#import pandas as pd
### parameters
import pandas as pd
import textwrap
import numpy as np
from collections import defaultdict
import matplotlib.pyplot as plt
mySpecie='Homo_sapiens'
#change base dir to your data location
baseDir='/cellar/users/btsui/Data/SRA/snp/'
skymap_snp_dir=baseDir+'{specie}_snp_pos/'.format(specie=mySpecie)
#7:140753336
VCF bitfield (VP) is detailed in :
https://ftp.ncbi.nlm.nih.gov/snp/specs/dbSNP_BitField_latest.pdf
inVcfDir='/data/cellardata/users/btsui/dbsnp/Homo_sapiens/All_20170710.f1_byte2_not_00.vcf.gz'
vcfDf=pd.read_csv(inVcfDir,sep='\t',header=None)
vcfDf.columns=['Chr','Pos','RsId','RefBase','AltBase','','','Annot']
vcfDf['Chr']=vcfDf['Chr'].astype(np.str)
/cellar/users/btsui/anaconda3/lib/python3.6/site-packages/IPython/core/interactiveshell.py:2785: DtypeWarning: Columns (0) have mixed types. Specify dtype option on import or set low_memory=False. interactivity=interactivity, compiler=compiler, result=result)
vcfDf['VP']=vcfDf['Annot'].str.extract('VP=0x(\w+);')
vcfDf.head()
Chr | Pos | RsId | RefBase | AltBase | Annot | VP | GENEINFO | VP_binary | |||
---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 14727 | rs1045587 | G | A | . | . | RS=1045587;RSPOS=14727;RV;dbSNPBuildID=117;SSR... | 050028040005000002000100 | DDX11L1 | 0000010100000000001010000000010000000000000001... |
1 | 1 | 630825 | rs9783068 | T | C | . | . | RS=9783068;RSPOS=630825;dbSNPBuildID=119;SSR=1... | 050028020005000002000140 | LOC101928626 | 0000010100000000001010000000001000000000000001... |
2 | 1 | 630833 | rs9701099 | C | T | . | . | RS=9701099;RSPOS=630833;dbSNPBuildID=119;SSR=1... | 050028020005000002000140 | LOC101928626 | 0000010100000000001010000000001000000000000001... |
3 | 1 | 817186 | rs3094315 | G | A | . | . | RS=3094315;RSPOS=817186;RV;dbSNPBuildID=103;SS... | 05012802000515053f000101 | FAM87B | 0000010100000001001010000000001000000000000001... |
4 | 1 | 833068 | rs12562034 | G | A | . | . | RS=12562034;RSPOS=833068;dbSNPBuildID=120;SSR=... | 050128080005170537000100 | LINC01128 | 0000010100000001001010000000100000000000000001... |
vcfDf['Annot'].values
array(['RS=1045587;RSPOS=14727;RV;dbSNPBuildID=117;SSR=0;SAO=0;VP=0x050028040005000002000100;GENEINFO=DDX11L1:100287102|WASH7P:653635;WGT=1;VC=SNV;PM;PMC;R3;ASP', 'RS=9783068;RSPOS=630825;dbSNPBuildID=119;SSR=1;SAO=0;VP=0x050028020005000002000140;GENEINFO=LOC101928626:101928626;WGT=1;VC=SNV;PM;PMC;R5;ASP', 'RS=9701099;RSPOS=630833;dbSNPBuildID=119;SSR=1;SAO=0;VP=0x050028020005000002000140;GENEINFO=LOC101928626:101928626;WGT=1;VC=SNV;PM;PMC;R5;ASP', ..., 'RS=41458645;RSPOS=16278;dbSNPBuildID=127;SSR=0;SAO=0;VP=0x050028000005000402000100;WGT=1;VC=SNV;PM;PMC;ASP;HD', 'RS=41378955;RSPOS=16390;dbSNPBuildID=127;SSR=0;SAO=0;VP=0x050028000005000402000100;WGT=1;VC=SNV;PM;PMC;ASP;HD', 'RS=3937033;RSPOS=16519;dbSNPBuildID=108;SSR=0;SAO=0;VP=0x050128020005000502000100;GENEINFO=ND6:4541;WGT=1;VC=SNV;PM;PMC;SLO;R5;ASP;HD;GNO'], dtype=object)
