Shell Programming and Scripting

PTPN11	5781	13324	28363	genomic	na	LRG_614:g.36663G>T	g.36663G>T	-	-	Yes	No	No
PTPN11	5781	13324	28363	coding	na	LRG_614t1:c.214G>T	c.214G>T	LRG_614p1:p.Ala72Ser	p.Ala72Ser	Yes	No	No
PTPN11	5781	13324	28363	coding	na	NM_002834.4:c.214G>T	c.214G>T	NP_002825.3:p.Ala72Ser	p.Ala72Ser	Yes	No	Yes
PTPN11	5781	13324	28363	coding	na	NM_080601.2:c.214G>T	c.214G>T	NP_542168.1:p.Ala72Ser	p.Ala72Ser	No	No	No

BEGIN { FS="[\t:]" }
{
    cnt[$1][$7]++
    max[$1] = (max[$1] > cnt[$1][$7] ? max[$1] : cnt[$1][$7])
}
END {
    for (word in cnt) {
        for (val in cnt[word]) {
            if (cnt[word][val] == max[word]) {
                print word, val
            }
        }
    }
}

PTPN11 LRG_614t1
PTPN11 LRG_614
PTPN11 NM_080601.2
PTPN11 NM_002834.4

file filename