
S4Vectors package itself.")
(license license:artistic2.0)))
(define-public r-iranges
(package
(name "r-iranges")
(version "2.6.0")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "IRanges" version))
(sha256
(base32
"0dz7z0pk8hq79mcgylw920999s08h6j8xrl31rdxhssmi7l8v6vy"))))
(properties
`((upstream-name . "IRanges")))
(build-system r-build-system)
(propagated-inputs
`(("r-biocgenerics" ,r-biocgenerics)
("r-s4vectors" ,r-s4vectors)))
(home-page "http://bioconductor.org/packages/IRanges")
(synopsis "Infrastructure for manipulating intervals on sequences")
(description
"This package provides efficient low-level and highly reusable S4 classes
for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
generally, data that can be organized sequentially (formally defined as
@code{Vector} objects), as well as views on these @code{Vector} objects.
Efficient list-like classes are also provided for storing big collections of
instances of the basic classes. All classes in the package use consistent
naming and share the same rich and consistent \"Vector API\" as much as
possible.")
(license license:artistic2.0)))
(define-public r-genomeinfodb
(package
(name "r-genomeinfodb")
(version "1.8.0")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "GenomeInfoDb" version))
(sha256
(base32
"0fcfzw3d0rxlc320bvz0vlxg26fa1278abhjmknb815046g7fn3s"))))
(properties
`((upstream-name . "GenomeInfoDb")))
(build-system r-build-system)
(propagated-inputs
`(("r-biocgenerics" ,r-biocgenerics)
("r-iranges" ,r-iranges)
("r-s4vectors" ,r-s4vectors)))
(home-page "http://bioconductor.org/packages/GenomeInfoDb")
(synopsis "Utilities for manipulating chromosome identifiers")
(description
"This package contains data and functions that define and allow
translation between different chromosome sequence naming conventions (e.g.,
\"chr1\" versus \"1\"), including a function that attempts to place sequence
names in their natural, rather than lexicographic, order.")
(license license:artistic2.0)))
(define-public r-variantannotation
(package
(name "r-variantannotation")
(version "1.18.0")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "VariantAnnotation" version))
(sha256
(base32
"1mjm5kav0mjymcj3ha1jnw9snym39w5vc2zkl25dpg78nl00nwar"))))
(properties
`((upstream-name . "VariantAnnotation")))
(inputs
`(("zlib" ,zlib)))
(propagated-inputs
`(("r-annotationdbi" ,r-annotationdbi)
("r-biocgenerics" ,r-biocgenerics)
("r-bsgenome" ,r-bsgenome)
("r-dbi" ,r-dbi)
("r-genomeinfodb" ,r-genomeinfodb)
("r-genomicfeatures" ,r-genomicfeatures)
("r-genomicranges" ,r-genomicranges)
("r-summarizedexperiment" ,r-summarizedexperiment)
("r-rsamtools" ,r-rsamtools)
("r-zlibbioc" ,r-zlibbioc)))
(build-system r-build-system)
(home-page "https://bioconductor.org/packages/VariantAnnotation")
(synopsis "Package for annotation of genetic variants")
(description "This R package can annotate variants, compute amino acid
coding changes and predict coding outcomes.")
(license license:artistic2.0)))
(define-public r-xvector
(package
(name "r-xvector")
(version "0.12.0")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "XVector" version))
(sha256
(base32
"0c9cqjcxxks3an4wiq167h2grxlfyazajn7bmxhbk42zifp8vmqp"))))
(properties
`((upstream-name . "XVector")))
(build-system r-build-system)
(arguments
`(#:phases
(modify-phases %standard-phases
(add-after 'unpack 'use-system-zlib
(lambda _
(substitute* "DESCRIPTION"
(("zlibbioc, ") ""))
(substitute* "NAMESPACE"
(("import\\(zlibbioc\\)") ""))
#t)))))
(inputs
`(("zlib" ,zlib)))
(propagated-inputs
`(("r-biocgenerics" ,r-biocgenerics)
("r-iranges" ,r-iranges)
("r-s4vectors" ,r-s4vectors)))
(home-page "http://bioconductor.org/packages/XVector")
(synopsis "Representation and manpulation of external sequences")
(description
"This package provides memory efficient S4 classes for storing sequences
\"externally\" (behind an R external pointer, or on disk).")
