Shell Programming and Scripting

Transc_ID    DP    Pval.cross
ID=GRMZM2G015073_T01    23.6044288292005    0.0206790394438121
ID=GRMZM2G465579_T01    2.42080832941224    0.566356492613311
ID=GRMZM2G356344_T01    31.0575268969536    0.489032543538082
ID=GRMZM2G044740_T01    8.33858514064342    0.125869127182036
ID=GRMZM2G420436_T01    4.08274762082918    0.0214579269824967
ID=GRMZM2G119852_T01    59.7782287606723    0.0372160593886689
ID=AC166636.1_FGT010    1.18004103601881    0.0180008630009030
ID=GRMZM2G100242_T02    61.4167813736184    0.0142003131557532
ID=GRMZM2G180458_T01    19.7051930517752    0.0643166007561127

CHR    START    END    Transc_ID    READ_COUNT    BASES_COV
    
chr1      268430147      268436813      ID=GRMZM2G015073_T01      362      4027
chr1      16776238      16779559      ID=GRMZM2G445588_T01      0      0
chr1      92273742      92275613      ID=GRMZM2G465579_T01      11      251
chr1      109050562      109054042      ID=GRMZM2G356344_T01      85      123
chr1      243260011      243280610      ID=GRMZM2G044740_T01      77      1480
chr1      260039640      260047849      ID=GRMZM2G420436_T01      13      1447
chr1      15724186      15728999      ID=GRMZM2G119852_T01      1032      1906
chr1      19922021      19924137      ID=AC166636.1_FGT010      3      89

awk 'NR==FNR{a[$4]=$5;next} a[$1] { print $0,"\t",a[$1]}' Gene_Count.txt Gene_Pval.txt

awk 'NR==FNR{a[$4]=$5;next}$1 in a{print $0" "a[$1]}' freq.txt Pval.txt

awk 'NR==FNR{a[$4]=$5}a[$1]{print $0"\t"a[$1]}' Gene_Count.txt Gene_Pval.txt

 #!/usr/bin/env ruby -w
gc=File.read("genecount").scan(/(ID=.[^ \t]*)[[:space:]]*(\d+)/).flatten!
h = Hash[*gc]
File.readlines("genepval").each do |line|
print "{line.chomp} #{h[line.split[0]]}\n" if line =~ /^ID=/
end