Experiments on sanity check

Author: Fang Zhang
Date: 2016.6.18
E-mail: fza34@sfu.ca

Experiment 20160618

Merge all unresistant vcf files. 9772 SNPs in total.

vcf-merge $(ls -1 *unresi.vcf.gz | perl -pe 's/\n/ /g') >merge.vcf

Veryfy whether intersection between merge.vcf and Resi-List-MasterV27_.vcf is empty. (Indeed empty)

cat merge.vcf | grep Mycobacterium |awk '{print $2}' > merge.txt
cat ../../../input/RESI_SNPs/Resi-List-MasterV27_.vcf | grep Mycobacterium | awk '{print $2}' > resi.txt
cat merge.txt resi.txt|sort -u|uniq -d

For sample in different experiments, intersection should be in 95%. Results are as below:

sample	GATK	mpileup	intersection	resi	unresi	unrepeted	repeted	SNP_frequency>1	sample_intersec	coverage	sample_alias
ERR553274	1398	1652	1330	18	1312	1156	156	1145	1110	95.16	8380-11
ERR553275	1334	1479	1289	18	1271	1144	127	1132	1110	95.16	8380-11
ERR551956	1443	1602	1391	24	1367	1195	172	1193	1155	95.14	6844-06
ERR551957	1418	1567	1358	24	1334	1178	156	1176	1155	95.14	6844-06
ERR552910	1443	1531	1406	22	1384	1224	160	1224	1190	94.97	9827-01
ERR552911	1424	1545	1383	21	1362	1221	141	1219	1190	94.97	9827-01
ERR551977	1377	1523	1332	18	1314	1196	118	1191	1167	94.8	1934-03
ERR551978	1414	1548	1359	19	1340	1213	127	1207	1167	94.8	1934-03
ERR552549	1436	1603	1355	20	1335	1200	135	1192	1162	94.78	8374-11
ERR552550	1387	1437	1338	20	1318	1198	120	1196	1162	94.78	8374-11
ERR550643	1291	1397	1266	18	1248	1138	110	1135	1110	94.71	2009-08
ERR550644	1328	1490	1280	17	1263	1153	110	1147	1110	94.71	2009-08
ERR553081	1395	1544	1357	19	1338	1204	134	1201	1173	94.44	1500-03
ERR553082	1444	1679	1385	17	1368	1219	149	1214	1173	94.44	1500-03
ERR551167	1400	1459	1365	24	1341	1195	146	1195	1170	94.35	8886-01
ERR551168	1429	1528	1391	23	1368	1216	152	1215	1170	94.35	8886-01
ERR550782	1475	2140	1427	23	1404	1232	172	1220	1176	94.31	10107-01
ERR550783	1480	2117	1427	23	1404	1246	158	1203	1176	94.31	10107-01
ERR550946	1402	1566	1344	20	1324	1168	156	1163	1125	94.3	4403-05
ERR550947	1379	1576	1329	20	1309	1159	150	1155	1125	94.3	4403-05
ERR551155	1453	1665	1378	23	1355	1211	144	1204	1160	94.16	8389-11
ERR551156	1387	1467	1346	22	1324	1188	136	1188	1160	94.16	8389-11
ERR550658	1451	2033	1401	23	1378	1236	142	1195	1169	94.12	709-05
ERR550659	1516	2301	1469	23	1446	1280	166	1216	1169	94.12	709-05
ERR550940	1488	1629	1404	21	1383	1225	158	1221	1168	93.82	8383-11
ERR550941	1406	1547	1352	21	1331	1196	135	1192	1168	93.82	8383-11
ERR551680	1448	1593	1389	20	1369	1208	161	1208	1164	93.8	7453-10
ERR551681	1421	1530	1356	19	1337	1199	138	1197	1164	93.8	7453-10
ERR551369	1451	1600	1368	18	1350	1222	128	1219	1171	93.76	R04-0039
ERR551370	1426	1589	1355	19	1336	1205	131	1201	1171	93.76	R04-0039
ERR551854	1353	1511	1317	19	1298	1185	113	1182	1158	93.69	4296-09
ERR551855	1423	1571	1365	19	1346	1213	133	1212	1158	93.69	4296-09
ERR552939	1497	2482	1457	23	1434	1265	169	1214	1169	93.67	685-05
