Update files and script

b2adc44d · Nicolò Gualandi · 3b56eecc · b2adc44d · b2adc44d · b2adc44d
Commit b2adc44d authored Nov 24, 2025 by Nicolò Gualandi
--- a/ClonalHema_Jakobsen_et_al.txt
+++ b/ClonalHema_Jakobsen_et_al.txt
+ASXL1
+ASXL2
+ATM
+ATRX
+BCOR
+BCORL1
+BRAF
+BRCC3
+BRINP3
+CALR
+CBL
+CBLB
+CDKN2A
+CEBPA
+CREBBP
+CSF1R
+CSF3R
+CTCF
+CUX1
+DDX3X
+DHX15
+DNMT3A
+EP300
+ETV6
+EZH2
+FBXW7
+FLT3
+GATA1
+GATA2
+GNAS
+GNB1
+HNRNPK
+HRAS
+IDH1
+IDH2
+IKZF1
+JAK2
+JAK3
+KANSL1
+KDM5A
+KDM6A
+KIT
+KMT2A
+KMT2C
+KMT2D
+KMT2E
+KRAS
+LUC7L2
+MAU2
+MED12
+MPL
+MTA2
+MYC
+MYD88
+NF1
+NIPBL
+NOTCH1
+NPM1
+NRAS
+PDGFRA
+PDS5B
+PHF6
+PIGA
+PPM1D
+PRDM1
+PRPF40B
+PRPF8
+PTEN
+PTPN11
+PTPRF
+RAD21
+RB1
+RIT1
+RUNX1
+SETBP1
+SETD2
+SETDB1
+SF1
+SF3A1
+SF3B1
+SH2B3
+SMC1A
+SMC3
+SMG1
+SRSF2
+STAG1
+STAG2
+STAT3
+STAT5B
+SUZ12
+TET2
+TP53
+U2AF1
+U2AF2
+WAPL
+WT1
+ZRSR2
--- a/Metadata.txt
+++ b/Metadata.txt
+ID	Sample	Age	Source	Concentration (ng/μL)	tot volume (uL)	Total DNA (ng)	Group_Age	Source.1
+2	PZ28	1975	Only Human	47.8	NA	1434	Young	General_pop
+3	P23	1929	Only Human	17	NA	510	Old	General_pop
+4	PZ39	1953	Only Human	20.4	NA	612	Old	General_pop
+17	PZ37	1940	Only Human	22	NA	660	Old	General_pop
+19	PZ36	1944	Only Human	22.6	NA	678	Old	General_pop
+26	PZ22	1960	Only Human	95	NA	2850	Young	General_pop
+43	34-OLD2	1951	Only Human	95.4	NA	2862	Old	General_pop
+44	34-OLD3	1948	Only Human	37.9	NA	1137	Old	General_pop
--- a/Mutect2_variants.txt
+++ b/Mutect2_variants.txt
+Sample	CHROM	POS	ID.x	REF	ALT	QUAL	FILTER	ANNOT	FORMAT	SAMPLE	Vars	DP	AD	VAF	AD_alt	orig.name	Common	snpEff_GeneName	Var.ID	ID.y	Age	Source	Concentration..ng.μL.	tot.volume..uL.	Total.DNA..ng.	Group_Age	Source.1	snpEff_Effect	snpEff_Impact	snpEff_Gene	snpEff_BioType	TYPE	ID_SAMPLE
+34-OLD2	chr7	152185587	rs145848316	C	A	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=548,488|53,53;DP=1152;ECNT=3;GERMQ=93;MBQ=20,20;MFRL=188,147;MMQ=60,45;MPOS=45;POPAF=7.30;TLOD=181.07;ANN=A|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|36/62|c.5104G>T|p.Ala1702Ser|5126/16878|5104/14952|1702/4983||;FREQ=GnomAD:1,1.428e-05,.|GnomAD_exomes:0.9933,0.006726,.|GoESP:0.9862,0.01376,.|KOREAN:0.9894,0.01061,.|MGP:0.985,0.01498,.|PRJEB37584:0.8256,0.1744,.|Qatari:0.9907,0.009259,.|TOMMO:0.9996,0.0004177,.|TOPMED:1,.,1.511e-05|dbGaP_PopFreq:0.9792,0.02077,0;RS=145848316;dbSNPBuildID=134	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1036,106:0.071:1142:549,32:476,74:548,488,53,53	chr7-152185587-C-A	1142	1036	0.0928196147110333	106	34-OLD2	FALSE	KMT2C	chr7_152185587	43	1951	Only Human	95.4	NA	2862	Old	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	34-OLD2_chr7-152185587-C-A
+34-OLD2	chr7	152247975	rs200598064	G	A	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=886,654|26,23;DP=1641;ECNT=4;GERMQ=93;MBQ=20,20;MFRL=203,145;MMQ=48,47;MPOS=4;POPAF=7.30;TLOD=58.72;ANN=A|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|15/62|c.2462C>T|p.Thr821Ile|2484/16878|2462/14952|821/4983||;FREQ=1000Genomes:0.9998,0.0001997,.|ExAC:0.9999,5.772e-05,.|KOREAN:0.9993,0.0006845,.|TOMMO:0.9998,0.000179,.|dbGaP_PopFreq:1,4.407e-05,.;RS=200598064;dbSNPBuildID=137	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1540,49:0.029:1589:735,25:787,23:886,654,26,23	chr7-152247975-G-A	1589	1540	0.0308370044052863	49	34-OLD2	FALSE	KMT2C	chr7_152247975	43	1951	Only Human	95.4	NA	2862	Old	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	34-OLD2_chr7-152247975-G-A
+34-OLD2	chr7	152273773	rs2096021736	C	T	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=876,919|11,22;DP=1869;ECNT=5;GERMQ=93;MBQ=20,20;MFRL=181,168;MMQ=59,37;MPOS=27;POPAF=7.30;TLOD=43.86;ANN=T|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|8/62|c.947G>A|p.Gly316Asp|969/16878|947/14952|316/4983||;RS=2096021736;dbSNPBuildID=155	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1795,33:0.018:1828:920,16:859,16:876,919,11,22	chr7-152273773-C-T	1828	1795	0.0180525164113786	33	34-OLD2	FALSE	KMT2C	chr7_152273773	43	1951	Only Human	95.4	NA	2862	Old	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	34-OLD2_chr7-152273773-C-T
+34-OLD3	chr7	152247975	rs200598064	G	A	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=1267,980|36,29;DP=2387;ECNT=4;GERMQ=93;MBQ=20,20;MFRL=192,134;MMQ=48,47;MPOS=5;POPAF=7.30;TLOD=83.40;ANN=A|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|15/62|c.2462C>T|p.Thr821Ile|2484/16878|2462/14952|821/4983||;FREQ=1000Genomes:0.9998,0.0001997,.|ExAC:0.9999,5.772e-05,.|KOREAN:0.9993,0.0006845,.|TOMMO:0.9998,0.000179,.|dbGaP_PopFreq:1,4.407e-05,.;RS=200598064;dbSNPBuildID=137	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:2247,65:0.025:2312:1135,32:1095,32:1267,980,36,29	chr7-152247975-G-A	2312	2247	0.0281141868512111	65	34-OLD3	FALSE	KMT2C	chr7_152247975	44	1948	Only Human	37.9	NA	1137	Old	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	34-OLD3_chr7-152247975-G-A
+34-OLD3	chr7	152265205	rs775803041	C	G	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=692,987|9,19;DP=1748;ECNT=5;GERMQ=93;MBQ=20,24;MFRL=180,165;MMQ=51,44;MPOS=12;POPAF=7.30;TLOD=32.57;ANN=G|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|9/62|c.1020G>C|p.Lys340Asn|1042/16878|1020/14952|340/4983||;FREQ=ExAC:0.9979,0.002112,.|GnomAD:1,.,7.216e-06|Korea1K:0.9924,0.007642,.|TOMMO:0.9999,.,5.967e-05|TOPMED:1,.,3.778e-06|dbGaP_PopFreq:0.9987,0.001295,0;RS=775803041;dbSNPBuildID=144	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1679,28:0.019:1707:825,21:827,7:692,987,9,19	chr7-152265205-C-G	1707	1679	0.0164030462800234	28	34-OLD3	FALSE	KMT2C	chr7_152265205	44	1948	Only Human	37.9	NA	1137	Old	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	34-OLD3_chr7-152265205-C-G
+P23	chr2	25240732	rs761987159	T	C	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=180,242|54,68;DP=555;ECNT=1;GERMQ=93;MBQ=20,20;MFRL=185,184;MMQ=60,60;MPOS=36;POPAF=7.30;TLOD=235.58;ANN=C|splice_acceptor_variant&intron_variant|HIGH|DNMT3A|DNMT3A|transcript|NM_022552.5|protein_coding|17/22|c.2083-2A>G||||||;LOF=(DNMT3A|DNMT3A|1|1.00);FREQ=ExAC:1,1.65e-05|GnomAD:1,7.131e-06|dbGaP_PopFreq:1,0;RS=761987159;dbSNPBuildID=144	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:422,122:0.228:544:219,75:202,41:180,242,54,68	chr2-25240732-T-C	544	422	0.224264705882353	122	P23	FALSE	DNMT3A	chr2_25240732	3	1929	Only Human	17	NA	510	Old	General_pop	splice_acceptor_variant&intron_variant	HIGH	DNMT3A	protein_coding	SNV	P23_chr2-25240732-T-C
+P23	chr7	152247975	rs200598064	G	A	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=735,539|27,21;DP=1361;ECNT=4;GERMQ=93;MBQ=20,20;MFRL=195,137;MMQ=48,45;MPOS=7;POPAF=7.30;TLOD=58.61;ANN=A|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|15/62|c.2462C>T|p.Thr821Ile|2484/16878|2462/14952|821/4983||;FREQ=1000Genomes:0.9998,0.0001997,.|ExAC:0.9999,5.772e-05,.|KOREAN:0.9993,0.0006845,.|TOMMO:0.9998,0.000179,.|dbGaP_PopFreq:1,4.407e-05,.;RS=200598064;dbSNPBuildID=137	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1274,48:0.033:1322:614,21:637,25:735,539,27,21	chr7-152247975-G-A	1322	1274	0.0363086232980333	48	P23	FALSE	KMT2C	chr7_152247975	3	1929	Only Human	17	NA	510	Old	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	P23_chr7-152247975-G-A
+PZ22	chr7	152247975	rs200598064	G	A	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=777,556|23,28;DP=1438;ECNT=6;GERMQ=93;MBQ=26,20;MFRL=221,136;MMQ=48,33;MPOS=5;POPAF=7.30;TLOD=65.45;ANN=A|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|15/62|c.2462C>T|p.Thr821Ile|2484/16878|2462/14952|821/4983||;FREQ=1000Genomes:0.9998,0.0001997,.|ExAC:0.9999,5.772e-05,.|KOREAN:0.9993,0.0006845,.|TOMMO:0.9998,0.000179,.|dbGaP_PopFreq:1,4.407e-05,.;RS=200598064;dbSNPBuildID=137	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1333,51:0.035:1384:661,26:652,25:777,556,23,28	chr7-152247975-G-A	1384	1333	0.036849710982659	51	PZ22	FALSE	KMT2C	chr7_152247975	26	1960	Only Human	95	NA	2850	Young	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	PZ22_chr7-152247975-G-A
+PZ22	chr7	152265049	rs146238849	G	T	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=934,421|58,24;DP=1477;ECNT=7;GERMQ=93;MBQ=20,20;MFRL=191,188;MMQ=48,47;MPOS=30;POPAF=7.30;TLOD=129.91;ANN=T|stop_gained|HIGH|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|9/62|c.1176C>A|p.Cys392*|1198/16878|1176/14952|392/4983||;LOF=(KMT2C|KMT2C|1|1.00);NMD=(KMT2C|KMT2C|1|1.00);FREQ=GnomAD_exomes:0.9971,.,0.002894|KOREAN:0.9949,.,0.005133|Korea1K:0.9924,.,0.007642|Siberian:0.5,.,0.5|TOMMO:0.9988,.,0.001193|dbGaP_PopFreq:0.9888,0,0.01123;RS=146238849;dbSNPBuildID=137	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1355,82:0.057:1437:676,40:659,40:934,421,58,24	chr7-152265049-G-T	1437	1355	0.0570633263743911	82	PZ22	FALSE	KMT2C	chr7_152265049	26	1960	Only Human	95	NA	2850	Young	General_pop	stop_gained	HIGH	KMT2C	protein_coding	SNV	PZ22_chr7-152265049-G-T
+PZ22	chr7	152265083	rs138908625	C	A	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=1166,767|68,41;DP=2094;ECNT=7;GERMQ=93;MBQ=20,20;MFRL=181,177;MMQ=48,47;MPOS=45;POPAF=7.30;TLOD=168.65;ANN=A|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|9/62|c.1142G>T|p.Arg381Leu|1164/16878|1142/14952|381/4983||;FREQ=GnomAD_exomes:0.9985,0.001496,.|GoESP:0.9966,0.003383,.|KOREAN:0.9918,0.008214,.|Korea1K:0.9907,0.009279,.|Siberian:0.5,0.5,.|TOMMO:0.9984,0.001611,.|dbGaP_PopFreq:0.9913,0.008728,.;RS=138908625;dbSNPBuildID=134	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1933,109:0.053:2042:774,53:777,54:1166,767,68,41	chr7-152265083-C-A	2042	1933	0.0533790401567091	109	PZ22	FALSE	KMT2C	chr7_152265083	26	1960	Only Human	95	NA	2850	Young	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	PZ22_chr7-152265083-C-A
+PZ22	chr7	152273773	rs2096021736	C	T	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=764,799|10,14;DP=1633;ECNT=7;GERMQ=93;MBQ=20,20;MFRL=198,170;MMQ=52,38;MPOS=26;POPAF=7.30;TLOD=20.04;ANN=T|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|8/62|c.947G>A|p.Gly316Asp|969/16878|947/14952|316/4983||;RS=2096021736;dbSNPBuildID=155	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1563,24:0.011:1587:772,12:737,12:764,799,10,14	chr7-152273773-C-T	1587	1563	0.0151228733459357	24	PZ22	FALSE	KMT2C	chr7_152273773	26	1960	Only Human	95	NA	2850	Young	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	PZ22_chr7-152273773-C-T
+PZ22	chr11	108335029	rs531980488	C	T	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=461,332|4,6;DP=822;ECNT=1;GERMQ=93;MBQ=20,30;MFRL=234,328;MMQ=60,60;MPOS=43;POPAF=7.30;TLOD=11.80;ANN=T|missense_variant|MODERATE|ATM|ATM|transcript|NM_000051.4|protein_coding|55/63|c.8071C>T|p.Arg2691Cys|8221/12915|8071/9171|2691/3056||,T|intragenic_variant|MODIFIER|C11orf65|C11orf65|gene_variant|C11orf65|||n.108335029G>A||||||;FREQ=1000Genomes:0.9998,.,.,0.0001997|ExAC:0.9999,.,.,0.0001072|GnomAD:0.9999,.,.,0.000107|GnomAD_exomes:0.9999,.,.,0.0001353|GoNL:0.999,.,.,0.001002|PRJEB37584:0.9975,.,.,0.002525|TOPMED:0.9999,.,.,9.445e-05|dbGaP_PopFreq:1,.,.,4.781e-05;RS=531980488;dbSNPBuildID=142	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:793,10:0.015:803:298,4:289,6:461,332,4,6	chr11-108335029-C-T	803	793	0.012453300124533	10	PZ22	FALSE	ATM	chr11_108335029	26	1960	Only Human	95	NA	2850	Young	General_pop	missense_variant	MODERATE	ATM	protein_coding	SNV	PZ22_chr11-108335029-C-T
+PZ28	chr7	152235864	rs77173318	C	A	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=255,255|17,17;DP=547;ECNT=11;GERMQ=93;MBQ=20,20;MFRL=175,124;MMQ=47,43;MPOS=40;POPAF=7.30;TLOD=52.41;ANN=A|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|17/62|c.2725G>T|p.Gly909Cys|2747/16878|2725/14952|909/4983||;FREQ=ExAC:0.9971,0.002918|GnomAD_exomes:0.9998,0.000206|GoESP:0.9961,0.003924|MGP:0.9963,0.003745|dbGaP_PopFreq:1,4.679e-05;RS=77173318;dbSNPBuildID=131	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:510,34:0.050:544:253,18:250,16:255,255,17,17	chr7-152235864-C-A	544	510	0.0625	34	PZ28	FALSE	KMT2C	chr7_152235864	2	1975	Only Human	47.8	NA	1434	Young	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	PZ28_chr7-152235864-C-A