vcfDf['GENEINFO']=vcfDf['Annot'].str.extract('GENEINFO=(\w+)',expand=False).values
#vcfDf.groupby(['GENEINFO']).size().median()
#somatic mutations vs germlime
num_of_byte=12
num_of_bits=num_of_byte*(8)
def toBin(my_hexdata):
Hex=int(my_hexdata,base=16)
return bin( Hex )[2:].zfill(num_of_bits)
dbsnpFlagDf=pd.read_csv('Data/dbsnpFlag.tsv',sep='\t')
#dbsnpFlagDf['Flag']=dbsnpFlagDf['Flag'].str.replace('[A-Z]','')
#dbsnpFlagDf['Flag']=dbsnpFlagDf['Flag'].astype(int)
dbsnpFlagDf_MultI=dbsnpFlagDf.set_index(['byte_left_to_right','bit'])['Link'].sort_index()
vcfDf['VP_binary']=vcfDf['VP'].apply(toBin).values
vcfDf.shape, 18846
((393242, 11), 18846)
vcfDf=vcfDf#[(vcfDf['Chr']=='7')&(vcfDf['Pos']==140753336)]
#12 byte, 24 hex digits
VP_binary_l=vcfDf.VP_binary.apply(lambda S:pd.Series(textwrap.wrap(S,8)))
byteFieldDf=VP_binary_l#.T.unstack().unstack()#.apply(len)
#VP_binary_l
#byte=11
myL=[]
myByteToNameS=pd.Series({1:'resource link properties',
2:'resource link properties',
3:'gene function properties',
4:'gene function properties',
5:'mapping properties',
6:'allele frequency properties',
7:'genotype properties',
8:'Validation by HapMap/TGP properties',
9:'phenotype properties',
10:'variation class',
11:'quality check',
12:'Version encoding',
})
for byte in np.arange(1,12):
tmpVC=byteFieldDf[byte].value_counts()#.head(n=10)
bitVectors=tmpVC.index.values
#dbsnpFlagDf_MultI.loc[byte]
myDict=defaultdict(str)
dbsnpFlagDf_MultI_sub=dbsnpFlagDf_MultI.loc[byte]
for bitVector in bitVectors:
#right to left, the bit vector from NCBI count from right to left, revert the order first
endianCorrectedVect=bitVector[::-1]
for i in range(len(endianCorrectedVect)):
if endianCorrectedVect[i]=='1':
dbSNP_field=dbsnpFlagDf_MultI_sub.loc[i+1]
myDict[bitVector]+=(dbSNP_field+'\n')
#dbsnpFlagDf_MultI.loc[byte].values
bitVectorToFnameS=pd.Series(myDict)
tmpVC2=tmpVC.head(n=10)
tmpS=pd.Series(index=bitVectorToFnameS.loc[tmpVC2.index].values, data=tmpVC2.values)
bitVectorS=pd.Series(index=bitVectorToFnameS.loc[bitVectors],data=bitVectors)
tmpDf=tmpS.to_frame('count')
tmpDf['bitVector']=bitVectorS[:]
myL.append(tmpDf)
/cellar/users/btsui/anaconda3/lib/python3.6/site-packages/ipykernel_launcher.py:39: FutureWarning: Passing list-likes to .loc or [] with any missing label will raise KeyError in the future, you can use .reindex() as an alternative. See the documentation here: https://pandas.pydata.org/pandas-docs/stable/indexing.html#deprecate-loc-reindex-listlike /cellar/users/btsui/anaconda3/lib/python3.6/site-packages/ipykernel_launcher.py:40: FutureWarning: Passing list-likes to .loc or [] with any missing label will raise KeyError in the future, you can use .reindex() as an alternative. See the documentation here: https://pandas.pydata.org/pandas-docs/stable/indexing.html#deprecate-loc-reindex-listlike
