Shell Programming and Scripting

Match:
chr15    68521889    C    T    exonic    CLN6    GOOD    50    het    4
chr7    147183143    A    G    intronic    CNTNAP2    GOOD    382    het    22
Missing in Reference but found in IDP:
chr2    51666313    T    C    intergenic    NRXN1,NONE    GOOD    108    het    7
chr2    166903445    T    C    exonic    SCN1A    GOOD    400    het    28
Missing in IDP but found in Reference:
2    166210776    C    T    exonic    SCN2A    c.[2994C>T]+[=]    3095    23.1    24.56
7    148106478    -    GT    intronic    CNTNAP2    c.3716-5_3716-4insGT    4168    28.6    51.01

chr2    50573818    50574097    NRXN1
chr7    148106400    148106550    CNTNAP2

Match:
chr15    68521889    C    T    exonic    CLN6    GOOD    50    het    4
chr7    147183143    A    G    intronic    CNTNAP2    GOOD    382    het    22
Missing in Reference but found in IDP:
chr2    51666313    T    C    intergenic    NRXN1,NONE    GOOD    108    het    7
chr2    166903445    T    C    exonic    SCN1A    GOOD    400    het    28
Missing in IDP but found in Reference:
2    166210776    C    T    exonic    SCN2A    c.[2994C>T]+[=]    3095    23.1    24.56
7    148106478    -    GT    intronic    CNTNAP2    c.3716-5_3716-4insGT    4168    28.6    51.01     low

awk -F'\t' -v OFS='\t' '
NR==FNR{ range[$1,$2]; next }
FNR==1
{
 for(x in range) {
 split(x, check, SUBSEP);
 if($1==check[1] && $2>=check[2] && $2<=check[3]) print "low"
 }
}
' file1 file2

awk 'FNR==NR{if($0 ~ /^[[:digit:]]/ || $0 ~ /^chr/){gsub(/[[:alpha:]]/,X,$1)};A[$1]=$2;B[$1]=$0;next} {gsub(/[[:alpha:]]/,X,$1)} ($1 in A){if((A[$1]>=$2 && A[$1]<=$3) || (A[$1]<=$2 && A[$1]>=$2)){print $0 FS "low";next}} END{for(i in A){print B[i]}} '  Input_file1  Input_file2

7 148106400 148106550 CNTNAP2 low
Missing in IDP but found in Reference:
7    148106478    -    GT    intronic    CNTNAP2    c.3716-5_3716-4insGT    4168    28.6    51.01
Match:
2    166210776    C    T    exonic    SCN2A    c.[2994C>T]+[=]    3095    23.1    24.56
15 68521889 C T exonic CLN6 GOOD 50 het 4

section 1 is Match:
section 2 is Missing in Reference but found in IDP:
section 3 is Missing in IDP but found in Reference:

#!/bin/ksh
TmpFile=${0##*/}.$$
awk '
BEGIN {	# Set input and output field separators...
	FS = OFS = "\t"
}
NR == FNR {
	# Grab low and high ends of ranges from the 1st input file...
	low[++c] = $2
	high[c] = $3
	next
}
sect == 3 {
	# We are in the 3rd section of the 2nd input file (after the section
	# header line)...
	# Look for a range of vaues from a line in the 1st file that includes
	# the 2nd field in this file...
	for(i = 1; i <= c; i++)
		if(low[i] <= $2 && $2 <= high[i]) {
			# Match found, add field and break out of loop.
			$(NF + 1) = "low"
			break
		}
}
/:$/ {	# Increment the 2nd input file section number when we find a colon at
	# the end of a line...
	sect++
}
1	# print the current contents of the 2nd file input line.
' file2 file1 > "$TmpFile" &&	# End awk script, specifying input files and
				# redirect the output to a temp file...
    cp "$TmpFile" file1 && 	# If the awk script was successful, copy the
    				# temp file back to the 2nd input file...
    rm "$TmpFile"		# and, if that was also successful, remove the
    				# temp file.