def ParseGFF(fname):
"""get contents from a decent GFF file.
"""
smap={1:'+' , -1:'-' }
for cid in ['Chr1', 'Chr2', 'Chr3', 'Chr4', 'Chr5', 'ChrM', 'ChrC']: ## change according to the GFF file TODO
fh = open(fname, 'rU')
limit_info = dict(gff_id=[cid], gff_source=['TAIR10']) ## change the source TODO According to the file type
for rec in GFF.parse(fh, limit_info=limit_info):
for each_rec in rec.features:
if each_rec.type=='gene':
for child in each_rec.sub_features:
print child.id, 'NULL', rec.id, smap[child.strand], child.type, child.location._start.position, child.location._end.position, each_rec.qualifiers['Note'][0]
cnt=1
for cod in child.sub_features:
fid=None
if cod.type=="five_prime_UTR":
fid=child.id+'_'+str(cnt)
cod.type='UTR5'
elif cod.type=="three_prime_UTR":
fid=child.id+'_'+str(cnt)
cod.type='UTR3'
elif cod.type=="CDS":
fid=child.id+'_'+str(cnt)
if fid:
print fid, child.id, rec.id, smap[cod.strand], cod.type, cod.location._start.position, cod.location._end.position,'NULL'
cnt+=1
break
fh.close()
def __main__():
try:
gff_file = sys.argv[1]
chrid = sys.argv[2]
source = sys.argv[3]
except:
sys.stderr.write('Access denied for a GFF file !\n')
sys.exit(-1)
#gff_source = ['rheMac2_ensGene', 'rheMac2_refGene', 'rheMac2_refSeqAnno', 'rheMac2_transMapAlnUcscGenes']
limit_parse = dict(
gff_id = [chrid],
gff_source = [source]
)
chrpos = dict()
fh = open(gff_file)
for rec in GFF.parse(fh, limit_info=limit_parse):
for element in rec.features:
chrpos[(element.location._start.position, element.location._end.position)] = 1
fh.close()
sorted_chrpos = [sort_pos for sort_pos in sorted(chrpos)]
WriteSortedGFF(gff_file, limit_parse, sorted_chrpos)
def ParserCommonType(fname, source):
gff_type = ['transcript', 'exon']
source_type = zip([source] * len(gff_type), gff_type)
filter_type = dict(gff_source_type=source_type,
gff_id=['I', 'II', 'III', 'IV', 'V', 'X'])
gene_cnt, genes_data = 1, []
gid = ordered_dict()
gfh = open(fname)
for rec in GFF.parse(gfh, limit_info=filter_type):
for feature in rec.features:
if feature.qualifiers['gene'][0] in gid:
gene = gid[feature.qualifiers['gene'][0]]
gene['is_alt_spliced'] = 1
gene['transcripts'].append(feature.id)
exon_pos = []
for xlevel in feature.sub_features:
exon_pos.append([
xlevel.location._start.position + 1,
xlevel.location._end.position
])
if orient == '-':
if exon_pos != [] and len(exon_pos) != 1:
if exon_pos[0][0] > exon_pos[-1][0]:
exon_pos.reverse()
gene["exons"].append(exon_pos)
gid[feature.qualifiers['gene'][0]] = gene
else:
gene = init_gene()
gene['id'] = gene_cnt
gene['name'] = feature.qualifiers['gene'][0]
gene['chr'] = rec.id
gene['source'] = feature.qualifiers['source'][0]
orient = None
if feature.strand == 1:
orient = '+'
else:
orient = '-'
gene['strand'] = orient
gene['is_alt_spliced'] = 0
gene['transcripts'].append(feature.id)
exon_pos = []
for xlevel in feature.sub_features:
exon_pos.append([
xlevel.location._start.position + 1,
xlevel.location._end.position
])
if orient == '-':
if exon_pos != [] and len(exon_pos) != 1:
if exon_pos[0][0] > exon_pos[-1][0]:
exon_pos.reverse()
gene["exons"].append(exon_pos)
gene_cnt += 1
gid[feature.qualifiers['gene'][0]] = gene
gfh.close()
for ent in gid.ordered_items():
cand = OrganizePacket(ent[1])
genes_data.append(cand)
return genes_data
def get_annotation(fname, rfname):
"""Parse genome annotation from GFF3 file.