(license license:artistic2.0)))
(define-public r-genomicranges
(package
(name "r-genomicranges")
(version "1.24.0")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "GenomicRanges" version))
(sha256
(base32
"1iyzg1npl3rnnslwq3h759vf0xhshnn5v801rnlj6bnxzhn9yaqh"))))
(properties
`((upstream-name . "GenomicRanges")))
(build-system r-build-system)
(propagated-inputs
`(("r-biocgenerics" ,r-biocgenerics)
("r-genomeinfodb" ,r-genomeinfodb)
("r-xvector" ,r-xvector)))
(home-page "http://bioconductor.org/packages/GenomicRanges")
(synopsis "Representation and manipulation of genomic intervals")
(description
"This package provides tools to efficiently represent and manipulate
genomic annotations and alignments is playing a central role when it comes to
analyzing high-throughput sequencing data (a.k.a. NGS data). The
GenomicRanges package defines general purpose containers for storing and
manipulating genomic intervals and variables defined along a genome.")
(license license:artistic2.0)))
(define-public r-biobase
(package
(name "r-biobase")
(version "2.30.0")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "Biobase" version))
(sha256
(base32
"1qasjpq3kw8h7qw8cin3bjvv1256hqr1mm24fq3v0ymxzlb66szi"))))
(properties
`((upstream-name . "Biobase")))
(build-system r-build-system)
(propagated-inputs
`(("r-biocgenerics" ,r-biocgenerics)))
(home-page "http://bioconductor.org/packages/Biobase")
(synopsis "Base functions for Bioconductor")
(description
"This package provides functions that are needed by many other packages
on Bioconductor or which replace R functions.")
(license license:artistic2.0)))
(define-public r-annotationdbi
(package
(name "r-annotationdbi")
(version "1.32.3")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "AnnotationDbi" version))
(sha256
(base32
"1v6x62hgys5827yg2xayjrd9xawbayzm6wy0q4vxh1s6yxc9bklj"))))
(properties
`((upstream-name . "AnnotationDbi")))
(build-system r-build-system)
(propagated-inputs
`(("r-biobase" ,r-biobase)
("r-biocgenerics" ,r-biocgenerics)
("r-dbi" ,r-dbi)
("r-iranges" ,r-iranges)
("r-rsqlite" ,r-rsqlite)
("r-s4vectors" ,r-s4vectors)))
(home-page "http://bioconductor.org/packages/AnnotationDbi")
(synopsis "Annotation database interface")
(description
"This package provides user interface and database connection code for
annotation data packages using SQLite data storage.")
(license license:artistic2.0)))
(define-public r-biomart
(package
(name "r-biomart")
(version "2.26.1")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "biomaRt" version))
(sha256
(base32
"1s709055abj2gd35g6nnk5d2ai5ii09iir270l2xika6pi62gj3f"))))
(properties
`((upstream-name . "biomaRt")))
(build-system r-build-system)
(propagated-inputs
`(("r-annotationdbi" ,r-annotationdbi)
("r-rcurl" ,r-rcurl)
("r-xml" ,r-xml)))
(home-page "http://bioconductor.org/packages/biomaRt")
(synopsis "Interface to BioMart databases")
(description
"biomaRt provides an interface to a growing collection of databases
implementing the @url{BioMart software suite, http://www.biomart.org}. The
package enables retrieval of large amounts of data in a uniform way without
the need to know the underlying database schemas or write complex SQL queries.
Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
users direct access to a diverse set of data and enable a wide range of
powerful online queries from gene annotation to database mining.")
(license license:artistic2.0)))
(define-public r-biocparallel
(package
(name "r-biocparallel")
(version "1.4.3")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "BiocParallel" version))
(sha256
(base32
"1f5mndx66vampcsq0n66afg6x851crl0h3nyv2nyp9bsgzj9cdzq"))))
(properties
`((upstream-name . "BiocParallel")))
(build-system r-build-system)
(propagated-inputs
`(("r-futile-logger" ,r-futile-logger)
("r-snow" ,r-snow)))
(home-page "http://bioconductor.org/packages/BiocParallel")
(synopsis "Bioconductor facilities for parallel evaluation")
(description
"This package provides modified versions and novel implementation of
functions for parallel evaluation, tailored to use with Bioconductor
objects.")
(license (list license:gpl2+ license:gpl3+))))
(define-public r-biostrings
(package
(name "r-biostrings")
(version "2.38.4")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "Biostrings" version))
(sha256
(base32
"0cjd7i4bdwabzb02gm753aji5xaihkj5ak8nb0d32cclxbj0hp33"))))
(properties
`((upstream-name . "Biostrings")))
(build-system r-build-system)
(propagated-inputs
`(("r-biocgenerics" ,r-biocgenerics)
("r-iranges" ,r-iranges)
("r-s4vectors" ,r-s4vectors)
("r-xvector" ,r-xvector)))
(home-page "http://bioconductor.org/packages/Biostrings")
(synopsis "String objects and algorithms for biological sequences")
(description
"This package provides memory efficient string containers, string
matching algorithms, and other utilities, for fast manipulation of large
biological sequences or sets of sequences.")