+PZ28	chr7	152247975	rs200598064	G	A	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=782,570|8,13;DP=1406;ECNT=5;GERMQ=93;MBQ=20,20;MFRL=206,150;MMQ=48,47;MPOS=7;POPAF=7.30;TLOD=18.16;ANN=A|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|15/62|c.2462C>T|p.Thr821Ile|2484/16878|2462/14952|821/4983||;FREQ=1000Genomes:0.9998,0.0001997,.|ExAC:0.9999,5.772e-05,.|KOREAN:0.9993,0.0006845,.|TOMMO:0.9998,0.000179,.|dbGaP_PopFreq:1,4.407e-05,.;RS=200598064;dbSNPBuildID=137	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1352,21:0.011:1373:701,13:636,7:782,570,8,13	chr7-152247975-G-A	1373	1352	0.0152949745083758	21	PZ28	FALSE	KMT2C	chr7_152247975	2	1975	Only Human	47.8	NA	1434	Young	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	PZ28_chr7-152247975-G-A
+PZ28	chr7	152265049	rs146238849	G	T	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=693,365|126,62;DP=1267;ECNT=3;GERMQ=93;MBQ=20,20;MFRL=180,166;MMQ=48,47;MPOS=39;POPAF=7.30;TLOD=376.15;ANN=T|stop_gained|HIGH|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|9/62|c.1176C>A|p.Cys392*|1198/16878|1176/14952|392/4983||;LOF=(KMT2C|KMT2C|1|1.00);NMD=(KMT2C|KMT2C|1|1.00);FREQ=GnomAD_exomes:0.9971,.,0.002894|KOREAN:0.9949,.,0.005133|Korea1K:0.9924,.,0.007642|Siberian:0.5,.,0.5|TOMMO:0.9988,.,0.001193|dbGaP_PopFreq:0.9888,0,0.01123;RS=146238849;dbSNPBuildID=137	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1058,188:0.142:1246:530,92:525,95:693,365,126,62	chr7-152265049-G-T	1246	1058	0.150882825040128	188	PZ28	FALSE	KMT2C	chr7_152265049	2	1975	Only Human	47.8	NA	1434	Young	General_pop	stop_gained	HIGH	KMT2C	protein_coding	SNV	PZ28_chr7-152265049-G-T
+PZ28	chr7	152265083	rs138908625	C	A	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=912,665|170,124;DP=1906;ECNT=3;GERMQ=93;MBQ=20,20;MFRL=169,159;MMQ=48,47;MPOS=41;POPAF=7.30;TLOD=564.13;ANN=A|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|9/62|c.1142G>T|p.Arg381Leu|1164/16878|1142/14952|381/4983||;FREQ=GnomAD_exomes:0.9985,0.001496,.|GoESP:0.9966,0.003383,.|KOREAN:0.9918,0.008214,.|Korea1K:0.9907,0.009279,.|Siberian:0.5,0.5,.|TOMMO:0.9984,0.001611,.|dbGaP_PopFreq:0.9913,0.008728,.;RS=138908625;dbSNPBuildID=134	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1577,294:0.144:1871:778,142:762,150:912,665,170,124	chr7-152265083-C-A	1871	1577	0.157135221806521	294	PZ28	FALSE	KMT2C	chr7_152265083	2	1975	Only Human	47.8	NA	1434	Young	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	PZ28_chr7-152265083-C-A
+PZ28	chr7	152265205	rs775803041	C	G	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=389,614|11,24;DP=1078;ECNT=9;GERMQ=93;MBQ=20,24;MFRL=184,161;MMQ=48,48;MPOS=12;POPAF=7.30;TLOD=52.93;ANN=G|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|9/62|c.1020G>C|p.Lys340Asn|1042/16878|1020/14952|340/4983||;FREQ=ExAC:0.9979,0.002112,.|GnomAD:1,.,7.216e-06|Korea1K:0.9924,0.007642,.|TOMMO:0.9999,.,5.967e-05|TOPMED:1,.,3.778e-06|dbGaP_PopFreq:0.9987,0.001295,0;RS=775803041;dbSNPBuildID=144	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1003,35:0.036:1038:490,18:499,17:389,614,11,24	chr7-152265205-C-G	1038	1003	0.033718689788054	35	PZ28	FALSE	KMT2C	chr7_152265205	2	1975	Only Human	47.8	NA	1434	Young	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	PZ28_chr7-152265205-C-G
+PZ36	chr7	152247975	rs200598064	G	A	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=998,755|16,16;DP=1834;ECNT=3;GERMQ=93;MBQ=27,20;MFRL=224,139;MMQ=48,47;MPOS=7;POPAF=7.30;TLOD=32.17;ANN=A|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|15/62|c.2462C>T|p.Thr821Ile|2484/16878|2462/14952|821/4983||;FREQ=1000Genomes:0.9998,0.0001997,.|ExAC:0.9999,5.772e-05,.|KOREAN:0.9993,0.0006845,.|TOMMO:0.9998,0.000179,.|dbGaP_PopFreq:1,4.407e-05,.;RS=200598064;dbSNPBuildID=137	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1753,32:0.015:1785:822,15:889,17:998,755,16,16	chr7-152247975-G-A	1785	1753	0.0179271708683473	32	PZ36	FALSE	KMT2C	chr7_152247975	19	1944	Only Human	22.6	NA	678	Old	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	PZ36_chr7-152247975-G-A
+PZ37	chr7	152265049	rs146238849	G	T	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=1145,564|62,29;DP=1847;ECNT=4;GERMQ=93;MBQ=20,20;MFRL=190,174;MMQ=48,47;MPOS=40;POPAF=7.30;TLOD=137.54;ANN=T|stop_gained|HIGH|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|9/62|c.1176C>A|p.Cys392*|1198/16878|1176/14952|392/4983||;LOF=(KMT2C|KMT2C|1|1.00);NMD=(KMT2C|KMT2C|1|1.00);FREQ=GnomAD_exomes:0.9971,.,0.002894|KOREAN:0.9949,.,0.005133|Korea1K:0.9924,.,0.007642|Siberian:0.5,.,0.5|TOMMO:0.9988,.,0.001193|dbGaP_PopFreq:0.9888,0,0.01123;RS=146238849;dbSNPBuildID=137	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1709,91:0.047:1800:851,51:836,38:1145,564,62,29	chr7-152265049-G-T	1800	1709	0.0505555555555556	91	PZ37	FALSE	KMT2C	chr7_152265049	17	1940	Only Human	22	NA	660	Old	General_pop	stop_gained	HIGH	KMT2C	protein_coding	SNV	PZ37_chr7-152265049-G-T
+PZ37	chr7	152265083	rs138908625	C	A	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=1404,1011|82,55;DP=2625;ECNT=4;GERMQ=93;MBQ=20,20;MFRL=178,173;MMQ=48,47;MPOS=42;POPAF=7.30;TLOD=208.16;ANN=A|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|9/62|c.1142G>T|p.Arg381Leu|1164/16878|1142/14952|381/4983||;FREQ=GnomAD_exomes:0.9985,0.001496,.|GoESP:0.9966,0.003383,.|KOREAN:0.9918,0.008214,.|Korea1K:0.9907,0.009279,.|Siberian:0.5,0.5,.|TOMMO:0.9984,0.001611,.|dbGaP_PopFreq:0.9913,0.008728,.;RS=138908625;dbSNPBuildID=134	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:2415,137:0.049:2552:900,73:874,60:1404,1011,82,55	chr7-152265083-C-A	2552	2415	0.0536833855799373	137	PZ37	FALSE	KMT2C	chr7_152265083	17	1940	Only Human	22	NA	660	Old	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	PZ37_chr7-152265083-C-A
+PZ37	chr7	152265205	rs775803041	C	G	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=607,898|25,59;DP=1646;ECNT=5;GERMQ=93;MBQ=23,20;MFRL=208,171;MMQ=50,45;MPOS=11;POPAF=7.30;TLOD=123.84;ANN=G|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|9/62|c.1020G>C|p.Lys340Asn|1042/16878|1020/14952|340/4983||;FREQ=ExAC:0.9979,0.002112,.|GnomAD:1,.,7.216e-06|Korea1K:0.9924,0.007642,.|TOMMO:0.9999,.,5.967e-05|TOPMED:1,.,3.778e-06|dbGaP_PopFreq:0.9987,0.001295,0;RS=775803041;dbSNPBuildID=144	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1505,84:0.053:1589:740,33:735,35:607,898,25,59	chr7-152265205-C-G	1589	1505	0.052863436123348	84	PZ37	FALSE	KMT2C	chr7_152265205	17	1940	Only Human	22	NA	660	Old	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	PZ37_chr7-152265205-C-G
+PZ37	chrX	45089879	.	C	T	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=662,831|14,16;DP=1558;ECNT=1;GERMQ=93;MBQ=20,27;MFRL=224,245;MMQ=60,60;MPOS=37;POPAF=7.30;TLOD=40.48;ANN=T|stop_gained|HIGH|KDM6A|KDM6A|transcript|XM_011543958.3|protein_coding|26/31|c.3841C>T|p.Gln1281*|4211/6031|3841/4470|1281/1489||;LOF=(KDM6A|KDM6A|1|1.00);NMD=(KDM6A|KDM6A|1|1.00)	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1493,30:0.021:1523:761,17:708,13:662,831,14,16	chrX-45089879-C-T	1523	1493	0.0196979645436638	30	PZ37	FALSE	KDM6A	chrX_45089879	17	1940	Only Human	22	NA	660	Old	General_pop	stop_gained	HIGH	KDM6A	protein_coding	SNV	PZ37_chrX-45089879-C-T
+PZ39	chr2	25234406	.	G	T	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=207,307|2,4;DP=533;ECNT=1;GERMQ=93;MBQ=20,36;MFRL=206,202;MMQ=60,60;MPOS=31;POPAF=7.30;TLOD=8.04;ANN=T|missense_variant|MODERATE|DNMT3A|DNMT3A|transcript|NM_022552.5|protein_coding|23/23|c.2612C>A|p.Pro871Gln|2889/9421|2612/2739|871/912||	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:514,6:0.016:520:264,5:244,1:207,307,2,4	chr2-25234406-G-T	520	514	0.0115384615384615	6	PZ39	FALSE	DNMT3A	chr2_25234406	4	1953	Only Human	20.4	NA	612	Old	General_pop	missense_variant	MODERATE	DNMT3A	protein_coding	SNV	PZ39_chr2-25234406-G-T
+PZ39	chr2	25243922	.	A	G	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=402,387|15,18;DP=843;ECNT=1;GERMQ=93;MBQ=20,20;MFRL=179,178;MMQ=60,60;MPOS=40;POPAF=7.30;TLOD=55.21;ANN=G|missense_variant|MODERATE|DNMT3A|DNMT3A|transcript|NM_022552.5|protein_coding|16/23|c.1912T>C|p.Ser638Pro|2189/9421|1912/2739|638/912||	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:789,33:0.041:822:413,15:370,18:402,387,15,18	chr2-25243922-A-G	822	789	0.0401459854014599	33	PZ39	FALSE	DNMT3A	chr2_25243922	4	1953	Only Human	20.4	NA	612	Old	General_pop	missense_variant	MODERATE	DNMT3A	protein_coding	SNV	PZ39_chr2-25243922-A-G
+PZ39	chr7	152247975	rs200598064	G	A	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=863,662|13,11;DP=1591;ECNT=5;GERMQ=93;MBQ=20,20;MFRL=199,140;MMQ=48,33;MPOS=10;POPAF=7.30;TLOD=39.77;ANN=A|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|15/62|c.2462C>T|p.Thr821Ile|2484/16878|2462/14952|821/4983||;FREQ=1000Genomes:0.9998,0.0001997,.|ExAC:0.9999,5.772e-05,.|KOREAN:0.9993,0.0006845,.|TOMMO:0.9998,0.000179,.|dbGaP_PopFreq:1,4.407e-05,.;RS=200598064;dbSNPBuildID=137	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1525,24:0.012:1549:829,11:690,13:863,662,13,11	chr7-152247975-G-A	1549	1525	0.0154938670109748	24	PZ39	FALSE	KMT2C	chr7_152247975	4	1953	Only Human	20.4	NA	612	Old	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	PZ39_chr7-152247975-G-A
+PZ39	chr7	152265049	rs146238849	G	T	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=739,438|43,17;DP=1255;ECNT=4;GERMQ=93;MBQ=20,20;MFRL=171,179;MMQ=48,47;MPOS=34;POPAF=7.30;TLOD=101.12;ANN=T|stop_gained|HIGH|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|9/62|c.1176C>A|p.Cys392*|1198/16878|1176/14952|392/4983||;LOF=(KMT2C|KMT2C|1|1.00);NMD=(KMT2C|KMT2C|1|1.00);FREQ=GnomAD_exomes:0.9971,.,0.002894|KOREAN:0.9949,.,0.005133|Korea1K:0.9924,.,0.007642|Siberian:0.5,.,0.5|TOMMO:0.9988,.,0.001193|dbGaP_PopFreq:0.9888,0,0.01123;RS=146238849;dbSNPBuildID=137	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1177,60:0.051:1237:531,35:641,25:739,438,43,17	chr7-152265049-G-T	1237	1177	0.0485044462409054	60	PZ39	FALSE	KMT2C	chr7_152265049	4	1953	Only Human	20.4	NA	612	Old	General_pop	stop_gained	HIGH	KMT2C	protein_coding	SNV	PZ39_chr7-152265049-G-T
+PZ39	chr7	152265083	rs138908625	C	A	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=987,758|59,45;DP=1909;ECNT=4;GERMQ=93;MBQ=20,20;MFRL=164,167;MMQ=48,47;MPOS=43;POPAF=7.30;TLOD=162.14;ANN=A|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|9/62|c.1142G>T|p.Arg381Leu|1164/16878|1142/14952|381/4983||;FREQ=GnomAD_exomes:0.9985,0.001496,.|GoESP:0.9966,0.003383,.|KOREAN:0.9918,0.008214,.|Korea1K:0.9907,0.009279,.|Siberian:0.5,0.5,.|TOMMO:0.9984,0.001611,.|dbGaP_PopFreq:0.9913,0.008728,.;RS=138908625;dbSNPBuildID=134	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1745,104:0.053:1849:798,48:921,54:987,758,59,45	chr7-152265083-C-A	1849	1745	0.0562466197944835	104	PZ39	FALSE	KMT2C	chr7_152265083	4	1953	Only Human	20.4	NA	612	Old	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	PZ39_chr7-152265083-C-A
+PZ39	chr7	152265205	rs775803041	C	G	.	clustered_events	AS_FilterStatus=SITE;AS_SB_TABLE=436,616|7,19;DP=1103;ECNT=9;GERMQ=93;MBQ=20,20;MFRL=178,166;MMQ=48,48;MPOS=15;POPAF=7.30;TLOD=36.65;ANN=G|missense_variant|MODERATE|KMT2C|KMT2C|transcript|XM_005250025.4|protein_coding|9/62|c.1020G>C|p.Lys340Asn|1042/16878|1020/14952|340/4983||;FREQ=ExAC:0.9979,0.002112,.|GnomAD:1,.,7.216e-06|Korea1K:0.9924,0.007642,.|TOMMO:0.9999,.,5.967e-05|TOPMED:1,.,3.778e-06|dbGaP_PopFreq:0.9987,0.001295,0;RS=775803041;dbSNPBuildID=144	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:1052,26:0.026:1078:507,13:528,13:436,616,7,19	chr7-152265205-C-G	1078	1052	0.0241187384044527	26	PZ39	FALSE	KMT2C	chr7_152265205	4	1953	Only Human	20.4	NA	612	Old	General_pop	missense_variant	MODERATE	KMT2C	protein_coding	SNV	PZ39_chr7-152265205-C-G
+PZ39	chr12	25225623	.	C	G	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=248,140|5,4;DP=404;ECNT=1;GERMQ=93;MBQ=20,20;MFRL=220,235;MMQ=60,60;MPOS=46;POPAF=7.30;TLOD=11.50;ANN=G|missense_variant|MODERATE|KRAS|KRAS|transcript|NM_001369786.1|protein_coding|4/6|c.441G>C|p.Lys147Asn|618/5417|441/570|147/189||	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:388,9:0.021:397:179,6:208,3:248,140,5,4	chr12-25225623-C-G	397	388	0.0226700251889169	9	PZ39	FALSE	KRAS	chr12_25225623	4	1953	Only Human	20.4	NA	612	Old	General_pop	missense_variant	MODERATE	KRAS	protein_coding	SNV	PZ39_chr12-25225623-C-G
--- a/OncoPrint.R
+++ b/OncoPrint.R
+library(stringr)
+library(RColorBrewer)
+library(ggplot2)
+library(dplyr)
+library(reshape2)
+library(ComplexHeatmap)
+
+#Load metadata
+metadata = read.delim("Metadata.txt")
+
+#Read clonal hematopoiesis associated genes from Jackbsen et al.