#tmpDf.shape
#tmpDf
#byteFieldDf[byte]
keys=np.arange(1,12)#myByteToNameS.loc[np.arange(1,12)].values.tolist()
#len(myL),len(keys)
#keys
mergedCountDf=pd.concat(myL,keys=keys,axis=0)#.dropna()
mergedStatDf=mergedCountDf.reset_index()
#mergedStatDf
mergedStatDf.columns=['Byte_left_to_right','Varation properties','Count','bitVector']
mergedStatDf['Variation_area']=myByteToNameS[mergedStatDf['Byte_left_to_right']].values
mergedStatDf['Varation properties']=mergedStatDf['Varation properties'].fillna('N/A')
#mergedStatDf
countDf=mergedStatDf.set_index(['Variation_area','bitVector','Byte_left_to_right','Varation properties'])[['Count']]
excel=pd.ExcelWriter('./Data/snp.count.xlsx')
countDf.to_excel(excel)
excel.close()
#6, 3
#'100100'
!echo $PWD/./Data/snp.count.xlsx
/cellar/users/btsui/Project/METAMAP/notebook/RapMapTest/XGS_WGS/./Data/snp.count.xlsx
input: bitVectors ouutoutput:
byte=5
tmpVC=byteFieldDf[byte].value_counts()#.head(n=10)
bitVectors=tmpVC.index.values
#dbsnpFlagDf_MultI.loc[byte]
myDict=defaultdict(str)
dbsnpFlagDf_MultI_sub=dbsnpFlagDf_MultI.loc[byte]
for bitVector in bitVectors:
#right to left, the bit vector from NCBI count from right to left, revert the order first
endianCorrectedVect=bitVector[::-1]
for i in range(len(endianCorrectedVect)):
if endianCorrectedVect[i]=='1':
###bit need to have a plus one
dbSNP_field=dbsnpFlagDf_MultI_sub.loc[i+1]
myDict[bitVector]+=(dbSNP_field+'\n')
#dbsnpFlagDf_MultI.loc[byte].values
bitVectorToFnameS=pd.Series(myDict)
#pd.Series(index=bitVectorToFnameS.loc[tmpVC2.index].values, data=tmpVC2.values)
bitVectorToFnameS
00000101 Weight (2 bits). Weight on NCBI reference asse... 00010101 Weight (2 bits). Weight on NCBI reference asse... 00001101 Weight (2 bits). Weight on NCBI reference asse... dtype: object
dbsnpFlagDf_MultI_sub
bit 1 Weight (2 bits). Weight on NCBI reference asse... 2 Weight (2 bits). Weight on NCBI reference asse... 3 Is Assembly specific. This bit is 1 if the snp... 4 Has Assembly conflict. This is for weight 1 an... 5 Has other snp. with exatly the same set of map... Name: Link, dtype: object
fig,ax=plt.subplots(figsize=(10,4))
tmpVC2=tmpVC.head(n=10)
ax=pd.Series(index=bitVectorToFnameS.loc[tmpVC2.index].values,data=tmpVC2.values).plot.bar()
/cellar/users/btsui/anaconda3/lib/python3.6/site-packages/ipykernel_launcher.py:4: FutureWarning: Passing list-likes to .loc or [] with any missing label will raise KeyError in the future, you can use .reindex() as an alternative. See the documentation here: https://pandas.pydata.org/pandas-docs/stable/indexing.html#deprecate-loc-reindex-listlike after removing the cwd from sys.path.
