def getMergedExonicRegions(transcripts):
# Return the merged exons in the format of list of (start, end)
all_exons = []
for transcript in transcripts:
all_exons += transcript.getExons()
all_exons = sorted(all_exons, key=itemgetter(0))
return Utility_extended.union(all_exons)
def Calculate3UTRUsage(entrez_genes, bedfile, column_index, chroms,
fragment_size, downstream_extension, outfile):
"""
entrez genes are made sure to be on one strand,
the bed file are reads for that strand
entrez_genes is a KnownEntrezGenes class object
The raw read file needs to conform to bed format
column_index: column in bed file for sorting
"""
# Separate reads by chrom
rawreadslibName1 = (bedfile).split('/')[-1]
rawreadssuffix1 = rawreadslibName1.split('.')[-1]
rawreadslibName1 = rawreadslibName1.split('.')[0]
rawreadsextension1 = "-" + rawreadslibName1 + '.' + rawreadssuffix1 + "1"
if Utility_extended.fileExists(bedfile):
if Utility_extended.chrom_files_exist(chroms, rawreadsextension1) != 1:
# Separate by chrom and sort by start
print chroms, rawreadsextension1, " files do not exist, separate by chroms and sort each file according to the second column. "
Utility_extended.separate_by_chrom_sort(chroms, bedfile,
rawreadsextension1,
[column_index])
else:
print bedfile, " is not found"
sys.exit(1)
# Here the output is 'a'
outf = open(outfile, 'a')
for chrom in chroms:
if chrom in entrez_genes.chroms:
# a KnownEntrezGenes object
entrez_genes_by_chrom = Entrez.KnownEntrezGenes(
[chrom], entrez_genes.subset_by_chrom(chrom))
# this_chrom_length = chrom_lengths[chrom]
# Get the read locations
if Utility_extended.fileExists(chrom + rawreadsextension1):
f = open(chrom + rawreadsextension1, 'r')
tag_positions = []
for line in f:
line = line.strip()
sline = line.split()
tag_positions.append(
associate_tags_with_regions.tag_position(
sline, fragment_size))
if not Utility_extended.is_list_sorted(tag_positions):
tag_positions.sort()
f.close()
for entrez_id in entrez_genes_by_chrom.entrez_ids:
gene = entrez_genes_by_chrom.entrez_genes[
entrez_id] # an EntrezGene class object
three_UTRs = gene.get_3UTRs(downstream_extension)
print three_UTRs
union = Utility_extended.union(
three_UTRs
) # Find the union of 3UTRs [(start, end)], returns a [(start,end)]
if len(union) > 1:
print "There are disjoint 3UTRs in %s" % (
str(entrez_id))
else:
# returns [((start, end), [tag_positions])], [tag_positions] = return[0][1]
inside_reads = (Utility_extended.
associate_simple_tags_with_regions(
tag_positions, union))[0][1]
total_read_count = len(inside_reads)
RUD = CUTR_vs_AUTR(three_UTRs, inside_reads,
gene.strand)
## For the set of genes, use the distal 3UTR at the designated representative 3UTR
#myindex = Calculate3UTRUsageIndexFromCuratedGenes.find_distal_3UTR(genes)
#gene = genes[myindex]
#results = ThreeUTRCharacteristics(gene, inside_reads)
gene_symbol = []
for mytranscript in gene.transcripts:
if mytranscript.additional_annotations[
0] not in gene_symbol:
gene_symbol.append(
mytranscript.additional_annotations[0])
union_length = union[0][1] - union[0][0] + 1
outline = str(entrez_id) + "\t" + str(
union_length) + "\t" + str(RUD) + "\t" + str(
total_read_count) + "\t" + ','.join([
transcript.name
for transcript in gene.transcripts
]) + "\t" + ','.join(gene_symbol) + "\n"
outf.write(outline)
outf.close()