+CH.genes = read.table("ClonalHema_Jakobsen_et_al.txt") 
+
+# List of samples to analyze
+samples <- c("PZ22", "P23","PZ28", "PZ36","PZ37","PZ39", "34-OLD2", "34-OLD3")
+
+######################### Part 1 ###############################################
+#import and process vcf files, if vcf files are not available skip directly to part 2 and import already processed txt files
+#Set working directory containing SnpSift annotated vcf files called using Mutect2
+wdir <- "Mutect2"
+
+###################### Mutect2 vcf processing ##################################
+#Create dataframe with variants from vcf files
+full.t <- data.frame()
+for (ss in samples) {
+  print(ss)
+  orig.name = ss
+  t <- read.table(gzfile(paste(wdir, ss, ".mutect2.filtermutectcalls.ANNOT.dbSNP.vcf.gz", sep = "")), comment.char = "#")
+  colnames(t) <- c("CHROM","POS","ID","REF","ALT","QUAL","FILTER", "ANNOT", "FORMAT", "SAMPLE")
+  if (grepl("_", ss)){
+    ss = unlist(strsplit(ss, "_"))[2]
+  }
+  t$Sample <- ss
+  t$Vars <- paste(t$CHROM, t$POS, t$REF, t$ALT, sep = "-")
+  t$DP <- as.numeric(str_split_fixed(t$SAMPLE, ":", 7)[,4])
+  t$AD <- as.numeric(str_split_fixed(str_split_fixed(t$SAMPLE, ":", 7)[,2], ",", 2)[,1])
+  t$VAF <- (t$DP - t$AD) / t$DP
+  t$AD_alt = t$DP - t$AD
+  t$orig.name = orig.name
+  t$Common = unlist(lapply(t$ANNOT, function(x) grepl("COMMON", x)))
+  full.t <- rbind(full.t, t)
+}
+
+# Filter CHR only
+chr <- c(paste0("chr", seq(1,22)), "chrX")
+full.t <- subset(full.t, CHROM %in% chr)
+full.t$CHROM <- factor(full.t$CHROM, levels = chr)
+
+# Remove Multi
+full.t.nomulti <- full.t[grep(",", full.t$ALT, value = F, invert = T), ]
+
+# Parse snpEff Annotation
+full.t.nomulti$snpEff_tmp <- lapply(full.t.nomulti$ANNOT, function(x){
+  tmp <- strsplit(x, ";")[[1]]
+  ann_pos <- length(tmp)
+  if (!startsWith(tmp[length(tmp)], "ANN")) {
+    for (i in seq(1,length(tmp))) {
+      if (startsWith(tmp[i], "ANN")) {
+        ann_pos <- i
+      }
+    }
+  }
+  tmp <- tmp[ann_pos]
+})
+
+full.t.nomulti$snpEff_GeneName <- sapply(full.t.nomulti$snpEff_tmp, function(tmp){
+  strsplit(tmp, "|", fixed = T)[[1]][5]
+}, USE.NAMES = F)
+
+full.t.nomulti.CHGenes = full.t.nomulti[full.t.nomulti$snpEff_Gene %in% CH.genes$V1,]
+full.t.nomulti.CHGenes$Var.ID = paste(full.t.nomulti.CHGenes$CHROM, full.t.nomulti.CHGenes$POS, sep = "_")
+full.t.nomulti.CHGenes = merge(full.t.nomulti.CHGenes, metadata, by = "Sample")
+full.t.nomulti.CHGenes$Sample = factor(full.t.nomulti.CHGenes$Sample)
+
+#Add information from SnpEff annotations
+full.t.nomulti.CHGenes$snpEff_Effect <- sapply(full.t.nomulti.CHGenes$snpEff_tmp, function(tmp){
+  strsplit(tmp, "|", fixed = T)[[1]][2]
+}, USE.NAMES = F)
+full.t.nomulti.CHGenes$snpEff_Impact <- sapply(full.t.nomulti.CHGenes$snpEff_tmp, function(tmp){
+  strsplit(tmp, "|", fixed = T)[[1]][3]
+}, USE.NAMES = F)
+full.t.nomulti.CHGenes$snpEff_Gene <- sapply(full.t.nomulti.CHGenes$snpEff_tmp, function(tmp){
+  strsplit(tmp, "|", fixed = T)[[1]][4]
+}, USE.NAMES = F)
+full.t.nomulti.CHGenes$snpEff_BioType <- sapply(full.t.nomulti.CHGenes$snpEff_tmp, function(tmp){
+  strsplit(tmp, "|", fixed = T)[[1]][8]
+}, USE.NAMES = F)
+full.t.nomulti.CHGenes$snpEff_tmp <- NULL
+
+#Add type of variantion: Indels, Snp, Other
+full.t.nomulti.CHGenes <- mutate(full.t.nomulti.CHGenes,
+                                 TYPE = case_when(nchar(REF) == 1 & nchar(ALT) == 1 & ALT != "*" ~ "SNV",
+                                                  nchar(REF) == 1 & nchar(ALT) == 1 & ALT == "*" ~ "MNV",
+                                                  nchar(REF) > nchar(ALT) & nchar(REF) - nchar(ALT) >= 1 ~ "DEL",
+                                                  nchar(REF) < nchar(ALT) & nchar(ALT) - nchar(REF) >= 1 ~ "INS",
+                                                  TRUE ~ "Other"))
+
+#Mantain only "deleterious" variantions
+deleterious = names(table(full.t.nomulti.CHGenes$snpEff_Effect))
+deleterious = c("disruptive_inframe_deletion", "frameshift_variant", "frameshift_variant&stop_gained", 
+                "missense_variant", "missense_variant&splice_region_variant", "splice_acceptor_variant&intron_variant", 
+                "splice_acceptor_variant&splice_donor_variant&disruptive_inframe_deletion&splice_region_variant&intron_variant", 
+                "splice_region_variant&intron_variant", "splice_region_variant&synonymous_variant" , 
+                "stop_gained", "stop_gained&splice_region_variant")
+full.t.nomulti.CHGenes = full.t.nomulti.CHGenes[full.t.nomulti.CHGenes$snpEff_Effect %in% deleterious,]
+
+
+#Apply filters: AD_alt > 5 SNV and AD_alt > 10 INDELS and PASS or "clustered_event"
+full.t.nomulti.CHGenes = full.t.nomulti.CHGenes[full.t.nomulti.CHGenes$FILTER == "PASS" | full.t.nomulti.CHGenes$FILTER == "clustered_events", ]
+full.t.nomulti.CHGenes = full.t.nomulti.CHGenes[ifelse( (full.t.nomulti.CHGenes$AD_alt >= 5 & full.t.nomulti.CHGenes$TYPE == "SNV") | 
+                                                          (full.t.nomulti.CHGenes$AD_alt >= 10 & (full.t.nomulti.CHGenes$TYPE == "DEL" | full.t.nomulti.CHGenes$TYPE == "INS") ),
+                                                        TRUE, FALSE), ]
+
+#Remove VAF > 0.4 & < 0.6 or > 0.9
+full.t.nomulti.CHGenes = full.t.nomulti.CHGenes[!(full.t.nomulti.CHGenes$VAF > 0.4 & full.t.nomulti.CHGenes$VAF < 0.6) & !full.t.nomulti.CHGenes$VAF > 0.9,]
+#Remove Common
+full.t.nomulti.CHGenes = full.t.nomulti.CHGenes[full.t.nomulti.CHGenes$Common == FALSE,]
+
+#VAF > 0.01
+full.t.nomulti.CHGenes = full.t.nomulti.CHGenes[full.t.nomulti.CHGenes$VAF > 0.01,]
+
+#Rename filterd dataframe
+full.t.nomulti.CHGenes.Mutect2 = full.t.nomulti.CHGenes
+
+
+###################### VarDict vcf processing ###################################
+wdir <- "VarDict"
+
+full.t <- data.frame()
+for (ss in samples) {
+  print(ss)
+  orig.name = ss
+  empty <- tryCatch({
+    df <- read.table(gzfile(paste(wdir, ss, ".ANNOT.dbSNP.vcf.gz", sep = "")), comment.char = "#")
+    nrow(df) == 0  
+  }, error = function(e) {
+    message("Error reading file, skipping: ", e$message)  
+    TRUE  
+  })
+  
+  if (empty == TRUE){
+    print("Skipping")
+    next
+  }
+  t <- read.table(gzfile(paste(wdir, ss, ".ANNOT.dbSNP.vcf.gz", sep = "")), comment.char = "#")
+  
+  colnames(t) <- c("CHROM","POS","ID","REF","ALT","QUAL","FILTER", "ANNOT", "FORMAT", "SAMPLE")
+  if (grepl("_", ss)){
+    ss = unlist(strsplit(ss, "_"))[2]
+  }
+  t$Sample <- ss
+  t$Vars <- paste(t$CHROM, t$POS, t$REF, t$ALT, sep = "-")
+  t$MQ = as.numeric(gsub("MQ=", "", str_split_fixed(t$ANNOT, ";", 20)[,15]))
+  t$SBF = as.numeric(gsub("SBF=", "", str_split_fixed(t$ANNOT, ";", 20)[,13]))
+  t$DP <- as.numeric(str_split_fixed(t$SAMPLE, ":", 7)[,2])
+  t$AD <- as.numeric(str_split_fixed(str_split_fixed(t$SAMPLE, ":", 7)[,4], ",", 2)[,1])
+  t$VAF <- (t$DP - t$AD) / t$DP
+  t$AD_alt = t$DP - t$AD
+  t$orig.name = orig.name
+  t$Common = unlist(lapply(t$ANNOT, function(x) grepl("COMMON", x)))
+  full.t <- rbind(full.t, t)
+}
+
+# Filter CHR only
+chr <- c(paste0("chr", seq(1,22)), "chrX")
+full.t <- subset(full.t, CHROM %in% chr)
+full.t$CHROM <- factor(full.t$CHROM, levels = chr)
+
+# Remove Multi
+full.t.nomulti <- full.t[grep(",", full.t$ALT, value = F, invert = T), ]
+
+## Parse snpEff Annotation
+full.t.nomulti$snpEff_tmp <- lapply(full.t.nomulti$ANNOT, function(x){
+  tmp <- strsplit(x, ";")[[1]]
+  ann_pos <- length(tmp)
+  if (!startsWith(tmp[length(tmp)], "ANN")) {
+    for (i in seq(1,length(tmp))) {
+      if (startsWith(tmp[i], "ANN")) {
+        ann_pos <- i
+      }
+    }
+  }
+  tmp <- tmp[ann_pos]
+})
+
+full.t.nomulti$snpEff_GeneName <- sapply(full.t.nomulti$snpEff_tmp, function(tmp){
+  strsplit(tmp, "|", fixed = T)[[1]][5]
+}, USE.NAMES = F)
+
+#Selevct only CH genes
+full.t.nomulti.CHGenes = full.t.nomulti[full.t.nomulti$snpEff_Gene %in% CH.genes$V1,]
+full.t.nomulti.CHGenes$Var.ID = paste(full.t.nomulti.CHGenes$CHROM, full.t.nomulti.CHGenes$POS, sep = "_")
+full.t.nomulti.CHGenes = merge(full.t.nomulti.CHGenes, metadata, by = "Sample")
+full.t.nomulti.CHGenes$Sample = factor(full.t.nomulti.CHGenes$Sample)
+
+full.t.nomulti.CHGenes$snpEff_Effect <- sapply(full.t.nomulti.CHGenes$snpEff_tmp, function(tmp){
+  strsplit(tmp, "|", fixed = T)[[1]][2]
+}, USE.NAMES = F)
+full.t.nomulti.CHGenes$snpEff_Impact <- sapply(full.t.nomulti.CHGenes$snpEff_tmp, function(tmp){
+  strsplit(tmp, "|", fixed = T)[[1]][3]
+}, USE.NAMES = F)
+full.t.nomulti.CHGenes$snpEff_Gene <- sapply(full.t.nomulti.CHGenes$snpEff_tmp, function(tmp){
+  strsplit(tmp, "|", fixed = T)[[1]][4]
+}, USE.NAMES = F)
+full.t.nomulti.CHGenes$snpEff_BioType <- sapply(full.t.nomulti.CHGenes$snpEff_tmp, function(tmp){
+  strsplit(tmp, "|", fixed = T)[[1]][8]
+}, USE.NAMES = F)
+full.t.nomulti.CHGenes$snpEff_tmp <- NULL
+
+#Add type
+full.t.nomulti.CHGenes <- mutate(full.t.nomulti.CHGenes,
+                                 TYPE = case_when(nchar(REF) == 1 & nchar(ALT) == 1 & ALT != "*" ~ "SNV",
+                                                  nchar(REF) == 1 & nchar(ALT) == 1 & ALT == "*" ~ "MNV",
+                                                  nchar(REF) > nchar(ALT) & nchar(REF) - nchar(ALT) >= 1 ~ "DEL",
+                                                  nchar(REF) < nchar(ALT) & nchar(ALT) - nchar(REF) >= 1 ~ "INS",
+                                                  TRUE ~ "Other"))
+
+#Only deleterouis mutations
+deleterious = names(table(full.t.nomulti.CHGenes$snpEff_Effect))
+deleterious = c("disruptive_inframe_deletion", "frameshift_variant", "frameshift_variant&stop_gained", 
+                "missense_variant", "missense_variant&splice_region_variant", "splice_acceptor_variant&intron_variant", 
+                "splice_acceptor_variant&splice_donor_variant&disruptive_inframe_deletion&splice_region_variant&intron_variant", 
+                "splice_region_variant&intron_variant", "splice_region_variant&synonymous_variant" , 
+                "stop_gained", "stop_gained&splice_region_variant")
+full.t.nomulti.CHGenes = full.t.nomulti.CHGenes[full.t.nomulti.CHGenes$snpEff_Effect %in% deleterious,]
+
+#Apply filters: AD_alt > 5 SNV and AD_alt > 10 INDELS and PASS or "clustered_event"
+full.t.nomulti.CHGenes = full.t.nomulti.CHGenes[full.t.nomulti.CHGenes$FILTER == "PASS", ]
+full.t.nomulti.CHGenes = full.t.nomulti.CHGenes[ifelse( (full.t.nomulti.CHGenes$AD_alt >= 5 & full.t.nomulti.CHGenes$TYPE == "SNV") | 
+                                                          (full.t.nomulti.CHGenes$AD_alt >= 10 & (full.t.nomulti.CHGenes$TYPE == "DEL" | full.t.nomulti.CHGenes$TYPE == "INS") ),
+                                                        TRUE, FALSE), ]
+
+#Remove VAF > 0.4 & < 0.6 or > 0.9
+full.t.nomulti.CHGenes = full.t.nomulti.CHGenes[!(full.t.nomulti.CHGenes$VAF > 0.4 & full.t.nomulti.CHGenes$VAF < 0.6) & !full.t.nomulti.CHGenes$VAF > 0.9,]
+
+#Quality >= 25 and MQ >= 40 and SBF <= 0.0001
+full.t.nomulti.CHGenes = full.t.nomulti.CHGenes[full.t.nomulti.CHGenes$QUAL >= 30,]
+full.t.nomulti.CHGenes = full.t.nomulti.CHGenes[full.t.nomulti.CHGenes$MQ >= 40,]
+full.t.nomulti.CHGenes = full.t.nomulti.CHGenes[full.t.nomulti.CHGenes$SBF >= 0.0001,]
+#Remove Common
+full.t.nomulti.CHGenes = full.t.nomulti.CHGenes[full.t.nomulti.CHGenes$Common == FALSE,]
+
+#VAF > 0.01
+full.t.nomulti.CHGenes = full.t.nomulti.CHGenes[full.t.nomulti.CHGenes$VAF > 0.01,]
+
+full.t.nomulti.CHGenes.VarDict = full.t.nomulti.CHGenes
+
+
+############################## Part 2  #########################################
+################ Oncoplot for common consensus mutations #######################
+
+full.t.nomulti.CHGenes.Mutect2 = read.delim("Mutect2_variants.txt")
+full.t.nomulti.CHGenes.VarDict = read.delim("VarDict_variants.txt")
+
+#Find common variantions called by both Mutect2 and VarDict
+full.t.nomulti.CHGenes.VarDict$ID_SAMPLE = paste(full.t.nomulti.CHGenes.VarDict$Sample, full.t.nomulti.CHGenes.VarDict$Vars, sep = "_")
+full.t.nomulti.CHGenes.Mutect2$ID_SAMPLE = paste(full.t.nomulti.CHGenes.Mutect2$Sample, full.t.nomulti.CHGenes.Mutect2$Vars, sep = "_")
+common = intersect(full.t.nomulti.CHGenes.VarDict$ID_SAMPLE, full.t.nomulti.CHGenes.Mutect2$ID_SAMPLE)
+full.t.nomulti.CHGenes.common = full.t.nomulti.CHGenes.Mutect2[full.t.nomulti.CHGenes.Mutect2$ID_SAMPLE %in% common & full.t.nomulti.CHGenes.Mutect2$TYPE == "SNV",]
+
+#Select samples
+toinclude = samples
+
+#Create Input matrix for oncoPrint
+mutation_matrix = aggregate(TYPE ~ snpEff_GeneName + Sample, data = full.t.nomulti.CHGenes.common, 
+                            FUN = function(x) paste(x, collapse = ";"))
+mutation_matrix <- dcast(mutation_matrix, snpEff_GeneName ~ Sample, value.var = "TYPE", fill = "")
+rownames(mutation_matrix) = mutation_matrix$snpEff_GeneName
+mutation_matrix$snpEff_GeneName = NULL
+
+#Check that all samples are present in matrix, some sample may have 0 mutations, if not present add them back
+tobeadded = toinclude[!(toinclude %in% colnames(mutation_matrix))]
+if (length(tobeadded) > 0){
+  print("Add missing")
+  tmp.frame = data.frame(matrix(ncol = length(tobeadded)))
+  colnames(tmp.frame) = tobeadded
+  mutation_matrix = cbind(mutation_matrix, tmp.frame)
+}
+
+#Add also gene with 0 mutations 
+tobeadded = unique(CH.genes[!(CH.genes$V1 %in% rownames(mutation_matrix)), "V1"])
+if (length(tobeadded) > 0){
+  print("Add missing genes with 0 mutations")
+  tmp.frame = data.frame(matrix(nrow = length(tobeadded), ncol = ncol(mutation_matrix)))
+  colnames(tmp.frame) = colnames(mutation_matrix)
+  rownames(tmp.frame) = tobeadded
+  mutation_matrix = rbind(mutation_matrix, tmp.frame)
+}
+
+
+#Create annotations dataframe
+cohort_info = as.data.frame(metadata[metadata$Sample %in% toinclude,c ("Sample", "Source.1")])
+rownames(cohort_info) = cohort_info$Sample
+cohort_info = cohort_info[colnames(mutation_matrix),]
+
+ha <- HeatmapAnnotation(
+  Cohort = cohort_info$Source.1,
+  which = "col",
+  col = list(Cohort = c("General_pop" = "lightgreen"))
+)
+
+#Change names of file: from fastq names to general name 
+v <- c(
+  "PZ22:HD MA 2",
+  "P23:HD OLD 6",
+  "PZ28:HD MA 1",
+  "PZ36:HD OLD 8",
+  "PZ37:HD OLD 9",
+  "PZ39:HD MA 3",
+  "34-OLD2:HD OLD 16",
+  "34-OLD3:HD MA 8"
+)
+
+keys   <- sub(":.*$", "", v)
+values <- sub("^[^:]+:", "", v)
+x <- colnames(mutation_matrix)
+for(i in seq_along(keys)){
+  x <- gsub(keys[i], values[i], x, fixed = TRUE)
+}
+colnames(mutation_matrix) = x
+
+
+col = c("SNV" = "#008000")
+
+alter_fun = list(
+  background = function(x, y, w, h) {
+    grid.rect(x, y, w-unit(2, "pt"), h-unit(2, "pt"), 
+              gp = gpar(fill = "#CCCCCC", col = NA))
+  },
+  # big blue
+  INS = function(x, y, w, h) {
+    grid.rect(x, y, w-unit(2, "pt"), h-unit(2, "pt"), 
+              gp = gpar(fill = col["INS"], col = NA))
+  },
+  # big red
+  DEL = function(x, y, w, h) {
+    grid.rect(x, y, w-unit(2, "pt"), h-unit(2, "pt"), 
+              gp = gpar(fill = col["DEL"], col = NA))
+  },
+  # small green
+  SNV = function(x, y, w, h) {
+    grid.rect(x, y, w-unit(2, "pt"), h*0.33, 
+              gp = gpar(fill = col["SNV"], col = NA))
+  }
+)
+
+
+
+# Do Oncoprint
+oncoPrint(mutation_matrix,
+          row_names_gp = gpar(fontsize = 10),pct_gp = gpar(fontsize = 10),
+          remove_empty_rows = T, 
+          alter_fun = alter_fun, col = col, 
+          column_order = colnames(mutation_matrix),
+          show_column_names = TRUE,
+          show_row_names = TRUE,
+          show_pct = F,
+          bottom_annotation = ha)
--- a/README.md
+++ b/README.md
-Code and files for WES analysis
+#Whole-Exome Sequencing (WES) Analysis
+
+This repository contains the files and scripts used for the WES analysis presented in:
+
+Lettera et al., 2025
+Molecular and phenotypic blueprint of the hematopoietic compartment reveals proliferation stress as a driver of age-associated human stem cell dysfunctions
+
+#Study Context
+
+Whole-exome sequencing (WES) was performed to evaluate potential genomic alterations in human hematopoietic stem cells during aging. The analysis focused on variant detection and functional annotation.
+
+#Repository Description
+
+OncoPrint.R: contains the code to process, filter, and create an oncoprint plot from VCF files.
+
+ClonalHema_Jakobsen_et_al.txt: contains the list of clonal hematopoiesis–associated genes from Jakobsen et al.
+
+Metadata.txt: contains information about the samples.
+
+Mutect2_variants.txt: contains the already computed and filtered matrix of variants called using the Mutect2 pipeline.
+
+VarDict_variants.txt: contains the already computed and filtered matrix of variants called using the VarDict pipeline.
+
+#Data Availability
+
+Raw FASTQ files are available in the European Nucleotide Archive (ENA), accession code: PRJEB93902.
+
+#Tools and Notes
+
+Variants are called using both Mutect2 and VarDict to select a set of high-confidence variants.
+
+Variants were then filtered for quality, coverage, presence in a panel of genes related to clonal hematopoiesis, and effect on the harboring gene.
+
+The oncoprint was generated using the ComplexHeatmap R package to explore variant distributions across genes and samples.
+
+#Citation
+
+If you use this repository or data, please cite:
+
+Lettera et al., Molecular and phenotypic blueprint of the hematopoietic compartment reveals proliferation stress as a driver of age-associated human stem cell dysfunctions
+
+Thank you.
