charge

最经典的分子对结软件

#!/usr/bin/nawk -f

# a script to compute residue composition and total charge on a peptide/protein

BEGIN{
	if (ARGC != 2)
		{
		print "Usage:  charge <pdb_filename>";
		err=1;
		exit
		}
	else
		{
		err=0
		}
}

($3=="CA")		{nres++}
($3=="CA" && $4=="ALA")	{nala++}
($3=="CA" && $4=="ARG")	{narg++}
($3=="CA" && $4=="ASN")	{nasn++}
($3=="CA" && $4=="ASP")	{nasp++}
($3=="CA" && $4=="CYS")	{ncys++}
($3=="CA" && $4=="CYX")	{ncys++}
($3=="CA" && $4=="GLU")	{nglu++}
($3=="CA" && $4=="GLN")	{ngln++}
($3=="CA" && $4=="GLY")	{ngly++}
($3=="CA" && $4=="HIS")	{nhis++}
($3=="CA" && $4=="HIP")	{nhis++}
($3=="CA" && $4=="ILE")	{nile++}
($3=="CA" && $4=="LEU")	{nleu++}
($3=="CA" && $4=="LYS")	{nlys++}
($3=="CA" && $4=="MET")	{nmet++}
($3=="CA" && $4=="PHE")	{nphe++}
($3=="CA" && $4=="PRO")	{npro++}
($3=="CA" && $4=="SER")	{nser++}
($3=="CA" && $4=="THR")	{nthr++}
($3=="CA" && $4=="TRP")	{ntrp++}
($3=="CA" && $4=="TYR")	{ntyr++}
($3=="CA" && $4=="VAL")	{nval++}

END{
	if (err == 0)
		{
		nunk = nres - nala - narg - nasn -nasp - ncys - nglu - ngln -ngly - nhis - nile - nleu - nlys - nmet - nphe - npro - nser - nthr - ntrp - ntyr - nval

		chg = narg + nhis + nlys - nasp - nglu

		print " Residue composition for " FILENAME":"
		printf("%s %20s:%4d\n", " ", "alanine",		nala)
		printf("%s %20s:%4d\n", "+", "arginine",	narg)
		printf("%s %20s:%4d\n", " ", "asparagine",	nasn)
		printf("%s %20s:%4d\n", "-", "aspartate",	nasp)
		printf("%s %20s:%4d\n", " ", "cysteine",	ncys)
		printf("%s %20s:%4d\n", "-", "glutamate",	nglu)
		printf("%s %20s:%4d\n", " ", "glutamine",	ngln)
		printf("%s %20s:%4d\n", " ", "glycine",		ngly)
		printf("%s %20s:%4d\n", "+", "histidine",	nhis)
		printf("%s %20s:%4d\n", " ", "isoleucine",	nile)
		printf("%s %20s:%4d\n", " ", "leucine",		nleu)
		printf("%s %20s:%4d\n", "+", "lysine",		nlys)
		printf("%s %20s:%4d\n", " ", "methionine",	nmet)
		printf("%s %20s:%4d\n", " ", "phenylalanine",	nphe)
		printf("%s %20s:%4d\n", " ", "proline",		npro)
		printf("%s %20s:%4d\n", " ", "serine",		nser)
		printf("%s %20s:%4d\n", " ", "threonine",	nthr)
		printf("%s %20s:%4d\n", " ", "tryptophan",	ntrp)
		printf("%s %20s:%4d\n", " ", "tyrosine",	ntyr)
		printf("%s %20s:%4d\n", " ", "valine",		nval)
		printf("%s %20s:%4d\n", " ", "UNKNOWN",		nunk)
		print "  =========================";
		printf("%s %20s:%4d\n", " ", "TOTAL",		nres);
		print ""
		printf("%s %20s:%4d\n", " ", "Total charge",	chg);
		print ""
		}
}