(license license:artistic2.0)))
(define-public r-rsamtools
(package
(name "r-rsamtools")
(version "1.22.0")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "Rsamtools" version))
(sha256
(base32
"1yc3nzzms3igjwr4l9yd3wdac95glcs08b4cfp7disyly0wcskjd"))))
(properties
`((upstream-name . "Rsamtools")))
(build-system r-build-system)
(arguments
`(#:phases
(modify-phases %standard-phases
(add-after 'unpack 'use-system-zlib
(lambda _
(substitute* "DESCRIPTION"
(("zlibbioc, ") ""))
(substitute* "NAMESPACE"
(("import\\(zlibbioc\\)") ""))
#t)))))
(inputs
`(("zlib" ,zlib)))
(propagated-inputs
`(("r-biocgenerics" ,r-biocgenerics)
("r-biocparallel" ,r-biocparallel)
("r-biostrings" ,r-biostrings)
("r-bitops" ,r-bitops)
("r-genomeinfodb" ,r-genomeinfodb)
("r-genomicranges" ,r-genomicranges)
("r-iranges" ,r-iranges)
("r-s4vectors" ,r-s4vectors)
("r-xvector" ,r-xvector)))
(home-page "http://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
(synopsis "Interface to samtools, bcftools, and tabix")
(description
"This package provides an interface to the 'samtools', 'bcftools', and
'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
binary variant call (BCF) and compressed indexed tab-delimited (tabix)
files.")
(license license:expat)))
(define-public r-summarizedexperiment
(package
(name "r-summarizedexperiment")
(version "1.0.2")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "SummarizedExperiment" version))
(sha256
(base32
"1gpmh1mi70m5k5qnyjs1h0qn8ajrzalzic7k3762xchxsmmdvxn4"))))
(properties
`((upstream-name . "SummarizedExperiment")))
(build-system r-build-system)
(propagated-inputs
`(("r-biobase" ,r-biobase)
("r-biocgenerics" ,r-biocgenerics)
("r-genomeinfodb" ,r-genomeinfodb)
("r-genomicranges" ,r-genomicranges)
("r-iranges" ,r-iranges)
("r-s4vectors" ,r-s4vectors)))
(home-page "http://bioconductor.org/packages/SummarizedExperiment")
(synopsis "Container for representing genomic ranges by sample")
(description
"The SummarizedExperiment container contains one or more assays, each
represented by a matrix-like object of numeric or other mode. The rows
typically represent genomic ranges of interest and the columns represent
samples.")
(license license:artistic2.0)))
(define-public r-genomicalignments
(package
(name "r-genomicalignments")
(version "1.6.3")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "GenomicAlignments" version))
(sha256
(base32
"02b9j1pfd39bkvb623k5k0ziq9rpw093hifqw65vb954dwj29jhd"))))
(properties
`((upstream-name . "GenomicAlignments")))
(build-system r-build-system)
(propagated-inputs
`(("r-biocgenerics" ,r-biocgenerics)
("r-biocparallel" ,r-biocparallel)
("r-biostrings" ,r-biostrings)
("r-genomeinfodb" ,r-genomeinfodb)
("r-genomicranges" ,r-genomicranges)
("r-iranges" ,r-iranges)
("r-rsamtools" ,r-rsamtools)
("r-s4vectors" ,r-s4vectors)
("r-summarizedexperiment" ,r-summarizedexperiment)))
(home-page "http://bioconductor.org/packages/GenomicAlignments")
(synopsis "Representation and manipulation of short genomic alignments")
(description
"This package provides efficient containers for storing and manipulating
short genomic alignments (typically obtained by aligning short reads to a
reference genome). This includes read counting, computing the coverage,
junction detection, and working with the nucleotide content of the
alignments.")
(license license:artistic2.0)))
(define-public r-rtracklayer
(package
(name "r-rtracklayer")
(version "1.30.4")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "rtracklayer" version))
(sha256
(base32
"0knjnwywh9k726mq28s3sy013zhw6d6nfa8hfw670720nq18i2p0"))))
(build-system r-build-system)
(arguments
`(#:phases
(modify-phases %standard-phases
(add-after 'unpack 'use-system-zlib
(lambda _
(substitute* "DESCRIPTION"
(("zlibbioc, ") ""))
(substitute* "NAMESPACE"
(("import\\(zlibbioc\\)") ""))
#t)))))
(inputs
`(("zlib" ,zlib)))
(propagated-inputs
`(("r-biocgenerics" ,r-biocgenerics)
("r-biostrings" ,r-biostrings)
("r-genomeinfodb" ,r-genomeinfodb)
("r-genomicalignments" ,r-genomicalignments)
("r-genomicranges" ,r-genomicranges)
("r-iranges" ,r-iranges)
("r-rcurl" ,r-rcurl)
("r-rsamtools" ,r-rsamtools)
("r-s4vectors" ,r-s4vectors)
("r-xml" ,r-xml)
("r-xvector" ,r-xvector)))
(home-page "http://bioconductor.org/packages/rtracklayer")
(synopsis "R interface to genome browsers and their annotation tracks")
(description
"rtracklayer is an extensible framework for interacting with multiple
genome browsers (currently UCSC built-in) and manipulating annotation tracks
in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
built-in). The user may export/import tracks to/from the supported browsers,
as well as query and modify the browser state, such as the current viewport.")