--- a/VarDict_variants.txt
+++ b/VarDict_variants.txt
+Sample	CHROM	POS	ID.x	REF	ALT	QUAL	FILTER	ANNOT	FORMAT	SAMPLE	Vars	MQ	SBF	DP	AD	VAF	AD_alt	orig.name	Common	snpEff_GeneName	Var.ID	ID.y	Age	Source	Concentration..ng.μL.	tot.volume..uL.	Total.DNA..ng.	Group_Age	Source.1	snpEff_Effect	snpEff_Impact	snpEff_Gene	snpEff_BioType	TYPE	ID_SAMPLE
+34-OLD2	chr2	25246656	rs754223052	G	A	135	PASS	SAMPLE=34-OLD2;TYPE=SNV;DP=1283;VD=14;AF=0.0109;BIAS=2:2;REFBIAS=701:568;VARBIAS=7:7;PMEAN=33.1;PSTD=1;QUAL=35.7;QSTD=1;SBF=0.78964;ODDRATIO=1.23395;MQ=60;SN=28;HIAF=0.0111;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=1;NM=1.1;HICNT=14;HICOV=1262;LSEQ=GCCCTTAGGGCCAGAAGGCT;RSEQ=GAAGCCCCCCAGGGCCCATT;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|stop_gained|HIGH|DNMT3A|DNMT3A|transcript|NM_022552.5|protein_coding|10/23|c.1243C>T|p.Gln415*|1520/9421|1243/2739|415/912||;LOF=(DNMT3A|DNMT3A|1|1.00);NMD=(DNMT3A|DNMT3A|1|1.00);FREQ=ExAC:1,1.699e-05|GnomAD:1,7.129e-06|TOMMO:0.9999,0.0001193|dbGaP_PopFreq:1,0;RS=754223052;dbSNPBuildID=144	GT:DP:VD:AD:AF:RD:ALD	0/1:1283:14:1269,14:0.0109:701,568:7,7	chr2-25246656-G-A	60	0.78964	1283	1269	0.0109119251753702	14	34-OLD2	FALSE	DNMT3A	chr2_25246656	43	1951	Only Human	95.4	NA	2862	Old	General_pop	stop_gained	HIGH	DNMT3A	protein_coding	SNV	34-OLD2_chr2-25246656-G-A
+34-OLD2	chr3	136422412	.	C	A	123	PASS	SAMPLE=34-OLD2;TYPE=SNV;DP=683;VD=17;AF=0.0249;BIAS=2:2;REFBIAS=419:247;VARBIAS=13:4;PMEAN=11.1;PSTD=1;QUAL=30.1;QSTD=1;SBF=0.31475;ODDRATIO=1.91424196018377;MQ=60;SN=4.667;HIAF=0.0212;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=1;NM=2.0;HICNT=14;HICOV=661;LSEQ=ATTAACTTTAGAACAGACCT;RSEQ=TTGCAATAGGTCTTCCACAG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|stop_gained&splice_region_variant|HIGH|STAG1|STAG1|transcript|NM_005862.3|protein_coding|19/34|c.2035G>T|p.Glu679*|2302/6062|2035/3777|679/1258||;LOF=(STAG1|STAG1|1|1.00);NMD=(STAG1|STAG1|1|1.00)	GT:DP:VD:AD:AF:RD:ALD	0/1:683:17:666,17:0.0249:419,247:13,4	chr3-136422412-C-A	60	0.31475	683	666	0.0248901903367496	17	34-OLD2	FALSE	STAG1	chr3_136422412	43	1951	Only Human	95.4	NA	2862	Old	General_pop	stop_gained&splice_region_variant	HIGH	STAG1	protein_coding	SNV	34-OLD2_chr3-136422412-C-A
+34-OLD2	chr17	31232070	rs777759972	C	T	120	PASS	SAMPLE=34-OLD2;TYPE=SNV;DP=528;VD=17;AF=0.0322;BIAS=2:2;REFBIAS=232:277;VARBIAS=14:3;PMEAN=18.7;PSTD=1;QUAL=29.6;QSTD=1;SBF=0.00491;ODDRATIO=5.55524693072607;MQ=60;SN=2.4;HIAF=0.0273;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=2.1;HICNT=12;HICOV=439;LSEQ=TTTTTTTTTTTTTTTTTTTT;RSEQ=AGAGATTTGGACCAGGCAAG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|splice_region_variant&intron_variant|LOW|NF1|NF1|transcript|NM_001042492.3|protein_coding|24/57|c.3198-3C>T||||||;FREQ=ExAC:0.9996,.,0.0004148|GnomAD_exomes:0.995,.,0.005024|KOREAN:0.8931,.,0.1069|Siberian:0.5,.,0.5|dbGaP_PopFreq:0.9999,0,0;RS=777759972;dbSNPBuildID=144	GT:DP:VD:AD:AF:RD:ALD	0/1:528:17:509,17:0.0322:232,277:14,3	chr17-31232070-C-T	60	0.00491	528	509	0.0359848484848485	19	34-OLD2	FALSE	NF1	chr17_31232070	43	1951	Only Human	95.4	NA	2862	Old	General_pop	splice_region_variant&intron_variant	LOW	NF1	protein_coding	SNV	34-OLD2_chr17-31232070-C-T
+34-OLD2	chr19	33302135	.	C	G	117	PASS	SAMPLE=34-OLD2;TYPE=SNV;DP=235;VD=9;AF=0.0383;BIAS=2:2;REFBIAS=126:99;VARBIAS=5:4;PMEAN=11.6;PSTD=1;QUAL=37;QSTD=1;SBF=1;ODDRATIO=1.01811;MQ=60;SN=18;HIAF=0.0402;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=1;NM=2.3;HICNT=9;HICOV=224;LSEQ=GCCGCCCGTGGGGCCCACGG;RSEQ=CGCCTTGGCCTTCTCCTGCT;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=G|missense_variant|MODERATE|CEBPA|CEBPA|transcript|NM_001287424.2|protein_coding|1/1|c.385G>C|p.Ala129Pro|400/2601|385/1182|129/393||WARNING_TRANSCRIPT_NO_START_CODON,G|upstream_gene_variant|MODIFIER|CEBPA-DT|CEBPA-DT|transcript|NR_026887.2|pseudogene||n.-686C>G|||||686|	GT:DP:VD:AD:AF:RD:ALD	0/1:235:9:225,9:0.0383:126,99:5,4	chr19-33302135-C-G	60	1	235	225	0.0425531914893617	10	34-OLD2	FALSE	CEBPA	chr19_33302135	43	1951	Only Human	95.4	NA	2862	Old	General_pop	missense_variant	MODERATE	CEBPA	protein_coding	SNV	34-OLD2_chr19-33302135-C-G
+34-OLD2	chrX	53396621	rs1556888082	G	T	74	PASS	SAMPLE=34-OLD2;TYPE=SNV;DP=489;VD=6;AF=0.0123;BIAS=2:0;REFBIAS=187:296;VARBIAS=0:6;PMEAN=19.3;PSTD=1;QUAL=29;QSTD=1;SBF=0.08702;ODDRATIO=0;MQ=60;SN=2;HIAF=0.0090;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=2.5;HICNT=4;HICOV=442;LSEQ=ATGTGTCTTTGTTCCTCCTG;RSEQ=TCCCAGCAGTGGGAACAGGA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|splice_region_variant&intron_variant|LOW|SMC1A|SMC1A|transcript|NM_006306.4|protein_coding|16/24|c.2563-4C>A||||||;FREQ=GnomAD_exomes:1,5.558e-06|dbGaP_PopFreq:0.9999,0.0001113;RS=1556888082;dbSNPBuildID=152	GT:DP:VD:AD:AF:RD:ALD	0/1:489:6:483,6:0.0123:187,296:0,6	chrX-53396621-G-T	60	0.08702	489	483	0.0122699386503067	6	34-OLD2	FALSE	SMC1A	chrX_53396621	43	1951	Only Human	95.4	NA	2862	Old	General_pop	splice_region_variant&intron_variant	LOW	SMC1A	protein_coding	SNV	34-OLD2_chrX-53396621-G-T
+34-OLD2	chrX	124071143	rs1403218809	A	T	84	PASS	SAMPLE=34-OLD2;TYPE=SNV;DP=461;VD=5;AF=0.0108;BIAS=2:2;REFBIAS=271:177;VARBIAS=3:2;PMEAN=31;PSTD=1;QUAL=36.6;QSTD=1;SBF=1;ODDRATIO=1.02068;MQ=60;SN=10;HIAF=0.0120;ADJAF=0;SHIFT3=4;MSI=3;MSILEN=1;NM=1.4;HICNT=5;HICOV=415;LSEQ=TTCCTCTTTTTTTTTTTTTT;RSEQ=AATAGGCCTTCACTATTCTG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|splice_region_variant&intron_variant|LOW|STAG2|STAG2|transcript|NM_001042749.2|protein_coding|24/34|c.2359-6A>T||||||;FREQ=GnomAD_exomes:0.9998,0.0001593|KOREAN:0.9884,0.01164|dbGaP_PopFreq:0.9957,0.004252;RS=1403218809;dbSNPBuildID=151	GT:DP:VD:AD:AF:RD:ALD	0/1:461:5:448,5:0.0108:271,177:3,2	chrX-124071143-A-T	60	1	461	448	0.0281995661605206	13	34-OLD2	FALSE	STAG2	chrX_124071143	43	1951	Only Human	95.4	NA	2862	Old	General_pop	splice_region_variant&intron_variant	LOW	STAG2	protein_coding	SNV	34-OLD2_chrX-124071143-A-T
+34-OLD3	chr5	37061024	.	T	A	116	PASS	SAMPLE=34-OLD3;TYPE=SNV;DP=845;VD=9;AF=0.0107;BIAS=2:2;REFBIAS=310:524;VARBIAS=3:6;PMEAN=17.6;PSTD=1;QUAL=36.7;QSTD=1;SBF=1;ODDRATIO=1.18301;MQ=60;SN=18;HIAF=0.0110;ADJAF=0;SHIFT3=1;MSI=2;MSILEN=3;NM=1.1;HICNT=9;HICOV=819;LSEQ=AAACAGTATCTAGATGTGAG;RSEQ=AGTAAAACCAAAAGTTTTTA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|splice_region_variant&intron_variant|LOW|NIPBL|NIPBL|transcript|NM_133433.4|protein_coding|45/46|c.7860+6T>A||||||	GT:DP:VD:AD:AF:RD:ALD	0/1:845:9:834,9:0.0107:310,524:3,6	chr5-37061024-T-A	60	1	845	834	0.0130177514792899	11	34-OLD3	FALSE	NIPBL	chr5_37061024	44	1948	Only Human	37.9	NA	1137	Old	General_pop	splice_region_variant&intron_variant	LOW	NIPBL	protein_coding	SNV	34-OLD3_chr5-37061024-T-A
+34-OLD3	chr5	150070179	.	T	C	146	PASS	SAMPLE=34-OLD3;TYPE=SNV;DP=1515;VD=18;AF=0.0119;BIAS=2:2;REFBIAS=745:751;VARBIAS=11:7;PMEAN=8.7;PSTD=1;QUAL=35.1;QSTD=1;SBF=0.3559;ODDRATIO=1.58360650545552;MQ=60;SN=17;HIAF=0.0115;ADJAF=0;SHIFT3=2;MSI=1;MSILEN=1;NM=1.3;HICNT=17;HICOV=1474;LSEQ=GGAGGTGAGTGGAGCCCACT;RSEQ=ACCTATCAGTGTGGCCACTG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=C|splice_region_variant&intron_variant|LOW|CSF1R|CSF1R|transcript|NM_001288705.3|protein_coding|8/20|c.1319+3A>G||||||	GT:DP:VD:AD:AF:RD:ALD	0/1:1515:18:1496,18:0.0119:745,751:11,7	chr5-150070179-T-C	60	0.3559	1515	1496	0.0125412541254125	19	34-OLD3	FALSE	CSF1R	chr5_150070179	44	1948	Only Human	37.9	NA	1137	Old	General_pop	splice_region_variant&intron_variant	LOW	CSF1R	protein_coding	SNV	34-OLD3_chr5-150070179-T-C
+34-OLD3	chr11	62598647	.	A	T	133	PASS	SAMPLE=34-OLD3;TYPE=SNV;DP=1341;VD=14;AF=0.0104;BIAS=2:2;REFBIAS=539:786;VARBIAS=6:8;PMEAN=10.6;PSTD=1;QUAL=35.1;QSTD=1;SBF=1;ODDRATIO=1.09361329833771;MQ=60;SN=28;HIAF=0.0107;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=1;NM=5.0;HICNT=14;HICOV=1310;LSEQ=TCTTCAAACTCCCCTGGGAG;RSEQ=TTAAAGAGGAAGAAACCAAG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|splice_region_variant&intron_variant|LOW|MTA2|MTA2|transcript|NM_004739.4|protein_coding|3/17|c.191-8T>A||||||,T|downstream_gene_variant|MODIFIER|EML3|EML3|transcript|XM_006718489.4|protein_coding||c.*3655T>A|||||3571|	GT:DP:VD:AD:AF:RD:ALD	0/1:1341:14:1325,14:0.0104:539,786:6,8	chr11-62598647-A-T	60	1	1341	1325	0.0119313944817301	16	34-OLD3	FALSE	MTA2	chr11_62598647	44	1948	Only Human	37.9	NA	1137	Old	General_pop	splice_region_variant&intron_variant	LOW	MTA2	protein_coding	SNV	34-OLD3_chr11-62598647-A-T
+34-OLD3	chr13	28004167	.	T	A	124	PASS	SAMPLE=34-OLD3;TYPE=SNV;DP=1214;VD=13;AF=0.0107;BIAS=2:2;REFBIAS=520:681;VARBIAS=7:6;PMEAN=16.9;PSTD=1;QUAL=33.6;QSTD=1;SBF=0.57585;ODDRATIO=1.52732382319699;MQ=60;SN=12;HIAF=0.0100;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=4.2;HICNT=12;HICOV=1203;LSEQ=AAACACGGCCATCCACATTC;RSEQ=GATACATCTGAATGTGGGAA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|missense_variant|MODERATE|FLT3|FLT3|transcript|NM_004119.3|protein_coding|24/24|c.2867A>T|p.Gln956Leu|2933/3826|2867/2982|956/993||	GT:DP:VD:AD:AF:RD:ALD	0/1:1214:13:1201,13:0.0107:520,681:7,6	chr13-28004167-T-A	60	0.57585	1214	1201	0.0107084019769358	13	34-OLD3	FALSE	FLT3	chr13_28004167	44	1948	Only Human	37.9	NA	1137	Old	General_pop	missense_variant	MODERATE	FLT3	protein_coding	SNV	34-OLD3_chr13-28004167-T-A
+34-OLD3	chr16	3728451	rs765821935	T	A	162	PASS	SAMPLE=34-OLD3;TYPE=SNV;DP=1909;VD=28;AF=0.0147;BIAS=2:2;REFBIAS=871:1010;VARBIAS=11:17;PMEAN=11.7;PSTD=1;QUAL=33.8;QSTD=1;SBF=0.56782;ODDRATIO=1.33256;MQ=60;SN=27;HIAF=0.0144;ADJAF=0;SHIFT3=0;MSI=4;MSILEN=3;NM=2.6;HICNT=27;HICOV=1871;LSEQ=GCTGCTGTTGCTGCTGCTGC;RSEQ=GCAGCAGCTGCCTCCGTAAC;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|missense_variant|MODERATE|CREBBP|CREBBP|transcript|NM_004380.3|protein_coding|31/31|c.6596A>T|p.Gln2199Leu|7393/10790|6596/7329|2199/2442||;FREQ=ExAC:1,1.71e-05|GnomAD:1,2.855e-05|GnomAD_exomes:1,2.45e-05|TOMMO:0.9999,5.967e-05|TOPMED:1,1.889e-05|dbGaP_PopFreq:0.9999,5.647e-05;RS=765821935;dbSNPBuildID=144	GT:DP:VD:AD:AF:RD:ALD	0/1:1909:28:1881,28:0.0147:871,1010:11,17	chr16-3728451-T-A	60	0.56782	1909	1881	0.0146673651126244	28	34-OLD3	FALSE	CREBBP	chr16_3728451	44	1948	Only Human	37.9	NA	1137	Old	General_pop	missense_variant	MODERATE	CREBBP	protein_coding	SNV	34-OLD3_chr16-3728451-T-A
+34-OLD3	chr19	17834693	.	T	A	134	PASS	SAMPLE=34-OLD3;TYPE=SNV;DP=1257;VD=14;AF=0.0111;BIAS=2:2;REFBIAS=559:676;VARBIAS=6:8;PMEAN=9.1;PSTD=1;QUAL=35.4;QSTD=1;SBF=1;ODDRATIO=1.10244;MQ=60;SN=28;HIAF=0.0123;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=3;NM=3.2;HICNT=14;HICOV=1141;LSEQ=TCCACTTGGGGGCCGGCAGC;RSEQ=GCTGCCGGTCCTCATAAAAT;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|missense_variant|MODERATE|JAK3|JAK3|transcript|NM_000215.4|protein_coding|17/24|c.2228A>T|p.Gln743Leu|2278/5386|2228/3375|743/1124||	GT:DP:VD:AD:AF:RD:ALD	0/1:1257:14:1235,14:0.0111:559,676:6,8	chr19-17834693-T-A	60	1	1257	1235	0.0175019888623707	22	34-OLD3	FALSE	JAK3	chr19_17834693	44	1948	Only Human	37.9	NA	1137	Old	General_pop	missense_variant	MODERATE	JAK3	protein_coding	SNV	34-OLD3_chr19-17834693-T-A
+34-OLD3	chr19	33302135	.	C	G	137	PASS	SAMPLE=34-OLD3;TYPE=SNV;DP=429;VD=19;AF=0.0443;BIAS=2:2;REFBIAS=227:182;VARBIAS=10:9;PMEAN=15.9;PSTD=1;QUAL=32.4;QSTD=1;SBF=0.81772;ODDRATIO=1.12222;MQ=60;SN=5.333;HIAF=0.0393;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=1;NM=2.8;HICNT=16;HICOV=407;LSEQ=GCCGCCCGTGGGGCCCACGG;RSEQ=CGCCTTGGCCTTCTCCTGCT;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=G|missense_variant|MODERATE|CEBPA|CEBPA|transcript|NM_001287424.2|protein_coding|1/1|c.385G>C|p.Ala129Pro|400/2601|385/1182|129/393||WARNING_TRANSCRIPT_NO_START_CODON,G|upstream_gene_variant|MODIFIER|CEBPA-DT|CEBPA-DT|transcript|NR_026887.2|pseudogene||n.-686C>G|||||686|	GT:DP:VD:AD:AF:RD:ALD	0/1:429:19:409,19:0.0443:227,182:10,9	chr19-33302135-C-G	60	0.81772	429	409	0.0466200466200466	20	34-OLD3	FALSE	CEBPA	chr19_33302135	44	1948	Only Human	37.9	NA	1137	Old	General_pop	missense_variant	MODERATE	CEBPA	protein_coding	SNV	34-OLD3_chr19-33302135-C-G
+34-OLD3	chr21	34792311	rs1741971195	G	A	41	PASS	SAMPLE=34-OLD3;TYPE=SNV;DP=155;VD=3;AF=0.0194;BIAS=2:2;REFBIAS=91:56;VARBIAS=1:2;PMEAN=42.3;PSTD=1;QUAL=26.3;QSTD=1;SBF=0.55961;ODDRATIO=3.22386;MQ=60;SN=2;HIAF=0.0225;ADJAF=0;SHIFT3=1;MSI=2;MSILEN=2;NM=3.0;HICNT=2;HICOV=89;LSEQ=CAGGATGCGCGGCGGCGAGC;RSEQ=CTCGCCGCCCACCATGGAGA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|missense_variant|MODERATE|RUNX1|RUNX1|transcript|NM_001754.5|protein_coding|9/9|c.1267C>T|p.Arg423Cys|1461/5971|1267/1443|423/480||;FREQ=TOPMED:1,3.778e-06|dbGaP_PopFreq:1,0;RS=1741971195;dbSNPBuildID=155	GT:DP:VD:AD:AF:RD:ALD	0/1:155:3:147,3:0.0194:91,56:1,2	chr21-34792311-G-A	60	0.55961	155	147	0.0516129032258065	8	34-OLD3	FALSE	RUNX1	chr21_34792311	44	1948	Only Human	37.9	NA	1137	Old	General_pop	missense_variant	MODERATE	RUNX1	protein_coding	SNV	34-OLD3_chr21-34792311-G-A