#100100
#why is this both missense and STOP-GAIN?
tmpVC2
00000101 376159 00000000 16748 00010101 170 00001101 165 Name: 5, dtype: int64
#00000101
#allele frequency properties
vcfDf['GENEINFO'].nunique()
0
vcfDf['GENEINFO']
0 NaN 1 NaN 2 NaN 3 NaN 4 NaN 5 NaN 6 NaN 7 NaN 8 NaN 9 NaN 10 NaN 11 NaN 12 NaN 13 NaN 14 NaN 15 NaN 16 NaN 17 NaN 18 NaN 19 NaN 20 NaN 21 NaN 22 NaN 23 NaN 24 NaN 25 NaN 26 NaN 27 NaN 28 NaN 29 NaN ... 393212 NaN 393213 NaN 393214 NaN 393215 NaN 393216 NaN 393217 NaN 393218 NaN 393219 NaN 393220 NaN 393221 NaN 393222 NaN 393223 NaN 393224 NaN 393225 NaN 393226 NaN 393227 NaN 393228 NaN 393229 NaN 393230 NaN 393231 NaN 393232 NaN 393233 NaN 393234 NaN 393235 NaN 393236 NaN 393237 NaN 393238 NaN 393239 NaN 393240 NaN 393241 NaN Name: GENEINFO, Length: 393242, dtype: object
bitVector='00001111'
endianCorrectedVect=bitVector[::-1]
m_binary=(byteFieldDf[byte]==bitVector).values
#vcfDf['GENEINFO'].value_counts()
#bitVectorToFnameS.values
#bitVectorToFnameS.loc[bitVector]
#m=vcfDf['VP_binary'].str.contains('\w+{}00001010'.format(8*3))
#missense,nc transcript variant for the first couple, missense,nc transcript variant
"""
00001010, seem to be all: missense,nc transcript variant
00000011: rs267598747:synonymous codon, synon codon
r vcfDf and
Hypothesis on bug: the mapping is mostlikely off
"""
#
'\n00001010, seem to be all: missense,nc transcript variant\n00000011: rs267598747:synonymous codon, synon codon\n\nr vcfDf and \n\nHypothesis on bug: the mapping is mostlikely off \n'
bitVectorToFnameS.index[0]
'00001010'
bitVectorToFnameS.iloc[0]
'Has reference. A coding region variation where one allele in the set is identical to the reference sequence. FxnCode = 8\nHas non-synonymous missense. A coding region variation where one allele in the set changes protein peptide. FxnClass = 42\n'
"""
byte 4: 00001010
2,4
has one allele:
"""
'\nbyte 4: 00001010\n2,4\n\nhas one allele: \n\n'
vcfDf[m_binary]
Chr | Pos | RsId | RefBase | AltBase | Annot | VP | VP_binary | |||
---|---|---|---|---|---|---|---|---|---|---|
28183 | 1 | 235766122 | rs80338660 | G | A,C,T | . | . | RS=80338660;RSPOS=235766122;RV;dbSNPBuildID=13... | 050168000f05040026110104 | 0000010100000001011010000000000000001111000001... |
30958 | 2 | 1487841 | rs121908082 | C | A,G,T | . | . | RS=121908082;RSPOS=1487841;dbSNPBuildID=132;SS... | 050268080f05040002110100 | 0000010100000010011010000000100000001111000001... |
34025 | 2 | 31386525 | rs119460972 | G | A,C,T | . | . | RS=119460972;RSPOS=31386525;RV;dbSNPBuildID=13... | 050268000f05040002110104 | 0000010100000010011010000000000000001111000001... |
37812 | 2 | 47798725 | rs63749980 | C | A,G,T | . | . | RS=63749980;RSPOS=47798725;dbSNPBuildID=137;SS... | 050060400f05040002100104 | 0000010100000000011000000100000000001111000001... |
38040 | 2 | 47799427 | rs63750909 | C | A,G,T | . | . | RS=63750909;RSPOS=47799427;dbSNPBuildID=137;SS... | 050268000f05000002100104 | 0000010100000010011010000000000000001111000001... |
40404 | 2 | 61839437 | rs202193201 | G | A,C,T | . | . | RS=202193201;RSPOS=61839437;dbSNPBuildID=137;S... | 050068000f05040036110100 | 0000010100000000011010000000000000001111000001... |
