#! /usr/bin/python

import SeqIO, Seq, random, sys, re

_usage="""
USAGE:  siRNA.py  fastafile

Reads in a fasta format sequence,  identifies all AAN(19)TT and 
AAN(21) motifs, and outputs a table with the motif positions
and GC-content.

$Id: siRNA.py,v 1.1.1.1 2003/03/03 15:46:33 wresch Exp $"""

def main():
	if len(sys.argv) != 2:
		print _usage
	
	#read sequence in fasta format
	seqs = SeqIO.readFasta(filename=sys.argv[1], degap=1, output='list')		
	#strict rule
	strictDEF = r"AA.{19,19}TT"
	strictREO = re.compile(strictDEF, re.I)
	#more relaxed
	relaxedDEF = r"AA.{19,19}.."
	relaxedREO = re.compile(relaxedDEF, re.I)
	
	#find targets for all sequeces
	for seq in seqs:
		outputMatches(strictREO, "STRICT MATCHES", seq.getSeq())
		outputMatches(relaxedREO, "RELAXED MATCHES", seq.getSeq())
		
			
def outputMatches(reo, comment, seq):
	complementDict = {"G":"C","C":"G","A":"T","T":"A"}
	targetIter = reo.finditer(seq.upper())
	print 70*"-","\n", comment, "\n%4s %10s %10s %27s %11s" % ("#","from","to","structure","%GC[1-21]")
	print 70*"-"
	counter=0
	for target in targetIter:
			compDict = {"A":0, "G":0, "T":0,"C":0}
			complement = ""
			for nt in target.group()[0:21]:
				compDict[nt] += 1
				complement += complementDict[nt]
			gc = (compDict["G"]+compDict["C"])/21.0*100.0
			counter += 1
			print "%4i %10i %10i  5'P--%-24s %8.1f" % (counter, target.start(), target.end(), target.group()[2:], gc)
			print "%4s %10s %10s  %24s--P-5'" % ("","","",complement)
	
	
main()