UNIX for Dummies Questions & Answers

 -o, --only-matching
              Print only the matched (non-empty) parts of a matching line, with each such part on a separate output line.

#! /bin/bash

while read x
do
    while read f1
    do
        echo $x | grep -q -w $f1
        if [ $? -eq 0 ]
        then
            y=`echo "$x" | sed "s/\(.*\)\t.*$f1.*/\1\t$f1/"`
            while read f2
            do
                echo "$x" | grep -q -w $f2
                if [ $? -eq 0 ]
                then
                    echo -e "$y\t$f2" >> output.tab
                    break
                fi
            done < file2.tab
            break
        fi
    done < file1.tab
done < bigdb.tab

NR==FNR {
split($3,a,","); for (i in a) vl[a[i]] = $1 FS $2 FS vl[a[i]]
}
NR!=FNR {
idx=$1
OFS="\t"
if ( idx in vl ) {
	final[vl[idx]] = final[vl[idx]] OFS idx
	}
}
END {
	for ( z in final )
	print z FS final[z]
}

awk -f program.awk bigdb.tab file1.tab file2.tab

db1   0001   A_ent,B_ent,C_ent,D_ent   C_ent

db1	12665591	LFTY2_ent,SNF5_ent,SMRC1_ent,ACL6A_ent,SMRD1_ent,SMRC2_ent,ARI1A_ent,ARI1B_ent,SMRD2_ent,ENL_ent
db2,db3,db1,db4,db5,db6	7682714,16094384,15570572,16713569,15144186,10066823,9183008	LYN_ent,HCLS1_ent
db7	68465376,76987269,3877	AKT1_ent,AKT2_ent,AKT3_ent,ARAF_ent,ARNT2_ent,ARNT_ent,BRAF_ent,CBP_ent,CDC42_ent,CRKL_ent,CRK_ent,CUL2_ent,EGLN1_ent

ACL6A_ent
BRAF_ent
YYYP_ent
UYTR_ent

SMRD2_ent
HCLS1_ent
ETS1_ent
CUL2_ent

db1	12665591	ACL6A_ent	SMRD2_ent
db7	68465376,76987269,3877	BRAF_ent	CUL2_ent