+34-OLD3	chrX	53396621	rs1556888082	G	T	121	PASS	SAMPLE=34-OLD3;TYPE=SNV;DP=653;VD=25;AF=0.0383;BIAS=2:2;REFBIAS=247:381;VARBIAS=5:20;PMEAN=17.2;PSTD=1;QUAL=26.1;QSTD=1;SBF=0.05961;ODDRATIO=2.5899;MQ=60;SN=1.778;HIAF=0.0271;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=1.4;HICNT=16;HICOV=590;LSEQ=ATGTGTCTTTGTTCCTCCTG;RSEQ=TCCCAGCAGTGGGAACAGGA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|splice_region_variant&intron_variant|LOW|SMC1A|SMC1A|transcript|NM_006306.4|protein_coding|16/24|c.2563-4C>A||||||;FREQ=GnomAD_exomes:1,5.558e-06|dbGaP_PopFreq:0.9999,0.0001113;RS=1556888082;dbSNPBuildID=152	GT:DP:VD:AD:AF:RD:ALD	0/1:653:25:628,25:0.0383:247,381:5,20	chrX-53396621-G-T	60	0.05961	653	628	0.0382848392036753	25	34-OLD3	FALSE	SMC1A	chrX_53396621	44	1948	Only Human	37.9	NA	1137	Old	General_pop	splice_region_variant&intron_variant	LOW	SMC1A	protein_coding	SNV	34-OLD3_chrX-53396621-G-T
+34-OLD3	chrX	77681783	.	G	T	100	PASS	SAMPLE=34-OLD3;TYPE=SNV;DP=644;VD=8;AF=0.0124;BIAS=2:2;REFBIAS=311:325;VARBIAS=2:6;PMEAN=13.5;PSTD=1;QUAL=33.4;QSTD=1;SBF=0.28754;ODDRATIO=2.86673;MQ=60;SN=7;HIAF=0.0111;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=2.6;HICNT=7;HICOV=629;LSEQ=TATCTTCAGAACTTTCCTCA;RSEQ=CATCAGATGATGATGAGCCA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|missense_variant|MODERATE|ATRX|ATRX|transcript|NM_000489.6|protein_coding|9/35|c.3473C>A|p.Ala1158Asp|3688/11165|3473/7479|1158/2492||	GT:DP:VD:AD:AF:RD:ALD	0/1:644:8:636,8:0.0124:311,325:2,6	chrX-77681783-G-T	60	0.28754	644	636	0.0124223602484472	8	34-OLD3	FALSE	ATRX	chrX_77681783	44	1948	Only Human	37.9	NA	1137	Old	General_pop	missense_variant	MODERATE	ATRX	protein_coding	SNV	34-OLD3_chrX-77681783-G-T
+34-OLD3	chrX	124071142	rs766542365	T	A	96	PASS	SAMPLE=34-OLD3;TYPE=SNV;DP=528;VD=8;AF=0.0152;BIAS=2:2;REFBIAS=323:193;VARBIAS=5:3;PMEAN=42.2;PSTD=1;QUAL=32.1;QSTD=1;SBF=1;ODDRATIO=1.00414;MQ=60;SN=7;HIAF=0.0140;ADJAF=0;SHIFT3=0;MSI=3;MSILEN=1;NM=1.8;HICNT=7;HICOV=500;LSEQ=TTTCCTCTTTTTTTTTTTTT;RSEQ=AAATAGGCCTTCACTATTCT;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|splice_region_variant&intron_variant|LOW|STAG2|STAG2|transcript|NM_001042749.2|protein_coding|24/34|c.2359-7T>A||||||;FREQ=ExAC:1,1.204e-05|GnomAD_exomes:1,1.801e-05|TOPMED:1,1.133e-05|dbGaP_PopFreq:1,0;RS=766542365;dbSNPBuildID=144	GT:DP:VD:AD:AF:RD:ALD	0/1:528:8:516,8:0.0152:323,193:5,3	chrX-124071142-T-A	60	1	528	516	0.0227272727272727	12	34-OLD3	FALSE	STAG2	chrX_124071142	44	1948	Only Human	37.9	NA	1137	Old	General_pop	splice_region_variant&intron_variant	LOW	STAG2	protein_coding	SNV	34-OLD3_chrX-124071142-T-A
+P23	chr7	105105646	.	A	G	72	PASS	SAMPLE=P23;TYPE=SNV;DP=462;VD=5;AF=0.0108;BIAS=2:2;REFBIAS=180:277;VARBIAS=3:2;PMEAN=47.2;PSTD=1;QUAL=31.2;QSTD=1;SBF=0.38913;ODDRATIO=2.30404128841989;MQ=60;SN=4;HIAF=0.0092;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=1;NM=1.0;HICNT=4;HICOV=434;LSEQ=CACCATTCCTTTCAGAAAAA;RSEQ=GGAGAAGAAAAGAACCTACT;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=G|missense_variant|MODERATE|KMT2E|KMT2E|transcript|NM_018682.4|protein_coding|17/26|c.2404A>G|p.Arg802Gly|2775/7634|2404/5577|802/1858||	GT:DP:VD:AD:AF:RD:ALD	0/1:462:5:457,5:0.0108:180,277:3,2	chr7-105105646-A-G	60	0.38913	462	457	0.0108225108225108	5	P23	FALSE	KMT2E	chr7_105105646	3	1929	Only Human	17	NA	510	Old	General_pop	missense_variant	MODERATE	KMT2E	protein_coding	SNV	P23_chr7-105105646-A-G
+P23	chr9	5081861	rs764700283	G	A	75	PASS	SAMPLE=P23;TYPE=SNV;DP=453;VD=5;AF=0.011;BIAS=2:2;REFBIAS=179:269;VARBIAS=2:3;PMEAN=37;PSTD=1;QUAL=32.6;QSTD=1;SBF=1;ODDRATIO=1.00185342884336;MQ=60;SN=4;HIAF=0.0092;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=1;NM=1.0;HICNT=4;HICOV=433;LSEQ=TTTCTACAGCAACTTGGCAA;RSEQ=GTAAATTGTCAGAATTTTTT;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|splice_region_variant&synonymous_variant|LOW|JAK2|JAK2|transcript|NM_001322194.2|protein_coding|19/25|c.2571G>A|p.Lys857Lys|3166/7151|2571/3399|857/1132||,A|intragenic_variant|MODIFIER|INSL6|INSL6|gene_variant|INSL6|||n.5081861C>T||||||;FREQ=ExAC:1,8.26e-06,.|TOPMED:1,.,3.778e-06|dbGaP_PopFreq:1,0,2.822e-05;RS=764700283;dbSNPBuildID=144	GT:DP:VD:AD:AF:RD:ALD	0/1:453:5:448,5:0.011:179,269:2,3	chr9-5081861-G-A	60	1	453	448	0.011037527593819	5	P23	FALSE	JAK2	chr9_5081861	3	1929	Only Human	17	NA	510	Old	General_pop	splice_region_variant&synonymous_variant	LOW	JAK2	protein_coding	SNV	P23_chr9-5081861-G-A
+P23	chr10	87864146	.	G	C	36	PASS	SAMPLE=P23;TYPE=SNV;DP=179;VD=2;AF=0.0112;BIAS=2:2;REFBIAS=133:39;VARBIAS=1:1;PMEAN=56;PSTD=1;QUAL=36;QSTD=1;SBF=0.40795;ODDRATIO=3.37993;MQ=60;SN=4;HIAF=0.0299;ADJAF=0;SHIFT3=0;MSI=4;MSILEN=3;NM=5.0;HICNT=2;HICOV=67;LSEQ=CGGTTTTAAACCTCCCGTGC;RSEQ=CCGCCGCCGCACCCCCCGTG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=C|missense_variant|MODERATE|PTEN|PTEN|transcript|NM_001304717.5|protein_coding|2/10|c.196G>C|p.Ala66Pro|521/8514|196/1731|66/576||,C|upstream_gene_variant|MODIFIER|KLLN|KLLN|transcript|NM_001126049.2|protein_coding||c.-1659C>G|||||613|	GT:DP:VD:AD:AF:RD:ALD	0/1:179:2:172,2:0.0112:133,39:1,1	chr10-87864146-G-C	60	0.40795	179	172	0.0391061452513966	7	P23	FALSE	PTEN	chr10_87864146	3	1929	Only Human	17	NA	510	Old	General_pop	missense_variant	MODERATE	PTEN	protein_coding	SNV	P23_chr10-87864146-G-C
+P23	chr11	62598522	.	C	T	81	PASS	SAMPLE=P23;TYPE=SNV;DP=740;VD=8;AF=0.0108;BIAS=2:2;REFBIAS=357:375;VARBIAS=3:5;PMEAN=37.8;PSTD=1;QUAL=27;QSTD=1;SBF=0.72588;ODDRATIO=1.58569;MQ=60;SN=1.667;HIAF=0.0129;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=1.8;HICNT=5;HICOV=389;LSEQ=TGGCCCCAGTTGTCCTGTAC;RSEQ=GTATGTGGGTGGCTGGTAAT;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|missense_variant&splice_region_variant|MODERATE|MTA2|MTA2|transcript|NM_004739.4|protein_coding|4/18|c.308G>A|p.Arg103Gln|723/3083|308/2007|103/668||,T|downstream_gene_variant|MODIFIER|EML3|EML3|transcript|XM_006718489.4|protein_coding||c.*3780G>A|||||3696|	GT:DP:VD:AD:AF:RD:ALD	0/1:740:8:732,8:0.0108:357,375:3,5	chr11-62598522-C-T	60	0.72588	740	732	0.0108108108108108	8	P23	FALSE	MTA2	chr11_62598522	3	1929	Only Human	17	NA	510	Old	General_pop	missense_variant&splice_region_variant	MODERATE	MTA2	protein_coding	SNV	P23_chr11-62598522-C-T
+P23	chr17	42216064	.	C	A	83	PASS	SAMPLE=P23;TYPE=SNV;DP=758;VD=8;AF=0.0106;BIAS=2:2;REFBIAS=363:387;VARBIAS=5:3;PMEAN=40.9;PSTD=1;QUAL=27.8;QSTD=1;SBF=0.49427;ODDRATIO=1.77550513120983;MQ=60;SN=3;HIAF=0.0082;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=1;NM=1.9;HICNT=6;HICOV=736;LSEQ=AGTGGCCGTCGCATTGTTGT;RSEQ=CTGGCTGCCATGAACGATCA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|missense_variant|MODERATE|STAT5B|STAT5B|transcript|NM_012448.4|protein_coding|12/19|c.1423G>T|p.Asp475Tyr|1577/5079|1423/2364|475/787||	GT:DP:VD:AD:AF:RD:ALD	0/1:758:8:750,8:0.0106:363,387:5,3	chr17-42216064-C-A	60	0.49427	758	750	0.0105540897097625	8	P23	FALSE	STAT5B	chr17_42216064	3	1929	Only Human	17	NA	510	Old	General_pop	missense_variant	MODERATE	STAT5B	protein_coding	SNV	P23_chr17-42216064-C-A
+P23	chr17	46082511	.	G	T	78	PASS	SAMPLE=P23;TYPE=SNV;DP=589;VD=6;AF=0.0102;BIAS=2:2;REFBIAS=267:314;VARBIAS=2:4;PMEAN=25.2;PSTD=1;QUAL=30.3;QSTD=1;SBF=0.69246;ODDRATIO=1.69916;MQ=60;SN=2;HIAF=0.0071;ADJAF=0;SHIFT3=0;MSI=5;MSILEN=1;NM=2.0;HICNT=4;HICOV=563;LSEQ=ATAAGTCTGTTGTATGCTCT;RSEQ=GGGGAGGTACCTCCCCAAGA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|missense_variant|MODERATE|KANSL1|KANSL1|transcript|NM_001193466.2|protein_coding|4/15|c.1463C>A|p.Pro488Gln|1916/5331|1463/3318|488/1105||	GT:DP:VD:AD:AF:RD:ALD	0/1:589:6:581,6:0.0102:267,314:2,4	chr17-46082511-G-T	60	0.69246	589	581	0.0135823429541596	8	P23	FALSE	KANSL1	chr17_46082511	3	1929	Only Human	17	NA	510	Old	General_pop	missense_variant	MODERATE	KANSL1	protein_coding	SNV	P23_chr17-46082511-G-T
+P23	chr18	44950260	rs774907816	A	G	115	PASS	SAMPLE=P23;TYPE=SNV;DP=858;VD=9;AF=0.0105;BIAS=2:2;REFBIAS=397:452;VARBIAS=7:2;PMEAN=9.7;PSTD=1;QUAL=36.3;QSTD=1;SBF=0.09203;ODDRATIO=3.97930760047752;MQ=60;SN=18;HIAF=0.0106;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=1.4;HICNT=9;HICOV=849;LSEQ=CCCACCCAGCAGCTCTGCTG;RSEQ=GTGCAACGGGCTTCAGCCCT;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=G|missense_variant|MODERATE|SETBP1|SETBP1|transcript|XM_024451149.1|protein_coding|5/7|c.998A>G|p.Glu333Gly|1494/10177|998/4869|333/1622||;FREQ=ALSPAC:0.9997,0.0002595|GnomAD_exomes:1,4.034e-06|TWINSUK:1,0;RS=774907816;dbSNPBuildID=144	GT:DP:VD:AD:AF:RD:ALD	0/1:858:9:849,9:0.0105:397,452:7,2	chr18-44950260-A-G	60	0.09203	858	849	0.0104895104895105	9	P23	FALSE	SETBP1	chr18_44950260	3	1929	Only Human	17	NA	510	Old	General_pop	missense_variant	MODERATE	SETBP1	protein_coding	SNV	P23_chr18-44950260-A-G
+P23	chrX	71125659	rs2092301131	A	G	87	PASS	SAMPLE=P23;TYPE=SNV;DP=412;VD=7;AF=0.017;BIAS=2:2;REFBIAS=156:235;VARBIAS=4:3;PMEAN=34.7;PSTD=1;QUAL=31.3;QSTD=1;SBF=0.44595;ODDRATIO=2.00497233138183;MQ=60;SN=2.5;HIAF=0.0155;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=3.7;HICNT=5;HICOV=323;LSEQ=CCCCCTCATTCCCCCCCTCT;RSEQ=CAGACCAGCTTGCTCCTATT;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=G|splice_region_variant&intron_variant|LOW|MED12|MED12|transcript|NM_005120.3|protein_coding|16/44|c.2372-4A>G||||||;FREQ=dbGaP_PopFreq:1,0;RS=2092301131	GT:DP:VD:AD:AF:RD:ALD	0/1:412:7:391,7:0.017:156,235:4,3	chrX-71125659-A-G	60	0.44595	412	391	0.0509708737864078	21	P23	FALSE	MED12	chrX_71125659	3	1929	Only Human	17	NA	510	Old	General_pop	splice_region_variant&intron_variant	LOW	MED12	protein_coding	SNV	P23_chrX-71125659-A-G
+PZ22	chr11	108335029	rs531980488	C	T	105	PASS	SAMPLE=PZ22;TYPE=SNV;DP=834;VD=9;AF=0.0108;BIAS=2:2;REFBIAS=478:346;VARBIAS=4:5;PMEAN=37.2;PSTD=1;QUAL=33.4;QSTD=1;SBF=0.50424;ODDRATIO=1.72569;MQ=60;SN=18;HIAF=0.0197;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=1.9;HICNT=9;HICOV=457;LSEQ=AGTCATTTAAAGCAGAATTT;RSEQ=GCTTAGCAGGAGGTGTAAAT;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|missense_variant|MODERATE|ATM|ATM|transcript|NM_000051.4|protein_coding|55/63|c.8071C>T|p.Arg2691Cys|8221/12915|8071/9171|2691/3056||,T|intragenic_variant|MODIFIER|C11orf65|C11orf65|gene_variant|C11orf65|||n.108335029G>A||||||;FREQ=1000Genomes:0.9998,.,.,0.0001997|ExAC:0.9999,.,.,0.0001072|GnomAD:0.9999,.,.,0.000107|GnomAD_exomes:0.9999,.,.,0.0001353|GoNL:0.999,.,.,0.001002|PRJEB37584:0.9975,.,.,0.002525|TOPMED:0.9999,.,.,9.445e-05|dbGaP_PopFreq:1,.,.,4.781e-05;RS=531980488;dbSNPBuildID=142	GT:DP:VD:AD:AF:RD:ALD	0/1:834:9:824,9:0.0108:478,346:4,5	chr11-108335029-C-T	60	0.50424	834	824	0.0119904076738609	10	PZ22	FALSE	ATM	chr11_108335029	26	1960	Only Human	95	NA	2850	Young	General_pop	missense_variant	MODERATE	ATM	protein_coding	SNV	PZ22_chr11-108335029-C-T
+PZ22	chr17	31232070	rs777759972	C	T	98	PASS	SAMPLE=PZ22;TYPE=SNV;DP=460;VD=11;AF=0.0239;BIAS=2:2;REFBIAS=156:248;VARBIAS=9:2;PMEAN=17.6;PSTD=1;QUAL=28.6;QSTD=1;SBF=0.00858;ODDRATIO=7.12250712250712;MQ=60;SN=2.667;HIAF=0.0242;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=2.2;HICNT=8;HICOV=330;LSEQ=TTTTTTTTTTTTTTTTTTTT;RSEQ=AGAGATTTGGACCAGGCAAG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|splice_region_variant&intron_variant|LOW|NF1|NF1|transcript|NM_001042492.3|protein_coding|24/57|c.3198-3C>T||||||;FREQ=ExAC:0.9996,.,0.0004148|GnomAD_exomes:0.995,.,0.005024|KOREAN:0.8931,.,0.1069|Siberian:0.5,.,0.5|dbGaP_PopFreq:0.9999,0,0;RS=777759972;dbSNPBuildID=144	GT:DP:VD:AD:AF:RD:ALD	0/1:460:11:404,11:0.0239:156,248:9,2	chr17-31232070-C-T	60	0.00858	460	404	0.121739130434783	56	PZ22	FALSE	NF1	chr17_31232070	26	1960	Only Human	95	NA	2850	Young	General_pop	splice_region_variant&intron_variant	LOW	NF1	protein_coding	SNV	PZ22_chr17-31232070-C-T
+PZ22	chrX	41339028	rs980049998	T	A	81	PASS	SAMPLE=PZ22;TYPE=SNV;DP=554;VD=7;AF=0.0126;BIAS=2:2;REFBIAS=308:239;VARBIAS=4:3;PMEAN=45;PSTD=1;QUAL=29.1;QSTD=1;SBF=1;ODDRATIO=1.03457551366674;MQ=60;SN=14;HIAF=0.0134;ADJAF=0;SHIFT3=0;MSI=7;MSILEN=1;NM=2.0;HICNT=7;HICOV=522;LSEQ=AATTTTATATATATATATAT;RSEQ=TTTTTAGAAGGGCGCTATAT;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|splice_region_variant&intron_variant|LOW|DDX3X|DDX3X|transcript|NM_001356.5|protein_coding|2/16|c.104-8T>A||||||,A|upstream_gene_variant|MODIFIER|LOC105373184|LOC105373184|transcript|XR_001755833.1|pseudogene||n.-4085A>T|||||4085|,A|downstream_gene_variant|MODIFIER|LOC107985678|LOC107985678|transcript|XM_017030007.1|protein_coding||c.*2896T>A|||||1627|;FREQ=GnomAD:1,9.846e-06|TOPMED:1,3.778e-06|dbGaP_PopFreq:1,0;RS=980049998;dbSNPBuildID=150	GT:DP:VD:AD:AF:RD:ALD	0/1:554:7:547,7:0.0126:308,239:4,3	chrX-41339028-T-A	60	1	554	547	0.0126353790613718	7	PZ22	FALSE	DDX3X	chrX_41339028	26	1960	Only Human	95	NA	2850	Young	General_pop	splice_region_variant&intron_variant	LOW	DDX3X	protein_coding	SNV	PZ22_chrX-41339028-T-A