(license license:artistic2.0)))
(define-public r-genomicfeatures
(package
(name "r-genomicfeatures")
(version "1.22.13")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "GenomicFeatures" version))
(sha256
(base32
"0n3rkj66la6wizgcsf2rmwcsyfxz9kv5zak337lmk1raqfnancz4"))))
(properties
`((upstream-name . "GenomicFeatures")))
(build-system r-build-system)
(propagated-inputs
`(("r-annotationdbi" ,r-annotationdbi)
("r-biobase" ,r-biobase)
("r-biocgenerics" ,r-biocgenerics)
("r-biomart" ,r-biomart)
("r-biostrings" ,r-biostrings)
("r-dbi" ,r-dbi)
("r-genomeinfodb" ,r-genomeinfodb)
("r-genomicranges" ,r-genomicranges)
("r-iranges" ,r-iranges)
("r-rcurl" ,r-rcurl)
("r-rsqlite" ,r-rsqlite)
("r-rtracklayer" ,r-rtracklayer)
("r-s4vectors" ,r-s4vectors)
("r-xvector" ,r-xvector)))
(home-page "http://bioconductor.org/packages/GenomicFeatures")
(synopsis "Tools for working with transcript centric annotations")
(description
"This package provides a set of tools and methods for making and
manipulating transcript centric annotations. With these tools the user can
easily download the genomic locations of the transcripts, exons and cds of a
given organism, from either the UCSC Genome Browser or a BioMart
database (more sources will be supported in the future). This information is
then stored in a local database that keeps track of the relationship between
transcripts, exons, cds and genes. Flexible methods are provided for
extracting the desired features in a convenient format.")
(license license:artistic2.0)))
(define-public r-go-db
(package
(name "r-go-db")
(version "3.2.2")
(source (origin
(method url-fetch)
(uri (string-append "http://www.bioconductor.org/packages/"
"release/data/annotation/src/contrib/GO.db_"
version ".tar.gz"))
(sha256
(base32
"00gariag9ampz82dh0xllrc26r85d7vdcwc0vca5zdy147rwxr7f"))))
(properties
`((upstream-name . "GO.db")))
(build-system r-build-system)
(propagated-inputs
`(("r-annotationdbi" ,r-annotationdbi)))
(home-page "http://bioconductor.org/packages/GO.db")
(synopsis "Annotation maps describing the entire Gene Ontology")
(description
"The purpose of this GO.db annotation package is to provide detailed
information about the latest version of the Gene Ontologies.")
(license license:artistic2.0)))
(define-public r-graph
(package
(name "r-graph")
(version "1.48.0")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "graph" version))
(sha256
(base32
"16w75rji3kv24gfv44w66y1a2y75ax26rl470y3ypna0ndc3rrcd"))))
(build-system r-build-system)
(propagated-inputs
`(("r-biocgenerics" ,r-biocgenerics)))
(home-page "http://bioconductor.org/packages/graph")
(synopsis "Handle graph data structures in R")
(description
"This package implements some simple graph handling capabilities for R.")
(license license:artistic2.0)))
(define-public r-topgo
(package
(name "r-topgo")
(version "2.22.0")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "topGO" version))
(sha256
(base32
"029j9nb39b8l9xlzsp83pmjr8ap247aia387yzaa1yyw8klapdaf"))))
(properties
`((upstream-name . "topGO")))
(build-system r-build-system)
(propagated-inputs
`(("r-annotationdbi" ,r-annotationdbi)
("r-biobase" ,r-biobase)
("r-biocgenerics" ,r-biocgenerics)
("r-go-db" ,r-go-db)
("r-graph" ,r-graph)
("r-sparsem" ,r-sparsem)))
(home-page "http://bioconductor.org/packages/topGO")
(synopsis "Enrichment analysis for gene ontology")
(description
"The topGO package provides tools for testing @dfn{gene ontology} (GO)
terms while accounting for the topology of the GO graph. Different test
statistics and different methods for eliminating local similarities and
dependencies between GO terms can be implemented and applied.")
