Shell Programming and Scripting

$ awk -f code.awk test.txt >output.txt

$ awk code.awk test.txt >output.txt

#!/usr/bin/awk -f

BEGIN { FS="\t" }
NR==1 {next}    # skip header

# keep list of unique genes, in order
!($1 in genes_uniq) { genes_uniq[$1]; genes[gene_idx++]=$1; }

{
        # unquote
        gsub(/(^"|"$)/,"",$2)
        split($2, cols, /,/)
        for (col in cols) {
                if (cols[col] > max_col) max_col=cols[col]
                matrix[$1,cols[col]] = matrix[$1,cols[col]] "," $3
        }
}

END {
        # print header
        printf("gene\t")
        for (col = 1; col <= max_col; col++)
                printf("%d%c", col, (col==max_col)?"\n":"\t");

        for (i = 0; i < gene_idx; i++) {
                printf("%s\t", genes[i]);
                for (col = 1; col <= max_col; col++)
                        printf("%s%c", substr(matrix[genes[i],col],2),
                                (col==max_col)?"\n":"\t");
        }
}

 gene 1 2 3 4 5
a     @
 
b       #
 
c         @
      @
 
d             %
,*

{sub(/\r$/,"")}

gene sample identifier
C10orf107 NJATRTSP228B,ATRTSP228,ATRT34 pL132F
C10orf11 ATRT5B,ATRT5 
C10orf111 ATRT2B,ATRT2,ATRT4B,ATRT4,ATRT16B,ATRT16 pR62W
C10orf113 ATRT15B,ATRT15 
C10orf113 ATRT63 pA312T
C10orf12 ATRT33 pL314P
C10orf12 ATRT63 pE396G
C10orf12 ATRT45B,ATRT45 pP988A
C10orf12 ATRT46B,ATRT46 pR191C