Shell Programming and Scripting

ACTGCCCTG
ACCGGCTCC
ACAAATTTC
ACCCGGGTT

ACTGC
ACCGG
ACAAA
ACCCG

man awk

awk '
        BEGIN {
                A["CT"]
                A["TT"]
                min = 9
        }
        {
                S[++c] = $0
                for ( k in A )
                {
                        if ( $0 ~ k )
                                n = split ( $0, V, k )
                }
                if ( n > 2 )
                {
                        for ( i = 1; i <= ( n - 1 ); i++ )
                                L += length(V[i])
                        L += 2
                }
                if ( n == 2 )
                {
                        L = length (V[1])
                }
                printf "String: %s Characters Before: %d\n", $0, L
                min = ( min > L ) ? L : min
                L = 0
        }
        END {
                print "--------------------------------------"
                for ( i = 1; i <= c; i++ )
                        print substr(S[i], 1, min)
        }
' file

String: ACTGCCCTG Characters Before: 6
String: ACCGGCTCC Characters Before: 5
String: ACAAATTTC Characters Before: 5
String: ACCCGGGTT Characters Before: 7
--------------------------------------
ACTGC
ACCGG
ACAAA
ACCCG

awk -vNEED=CT,TT '
BEGIN{split(NEED,N,",");min=999}
FNR==NR {
  for (need in N) {
    pos=index(substr($0,3),N[need])
    if (pos && pos < min) min=pos
  }
  next
}
{ print substr($0,0,min+1) }' infile infile