+PZ22	chrX	53396621	rs1556888082	G	T	85	PASS	SAMPLE=PZ22;TYPE=SNV;DP=825;VD=10;AF=0.0121;BIAS=2:2;REFBIAS=286:528;VARBIAS=3:7;PMEAN=13.2;PSTD=1;QUAL=25.8;QSTD=1;SBF=1;ODDRATIO=1.26358;MQ=60;SN=2.333;HIAF=0.0094;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=3.3;HICNT=7;HICOV=746;LSEQ=ATGTGTCTTTGTTCCTCCTG;RSEQ=TCCCAGCAGTGGGAACAGGA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|splice_region_variant&intron_variant|LOW|SMC1A|SMC1A|transcript|NM_006306.4|protein_coding|16/24|c.2563-4C>A||||||;FREQ=GnomAD_exomes:1,5.558e-06|dbGaP_PopFreq:0.9999,0.0001113;RS=1556888082;dbSNPBuildID=152	GT:DP:VD:AD:AF:RD:ALD	0/1:825:10:814,10:0.0121:286,528:3,7	chrX-53396621-G-T	60	1	825	814	0.0133333333333333	11	PZ22	FALSE	SMC1A	chrX_53396621	26	1960	Only Human	95	NA	2850	Young	General_pop	splice_region_variant&intron_variant	LOW	SMC1A	protein_coding	SNV	PZ22_chrX-53396621-G-T
+PZ22	chrX	77681783	.	G	T	90	PASS	SAMPLE=PZ22;TYPE=SNV;DP=978;VD=12;AF=0.0123;BIAS=2:2;REFBIAS=459:507;VARBIAS=3:9;PMEAN=19.7;PSTD=1;QUAL=25.2;QSTD=1;SBF=0.15091;ODDRATIO=2.71329;MQ=60;SN=2;HIAF=0.0089;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=2.6;HICNT=8;HICOV=903;LSEQ=TATCTTCAGAACTTTCCTCA;RSEQ=CATCAGATGATGATGAGCCA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|missense_variant|MODERATE|ATRX|ATRX|transcript|NM_000489.6|protein_coding|9/35|c.3473C>A|p.Ala1158Asp|3688/11165|3473/7479|1158/2492||	GT:DP:VD:AD:AF:RD:ALD	0/1:978:12:966,12:0.0123:459,507:3,9	chrX-77681783-G-T	60	0.15091	978	966	0.0122699386503067	12	PZ22	FALSE	ATRX	chrX_77681783	26	1960	Only Human	95	NA	2850	Young	General_pop	missense_variant	MODERATE	ATRX	protein_coding	SNV	PZ22_chrX-77681783-G-T
+PZ28	chr3	136363457	.	T	C	59	PASS	SAMPLE=PZ28;TYPE=SNV;DP=355;VD=4;AF=0.0113;BIAS=2:2;REFBIAS=150:200;VARBIAS=2:2;PMEAN=53;PSTD=1;QUAL=29.5;QSTD=1;SBF=1;ODDRATIO=1.33221427334372;MQ=60;SN=3;HIAF=0.0087;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=1.5;HICNT=3;HICOV=346;LSEQ=CCTTAATAATATCACCATAG;RSEQ=CATTGTAATACTGTGAGGGA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=C|missense_variant|MODERATE|STAG1|STAG1|transcript|NM_005862.3|protein_coding|26/34|c.2696A>G|p.Asp899Gly|2963/6062|2696/3777|899/1258||	GT:DP:VD:AD:AF:RD:ALD	0/1:355:4:350,4:0.0113:150,200:2,2	chr3-136363457-T-C	60	1	355	350	0.0140845070422535	5	PZ28	FALSE	STAG1	chr3_136363457	2	1975	Only Human	47.8	NA	1434	Young	General_pop	missense_variant	MODERATE	STAG1	protein_coding	SNV	PZ28_chr3-136363457-T-C
+PZ28	chr9	83972932	.	G	A	86	PASS	SAMPLE=PZ28;TYPE=SNV;DP=521;VD=6;AF=0.0115;BIAS=2:2;REFBIAS=244:271;VARBIAS=3:3;PMEAN=40.3;PSTD=1;QUAL=33.5;QSTD=1;SBF=1;ODDRATIO=1.11043251346399;MQ=60;SN=5;HIAF=0.0099;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=1;NM=1.5;HICNT=5;HICOV=505;LSEQ=CAACTCTGTCAGTGGAATGA;RSEQ=GACAGCATTCCTGGAAAAGC;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|missense_variant|MODERATE|HNRNPK|HNRNPK|transcript|NM_002140.5|protein_coding|10/17|c.557C>T|p.Pro186Leu|777/2939|557/1395|186/464||,A|upstream_gene_variant|MODIFIER|MIR7-1|MIR7-1|transcript|NR_029605.1|pseudogene||n.-3075C>T|||||3075|	GT:DP:VD:AD:AF:RD:ALD	0/1:521:6:515,6:0.0115:244,271:3,3	chr9-83972932-G-A	60	1	521	515	0.0115163147792706	6	PZ28	FALSE	HNRNPK	chr9_83972932	2	1975	Only Human	47.8	NA	1434	Young	General_pop	missense_variant	MODERATE	HNRNPK	protein_coding	SNV	PZ28_chr9-83972932-G-A
+PZ28	chr9	136518583	rs555823368	G	A	67	PASS	SAMPLE=PZ28;TYPE=SNV;DP=527;VD=6;AF=0.0114;BIAS=2:2;REFBIAS=329:192;VARBIAS=2:4;PMEAN=32.7;PSTD=1;QUAL=26.2;QSTD=1;SBF=0.20171;ODDRATIO=3.41876;MQ=60;SN=2;HIAF=0.0079;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=2.5;HICNT=4;HICOV=507;LSEQ=GCGCCCACCTGGGCCTCAAG;RSEQ=CACTCACCTGTGCGGCCATG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|splice_region_variant&intron_variant|LOW|NOTCH1|NOTCH1|transcript|NM_017617.5|protein_coding|6/33|c.1099+8C>T||||||,A|downstream_gene_variant|MODIFIER|MIR4673|MIR4673|transcript|NR_039820.1|pseudogene||n.*985C>T|||||985|;FREQ=1000Genomes:0.9998,0.0001997|ExAC:1,2.323e-05|GnomAD_exomes:1,8.313e-06;RS=555823368;dbSNPBuildID=142	GT:DP:VD:AD:AF:RD:ALD	0/1:527:6:521,6:0.0114:329,192:2,4	chr9-136518583-G-A	60	0.20171	527	521	0.0113851992409867	6	PZ28	FALSE	NOTCH1	chr9_136518583	2	1975	Only Human	47.8	NA	1434	Young	General_pop	splice_region_variant&intron_variant	LOW	NOTCH1	protein_coding	SNV	PZ28_chr9-136518583-G-A
+PZ28	chr11	108246996	.	T	G	42	PASS	SAMPLE=PZ28;TYPE=SNV;DP=220;VD=3;AF=0.0136;BIAS=2:2;REFBIAS=137:78;VARBIAS=1:2;PMEAN=28.7;PSTD=1;QUAL=26.7;QSTD=1;SBF=0.55594;ODDRATIO=3.49171;MQ=60;SN=2;HIAF=0.0093;ADJAF=0;SHIFT3=0;MSI=4;MSILEN=1;NM=1.0;HICNT=2;HICOV=214;LSEQ=CAACAAAATGGAGAAGTATT;RSEQ=TATACAACTTATATGATCTG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=G|missense_variant|MODERATE|ATM|ATM|transcript|NM_000051.4|protein_coding|8/63|c.934T>G|p.Leu312Val|1084/12915|934/9171|312/3056||	GT:DP:VD:AD:AF:RD:ALD	0/1:220:3:215,3:0.0136:137,78:1,2	chr11-108246996-T-G	60	0.55594	220	215	0.0227272727272727	5	PZ28	FALSE	ATM	chr11_108246996	2	1975	Only Human	47.8	NA	1434	Young	General_pop	missense_variant	MODERATE	ATM	protein_coding	SNV	PZ28_chr11-108246996-T-G
+PZ28	chr12	111418644	rs1445323886	G	A	47	PASS	SAMPLE=PZ28;TYPE=SNV;DP=225;VD=3;AF=0.0133;BIAS=2:2;REFBIAS=118:102;VARBIAS=1:2;PMEAN=27.7;PSTD=1;QUAL=29.7;QSTD=1;SBF=0.59956;ODDRATIO=2.30527;MQ=60;SN=2;HIAF=0.0145;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=1;NM=2.0;HICNT=2;HICOV=138;LSEQ=CTGCCGCCCCCGGGACCCCC;RSEQ=GAGAGGCTGCTGAGACCCCC;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|missense_variant|MODERATE|SH2B3|SH2B3|transcript|XM_011537719.2|protein_coding|2/9|c.499G>A|p.Gly167Arg|880/5553|499/1851|167/616||;FREQ=GnomAD_exomes:1,2.059e-05|TOPMED:1,3.778e-06|dbGaP_PopFreq:1,0;RS=1445323886;dbSNPBuildID=151	GT:DP:VD:AD:AF:RD:ALD	0/1:225:3:220,3:0.0133:118,102:1,2	chr12-111418644-G-A	60	0.59956	225	220	0.0222222222222222	5	PZ28	FALSE	SH2B3	chr12_111418644	2	1975	Only Human	47.8	NA	1434	Young	General_pop	missense_variant	MODERATE	SH2B3	protein_coding	SNV	PZ28_chr12-111418644-G-A
+PZ28	chr17	31232070	rs777759972	C	T	62	PASS	SAMPLE=PZ28;TYPE=SNV;DP=325;VD=5;AF=0.0154;BIAS=2:0;REFBIAS=162:156;VARBIAS=5:0;PMEAN=18.2;PSTD=1;QUAL=26.8;QSTD=1;SBF=0.06129;ODDRATIO=0;MQ=60;SN=1.5;HIAF=0.0115;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=2.4;HICNT=3;HICOV=261;LSEQ=TTTTTTTTTTTTTTTTTTTT;RSEQ=AGAGATTTGGACCAGGCAAG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|splice_region_variant&intron_variant|LOW|NF1|NF1|transcript|NM_001042492.3|protein_coding|24/57|c.3198-3C>T||||||;FREQ=ExAC:0.9996,.,0.0004148|GnomAD_exomes:0.995,.,0.005024|KOREAN:0.8931,.,0.1069|Siberian:0.5,.,0.5|dbGaP_PopFreq:0.9999,0,0;RS=777759972;dbSNPBuildID=144	GT:DP:VD:AD:AF:RD:ALD	0/1:325:5:318,5:0.0154:162,156:5,0	chr17-31232070-C-T	60	0.06129	325	318	0.0215384615384615	7	PZ28	FALSE	NF1	chr17_31232070	2	1975	Only Human	47.8	NA	1434	Young	General_pop	splice_region_variant&intron_variant	LOW	NF1	protein_coding	SNV	PZ28_chr17-31232070-C-T
+PZ28	chr17	60647884	.	T	C	73	PASS	SAMPLE=PZ28;TYPE=SNV;DP=377;VD=5;AF=0.0133;BIAS=2:2;REFBIAS=250:122;VARBIAS=2:3;PMEAN=31.8;PSTD=1;QUAL=31.6;QSTD=1;SBF=0.33762;ODDRATIO=3.06374;MQ=60;SN=4;HIAF=0.0107;ADJAF=0;SHIFT3=0;MSI=5;MSILEN=1;NM=1.8;HICNT=4;HICOV=374;LSEQ=TCTTGCTTTTTCTGCTCCCT;RSEQ=CCCCCAGGTGATTTGTGGAG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=C|splice_region_variant&intron_variant|LOW|PPM1D|PPM1D|transcript|NM_003620.4|protein_coding|3/5|c.827-8T>C||||||	GT:DP:VD:AD:AF:RD:ALD	0/1:377:5:372,5:0.0133:250,122:2,3	chr17-60647884-T-C	60	0.33762	377	372	0.013262599469496	5	PZ28	FALSE	PPM1D	chr17_60647884	2	1975	Only Human	47.8	NA	1434	Young	General_pop	splice_region_variant&intron_variant	LOW	PPM1D	protein_coding	SNV	PZ28_chr17-60647884-T-C
+PZ28	chr19	33302135	.	C	G	97	PASS	SAMPLE=PZ28;TYPE=SNV;DP=170;VD=7;AF=0.0412;BIAS=2:2;REFBIAS=90:72;VARBIAS=4:3;PMEAN=13.1;PSTD=1;QUAL=34.7;QSTD=1;SBF=1;ODDRATIO=1.06627996246695;MQ=60;SN=6;HIAF=0.0382;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=1;NM=3.4;HICNT=6;HICOV=157;LSEQ=GCCGCCCGTGGGGCCCACGG;RSEQ=CGCCTTGGCCTTCTCCTGCT;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=G|missense_variant|MODERATE|CEBPA|CEBPA|transcript|NM_001287424.2|protein_coding|1/1|c.385G>C|p.Ala129Pro|400/2601|385/1182|129/393||WARNING_TRANSCRIPT_NO_START_CODON,G|upstream_gene_variant|MODIFIER|CEBPA-DT|CEBPA-DT|transcript|NR_026887.2|pseudogene||n.-686C>G|||||686|	GT:DP:VD:AD:AF:RD:ALD	0/1:170:7:162,7:0.0412:90,72:4,3	chr19-33302135-C-G	60	1	170	162	0.0470588235294118	8	PZ28	FALSE	CEBPA	chr19_33302135	2	1975	Only Human	47.8	NA	1434	Young	General_pop	missense_variant	MODERATE	CEBPA	protein_coding	SNV	PZ28_chr19-33302135-C-G
+PZ28	chr20	32359042	rs2048063016	C	T	67	PASS	SAMPLE=PZ28;TYPE=SNV;DP=402;VD=6;AF=0.0149;BIAS=2:2;REFBIAS=288:108;VARBIAS=4:2;PMEAN=29.3;PSTD=1;QUAL=26.3;QSTD=1;SBF=0.66701;ODDRATIO=1.33232;MQ=60;SN=2;HIAF=0.0138;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=2;NM=1.0;HICNT=4;HICOV=289;LSEQ=CCTTTTTCCGCTCGCCCTCG;RSEQ=GCCCCCCCCGCCCCGCGCAG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|missense_variant|MODERATE|ASXL1|ASXL1|transcript|XM_011528648.3|protein_coding|1/13|c.29C>T|p.Ala10Val|44/5980|29/4887|10/1628||;FREQ=GnomAD:1,7.162e-06|TOPMED:1,3.778e-06|dbGaP_PopFreq:1,0;RS=2048063016;dbSNPBuildID=155	GT:DP:VD:AD:AF:RD:ALD	0/1:402:6:396,6:0.0149:288,108:4,2	chr20-32359042-C-T	60	0.66701	402	396	0.0149253731343284	6	PZ28	FALSE	ASXL1	chr20_32359042	2	1975	Only Human	47.8	NA	1434	Young	General_pop	missense_variant	MODERATE	ASXL1	protein_coding	SNV	PZ28_chr20-32359042-C-T
+PZ28	chr21	34880572	rs993436723	C	T	72	PASS	SAMPLE=PZ28;TYPE=SNV;DP=576;VD=6;AF=0.0104;BIAS=2:2;REFBIAS=341:229;VARBIAS=4:2;PMEAN=36;PSTD=1;QUAL=28.2;QSTD=1;SBF=1;ODDRATIO=1.34244405364406;MQ=60;SN=2;HIAF=0.0104;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=1.8;HICNT=4;HICOV=384;LSEQ=CGTACCTCTTCCACTTCGAC;RSEQ=GACAAACCTGAGGTCATTAA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|missense_variant|MODERATE|RUNX1|RUNX1|transcript|NM_001754.5|protein_coding|5/9|c.493G>A|p.Gly165Ser|687/5971|493/1443|165/480||,T|upstream_gene_variant|MODIFIER|LOC112267915|LOC112267915|transcript|XR_002958649.1|pseudogene||n.-148C>T|||||148|;FREQ=GnomAD_exomes:1,3.977e-06|TOPMED:1,3.778e-06|dbGaP_PopFreq:1,0;RS=993436723;dbSNPBuildID=150	GT:DP:VD:AD:AF:RD:ALD	0/1:576:6:570,6:0.0104:341,229:4,2	chr21-34880572-C-T	60	1	576	570	0.0104166666666667	6	PZ28	FALSE	RUNX1	chr21_34880572	2	1975	Only Human	47.8	NA	1434	Young	General_pop	missense_variant	MODERATE	RUNX1	protein_coding	SNV	PZ28_chr21-34880572-C-T
+PZ28	chrX	71132508	.	G	A	85	PASS	SAMPLE=PZ28;TYPE=SNV;DP=566;VD=7;AF=0.0124;BIAS=2:2;REFBIAS=250:309;VARBIAS=4:3;PMEAN=48.4;PSTD=1;QUAL=30.3;QSTD=1;SBF=0.70615;ODDRATIO=1.64652418744031;MQ=60;SN=2.5;HIAF=0.0142;ADJAF=0;SHIFT3=1;MSI=1;MSILEN=1;NM=1.9;HICNT=5;HICOV=351;LSEQ=GCACCTGGGTTCCTCTTCAC;RSEQ=CAAAGAACGTGATCGACAAA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|missense_variant|MODERATE|MED12|MED12|transcript|NM_005120.3|protein_coding|31/45|c.4385G>A|p.Arg1462His|4544/6925|4385/6534|1462/2177||	GT:DP:VD:AD:AF:RD:ALD	0/1:566:7:559,7:0.0124:250,309:4,3	chrX-71132508-G-A	60	0.70615	566	559	0.0123674911660777	7	PZ28	FALSE	MED12	chrX_71132508	2	1975	Only Human	47.8	NA	1434	Young	General_pop	missense_variant	MODERATE	MED12	protein_coding	SNV	PZ28_chrX-71132508-G-A
+PZ28	chrX	71141970	.	C	T	70	PASS	SAMPLE=PZ28;TYPE=SNV;DP=486;VD=5;AF=0.0103;BIAS=2:2;REFBIAS=256:225;VARBIAS=3:2;PMEAN=43.6;PSTD=1;QUAL=30.4;QSTD=1;SBF=1;ODDRATIO=1.31760985572172;MQ=60;SN=4;HIAF=0.0086;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=1;NM=1.2;HICNT=4;HICOV=464;LSEQ=AACAACAGCTCTCTAGTAAG;RSEQ=CTGCCTGCCTTCCCAAGGAG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|splice_region_variant&intron_variant|LOW|MED12|MED12|transcript|NM_005120.3|protein_coding|44/44|c.6490+6C>T||||||,T|upstream_gene_variant|MODIFIER|NLGN3|NLGN3|transcript|NM_181303.2|protein_coding||c.-3195C>T|||||2871|	GT:DP:VD:AD:AF:RD:ALD	0/1:486:5:481,5:0.0103:256,225:3,2	chrX-71141970-C-T	60	1	486	481	0.0102880658436214	5	PZ28	FALSE	MED12	chrX_71141970	2	1975	Only Human	47.8	NA	1434	Young	General_pop	splice_region_variant&intron_variant	LOW	MED12	protein_coding	SNV	PZ28_chrX-71141970-C-T