;; Any version of the LGPL applies.
(license license:lgpl2.1+)))
(define-public r-bsgenome
(package
(name "r-bsgenome")
(version "1.38.0")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "BSgenome" version))
(sha256
(base32
"130w0m6q8kkca7gyz1aqj5jjhalwvwi6rk2yvbjrnj4gpnncyrd2"))))
(properties
`((upstream-name . "BSgenome")))
(build-system r-build-system)
(propagated-inputs
`(("r-biocgenerics" ,r-biocgenerics)
("r-biostrings" ,r-biostrings)
("r-genomeinfodb" ,r-genomeinfodb)
("r-genomicranges" ,r-genomicranges)
("r-iranges" ,r-iranges)
("r-rsamtools" ,r-rsamtools)
("r-rtracklayer" ,r-rtracklayer)
("r-s4vectors" ,r-s4vectors)
("r-xvector" ,r-xvector)))
(home-page "http://bioconductor.org/packages/BSgenome")
(synopsis "Infrastructure for Biostrings-based genome data packages")
(description
"This package provides infrastructure shared by all Biostrings-based
genome data packages and support for efficient SNP representation.")
(license license:artistic2.0)))
(define-public r-impute
(package
(name "r-impute")
(version "1.44.0")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "impute" version))
(sha256
(base32
"0y4x5jk7gsf4xn56jrkdcdnxpcfll4h6ivncd7n4snmzixldvmvw"))))
(inputs
`(("gfortran" ,gfortran)))
(build-system r-build-system)
(home-page "http://bioconductor.org/packages/impute")
(synopsis "Imputation for microarray data")
(description
"This package provides a function to impute missing gene expression
microarray data, using nearest neighbor averaging.")
(license license:gpl2+)))
(define-public r-seqpattern
(package
(name "r-seqpattern")
(version "1.2.0")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "seqPattern" version))
(sha256
(base32
"0p9zj6bic7sa0hb2bjm988kkk5n9r1kvlbqkzvy702f642n0j53i"))))
(properties
`((upstream-name . "seqPattern")))
(build-system r-build-system)
(propagated-inputs
`(("r-biostrings" ,r-biostrings)
("r-genomicranges" ,r-genomicranges)
("r-iranges" ,r-iranges)
("r-plotrix" ,r-plotrix)))
(home-page "http://bioconductor.org/packages/seqPattern")
(synopsis "Visualising oligonucleotide patterns and motif occurrences")
(description
"This package provides tools to visualize oligonucleotide patterns and
sequence motif occurrences across a large set of sequences centred at a common
reference point and sorted by a user defined feature.")
(license license:gpl3+)))
(define-public r-genomation
(package
(name "r-genomation")
(version "1.2.2")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "genomation" version))
(sha256
(base32
"0kvzwc21zsh2c8d34yn935ncn38bfkpzmknycd8h7b0521x20mi9"))))
(build-system r-build-system)
(propagated-inputs
`(("r-biostrings" ,r-biostrings)
("r-bsgenome" ,r-bsgenome)
("r-data-table" ,r-data-table)
("r-genomeinfodb" ,r-genomeinfodb)
("r-genomicalignments" ,r-genomicalignments)
("r-genomicranges" ,r-genomicranges)
("r-ggplot2" ,r-ggplot2)
("r-gridbase" ,r-gridbase)
("r-impute" ,r-impute)
("r-iranges" ,r-iranges)
("r-matrixstats" ,r-matrixstats)
("r-plotrix" ,r-plotrix)
("r-plyr" ,r-plyr)
("r-readr" ,r-readr)
("r-reshape2" ,r-reshape2)
("r-rsamtools" ,r-rsamtools)
("r-rtracklayer" ,r-rtracklayer)
("r-seqpattern" ,r-seqpattern)))
(home-page "http://bioinformatics.mdc-berlin.de/genomation/")
(synopsis "Summary, annotation and visualization of genomic data")
(description
"This package provides a package for summary and annotation of genomic
intervals. Users can visualize and quantify genomic intervals over
pre-defined functional regions, such as promoters, exons, introns, etc. The
genomic intervals represent regions with a defined chromosome position, which
may be associated with a score, such as aligned reads from HT-seq experiments,
TF binding sites, methylation scores, etc. The package can use any tabular
genomic feature data as long as it has minimal information on the locations of
genomic intervals. In addition, it can use BAM or BigWig files as input.")
(license license:artistic2.0)))
(define-public r-org-hs-eg-db
(package
(name "r-org-hs-eg-db")
(version "3.2.3")
(source (origin
(method url-fetch)
;; We cannot use bioconductor-uri here because this tarball is
;; located under "data/annotation/" instead of "bioc/".
