plink 格式中提取包含杂合位点的SNP位点

 

001、

(base) [b20223040323@admin2 test5]$ ls                ## 测试数据
outcome.map  outcome.ped
(base) [b20223040323@admin2 test5]$ cat outcome.ped
DOR     1       0       0       0       -9      G G     C C     G G     G G     A G     0 0
DOR     2       0       0       0       -9      C C     G G     G G     G G     G G     A A
DOR     3       0       0       0       -9      G G     C C     G G     G G     G G     G A
DOR     4       0       0       0       -9      C G     C C     G G     G G     G G     0 0
DOR     5       0       0       0       -9      G G     C C     G G     G G     G G     A A
DOR     6       0       0       0       -9      G G     C C     G G     G G     G G     A A
DOR     7       0       0       0       -9      G G     C C     G G     G G     A A     A A
DOR     9       0       0       0       -9      G G     G G     G G     G G     A A     A A
(base) [b20223040323@admin2 test5]$ plink --file outcome --recode A --out outcome &> /dev/null       ## 转换格式，minor allele 为0， major alles 为2， het为1
(base) [b20223040323@admin2 test5]$ ls
outcome.log  outcome.map  outcome.nosex  outcome.ped  outcome.raw
(base) [b20223040323@admin2 test5]$ cat outcome.raw
FID IID PAT MAT SEX PHENOTYPE snp1_C snp2_G snp3_0 snp4_0 snp5_A snp6_G
DOR 1 0 0 0 -9 0 0 0 0 1 NA
DOR 2 0 0 0 -9 2 2 0 0 0 0
DOR 3 0 0 0 -9 0 0 0 0 0 1
DOR 4 0 0 0 -9 1 0 0 0 0 NA
DOR 5 0 0 0 -9 0 0 0 0 0 0
DOR 6 0 0 0 -9 0 0 0 0 0 0
DOR 7 0 0 0 -9 0 0 0 0 2 0
DOR 9 0 0 0 -9 0 2 0 0 2 0          ## 利用awk命令进行统计
(base) [b20223040323@admin2 test5]$ awk 'NR == 1 {for(i = 7; i <= NF; i++) {ay1[i] = $i}; next}{for(j = 7; j <= NF; j++){if($j == 1) {ay2[ay1[j]]}}} END {for(k in ay2) {print k}}' outcome.raw
snp6_G
snp5_A
snp1_C
(base) [b20223040323@admin2 test5]$ awk 'NR == 1 {for(i = 7; i <= NF; i++) {ay1[i] = $i}; next}{for(j = 7; j <= NF; j++){if($j == 1) {ay2[ay1[j]]}}} END {for(k in ay2) {print k}}' outcome.raw | while read i; do echo ${i%_*}; done
snp6
snp5
snp1

 

 。