+PZ28	chrX	124071142	rs766542365	T	A	58	PASS	SAMPLE=PZ28;TYPE=SNV;DP=289;VD=3;AF=0.0104;BIAS=2:2;REFBIAS=185:94;VARBIAS=1:2;PMEAN=53.7;PSTD=1;QUAL=36.7;QSTD=1;SBF=0.268;ODDRATIO=3.91559;MQ=60;SN=6;HIAF=0.0112;ADJAF=0;SHIFT3=0;MSI=3;MSILEN=1;NM=1.3;HICNT=3;HICOV=269;LSEQ=TTTCCTCTTTTTTTTTTTTT;RSEQ=AAATAGGCCTTCACTATTCT;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|splice_region_variant&intron_variant|LOW|STAG2|STAG2|transcript|NM_001042749.2|protein_coding|24/34|c.2359-7T>A||||||;FREQ=ExAC:1,1.204e-05|GnomAD_exomes:1,1.801e-05|TOPMED:1,1.133e-05|dbGaP_PopFreq:1,0;RS=766542365;dbSNPBuildID=144	GT:DP:VD:AD:AF:RD:ALD	0/1:289:3:279,3:0.0104:185,94:1,2	chrX-124071142-T-A	60	0.268	289	279	0.0346020761245675	10	PZ28	FALSE	STAG2	chrX_124071142	2	1975	Only Human	47.8	NA	1434	Young	General_pop	splice_region_variant&intron_variant	LOW	STAG2	protein_coding	SNV	PZ28_chrX-124071142-T-A
+PZ28	chrX	124071143	rs1403218809	A	T	82	PASS	SAMPLE=PZ28;TYPE=SNV;DP=286;VD=5;AF=0.0175;BIAS=2:2;REFBIAS=179:97;VARBIAS=2:3;PMEAN=25.2;PSTD=1;QUAL=35.6;QSTD=1;SBF=0.35141;ODDRATIO=2.75734;MQ=60;SN=10;HIAF=0.0202;ADJAF=0;SHIFT3=4;MSI=3;MSILEN=1;NM=2.0;HICNT=5;HICOV=248;LSEQ=TTCCTCTTTTTTTTTTTTTT;RSEQ=AATAGGCCTTCACTATTCTG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|splice_region_variant&intron_variant|LOW|STAG2|STAG2|transcript|NM_001042749.2|protein_coding|24/34|c.2359-6A>T||||||;FREQ=GnomAD_exomes:0.9998,0.0001593|KOREAN:0.9884,0.01164|dbGaP_PopFreq:0.9957,0.004252;RS=1403218809;dbSNPBuildID=151	GT:DP:VD:AD:AF:RD:ALD	0/1:286:5:276,5:0.0175:179,97:2,3	chrX-124071143-A-T	60	0.35141	286	276	0.034965034965035	10	PZ28	FALSE	STAG2	chrX_124071143	2	1975	Only Human	47.8	NA	1434	Young	General_pop	splice_region_variant&intron_variant	LOW	STAG2	protein_coding	SNV	PZ28_chrX-124071143-A-T
+PZ36	chr13	32770113	rs200255626	T	C	75	PASS	SAMPLE=PZ36;TYPE=SNV;DP=777;VD=8;AF=0.0103;BIAS=2:2;REFBIAS=516:247;VARBIAS=5:3;PMEAN=9.4;PSTD=1;QUAL=25.2;QSTD=1;SBF=0.7187;ODDRATIO=1.25303;MQ=60;SN=1.667;HIAF=0.0087;ADJAF=0;SHIFT3=0;MSI=4;MSILEN=1;NM=2.9;HICNT=5;HICOV=575;LSEQ=ATAAATTGTGATTTTTTTTT;RSEQ=CCCCTAGTCTGAATTGGAGA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=C|splice_region_variant&intron_variant|LOW|PDS5B|PDS5B|transcript|XM_005266298.4|protein_coding|31/34|c.3625-8T>C||||||;FREQ=Estonian:0.9998,0.0002232|ExAC:0.9999,0.0001352|GnomAD:0.9999,8.246e-05|GnomAD_exomes:0.9999,0.0001378|KOREAN:0.9949,0.005133|Korea1K:0.9995,0.0005459|SGDP_PRJ:0.5,0.5|TOPMED:0.9999,0.0001035|dbGaP_PopFreq:0.9999,0.0001231;RS=200255626;dbSNPBuildID=137	GT:DP:VD:AD:AF:RD:ALD	0/1:777:8:763,8:0.0103:516,247:5,3	chr13-32770113-T-C	60	0.7187	777	763	0.018018018018018	14	PZ36	FALSE	PDS5B	chr13_32770113	19	1944	Only Human	22.6	NA	678	Old	General_pop	splice_region_variant&intron_variant	LOW	PDS5B	protein_coding	SNV	PZ36_chr13-32770113-T-C
+PZ36	chrX	53396621	rs1556888082	G	T	100	PASS	SAMPLE=PZ36;TYPE=SNV;DP=969;VD=16;AF=0.0165;BIAS=2:2;REFBIAS=332:620;VARBIAS=5:11;PMEAN=20.7;PSTD=1;QUAL=25.1;QSTD=1;SBF=1;ODDRATIO=1.17785;MQ=60;SN=1.667;HIAF=0.0112;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=2.3;HICNT=10;HICOV=893;LSEQ=ATGTGTCTTTGTTCCTCCTG;RSEQ=TCCCAGCAGTGGGAACAGGA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|splice_region_variant&intron_variant|LOW|SMC1A|SMC1A|transcript|NM_006306.4|protein_coding|16/24|c.2563-4C>A||||||;FREQ=GnomAD_exomes:1,5.558e-06|dbGaP_PopFreq:0.9999,0.0001113;RS=1556888082;dbSNPBuildID=152	GT:DP:VD:AD:AF:RD:ALD	0/1:969:16:952,16:0.0165:332,620:5,11	chrX-53396621-G-T	60	1	969	952	0.0175438596491228	17	PZ36	FALSE	SMC1A	chrX_53396621	19	1944	Only Human	22.6	NA	678	Old	General_pop	splice_region_variant&intron_variant	LOW	SMC1A	protein_coding	SNV	PZ36_chrX-53396621-G-T
+PZ36	chrX	124061769	rs865773819	A	T	82	PASS	SAMPLE=PZ36;TYPE=SNV;DP=406;VD=7;AF=0.0172;BIAS=2:0;REFBIAS=148:235;VARBIAS=7:0;PMEAN=11.9;PSTD=1;QUAL=29.4;QSTD=1;SBF=0.00144;ODDRATIO=0;MQ=60;SN=2.5;HIAF=0.0179;ADJAF=0;SHIFT3=1;MSI=1;MSILEN=1;NM=2.1;HICNT=5;HICOV=279;LSEQ=TTTTTTTTTTTTTTTTTTTT;RSEQ=GCACTAACAGATAGGCAAGA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|splice_acceptor_variant&intron_variant|HIGH|STAG2|STAG2|transcript|NM_001042749.2|protein_coding|16/34|c.1535-2A>T||||||;LOF=(STAG2|STAG2|1|1.00);FREQ=KOREAN:0.9715,.,0.02852|Qatari:0.963,.,0.03704|dbGaP_PopFreq:0.9979,0,0;RS=865773819;dbSNPBuildID=147	GT:DP:VD:AD:AF:RD:ALD	0/1:406:7:383,7:0.0172:148,235:7,0	chrX-124061769-A-T	60	0.00144	406	383	0.0566502463054187	23	PZ36	FALSE	STAG2	chrX_124061769	19	1944	Only Human	22.6	NA	678	Old	General_pop	splice_acceptor_variant&intron_variant	HIGH	STAG2	protein_coding	SNV	PZ36_chrX-124061769-A-T
+PZ36	chrX	124066171	rs1387486095	A	T	76	PASS	SAMPLE=PZ36;TYPE=SNV;DP=569;VD=7;AF=0.0123;BIAS=2:2;REFBIAS=216:308;VARBIAS=5:2;PMEAN=11.1;PSTD=1;QUAL=27.1;QSTD=1;SBF=0.13372;ODDRATIO=3.5564407141333;MQ=59.1;SN=2.5;HIAF=0.0120;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=1.9;HICNT=5;HICOV=417;LSEQ=TTTTTTTTTTTTTTTTTTTT;RSEQ=CAGTGCCCATGACCTTTCAA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|splice_region_variant&intron_variant|LOW|STAG2|STAG2|transcript|NM_001042749.2|protein_coding|21/34|c.2097-4A>T||||||;FREQ=GnomAD_exomes:1,1.337e-05,.|KOREAN:0.9712,.,0.02885|TOMMO:0.9998,.,0.0001569|TOPMED:1,3.778e-06,.|dbGaP_PopFreq:1,0,0;RS=1387486095;dbSNPBuildID=151	GT:DP:VD:AD:AF:RD:ALD	0/1:569:7:524,7:0.0123:216,308:5,2	chrX-124066171-A-T	59.1	0.13372	569	524	0.0790861159929701	45	PZ36	FALSE	STAG2	chrX_124066171	19	1944	Only Human	22.6	NA	678	Old	General_pop	splice_region_variant&intron_variant	LOW	STAG2	protein_coding	SNV	PZ36_chrX-124066171-A-T
+PZ37	chr7	101817559	rs1463171639	C	G	94	PASS	SAMPLE=PZ37;TYPE=SNV;DP=588;VD=12;AF=0.0204;BIAS=2:2;REFBIAS=367:207;VARBIAS=7:5;PMEAN=12.2;PSTD=1;QUAL=26.4;QSTD=1;SBF=0.76434;ODDRATIO=1.26584;MQ=60;SN=3;HIAF=0.0251;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=1;NM=4.4;HICNT=9;HICOV=359;LSEQ=CCACCCCCCGCCCGGAGGAG;RSEQ=GGCGCACCCTTAGGGTCCGC;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=G|missense_variant|MODERATE|CUX1|CUX1|transcript|XM_005250150.3|protein_coding|1/24|c.220C>G|p.Arg74Gly|480/14266|220/4815|74/1604||;FREQ=GnomAD:1,7.146e-06|dbGaP_PopFreq:1,0;RS=1463171639;dbSNPBuildID=151	GT:DP:VD:AD:AF:RD:ALD	0/1:588:12:574,12:0.0204:367,207:7,5	chr7-101817559-C-G	60	0.76434	588	574	0.0238095238095238	14	PZ37	FALSE	CUX1	chr7_101817559	17	1940	Only Human	22	NA	660	Old	General_pop	missense_variant	MODERATE	CUX1	protein_coding	SNV	PZ37_chr7-101817559-C-G
+PZ37	chr7	140924610	rs1325363555	C	T	43	PASS	SAMPLE=PZ37;TYPE=SNV;DP=223;VD=3;AF=0.0135;BIAS=2:2;REFBIAS=91:120;VARBIAS=1:2;PMEAN=28;PSTD=1;QUAL=27.7;QSTD=1;SBF=1;ODDRATIO=1.51383;MQ=60;SN=2;HIAF=0.0299;ADJAF=0;SHIFT3=0;MSI=3;MSILEN=6;NM=2.7;HICNT=2;HICOV=67;LSEQ=AGCCGAAGAGGCCGCGGCGC;RSEQ=GGCGCCGGCGCCGGCCTCGG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|missense_variant|MODERATE|BRAF|BRAF|transcript|NM_001374258.1|protein_coding|1/20|c.94G>A|p.Gly32Ser|320/9807|94/2424|32/807||,T|upstream_gene_variant|MODIFIER|LOC105375536|LOC105375536|transcript|XR_002956519.1|pseudogene||n.-476C>T|||||476|;FREQ=GnomAD:1,7.168e-06|TOPMED:1,3.778e-06|dbGaP_PopFreq:0.9999,7.117e-05;RS=1325363555;dbSNPBuildID=151	GT:DP:VD:AD:AF:RD:ALD	0/1:223:3:211,3:0.0135:91,120:1,2	chr7-140924610-C-T	60	1	223	211	0.0538116591928251	12	PZ37	FALSE	BRAF	chr7_140924610	17	1940	Only Human	22	NA	660	Old	General_pop	missense_variant	MODERATE	BRAF	protein_coding	SNV	PZ37_chr7-140924610-C-T
+PZ37	chr10	87863960	rs1858361928	G	A	63	PASS	SAMPLE=PZ37;TYPE=SNV;DP=402;VD=5;AF=0.0124;BIAS=2:2;REFBIAS=221:174;VARBIAS=4:1;PMEAN=22;PSTD=1;QUAL=27.4;QSTD=1;SBF=0.39143;ODDRATIO=3.14149283739633;MQ=60;SN=4;HIAF=0.0106;ADJAF=0;SHIFT3=2;MSI=7;MSILEN=1;NM=2.8;HICNT=4;HICOV=379;LSEQ=CCTCCCGCTCCTGGAGCGGG;RSEQ=GGGAGAAGCGGCGGCGGCGG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|missense_variant|MODERATE|PTEN|PTEN|transcript|NM_001304717.5|protein_coding|1/10|c.11G>A|p.Gly4Glu|336/8514|11/1731|4/576||,A|upstream_gene_variant|MODIFIER|KLLN|KLLN|transcript|NM_001126049.2|protein_coding||c.-1473C>T|||||427|;FREQ=GnomAD:1,7.172e-06;RS=1858361928;dbSNPBuildID=155	GT:DP:VD:AD:AF:RD:ALD	0/1:402:5:395,5:0.0124:221,174:4,1	chr10-87863960-G-A	60	0.39143	402	395	0.0174129353233831	7	PZ37	FALSE	PTEN	chr10_87863960	17	1940	Only Human	22	NA	660	Old	General_pop	missense_variant	MODERATE	PTEN	protein_coding	SNV	PZ37_chr10-87863960-G-A
+PZ37	chr16	3793408	.	A	C	97	PASS	SAMPLE=PZ37;TYPE=SNV;DP=736;VD=9;AF=0.0122;BIAS=2:2;REFBIAS=490:236;VARBIAS=7:2;PMEAN=13.6;PSTD=1;QUAL=30.7;QSTD=1;SBF=0.72567;ODDRATIO=1.68463611859838;MQ=60;SN=8;HIAF=0.0113;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=1.8;HICNT=8;HICOV=709;LSEQ=TGGCAGGCTTTCCCAGCCTG;RSEQ=CAATGCGTCATGTGATTCAA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=C|missense_variant|MODERATE|CREBBP|CREBBP|transcript|NM_004380.3|protein_coding|4/31|c.1194T>G|p.Cys398Trp|1991/10790|1194/7329|398/2442||	GT:DP:VD:AD:AF:RD:ALD	0/1:736:9:726,9:0.0122:490,236:7,2	chr16-3793408-A-C	60	0.72567	736	726	0.0135869565217391	10	PZ37	FALSE	CREBBP	chr16_3793408	17	1940	Only Human	22	NA	660	Old	General_pop	missense_variant	MODERATE	CREBBP	protein_coding	SNV	PZ37_chr16-3793408-A-C
+PZ37	chr19	33302135	.	C	G	101	PASS	SAMPLE=PZ37;TYPE=SNV;DP=339;VD=10;AF=0.0295;BIAS=2:2;REFBIAS=207:122;VARBIAS=6:4;PMEAN=15;PSTD=1;QUAL=30.6;QSTD=1;SBF=1;ODDRATIO=1.13073;MQ=60;SN=9;HIAF=0.0282;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=1;NM=3.1;HICNT=9;HICOV=319;LSEQ=GCCGCCCGTGGGGCCCACGG;RSEQ=CGCCTTGGCCTTCTCCTGCT;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=G|missense_variant|MODERATE|CEBPA|CEBPA|transcript|NM_001287424.2|protein_coding|1/1|c.385G>C|p.Ala129Pro|400/2601|385/1182|129/393||WARNING_TRANSCRIPT_NO_START_CODON,G|upstream_gene_variant|MODIFIER|CEBPA-DT|CEBPA-DT|transcript|NR_026887.2|pseudogene||n.-686C>G|||||686|	GT:DP:VD:AD:AF:RD:ALD	0/1:339:10:329,10:0.0295:207,122:6,4	chr19-33302135-C-G	60	1	339	329	0.0294985250737463	10	PZ37	FALSE	CEBPA	chr19_33302135	17	1940	Only Human	22	NA	660	Old	General_pop	missense_variant	MODERATE	CEBPA	protein_coding	SNV	PZ37_chr19-33302135-C-G
+PZ37	chr19	33302422	.	T	C	77	PASS	SAMPLE=PZ37;TYPE=SNV;DP=499;VD=6;AF=0.012;BIAS=2:2;REFBIAS=233:258;VARBIAS=3:3;PMEAN=42.3;PSTD=1;QUAL=29.8;QSTD=1;SBF=1;ODDRATIO=1.10706417651031;MQ=60;SN=5;HIAF=0.0120;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=1;NM=4.8;HICNT=5;HICOV=418;LSEQ=CGGCCGACTCCATGGGGGAG;RSEQ=TAGAGTTCTCCCGGCATGGC;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=C|missense_variant|MODERATE|CEBPA|CEBPA|transcript|NM_001287424.2|protein_coding|1/1|c.98A>G|p.Asn33Ser|113/2601|98/1182|33/393||WARNING_TRANSCRIPT_NO_START_CODON,C|upstream_gene_variant|MODIFIER|CEBPA-DT|CEBPA-DT|transcript|NR_026887.2|pseudogene||n.-399T>C|||||399|	GT:DP:VD:AD:AF:RD:ALD	0/1:499:6:491,6:0.012:233,258:3,3	chr19-33302422-T-C	60	1	499	491	0.0160320641282565	8	PZ37	FALSE	CEBPA	chr19_33302422	17	1940	Only Human	22	NA	660	Old	General_pop	missense_variant	MODERATE	CEBPA	protein_coding	SNV	PZ37_chr19-33302422-T-C
+PZ37	chr19	33302425	.	G	A	77	PASS	SAMPLE=PZ37;TYPE=SNV;DP=490;VD=6;AF=0.0122;BIAS=2:2;REFBIAS=230:253;VARBIAS=3:3;PMEAN=41.7;PSTD=1;QUAL=30;QSTD=1;SBF=1;ODDRATIO=1.09978334268149;MQ=60;SN=2;HIAF=0.0086;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=4.8;HICNT=4;HICOV=463;LSEQ=CCGACTCCATGGGGGAGTTA;RSEQ=AGTTCTCCCGGCATGGCGAG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|missense_variant|MODERATE|CEBPA|CEBPA|transcript|NM_001287424.2|protein_coding|1/1|c.95C>T|p.Ser32Phe|110/2601|95/1182|32/393||WARNING_TRANSCRIPT_NO_START_CODON,A|upstream_gene_variant|MODIFIER|CEBPA-DT|CEBPA-DT|transcript|NR_026887.2|pseudogene||n.-396G>A|||||396|	GT:DP:VD:AD:AF:RD:ALD	0/1:490:6:483,6:0.0122:230,253:3,3	chr19-33302425-G-A	60	1	490	483	0.0142857142857143	7	PZ37	FALSE	CEBPA	chr19_33302425	17	1940	Only Human	22	NA	660	Old	General_pop	missense_variant	MODERATE	CEBPA	protein_coding	SNV	PZ37_chr19-33302425-G-A
+PZ37	chr19	33302429	.	T	C	88	PASS	SAMPLE=PZ37;TYPE=SNV;DP=455;VD=7;AF=0.0154;BIAS=2:2;REFBIAS=213:234;VARBIAS=3:4;PMEAN=44.6;PSTD=1;QUAL=31.6;QSTD=1;SBF=1;ODDRATIO=1.21316;MQ=60;SN=14;HIAF=0.0164;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=2;NM=4.4;HICNT=7;HICOV=428;LSEQ=CTCCATGGGGGAGTTAGAGT;RSEQ=CTCCCGGCATGGCGAGCCTC;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=C|missense_variant|MODERATE|CEBPA|CEBPA|transcript|NM_001287424.2|protein_coding|1/1|c.91A>G|p.Asn31Asp|106/2601|91/1182|31/393||WARNING_TRANSCRIPT_NO_START_CODON,C|upstream_gene_variant|MODIFIER|CEBPA-DT|CEBPA-DT|transcript|NR_026887.2|pseudogene||n.-392T>C|||||392|	GT:DP:VD:AD:AF:RD:ALD	0/1:455:7:447,7:0.0154:213,234:3,4	chr19-33302429-T-C	60	1	455	447	0.0175824175824176	8	PZ37	FALSE	CEBPA	chr19_33302429	17	1940	Only Human	22	NA	660	Old	General_pop	missense_variant	MODERATE	CEBPA	protein_coding	SNV	PZ37_chr19-33302429-T-C