(uri (string-append "http://www.bioconductor.org/packages/"
"release/data/annotation/src/contrib/"
"org.Hs.eg.db_" version ".tar.gz"))
(sha256
(base32
"0xicgkbh6xkvs74s1piafqac63dyz2ycdyil4pj4ghhxx2sabm6p"))))
(properties
`((upstream-name . "org.Hs.eg.db")))
(build-system r-build-system)
(propagated-inputs
`(("r-annotationdbi" ,r-annotationdbi)))
(home-page "http://www.bioconductor.org/packages/org.Hs.eg.db/")
(synopsis "Genome wide annotation for Human")
(description
"This package provides mappings from Entrez gene identifiers to various
annotations for the human genome.")
(license license:artistic2.0)))
(define-public r-org-ce-eg-db
(package
(name "r-org-ce-eg-db")
(version "3.2.3")
(source (origin
(method url-fetch)
;; We cannot use bioconductor-uri here because this tarball is
;; located under "data/annotation/" instead of "bioc/".
(uri (string-append "http://www.bioconductor.org/packages/"
"release/data/annotation/src/contrib/"
"org.Ce.eg.db_" version ".tar.gz"))
(sha256
(base32
"1d0lx00ybq34yqs6mziaa0lrh77xm0ggsmi76g6k95f77gi7m1sw"))))
(properties
`((upstream-name . "org.Ce.eg.db")))
(build-system r-build-system)
(propagated-inputs
`(("r-annotationdbi" ,r-annotationdbi)))
(home-page "http://www.bioconductor.org/packages/org.Ce.eg.db/")
(synopsis "Genome wide annotation for Worm")
(description
"This package provides mappings from Entrez gene identifiers to various
annotations for the genome of the model worm Caenorhabditis elegans.")
(license license:artistic2.0)))
(define-public r-org-dm-eg-db
(package
(name "r-org-dm-eg-db")
(version "3.2.3")
(source (origin
(method url-fetch)
;; We cannot use bioconductor-uri here because this tarball is
;; located under "data/annotation/" instead of "bioc/".
(uri (string-append "http://www.bioconductor.org/packages/"
"release/data/annotation/src/contrib/"
"org.Dm.eg.db_" version ".tar.gz"))
(sha256
(base32
"0mib46c7nr00l7mh290n383za9hyl91a1dc6jhjbk884jmxaxyz6"))))
(properties
`((upstream-name . "org.Dm.eg.db")))
(build-system r-build-system)
(propagated-inputs
`(("r-annotationdbi" ,r-annotationdbi)))
(home-page "http://www.bioconductor.org/packages/org.Dm.eg.db/")
(synopsis "Genome wide annotation for Fly")
(description
"This package provides mappings from Entrez gene identifiers to various
annotations for the genome of the model fruit fly Drosophila melanogaster.")
(license license:artistic2.0)))
(define-public r-org-mm-eg-db
(package
(name "r-org-mm-eg-db")
(version "3.2.3")
(source (origin
(method url-fetch)
;; We cannot use bioconductor-uri here because this tarball is
;; located under "data/annotation/" instead of "bioc/".
(uri (string-append "http://www.bioconductor.org/packages/"
"release/data/annotation/src/contrib/"
"org.Mm.eg.db_" version ".tar.gz"))
(sha256
(base32
"0wh1pm3npdg7070875kfgiid3bqkz3q7rq6snhk6bxfvph00298y"))))
(properties
`((upstream-name . "org.Mm.eg.db")))
(build-system r-build-system)
(propagated-inputs
`(("r-annotationdbi" ,r-annotationdbi)))
(home-page "http://www.bioconductor.org/packages/org.Mm.eg.db/")
(synopsis "Genome wide annotation for Mouse")
(description
"This package provides mappings from Entrez gene identifiers to various
annotations for the genome of the model mouse Mus musculus.")
(license license:artistic2.0)))
(define-public r-seqlogo
(package
(name "r-seqlogo")
(version "1.36.0")
(source
(origin
(method url-fetch)
(uri (bioconductor-uri "seqLogo" version))
(sha256
(base32
"0kn1a1nf2j4v9c09vjkz9bmxlln7yhg87bnyrdsxy1m55x56rn5k"))))
(properties `((upstream-name . "seqLogo")))
(build-system r-build-system)
(home-page "http://bioconductor.org/packages/seqLogo")
(synopsis "Sequence logos for DNA sequence alignments")
(description
"seqLogo takes the position weight matrix of a DNA sequence motif and
plots the corresponding sequence logo as introduced by Schneider and
Stephens (1990).")