64305 | 2 | 233682328 | rs17863778 | C | A,G,T | . | . | RS=17863778;RSPOS=233682328;dbSNPBuildID=126;S... | 050138080f05150036000104 | 0000010100000001001110000000100000001111000001... |
76916 | 3 | 70976982 | rs775136381 | G | A,C,T | . | . | RS=775136381;RSPOS=70976982;dbSNPBuildID=144;S... | 050060000f05040002100104 | 0000010100000000011000000000000000001111000001... |
87284 | 4 | 1004286 | rs121965031 | C | A,G,T | . | . | RS=121965031;RSPOS=1004286;dbSNPBuildID=133;SS... | 050068000f05040002110104 | 0000010100000000011010000000000000001111000001... |
99485 | 4 | 154796798 | rs144494582 | C | A,G,T | . | . | RS=144494582;RSPOS=154796798;dbSNPBuildID=134;... | 050060000f05040002100124 | 0000010100000000011000000000000000001111000001... |
117339 | 5 | 140557175 | rs250426 | G | A,T | . | . | RS=250426;RSPOS=140557175;dbSNPBuildID=79;SSR=... | 050128000f05150537000100 | 0000010100000001001010000000000000001111000001... |
125994 | 6 | 25777954 | rs2328894 | C | T | . | . | RS=2328894;RSPOS=25777954;dbSNPBuildID=100;SSR... | 050128080f05040537000101 | 0000010100000001001010000000100000001111000001... |
127114 | 6 | 29942978 | rs41542015 | C | A,G,T | . | . | RS=41542015;RSPOS=29942978;dbSNPBuildID=137;SS... | 050260000f05000002100104 | 0000010100000010011000000000000000001111000001... |
127230 | 6 | 29943317 | rs41561714 | G | A,C,T | . | . | RS=41561714;RSPOS=29943317;dbSNPBuildID=137;SS... | 050260000f05000002100104 | 0000010100000010011000000000000000001111000001... |
127256 | 6 | 29943344 | rs41556016 | C | A,G,T | . | . | RS=41556016;RSPOS=29943344;dbSNPBuildID=137;SS... | 050260000f05040002100104 | 0000010100000010011000000000000000001111000001... |
127379 | 6 | 29943488 | rs41558913 | C | A,G,T | . | . | RS=41558913;RSPOS=29943488;dbSNPBuildID=137;SS... | 050260000f05000002100104 | 0000010100000010011000000000000000001111000001... |
128772 | 6 | 31271128 | rs281860527 | G | A,C,T | . | . | RS=281860527;RSPOS=31271128;RV;dbSNPBuildID=13... | 050260000f05000002100104 | 0000010100000010011000000000000000001111000001... |
129009 | 6 | 31271647 | rs41549514 | G | A,C,T | . | . | RS=41549514;RSPOS=31271647;RV;dbSNPBuildID=137... | 050260000f05000002100104 | 0000010100000010011000000000000000001111000001... |
129627 | 6 | 31356222 | rs41557820 | G | A,C,T | . | . | RS=41557820;RSPOS=31356222;RV;dbSNPBuildID=137... | 050260020f05040002100104 | 0000010100000010011000000000001000001111000001... |
129891 | 6 | 31356736 | rs41541213 | G | A,C,T | . | . | RS=41541213;RSPOS=31356736;RV;dbSNPBuildID=137... | 050260020f05040002100104 | 0000010100000010011000000000001000001111000001... |
153965 | 7 | 21748602 | rs121908854 | C | A,G,T | . | . | RS=121908854;RSPOS=21748602;dbSNPBuildID=133;S... | 050368000f05040436110104 | 0000010100000011011010000000000000001111000001... |
158813 | 7 | 76515138 | rs1799125 | A | C,T | . | . | RS=1799125;RSPOS=76515138;dbSNPBuildID=89;SSR=... | 050128080f0515053f000140 | 0000010100000001001010000000100000001111000001... |
169544 | 7 | 150950336 | rs189014161 | G | A,C,T | . | . | RS=189014161;RSPOS=150950336;dbSNPBuildID=135;... | 050268000f05040036110104 | 0000010100000010011010000000000000001111000001... |