+PZ37	chrX	45089879	.	C	T	154	PASS	SAMPLE=PZ37;TYPE=SNV;DP=1588;VD=30;AF=0.0189;BIAS=2:2;REFBIAS=686:870;VARBIAS=14:16;PMEAN=39.8;PSTD=1;QUAL=31.5;QSTD=1;SBF=0.85346;ODDRATIO=1.10961928962173;MQ=60;SN=60;HIAF=0.0197;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=1.3;HICNT=30;HICOV=1520;LSEQ=CAGGCACTGTTCATTGGGTT;RSEQ=AGGCTATTGGCTGGTGCAAC;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|stop_gained|HIGH|KDM6A|KDM6A|transcript|XM_011543958.3|protein_coding|26/31|c.3841C>T|p.Gln1281*|4211/6031|3841/4470|1281/1489||;LOF=(KDM6A|KDM6A|1|1.00);NMD=(KDM6A|KDM6A|1|1.00)	GT:DP:VD:AD:AF:RD:ALD	0/1:1588:30:1556,30:0.0189:686,870:14,16	chrX-45089879-C-T	60	0.85346	1588	1556	0.0201511335012594	32	PZ37	FALSE	KDM6A	chrX_45089879	17	1940	Only Human	22	NA	660	Old	General_pop	stop_gained	HIGH	KDM6A	protein_coding	SNV	PZ37_chrX-45089879-C-T
+PZ37	chrX	53396621	rs1556888082	G	T	117	PASS	SAMPLE=PZ37;TYPE=SNV;DP=1166;VD=18;AF=0.0154;BIAS=2:2;REFBIAS=404:744;VARBIAS=5:13;PMEAN=10.2;PSTD=1;QUAL=28.2;QSTD=1;SBF=0.62375;ODDRATIO=1.41143;MQ=60;SN=3.5;HIAF=0.0130;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=2.1;HICNT=14;HICOV=1081;LSEQ=ATGTGTCTTTGTTCCTCCTG;RSEQ=TCCCAGCAGTGGGAACAGGA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|splice_region_variant&intron_variant|LOW|SMC1A|SMC1A|transcript|NM_006306.4|protein_coding|16/24|c.2563-4C>A||||||;FREQ=GnomAD_exomes:1,5.558e-06|dbGaP_PopFreq:0.9999,0.0001113;RS=1556888082;dbSNPBuildID=152	GT:DP:VD:AD:AF:RD:ALD	0/1:1166:18:1148,18:0.0154:404,744:5,13	chrX-53396621-G-T	60	0.62375	1166	1148	0.0154373927958834	18	PZ37	FALSE	SMC1A	chrX_53396621	17	1940	Only Human	22	NA	660	Old	General_pop	splice_region_variant&intron_variant	LOW	SMC1A	protein_coding	SNV	PZ37_chrX-53396621-G-T
+PZ37	chrX	77681783	.	G	T	114	PASS	SAMPLE=PZ37;TYPE=SNV;DP=1179;VD=23;AF=0.0195;BIAS=2:2;REFBIAS=542:613;VARBIAS=4:19;PMEAN=14.9;PSTD=1;QUAL=25.4;QSTD=1;SBF=0.00521;ODDRATIO=4.19543;MQ=60;SN=2.286;HIAF=0.0148;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=2.1;HICNT=16;HICOV=1079;LSEQ=TATCTTCAGAACTTTCCTCA;RSEQ=CATCAGATGATGATGAGCCA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|missense_variant|MODERATE|ATRX|ATRX|transcript|NM_000489.6|protein_coding|9/35|c.3473C>A|p.Ala1158Asp|3688/11165|3473/7479|1158/2492||	GT:DP:VD:AD:AF:RD:ALD	0/1:1179:23:1155,23:0.0195:542,613:4,19	chrX-77681783-G-T	60	0.00521	1179	1155	0.0203562340966921	24	PZ37	FALSE	ATRX	chrX_77681783	17	1940	Only Human	22	NA	660	Old	General_pop	missense_variant	MODERATE	ATRX	protein_coding	SNV	PZ37_chrX-77681783-G-T
+PZ37	chrX	77682802	.	G	C	116	PASS	SAMPLE=PZ37;TYPE=SNV;DP=1194;VD=13;AF=0.0109;BIAS=2:2;REFBIAS=545:631;VARBIAS=6:7;PMEAN=12.7;PSTD=1;QUAL=31.6;QSTD=1;SBF=1;ODDRATIO=1.00765;MQ=60;SN=26;HIAF=0.0125;ADJAF=0;SHIFT3=3;MSI=1;MSILEN=1;NM=4.2;HICNT=13;HICOV=1043;LSEQ=ATCTCTTTTTCTAATTCTGA;RSEQ=TCATAATTAGAAGACTCAGA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=C|missense_variant|MODERATE|ATRX|ATRX|transcript|NM_000489.6|protein_coding|9/35|c.2454C>G|p.Asp818Glu|2669/11165|2454/7479|818/2492||	GT:DP:VD:AD:AF:RD:ALD	0/1:1194:13:1176,13:0.0109:545,631:6,7	chrX-77682802-G-C	60	1	1194	1176	0.0150753768844221	18	PZ37	FALSE	ATRX	chrX_77682802	17	1940	Only Human	22	NA	660	Old	General_pop	missense_variant	MODERATE	ATRX	protein_coding	SNV	PZ37_chrX-77682802-G-C
+PZ37	chrX	124071142	rs766542365	T	A	87	PASS	SAMPLE=PZ37;TYPE=SNV;DP=892;VD=10;AF=0.0112;BIAS=2:2;REFBIAS=575:301;VARBIAS=7:3;PMEAN=38.1;PSTD=1;QUAL=26.2;QSTD=1;SBF=1;ODDRATIO=1.22115032360484;MQ=60;SN=4;HIAF=0.0097;ADJAF=0;SHIFT3=0;MSI=3;MSILEN=1;NM=1.8;HICNT=8;HICOV=828;LSEQ=TTTCCTCTTTTTTTTTTTTT;RSEQ=AAATAGGCCTTCACTATTCT;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|splice_region_variant&intron_variant|LOW|STAG2|STAG2|transcript|NM_001042749.2|protein_coding|24/34|c.2359-7T>A||||||;FREQ=ExAC:1,1.204e-05|GnomAD_exomes:1,1.801e-05|TOPMED:1,1.133e-05|dbGaP_PopFreq:1,0;RS=766542365;dbSNPBuildID=144	GT:DP:VD:AD:AF:RD:ALD	0/1:892:10:876,10:0.0112:575,301:7,3	chrX-124071142-T-A	60	1	892	876	0.0179372197309417	16	PZ37	FALSE	STAG2	chrX_124071142	17	1940	Only Human	22	NA	660	Old	General_pop	splice_region_variant&intron_variant	LOW	STAG2	protein_coding	SNV	PZ37_chrX-124071142-T-A
+PZ39	chr2	25234406	.	G	T	94	PASS	SAMPLE=PZ39;TYPE=SNV;DP=526;VD=6;AF=0.0114;BIAS=2:2;REFBIAS=210:310;VARBIAS=2:4;PMEAN=31.2;PSTD=1;QUAL=36.7;QSTD=1;SBF=1;ODDRATIO=1.35408;MQ=60;SN=12;HIAF=0.0117;ADJAF=0;SHIFT3=0;MSI=3;MSILEN=1;NM=1.0;HICNT=6;HICOV=513;LSEQ=AGACGTCAGTATAGTGGACT;RSEQ=GGAAACCAAATACCCTGGGG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|missense_variant|MODERATE|DNMT3A|DNMT3A|transcript|NM_022552.5|protein_coding|23/23|c.2612C>A|p.Pro871Gln|2889/9421|2612/2739|871/912||	GT:DP:VD:AD:AF:RD:ALD	0/1:526:6:520,6:0.0114:210,310:2,4	chr2-25234406-G-T	60	1	526	520	0.0114068441064639	6	PZ39	FALSE	DNMT3A	chr2_25234406	4	1953	Only Human	20.4	NA	612	Old	General_pop	missense_variant	MODERATE	DNMT3A	protein_coding	SNV	PZ39_chr2-25234406-G-T
+PZ39	chr2	25243922	.	A	G	182	PASS	SAMPLE=PZ39;TYPE=SNV;DP=837;VD=34;AF=0.0406;BIAS=2:2;REFBIAS=411:391;VARBIAS=16:18;PMEAN=39.1;PSTD=1;QUAL=35.8;QSTD=1;SBF=0.72692;ODDRATIO=1.18231;MQ=60;SN=68;HIAF=0.0414;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=1.2;HICNT=34;HICOV=822;LSEQ=AGCGATTCCATCAAAGAGAG;RSEQ=CAGCACCCGGATGGGCTTCC;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=G|missense_variant|MODERATE|DNMT3A|DNMT3A|transcript|NM_022552.5|protein_coding|16/23|c.1912T>C|p.Ser638Pro|2189/9421|1912/2739|638/912||	GT:DP:VD:AD:AF:RD:ALD	0/1:837:34:802,34:0.0406:411,391:16,18	chr2-25243922-A-G	60	0.72692	837	802	0.041816009557945	35	PZ39	FALSE	DNMT3A	chr2_25243922	4	1953	Only Human	20.4	NA	612	Old	General_pop	missense_variant	MODERATE	DNMT3A	protein_coding	SNV	PZ39_chr2-25243922-A-G
+PZ39	chr3	128487006	rs1392814696	C	T	58	PASS	SAMPLE=PZ39;TYPE=SNV;DP=343;VD=5;AF=0.0146;BIAS=2:2;REFBIAS=122:216;VARBIAS=2:3;PMEAN=25;PSTD=1;QUAL=25;QSTD=1;SBF=1;ODDRATIO=1.17973220079042;MQ=60;SN=1.5;HIAF=0.0250;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=2;NM=1.8;HICNT=3;HICOV=120;LSEQ=CGGCCGGGTGCGCCATCCAG;RSEQ=GCGGCTGCTCGGGCGCCACC;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|missense_variant|MODERATE|GATA2|GATA2|transcript|NM_001145661.2|protein_coding|3/7|c.26G>A|p.Arg9His|461/3470|26/1443|9/480||,T|upstream_gene_variant|MODIFIER|GATA2-AS1|GATA2-AS1|transcript|NR_125398.1|pseudogene||n.-2197C>T|||||2197|;FREQ=TOPMED:1,3.778e-06,.|dbGaP_PopFreq:1,0,0;RS=1392814696;dbSNPBuildID=151	GT:DP:VD:AD:AF:RD:ALD	0/1:343:5:338,5:0.0146:122,216:2,3	chr3-128487006-C-T	60	1	343	338	0.0145772594752187	5	PZ39	FALSE	GATA2	chr3_128487006	4	1953	Only Human	20.4	NA	612	Old	General_pop	missense_variant	MODERATE	GATA2	protein_coding	SNV	PZ39_chr3-128487006-C-T
+PZ39	chr3	136421100	.	A	G	44	PASS	SAMPLE=PZ39;TYPE=SNV;DP=220;VD=3;AF=0.0136;BIAS=2:2;REFBIAS=120:95;VARBIAS=2:1;PMEAN=37.3;PSTD=1;QUAL=28;QSTD=1;SBF=1;ODDRATIO=1.58012830641848;MQ=60;SN=2;HIAF=0.0092;ADJAF=0;SHIFT3=0;MSI=4;MSILEN=1;NM=2.0;HICNT=2;HICOV=217;LSEQ=TAAAATAACGTACTTGTGAA;RSEQ=AGAAGTTAACCGCTTTAATG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=G|missense_variant|MODERATE|STAG1|STAG1|transcript|NM_005862.3|protein_coding|20/34|c.2101T>C|p.Phe701Leu|2368/6062|2101/3777|701/1258||	GT:DP:VD:AD:AF:RD:ALD	0/1:220:3:215,3:0.0136:120,95:2,1	chr3-136421100-A-G	60	1	220	215	0.0227272727272727	5	PZ39	FALSE	STAG1	chr3_136421100	4	1953	Only Human	20.4	NA	612	Old	General_pop	missense_variant	MODERATE	STAG1	protein_coding	SNV	PZ39_chr3-136421100-A-G
+PZ39	chr3	136422412	.	C	A	77	PASS	SAMPLE=PZ39;TYPE=SNV;DP=354;VD=6;AF=0.0169;BIAS=2:2;REFBIAS=232:116;VARBIAS=4:2;PMEAN=15.7;PSTD=1;QUAL=30;QSTD=1;SBF=1;ODDRATIO=1;MQ=60;SN=5;HIAF=0.0149;ADJAF=0;SHIFT3=0;MSI=2;MSILEN=1;NM=2.0;HICNT=5;HICOV=336;LSEQ=ATTAACTTTAGAACAGACCT;RSEQ=TTGCAATAGGTCTTCCACAG;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=A|stop_gained&splice_region_variant|HIGH|STAG1|STAG1|transcript|NM_005862.3|protein_coding|19/34|c.2035G>T|p.Glu679*|2302/6062|2035/3777|679/1258||;LOF=(STAG1|STAG1|1|1.00);NMD=(STAG1|STAG1|1|1.00)	GT:DP:VD:AD:AF:RD:ALD	0/1:354:6:348,6:0.0169:232,116:4,2	chr3-136422412-C-A	60	1	354	348	0.0169491525423729	6	PZ39	FALSE	STAG1	chr3_136422412	4	1953	Only Human	20.4	NA	612	Old	General_pop	stop_gained&splice_region_variant	HIGH	STAG1	protein_coding	SNV	PZ39_chr3-136422412-C-A
+PZ39	chr12	25225623	.	C	G	112	PASS	SAMPLE=PZ39;TYPE=SNV;DP=404;VD=8;AF=0.0198;BIAS=2:2;REFBIAS=254:142;VARBIAS=5:3;PMEAN=49.5;PSTD=1;QUAL=37.5;QSTD=1;SBF=1;ODDRATIO=1.07305;MQ=60;SN=16;HIAF=0.0201;ADJAF=0;SHIFT3=0;MSI=3;MSILEN=1;NM=1.0;HICNT=8;HICOV=398;LSEQ=GTGTTACTTACCTGTCTTGT;RSEQ=TTTGCTGATGTTTCAATAAA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=G|missense_variant|MODERATE|KRAS|KRAS|transcript|NM_001369786.1|protein_coding|4/6|c.441G>C|p.Lys147Asn|618/5417|441/570|147/189||	GT:DP:VD:AD:AF:RD:ALD	0/1:404:8:396,8:0.0198:254,142:5,3	chr12-25225623-C-G	60	1	404	396	0.0198019801980198	8	PZ39	FALSE	KRAS	chr12_25225623	4	1953	Only Human	20.4	NA	612	Old	General_pop	missense_variant	MODERATE	KRAS	protein_coding	SNV	PZ39_chr12-25225623-C-G
+PZ39	chr13	32742726	.	A	G	63	PASS	SAMPLE=PZ39;TYPE=SNV;DP=306;VD=5;AF=0.0163;BIAS=2:2;REFBIAS=113:188;VARBIAS=2:3;PMEAN=22.6;PSTD=1;QUAL=27.4;QSTD=1;SBF=1;ODDRATIO=1.10875808007451;MQ=60;SN=1.5;HIAF=0.0100;ADJAF=0;SHIFT3=1;MSI=2;MSILEN=1;NM=1.4;HICNT=3;HICOV=299;LSEQ=TGACAGAACAGGGGAAAATT;RSEQ=GGTATGCAATTACTATTTCA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=G|missense_variant&splice_region_variant|MODERATE|PDS5B|PDS5B|transcript|XM_005266298.4|protein_coding|23/35|c.2611A>G|p.Ser871Gly|2792/5584|2611/4347|871/1448||	GT:DP:VD:AD:AF:RD:ALD	0/1:306:5:301,5:0.0163:113,188:2,3	chr13-32742726-A-G	60	1	306	301	0.0163398692810458	5	PZ39	FALSE	PDS5B	chr13_32742726	4	1953	Only Human	20.4	NA	612	Old	General_pop	missense_variant&splice_region_variant	MODERATE	PDS5B	protein_coding	SNV	PZ39_chr13-32742726-A-G
+PZ39	chrX	48791143	.	T	C	103	PASS	SAMPLE=PZ39;TYPE=SNV;DP=543;VD=8;AF=0.0147;BIAS=2:2;REFBIAS=306:228;VARBIAS=5:3;PMEAN=8.4;PSTD=1;QUAL=34.6;QSTD=1;SBF=1;ODDRATIO=1.24134164204672;MQ=60;SN=16;HIAF=0.0150;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=1.5;HICNT=8;HICOV=532;LSEQ=GCCTGGGGTCCCTGGGGACC;RSEQ=CAGAGCCCCTCCCCCAGTTT;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=C|missense_variant|MODERATE|GATA1|GATA1|transcript|XM_011543897.2|protein_coding|2/6|c.34T>C|p.Ser12Pro|159/1529|34/1257|12/418||	GT:DP:VD:AD:AF:RD:ALD	0/1:543:8:534,8:0.0147:306,228:5,3	chrX-48791143-T-C	60	1	543	534	0.0165745856353591	9	PZ39	FALSE	GATA1	chrX_48791143	4	1953	Only Human	20.4	NA	612	Old	General_pop	missense_variant	MODERATE	GATA1	protein_coding	SNV	PZ39_chrX-48791143-T-C
+PZ39	chrX	53412930	.	C	T	83	PASS	SAMPLE=PZ39;TYPE=SNV;DP=478;VD=5;AF=0.0105;BIAS=2:2;REFBIAS=265:208;VARBIAS=2:3;PMEAN=47;PSTD=1;QUAL=36;QSTD=1;SBF=0.65872;ODDRATIO=1.90843;MQ=60;SN=10;HIAF=0.0194;ADJAF=0;SHIFT3=0;MSI=1;MSILEN=1;NM=1.0;HICNT=5;HICOV=258;LSEQ=TCTCAATCTGCTGCTGCTCC;RSEQ=GCATCATTTTGCCCAGCTCC;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=T|missense_variant|MODERATE|SMC1A|SMC1A|transcript|NM_006306.4|protein_coding|5/25|c.824G>A|p.Arg275Gln|878/9710|824/3702|275/1233||	GT:DP:VD:AD:AF:RD:ALD	0/1:478:5:473,5:0.0105:265,208:2,3	chrX-53412930-C-T	60	0.65872	478	473	0.0104602510460251	5	PZ39	FALSE	SMC1A	chrX_53412930	4	1953	Only Human	20.4	NA	612	Old	General_pop	missense_variant	MODERATE	SMC1A	protein_coding	SNV	PZ39_chrX-53412930-C-T
+PZ39	chrX	77682802	.	G	C	60	PASS	SAMPLE=PZ39;TYPE=SNV;DP=386;VD=4;AF=0.0104;BIAS=2:2;REFBIAS=187:193;VARBIAS=1:3;PMEAN=14.2;PSTD=1;QUAL=30.2;QSTD=1;SBF=0.62336;ODDRATIO=2.89962;MQ=60;SN=3;HIAF=0.0086;ADJAF=0;SHIFT3=3;MSI=1;MSILEN=1;NM=2.8;HICNT=3;HICOV=349;LSEQ=ATCTCTTTTTCTAATTCTGA;RSEQ=TCATAATTAGAAGACTCAGA;DUPRATE=0;SPLITREAD=0;SPANPAIR=0;ANN=C|missense_variant|MODERATE|ATRX|ATRX|transcript|NM_000489.6|protein_coding|9/35|c.2454C>G|p.Asp818Glu|2669/11165|2454/7479|818/2492||	GT:DP:VD:AD:AF:RD:ALD	0/1:386:4:380,4:0.0104:187,193:1,3	chrX-77682802-G-C	60	0.62336	386	380	0.0155440414507772	6	PZ39	FALSE	ATRX	chrX_77682802	4	1953	Only Human	20.4	NA	612	Old	General_pop	missense_variant	MODERATE	ATRX	protein_coding	SNV	PZ39_chrX-77682802-G-C