(license license:lgpl2.0+)))
(define-public r-bsgenome-hsapiens-ucsc-hg19
(package
(name "r-bsgenome-hsapiens-ucsc-hg19")
(version "1.4.0")
(source (origin
(method url-fetch)
;; We cannot use bioconductor-uri here because this tarball is
;; located under "data/annotation/" instead of "bioc/".
(uri (string-append "http://www.bioconductor.org/packages/"
"release/data/annotation/src/contrib/"
"BSgenome.Hsapiens.UCSC.hg19_"
version ".tar.gz"))
(sha256
(base32
"1y0nqpk8cw5a34sd9hmin3z4v7iqm6hf6l22cl81vlbxqbjibxc8"))))
(properties
`((upstream-name . "BSgenome.Hsapiens.UCSC.hg19")))
(build-system r-build-system)
;; As this package provides little more than a very large data file it
;; doesn't make sense to build substitutes.
(arguments `(#:substitutable? #f))
(propagated-inputs
`(("r-bsgenome" ,r-bsgenome)))
(home-page
"http://www.bioconductor.org/packages/BSgenome.Hsapiens.UCSC.hg19/")
(synopsis "Full genome sequences for Homo sapiens")
(description
"This package provides full genome sequences for Homo sapiens as provided
by UCSC (hg19, February 2009) and stored in Biostrings objects.")
(license license:artistic2.0)))
(define-public r-bsgenome-mmusculus-ucsc-mm9
(package
(name "r-bsgenome-mmusculus-ucsc-mm9")
(version "1.4.0")
(source (origin
(method url-fetch)
;; We cannot use bioconductor-uri here because this tarball is
;; located under "data/annotation/" instead of "bioc/".
(uri (string-append "http://www.bioconductor.org/packages/"
"release/data/annotation/src/contrib/"
"BSgenome.Mmusculus.UCSC.mm9_"
version ".tar.gz"))
(sha256
(base32
"1birqw30g2azimxpnjfzmkphan7x131yy8b9h85lfz5fjdg7841i"))))
(properties
`((upstream-name . "BSgenome.Mmusculus.UCSC.mm9")))
(build-system r-build-system)
;; As this package provides little more than a very large data file it
;; doesn't make sense to build substitutes.
(arguments `(#:substitutable? #f))
(propagated-inputs
`(("r-bsgenome" ,r-bsgenome)))
(home-page
"http://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm9/")
(synopsis "Full genome sequences for Mouse")
(description
"This package provides full genome sequences for Mus musculus (Mouse) as
provided by UCSC (mm9, July 2007) and stored in Biostrings objects.")
(license license:artistic2.0)))
(define-public r-bsgenome-celegans-ucsc-ce6
(package
(name "r-bsgenome-celegans-ucsc-ce6")
(version "1.4.0")
(source (origin
(method url-fetch)
;; We cannot use bioconductor-uri here because this tarball is
;; located under "data/annotation/" instead of "bioc/".
(uri (string-append "http://www.bioconductor.org/packages/"
"release/data/annotation/src/contrib/"
"BSgenome.Celegans.UCSC.ce6_"
version ".tar.gz"))
(sha256
(base32
"0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
(properties
`((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
(build-system r-build-system)
;; As this package provides little more than a very large data file it
;; doesn't make sense to build substitutes.
(arguments `(#:substitutable? #f))
(propagated-inputs
`(("r-bsgenome" ,r-bsgenome)))
(home-page
"http://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
(synopsis "Full genome sequences for Worm")
(description
"This package provides full genome sequences for Caenorhabditis
elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
objects.")
(license license:artistic2.0)))
(define-public r-bsgenome-dmelanogaster-ucsc-dm3
(package
(name "r-bsgenome-dmelanogaster-ucsc-dm3")
(version "1.4.0")
(source (origin
(method url-fetch)
;; We cannot use bioconductor-uri here because this tarball is
;; located under "data/annotation/" instead of "bioc/".
(uri (string-append "http://www.bioconductor.org/packages/"
"release/data/annotation/src/contrib/"
"BSgenome.Dmelanogaster.UCSC.dm3_"
version ".tar.gz"))
(sha256
(base32
"19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
(properties
`((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
(build-system r-build-system)
;; As this package provides little more than a very large data file it
;; doesn't make sense to build substitutes.
(arguments `(#:substitutable? #f))
(propagated-inputs
`(("r-bsgenome" ,r-bsgenome)))
(home-page
"http://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
(synopsis "Full genome sequences for Fly")
(description
"This package provides full genome sequences for Drosophila
melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
Biostrings objects.")