179309 | 8 | 86668055 | rs267606739 | G | A,C,T | . | . | RS=267606739;RSPOS=86668055;RV;dbSNPBuildID=13... | 050068000f05040026110104 | 0000010100000000011010000000000000001111000001... |
193313 | 9 | 100292976 | rs267607185 | C | A,G,T | . | . | RS=267607185;RSPOS=100292976;dbSNPBuildID=137;... | 050068000f05040026110104 | 0000010100000000011010000000000000001111000001... |
204773 | 10 | 49156232 | rs267602505 | G | A | . | . | RS=267602505;RSPOS=49156232;dbSNPBuildID=137;S... | 0500600c0f05000002100120 | 0000010100000000011000000000110000001111000001... |
207374 | 10 | 70771398 | rs149097055 | G | A,T | . | . | RS=149097055;RSPOS=70771398;dbSNPBuildID=134;S... | 050060840f05040426100120 | 0000010100000000011000001000010000001111000001... |
221031 | 11 | 6394209 | rs771336819 | T | A,C | . | . | RS=771336819;RSPOS=6394209;dbSNPBuildID=144;SS... | 050068000f05000002100100 | 0000010100000000011010000000000000001111000001... |
227459 | 11 | 61397797 | rs11230683 | C | A,G,T | . | . | RS=11230683;RSPOS=61397797;dbSNPBuildID=120;SS... | 050068000f05040436110100 | 0000010100000000011010000000000000001111000001... |
232976 | 11 | 94447276 | rs774277300 | G | A,C,T | . | . | RS=774277300;RSPOS=94447276;dbSNPBuildID=136;S... | 050060000f05040002100100 | 0000010100000000011000000000000000001111000001... |
233099 | 11 | 94467821 | rs371077728 | G | A,C,T | . | . | RS=371077728;RSPOS=94467821;dbSNPBuildID=138;S... | 050260020f05040002100104 | 0000010100000010011000000000001000001111000001... |
254033 | 12 | 100532538 | rs113090017 | C | A,G,T | . | . | RS=113090017;RSPOS=100532538;dbSNPBuildID=132;... | 050128080f05040102000104 | 0000010100000001001010000000100000001111000001... |
259803 | 13 | 23331644 | rs141315518 | G | A,C,T | . | . | RS=141315518;RSPOS=23331644;dbSNPBuildID=134;S... | 050068000f05040036110100 | 0000010100000000011010000000000000001111000001... |
264058 | 13 | 32340280 | rs80358825 | T | A,C,G | . | . | RS=80358825;RSPOS=32340280;dbSNPBuildID=132;SS... | 050168000f05000002100104 | 0000010100000001011010000000000000001111000001... |
285732 | 15 | 40625535 | rs191249840 | C | A,G,T | . | . | RS=191249840;RSPOS=40625535;dbSNPBuildID=135;S... | 050128000f05040036000100 | 0000010100000001001010000000000000001111000001... |
286483 | 15 | 44573661 | rs147713329 | G | A,C,T | . | . | RS=147713329;RSPOS=44573661;dbSNPBuildID=134;S... | 050168080f05000002110104 | 0000010100000001011010000000100000001111000001... |
289049 | 15 | 51404533 | rs368085516 | C | A,G,T | . | . | RS=368085516;RSPOS=51404533;dbSNPBuildID=138;S... | 050028080f05040002000104 | 0000010100000000001010000000100000001111000001... |
293624 | 15 | 89316771 | rs144346886 | G | A,C,T | . | . | RS=144346886;RSPOS=89316771;dbSNPBuildID=134;S... | 050268800f05040026100100 | 0000010100000010011010001000000000001111000001... |
310193 | 16 | 75556198 | rs397514609 | A | G,T | . | . | RS=397514609;RSPOS=75556198;RV;dbSNPBuildID=13... | 050068000f05000002110100 | 0000010100000000011010000000000000001111000001... |
310646 | 16 | 79211721 | rs372635911 | C | A,G,T | . | . | RS=372635911;RSPOS=79211721;dbSNPBuildID=138;S... | 050260800f05040002100100 | 0000010100000010011000001000000000001111000001... |
