def _create_background(self, bg_type, bedfile, fafile, outfile, organism="hg18", width=200, nr_times=10):
fg = Fasta(fafile)
if bg_type == "random":
if int(self.markov_model) >= 6:
self.logger.warn("Are you sure about the Markov model? It seems too high!")
else:
order = {"1":"1st","2":"2nd", "3":"3rd", "4":"4th", "5":"5th"}[str(self.markov_model)]
self.logger.debug("Creating random background (%s order Markov)" % order)
m = MarkovFasta(fg, k=int(self.markov_model), n=nr_times * len(fg))
m.writefasta(outfile)
self.logger.debug("Random background: %s", outfile)
# return the number of random sequences created
return len(m)
elif bg_type == "genomic":
self.logger.debug("Creating genomic background")
index_dir = os.path.join(self.config.get_index_dir(), organism)
f = RandomGenomicFasta(index_dir, width, nr_times * len(fg))
f.writefasta(outfile)
return len(f)
elif bg_type == "gc":
self.logger.debug("Creating GC matched background")
f = MatchedGcFasta(fafile, organism, nr_times * len(fg))
f.writefasta(outfile)
self.logger.debug("GC matched background: %s", outfile)
return len(f)
elif bg_type == "promoter":
gene_file = os.path.join(self.config.get_gene_dir(), "%s.bed" % organism)
index_dir = os.path.join(self.config.get_index_dir(), organism)
self.logger.info(
"Creating random promoter background (%s, using genes in %s)",
organism, gene_file)
f = PromoterFasta(gene_file, index_dir, width, nr_times * len(fg))
f.writefasta(outfile)
self.logger.debug("Random promoter background: %s", outfile)
return len(f)
elif bg_type == "user":
bg_file = self.params["user_background"]
if not os.path.exists(bg_file):
self.logger.error(
"User-specified background file %s does not exist!",
bg_file)
sys.exit(1)
else:
self.logger.info("Copying user-specified background file %s to %s.",
bg_file, outfile)
fa = Fasta(bg_file)
l = median([len(seq) for seq in fa.seqs])
if l < width * 0.95 or l > width * 1.05:
self.logger.warn("The user-specified background file %s contains sequences with a median length of %s, while GimmeMotifs predicts motifs in sequences of length %s. This will influence the statistics! It is recommended to use background sequences of the same length.", bg_file, l, width)
fa.writefasta(outfile)
return len(fa)
def _create_background(self, bg_type, bedfile, fafile, outfile, organism="hg18", width=200, nr_times=10):
if bg_type == "random":
if int(self.markov_model) >= 6:
self.logger.warn("Are you sure about the Markov model? It seems too high!")
else:
order = {"1":"1st","2":"2nd", "3":"3rd", "4":"4th", "5":"5th"}[str(self.markov_model)]
self.logger.info("Creating random background (%s order Markov)" % order)
f = Fasta(fafile)
m = MarkovFasta(f, k=int(self.markov_model))
m.writefasta(outfile)
self.logger.debug("Random background: %s" % (outfile))
# return the number of random sequences created
return len(m)
elif bg_type == "genomic_matched":
gene_file = os.path.join(self.config.get_gene_dir(), "%s.bed" % organism)
index_dir = os.path.join(self.config.get_index_dir(), organism)
self.logger.info("Creating matched genomic background (%s, using genes in %s)" % (organism, gene_file))
f = MatchedGenomicFasta(bedfile, gene_file, index_dir, width, nr_times)
f.writefasta(outfile)
self.logger.debug("Matched genomic background: %s" % (outfile))
return len(f)
elif bg_type == "promoter":
gene_file = os.path.join(self.config.get_gene_dir(), "%s.bed" % organism)
index_dir = os.path.join(self.config.get_index_dir(), organism)
self.logger.info("Creating random promoter background (%s, using genes in %s)" % (organism, gene_file))
fg = Fasta(fafile)
f = PromoterFasta(gene_file, index_dir, width, nr_times * len(fg))
f.writefasta(outfile)
self.logger.debug("Random promoter background: %s" % (outfile))
return len(f)
elif bg_type == "user":
bg_file = self.params["user_background"]
if not os.path.exists(bg_file):
self.logger.error("User-specified background file %s does not exist!" % bg_file)
sys.exit(1)
else:
self.logger.info("Copying user-specified background file %s to %s." % (bg_file, outfile))
fa = Fasta(bg_file)
l = median([len(seq) for seq in fa.seqs])
if l < width * 0.95 or l > width * 1.05:
self.logger.warn("The user-specified background file %s contains sequences with a median length of %s, while GimmeMotifs predicts motifs in sequences of length %s. This will influence the statistics! It is recommended to use background sequences of the same length." % (bg_file, l, width))
fa.writefasta(outfile)
return len(fa)
