Shell Programming and Scripting

 
AGRN 
CCDC39  
CCDC40  
CFTR

 
chr1    955543  955763  chr1:955543-955763 AGRN-6|gc=75    1   0 
chr1    955543  955763  chr1:955543-955763 AGRN-6|gc=75    2   2 
chr1    955543  955763  chr1:955543-955763 AGRN-6|gc=75    3   2

chr1:955543-955763 AGRN|gc=75 3 bases with an average of 0.7

  awk '
 NR == FNR {input[$0]; next}
 {
    split($5, a, "-")
    if (a[1] in input) {
         key = $4 OFS $5
         n[key]++
         sum[key] += $7
     }
 }
 END {
     for (key in n) 
         printf "%s %.1f\n", key, sum[key]/n[key]
 }
' search.txt input.txt > output.txt

BEGIN { 
    slen = 0; 
} 
 
# get input file(s) 
ARGIND > 1 { 
    ###printf("input_push: DEBUG %s\n",$0); 
    input[$0]; 
    next; 
} 
 
# get single search list 
{ 
    ###printf("search_push: DEBUG %s\n",$0); 
    search[slen++] = $0; 
    next; 
} 
 
END { 
    # sum up data 
    for (sidx = 0;  sidx < slen;  ++sidx) { 
        sval = search[sidx]; 
        ###printf("search_end: DEBUG %s\n",sval); 
 
        split(sval,sary) 
        split(sary[5],a,"-"); 
        ###printf("search_end: DEBUG sary[5]='%s' a[1]='%s'\n",sary[5],a[1]); 
 
        if (a[1] in input) { 
            key = sary[4] OFS sary[5] 
            n[key]++ 
            sum[key] = sary[7] 
        } 
    } 
 
    for (key in n) 
        printf "%s %.1f\n", key, sum[key]/n[key] 
}

awk '
 NR == FNR {input[$0]; next}
 {
    split($5, a, "-")
    if (a[1] in input) {
         key = $4 OFS $5
         n[key]++
         sum[key] += $7
     }
 }
 END {
     for (key in n) 
         printf "%s %.1f\n", key, sum[key]/n[key]
 }
' input.txt search.txt > output.txt

chr1:955543 AGRN-6|gc=75 1.3

awk '
 NR == FNR {input[$1]; next}
 {
    split($5, a, "-")
    if (a[1] in input) {
         key = $4 OFS $5
         n[key]++
         sum[key] += $7
         six[key]  = $6
     }
 }
 END {
     for (key in n)
         printf "%s %s bases with an average of %.1f\n", key, six[key], sum[key]/n[key]
 }
' file2 file1
chr1:955543-955763 AGRN-6|gc=75 3 bases with an average of 1.3