ERR552940	1556	2261	1510	23	1487	1342	145	1203	1169	93.67	685-05
ERR551821	1476	2098	1429	24	1405	1246	159	1222	1180	93.65	711-05
ERR551822	1502	2189	1440	23	1417	1252	165	1218	1180	93.65	711-05
ERR552493	1501	2251	1441	21	1420	1243	177	1218	1173	93.62	8888-01
ERR552494	1479	2021	1436	21	1415	1260	155	1208	1173	93.62	8888-01
ERR551693	1421	1573	1366	22	1344	1220	124	1218	1170	93.6	1511-02
ERR551694	1409	1517	1349	22	1327	1205	122	1202	1170	93.6	1511-02
ERR553156	1411	1552	1375	18	1357	1222	135	1217	1159	93.24	5569-09
ERR553157	1355	1507	1325	19	1306	1200	106	1185	1159	93.24	5569-09
ERR551927	1389	1492	1337	20	1317	1190	127	1185	1152	93.2	10737-02
ERR551928	1423	1540	1361	20	1341	1208	133	1203	1152	93.2	10737-02
ERR552444	1394	1622	1362	18	1344	1182	162	1177	1118	92.7	7461-10
ERR552445	1343	1579	1304	18	1286	1162	124	1147	1118	92.7	7461-10
ERR552894	1431	1559	1365	20	1345	1215	130	1210	1145	92.41	7426-10
ERR552895	1337	1440	1307	19	1288	1176	112	1174	1145	92.41	7426-10
ERR553303	1320	1386	1298	26	1272	1176	96	1167	1128	91.78	8073-07
ERR553304	1388	1467	1346	26	1320	1194	126	1190	1128	91.78	8073-07
ERR551184	1380	1558	1337	17	1320	1166	154	1157	1080	91.37	11251-09
ERR551185	1291	1465	1262	18	1244	1128	116	1105	1080	91.37	11251-09
ERR551804	1443	1722	1401	24	1377	1233	144	1206	1141	91.21	7942-05
ERR551805	1373	1476	1352	24	1328	1206	122	1190	1141	91.21	7942-05
ERR551806	1395	1557	1357	24	1333	1208	125	1192	1141	91.21	7942-05
ERR551556	1435	1755	1400	24	1376	1218	158	1201	1111	89.74	2389-05
ERR551557	1335	1433	1317	23	1294	1179	115	1165	1111	89.74	2389-05
ERR551558	1354	1589	1329	21	1308	1199	109	1174	1111	89.74	2389-05
ERR551360	1464	1741	1422	23	1399	1231	168	1209	1119	89.38	3811-05
ERR551361	1420	1570	1378	23	1355	1209	146	1187	1119	89.38	3811-05
ERR551362	1401	1632	1363	24	1339	1203	136	1179	1119	89.38	3811-05
ERR550777	1375	1585	1342	23	1319	1191	128	1174	1102	88.44	8455-05
ERR550778	1420	1565	1372	25	1347	1208	139	1200	1102	88.44	8455-05
ERR550779	1335	1526	1324	24	1300	1185	115	1172	1102	88.44	8455-05
ERR551943	1256	1339	1239	21	1218	1131	87	1129	1094	86.96	9052-05
ERR551944	1446	1580	1377	23	1354	1228	126	1220	1094	86.96	9052-05
ERR551945	1449	1537	1405	24	1381	1217	164	1216	1094	86.96	9052-05
ERR552689	1423	1533	1375	20	1355	1216	139	1207	1035	84.21	178-03
ERR552690	1211	1268	1176	18	1158	1073	85	1057	1035	84.21	178-03
ERR552668	1304	1419	1291	23	1268	1146	122	1146	964	77.55	12448-03
ERR552669	1269	1504	1248	21	1227	1140	87	1074	964	77.55	12448-03
ERR552670	1419	2009	1392	22	1370	1237	133	1176	964	77.55	12448-03
ERR552671	1440	2160	1393	21	1372	1243	129	1183	964	77.55	12448-03
ERR551979	1139	1196	1118	15	1103	1032	71	1008	698	56.61	7187-09
ERR551980	1295	1456	1272	18	1254	1150	104	1140	698	56.61	7187-09
ERR551981	1247	1304	1204	17	1187	1095	92	1065	698	56.61	7187-09
ERR551982	1353	1483	1312	18	1294	1177	117	1175	698	56.61	7187-09
ERR551983	1061	1116	1041	15	1026	953	73	938	698	56.61	7187-09