316473 | 17 | 16940378 | rs72553885 | G | A,C,T | . | . | RS=72553885;RSPOS=16940378;RV;dbSNPBuildID=130... | 050028000f05040402000104 | 0000010100000000001010000000000000001111000001... |
317239 | 17 | 19347840 | rs373478202 | G | A,C,T | . | . | RS=373478202;RSPOS=19347840;dbSNPBuildID=138;S... | 050028000f05040026000100 | 0000010100000000001010000000000000001111000001... |
321820 | 17 | 43045729 | rs397509295 | G | A,C,T | . | . | RS=397509295;RSPOS=43045729;RV;dbSNPBuildID=13... | 050068800f05000002110104 | 0000010100000000011010001000000000001111000001... |
321925 | 17 | 43047687 | rs80357358 | A | G,T | . | . | RS=80357358;RSPOS=43047687;RV;dbSNPBuildID=132... | 050368000f05000002100100 | 0000010100000011011010000000000000001111000001... |
326230 | 17 | 44352087 | rs63751180 | C | A,G,T | . | . | RS=63751180;RSPOS=44352087;dbSNPBuildID=137;SS... | 050160000f05040002100104 | 0000010100000001011000000000000000001111000001... |
328849 | 17 | 58206159 | rs772719574 | G | A,T | . | . | RS=772719574;RSPOS=58206159;dbSNPBuildID=144;S... | 050028800f05040002000100 | 0000010100000000001010001000000000001111000001... |
341491 | 19 | 2853131 | rs267605399 | C | A,G,T | . | . | RS=267605399;RSPOS=2853131;dbSNPBuildID=137;SS... | 050260000f05040002100124 | 0000010100000010011000000000000000001111000001... |
344267 | 19 | 11105425 | rs769318035 | C | A,G,T | . | . | RS=769318035;RSPOS=11105425;dbSNPBuildID=144;S... | 050068080f05000002100104 | 0000010100000000011010000000100000001111000001... |
344478 | 19 | 11107402 | rs146651743 | C | A,G,T | . | . | RS=146651743;RSPOS=11107402;dbSNPBuildID=134;S... | 050268000f05040436100104 | 0000010100000010011010000000000000001111000001... |
344537 | 19 | 11107513 | rs13306512 | C | A,G,T | . | . | RS=13306512;RSPOS=11107513;dbSNPBuildID=121;SS... | 050268000f05040137100104 | 0000010100000010011010000000000000001111000001... |
344614 | 19 | 11110767 | rs13306515 | C | A,G,T | . | . | RS=13306515;RSPOS=11110767;dbSNPBuildID=121;SS... | 050368000f05040536100104 | 0000010100000011011010000000000000001111000001... |
345260 | 19 | 11120470 | rs112954220 | C | A,G,T | . | . | RS=112954220;RSPOS=11120470;dbSNPBuildID=132;S... | 050268080f05040002100104 | 0000010100000010011010000000100000001111000001... |
367901 | 22 | 16807899 | rs142425083 | G | A,C,T | . | . | RS=142425083;RSPOS=16807899;dbSNPBuildID=137;S... | 050060000f05040002100124 | 0000010100000000011000000000000000001111000001... |
373131 | 22 | 42128212 | rs367543000 | G | A,C,T | . | . | RS=367543000;RSPOS=42128212;RV;dbSNPBuildID=13... | 050060020f05040002110104 | 0000010100000000011000000000001000001111000001... |
373880 | 22 | 46356865 | rs779022860 | C | A,T | . | . | RS=779022860;RSPOS=46356865;dbSNPBuildID=144;S... | 050060000f05040002100100 | 0000010100000000011000000000000000001111000001... |
388490 | X | 154350109 | rs782308324 | G | A,C,T | . | . | RS=782308324;RSPOS=154350109;dbSNPBuildID=144;... | 050060000f05040002100104 | 0000010100000000011000000000000000001111000001... |
389190 | X | 154928647 | rs137852439 | G | A,C,T | . | . | RS=137852439;RSPOS=154928647;RV;dbSNPBuildID=1... | 050268000f05000002110104 | 0000010100000010011010000000000000001111000001... |