def main(fastafile, predfile, actualfile):
readfasta = True
#Load each gff
nucstats, exonstats, genestats = zeros(4), zeros(4), zeros(4)
exonclassified = {'ME':0, 'WE':0, 'PE':0, 'CE':0}
splicestats = {}
predicted = Features(predfile, 'exon')
actual = Features(actualfile)
syncReferences(actual, predicted)
#Nucleotide stats
if readfasta == True:
try:
fastaseqs = fasta.loadMfa(fastafile)
except StandardError:
print "Failed to load fasta sequence."
sys.exit(2)
for (head,seq) in fastaseqs:
header = head.split(':')
#print header, head, head in actual
if header[0] in actual: title = header[0]
if head in actual: title = head
startref = string.atoi(header[1])
endref = startref + len(seq) - 1
#verifyFasta(head,seq,predlist)
if title in actual:
actualnuc = exonString(actual[title], startref, endref)
predictednuc = exonString(predicted[title], startref, endref)
stats = computeNucStats(actualnuc, predictednuc)
nucstats += stats
else:
print 'Sequence from ', title, ' has no actual gene annotation. Skipping.'
#Exon, gene stats
for ref in actual:
computeSpliceStats(actual, predicted, ref, splicestats)
classifyExonStats(actual, predicted, ref, exonclassified)
exonstats += computeExonStats(actual, predicted, ref)
genestats += computeGeneStats(actual, predicted, ref)
return (nucstats, exonstats, genestats, exonclassified)
sys.exit(0)
if o in("-f", "--fasta"):
if len(a):
fastafile = a
readfasta = True
#Load each gff
nucstats, exonstats, genestats = zeros(4), zeros(4), zeros(4)
exonclassified = {'ME':0, 'WE':0, 'PE':0, 'CE':0}
splicestats = {}
predicted = Features(args[0], 'exon')
actual = Features(args[1])
syncReferences(actual, predicted)
#Nucleotide stats
if readfasta == True:
try:
fastaseqs = fasta.loadMfa(fastafile)
except StandardError:
print "Failed to load fasta sequence."
sys.exit(2)
for (head,seq) in fastaseqs:
header = head.split(':')
#print header, head, head in actual
if header[0] in actual: title = header[0]
if head in actual: title = head
startref = string.atoi(header[1])
endref = startref + len(seq) - 1
#verifyFasta(head,seq,predlist)
if title in actual:
actualnuc = exonString(actual[title], startref, endref)
predictednuc = exonString(predicted[title], startref, endref)
stats = computeNucStats(actualnuc, predictednuc)
#!/usr/bin/env python
"""viewallgff.py <fasta_file> <gff_file>
Script to output sequences, combined into one gene, from a list of gff features
"""
import fasta, sys
from common.feature import *
from common.sequence import *
if len(sys.argv) != 3:
print __doc__
sys.exit(0)
genes = Features(sys.argv[2])
fastaseqs = fasta.loadMfa(sys.argv[1])
flank = 0
for (head,seq) in fastaseqs:
header = head.split(':')
startref = int(header[1])
if head in genes: ref = head; print ref
else: ref = header[0]
if ref in genes:
for name in genes[ref]:
gene = genes[ref][name]
print '>' + name
codingsequence = ''
coords= gene.coords[:]
if gene.strand == '-':
coords.reverse()