(license license:artistic2.0)))
(define-public r-motifrg
(package
(name "r-motifrg")
(version "1.14.0")
(source
(origin
(method url-fetch)
(uri (bioconductor-uri "motifRG" version))
(sha256
(base32
"1v9zm5629k2lcqbbgw8bwflvbircyxkfavbkvmbd212kgwcng8vn"))))
(properties `((upstream-name . "motifRG")))
(build-system r-build-system)
(propagated-inputs
`(("r-biostrings" ,r-biostrings)
("r-bsgenome" ,r-bsgenome)
("r-bsgenome.hsapiens.ucsc.hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
("r-iranges" ,r-iranges)
("r-seqlogo" ,r-seqlogo)
("r-xvector" ,r-xvector)))
(home-page "http://bioconductor.org/packages/motifRG")
(synopsis "Discover motifs in high throughput sequencing data")
(description
"This package provides tools for discriminative motif discovery in high
throughput genetic sequencing data sets using regression methods.")
(license license:artistic2.0)))
(define-public r-qtl
(package
(name "r-qtl")
(version "1.39-5")
(source
(origin
(method url-fetch)
(uri (string-append "mirror://cran/src/contrib/qtl_"
version ".tar.gz"))
(sha256
(base32
"1grwgvyv7x0dgay1858bg7qf4wk47gpnq7qkqpcda9cn0h970d6f"))))
(build-system r-build-system)
(home-page "http://rqtl.org/")
(synopsis "R package for analyzing QTL experiments in genetics")
(description "R/qtl is an extension library for the R statistics
system. It is used to analyze experimental crosses for identifying
genes contributing to variation in quantitative traits (so-called
quantitative trait loci, QTLs).
Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
identify genotyping errors, and to perform single-QTL and two-QTL,
two-dimensional genome scans.")
(license license:gpl3)))
(define-public r-zlibbioc
(package
(name "r-zlibbioc")
(version "1.16.0")
(source (origin
(method url-fetch)
(uri (bioconductor-uri "zlibbioc" version))
(sha256
(base32
"01wc26ndg4jsn1wyrl6zzq636gxaip5fci0xapym4lh9wryc4wnw"))))
(properties
`((upstream-name . "zlibbioc")))
(build-system r-build-system)
(home-page "https://bioconductor.org/packages/zlibbioc")
(synopsis "Provider for zlib-1.2.5 to R packages")
(description "This package uses the source code of zlib-1.2.5 to create
libraries for systems that do not have these available via other means.")
(license license:artistic2.0)))
(define-public pepr
(package
(name "pepr")
(version "1.0.9")
(source (origin
(method url-fetch)
(uri (string-append "https://pypi.python.org/packages/source/P"
"/PePr/PePr-" version ".tar.gz"))
(sha256
(base32
"0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
(build-system python-build-system)
(arguments
`(#:python ,python-2 ; python2 only
#:tests? #f ; no tests included
#:phases
(modify-phases %standard-phases
;; When setuptools is used a ".egg" archive is generated and
;; installed. This makes it hard to actually run PePr. This issue
;; has been reported upstream:
;; https://github.com/shawnzhangyx/PePr/issues/9
(add-after 'unpack 'disable-egg-generation
(lambda _
(substitute* "setup.py"
(("from setuptools import setup")
"from distutils.core import setup"))
#t)))))
(propagated-inputs
`(("python2-numpy" ,python2-numpy)
("python2-scipy" ,python2-scipy)
("python2-pysam" ,python2-pysam)))
(home-page "https://code.google.com/p/pepr-chip-seq/")
(synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
(description
"PePr is a ChIP-Seq peak calling or differential binding analysis tool
that is primarily designed for data with biological replicates. It uses a
negative binomial distribution to model the read counts among the samples in
the same group, and look for consistent differences between ChIP and control
group or two ChIP groups run under different conditions.")
(license license:gpl3+)))
(define-public filevercmp
(let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
(package
(name "filevercmp")
(version (string-append "0-1." (string-take commit 7)))
(source (origin
(method url-fetch)
(uri (string-append "https://github.com/ekg/filevercmp/archive/"
commit ".tar.gz"))
(file-name (string-append name "-" version ".tar.gz"))
(sha256
(base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
(build-system gnu-build-system)
(arguments
`(#:tests? #f ; There are no tests to run.
#:phases
(modify-phases %standard-phases
(delete 'configure) ; There is no configure phase.
(replace 'install
(lambda* (#:key outputs #:allow-other-keys)
(let ((bin (string-append (assoc-ref outputs "out") "/bin")))
(install-file "filevercmp" bin)))))))
(home-page "https://github.com/ekg/filevercmp")
(synopsis "This program compares version strings")
(description "This program compares version strings. It intends to be a
replacement for strverscmp.")
(license license:gpl3+))))
|