def intersectcirc(self, circ_file, modified_gtf_file, strand=True):
# imput the result file of print_start_end_file
#intersectBed -a start.bed -b Drosophila_melanogaster.BDGP5.75.exon_id.dedup.gtf -wa -wb -loj > tmpintersect.2
circ = pybedtools.BedTool(circ_file)
gtf = pybedtools.BedTool(modified_gtf_file)
if strand:
intersectfile = circ.intersect(gtf,
wa=True,
wb=True,
loj=True,
s=True,
nonamecheck=True)
else:
intersectfile = circ.intersect(gtf,
wa=True,
wb=True,
loj=True,
nonamecheck=True)
# Store circExons as: circle start or end intervals as key, custom_exon_id as value
circExons = {}
for lin in intersectfile:
lin_split = str(lin).split('\t')
if lin_split[14].strip('\n') == '.':
#lin_split[11] = ''
pass
else:
circExons.setdefault(
HTSeq.GenomicInterval(lin_split[0], int(lin_split[1]),
int(lin_split[2]), lin_split[5]),
set()).add(
HTSeq.parse_GFF_attribute_string(
lin_split[14])['custom_exon_id'])
#circExons.setdefault( HTSeq.GenomicInterval(lin_split[0],int(lin_split[1]),int(lin_split[2]),lin_split[9]), [] ).append( { HTSeq.GenomicInterval(lin_split[3],int(lin_split[6]),int(lin_split[7]),lin_split[9]):HTSeq.parse_GFF_attribute_string(lin_split[11]) })
return circExons
def loadFromFile(
cls,
org,
inputgff="/mnt/c/ownCloud/data/miRExplore/obodir/mm10_primary_assembly_and_lncRNA.gtf"
):
ret = GeneNeighbourDB(org)
with open(inputgff, 'r') as fin:
addedGenes = 0
for line in fin:
line = line.strip().split()
#print(line)
chr = line[0]
type = line[2]
if type != 'gene':
continue
attrStr = "\t".join(line[8:])
allAttr = HTSeq.parse_GFF_attribute_string(attrStr=attrStr)
geneID = allAttr.get('gene_id', None)
if geneID != None:
origID = geneID
if "." in geneID:
geneID = geneID[:geneID.index(".")]
if geneID in ret.id2pos:
print("Duplicate gene ID", geneID, origID)
start = int(line[3])
end = int(line[4])
strand = line[6]
ret.chr2neighbours[chr].addi(start, end, geneID)
ret.id2pos[geneID] = (chr, start, end, strand)
addedGenes += 1
if addedGenes % 10000 == 0:
print("Added Genes", addedGenes)
print(addedGenes)
return ret
def searchGeneName(self, annotationstring):
if annotationstring == '.':
genes = 'N/A'
else:
# Split the annotationstring by ',' which collapsed by bedtools groupby
annotationstrings = annotationstring.split(',')
collect = set()
for annotation in annotationstrings:
try:
attr = HTSeq.parse_GFF_attribute_string(annotation)
# Search for gene_name which is used by ensembl gtf annotation
try:
gene = attr['gene_name']
except KeyError:
# Search for gene, which might used in GFF annotation
try:
gene = attr['gene']
except KeyError:
# Search for gene_id
try:
gene = attr['gene_id']
except KeyError:
try:
gene = attr['transcript_id']
except KeyError:
gene = 'N/A'
except:
gene = self.searchGeneName1(annotation)
collect.add(gene)
# Collapse all genes togethor
if len(collect) > 1:
try:
collect.remove('N/A')
except KeyError:
pass
genes = ','.join(collect)
return genes
def searchGeneName(self,annotationstring):
if annotationstring == '.':
genes = 'N/A'
else:
# Split the annotationstring by ',' which collapsed by bedtools groupby
annotationstrings = annotationstring.split(',')
collect = set()
for annotation in annotationstrings:
try:
attr = HTSeq.parse_GFF_attribute_string(annotation)
# Search for gene_name which is used by ensembl gtf annotation
try:
gene = attr['gene_name']
except KeyError:
# Search for gene, which might used in GFF annotation
try:
gene = attr['gene']
except KeyError:
# Search for gene_id
try:
gene = attr['gene_id']
except KeyError:
try:
gene = attr['transcript_id']
except KeyError:
gene = 'N/A'
except:
gene = self.searchGeneName1(annotation)
collect.add(gene)
# Collapse all genes togethor
if len(collect) > 1:
try:
collect.remove('N/A')
except KeyError:
pass
genes = ','.join(collect)
return genes
def intersectcirc(self, circ_file, modified_gtf_file):
# imput the result file of print_start_end_file
import pybedtools
#intersectBed -a start.bed -b Drosophila_melanogaster.BDGP5.75.exon_id.dedup.gtf -wa -wb -loj > tmpintersect.2
circ = pybedtools.BedTool(circ_file)
gtf = pybedtools.BedTool(modified_gtf_file)
intersectfile = circ.intersect(gtf,wa=True,wb=True,loj=True)
# Store circExons as: circle start or end intervals as key, custom_exon_id as value
circExons = {}
for lin in intersectfile:
lin_split = str(lin).split('\t')
if lin_split[11].strip('\n') == '.':
#lin_split[11] = ''
pass
else:
circExons.setdefault( HTSeq.GenomicInterval(lin_split[0],int(lin_split[1]),int(lin_split[2]),lin_split[9]), set() ).add( HTSeq.parse_GFF_attribute_string(lin_split[11])['custom_exon_id'] )
#circExons.setdefault( HTSeq.GenomicInterval(lin_split[0],int(lin_split[1]),int(lin_split[2]),lin_split[9]), [] ).append( { HTSeq.GenomicInterval(lin_split[3],int(lin_split[6]),int(lin_split[7]),lin_split[9]):HTSeq.parse_GFF_attribute_string(lin_split[11]) })
return circExons