"""
smap={1:'+', -1:'-'}
from Core import GFF
te_featdb, teg_featdb, ribo_featdb, oth_featdb=dict(), dict(), dict(), dict()
for cid in ['Chr1', 'Chr2', 'Chr3', 'Chr4', 'Chr5', 'ChrM', 'ChrC']:
sys.stderr.write(cid+".....\n")
fh = open(fname, 'rU')
limit_info = dict(gff_id=[cid], gff_source=['TAIR10'])
for rec in GFF.parse(fh, limit_info=limit_info):
for each_rec in rec.features:
if each_rec.type=='gene':
for child in each_rec.sub_features:
if child.type in ['mRNA', 'miRNA', 'ncRNA', 'snoRNA', 'snRNA', 'tRNA']:
if cid in oth_featdb:
oth_featdb[cid][(int(each_rec.location._start.position),
int(each_rec.location._end.position))]=smap[each_rec.strand]
else:
oth_featdb[cid]={(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
smap[each_rec.strand]}
elif each_rec.type=='transposable_element_gene':
if cid in teg_featdb:
teg_featdb[cid][(int(each_rec.location._start.position),
int(each_rec.location._end.position))]=smap[each_rec.strand]
else:
teg_featdb[cid]={(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
smap[each_rec.strand]}
elif each_rec.type=='transposable_element':
if cid in te_featdb:
te_featdb[cid][(each_rec.id, int(each_rec.location._start.position),
int(each_rec.location._end.position))]=smap[each_rec.strand]
else:
te_featdb[cid]={(each_rec.id, int(each_rec.location._start.position),
int(each_rec.location._end.position)):
smap[each_rec.strand]}
elif each_rec.type=='pseudogene':
if cid in oth_featdb:
oth_featdb[cid][(int(each_rec.location._start.position),
int(each_rec.location._end.position))]=smap[each_rec.strand]
else:
oth_featdb[cid]={(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
smap[each_rec.strand]}
fh.close()
## add additional rRNA related location from A. thaliana
fh=open(rfname, 'rU')
for line in fh:
line=line.strip('\n\r').split(' ')
if line[0] in ribo_featdb:
ribo_featdb[line[0]][(int(line[1]), int(line[2]))]=line[3]
else:
ribo_featdb[line[0]]={(int(line[1]), int(line[2])):line[3]}
fh.close()
return te_featdb, teg_featdb, ribo_featdb, oth_featdb
def get_Feature(fname):
"""Extract genome annotation information from a provided GFF file.
"""
from Core import GFF
te_featdb, psd_featdb, cg_featdb, oth_featdb, ribo_featdb = dict(), dict(), dict(), dict(), dict()
for cid in ['Chr1', 'Chr2', 'Chr3', 'Chr4', 'Chr5', 'ChrM', 'ChrC']: ## change according to the GFF file TODO According to the file type add chromosome number automatically.
print cid
fh = open(fname, 'rU')
limit_info = dict(gff_id=[cid], gff_source=['TAIR10']) ## change the source TODO According to the file type add source flag automatically
for rec in GFF.parse(fh, limit_info=limit_info):
for each_rec in rec.features:
if each_rec.type=='gene':
for child in each_rec.sub_features:
if child.type=='mRNA':
if cid in cg_featdb:
cg_featdb[cid][(int(each_rec.location._start.position),
int(each_rec.location._end.position))]=each_rec.strand
else:
cg_featdb[cid]={(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand}
elif each_rec.sub_features[0].type in ['miRNA', 'ncRNA', 'snoRNA', 'snRNA', 'tRNA']:
if cid in oth_featdb:
oth_featdb[cid][(int(each_rec.location._start.position),
int(each_rec.location._end.position))]=each_rec.strand
else:
oth_featdb[cid]={(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand}
elif each_rec.sub_features[0].type=='rRNA':
if cid in ribo_featdb:
ribo_featdb[cid][(int(each_rec.location._start.position),
int(each_rec.location._end.position))]=each_rec.strand
else:
ribo_featdb[cid]={(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand}
elif each_rec.type=='pseudogene':
if cid in psd_featdb:
psd_featdb[cid][(int(each_rec.location._start.position),
int(each_rec.location._end.position))]=each_rec.strand
else:
psd_featdb[cid]={(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand}
elif each_rec.type in ['transposable_element', 'transposable_element_gene']:
if cid in te_featdb:
te_featdb[cid][(int(each_rec.location._start.position),
int(each_rec.location._end.position))]=each_rec.strand
else:
te_featdb[cid]={(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand}
fh.close()
return te_featdb, psd_featdb, cg_featdb, oth_featdb, ribo_featdb
def __main__():
try:
gff_fname = sys.argv[1]
fasta_fname = sys.argv[2]
gb_fname = sys.argv[3]
except:
print __doc__
sys.exit(-1)
fasta_rec = SeqIO.to_dict(SeqIO.parse(fasta_fname, "fasta", generic_dna))
gff_rec = GFF.parse(gff_fname, fasta_rec)
SeqIO.write(gff_rec, gb_fname, "genbank")
def __main__():
try:
gff_fname = sys.argv[1]
fasta_fname = sys.argv[2]
gb_fname = sys.argv[3]
except:
print __doc__
sys.exit(-1)
fasta_rec = SeqIO.to_dict(SeqIO.parse(fasta_fname, "fasta", generic_dna))
gff_rec = GFF.parse(gff_fname, fasta_rec)
SeqIO.write(gff_rec, gb_fname, "genbank")
def ParserCommonType(fname, source):
gff_type=['transcript', 'exon']
source_type = zip([source] * len(gff_type), gff_type)
filter_type = dict(gff_source_type = source_type, gff_id = ['I', 'II', 'III', 'IV', 'V', 'X'])
gene_cnt, genes_data = 1, []
gid = ordered_dict()
gfh = open(fname)
for rec in GFF.parse(gfh, limit_info=filter_type):
for feature in rec.features:
if feature.qualifiers['gene'][0] in gid:
gene = gid[feature.qualifiers['gene'][0]]
gene['is_alt_spliced'] = 1
gene['transcripts'].append(feature.id)
exon_pos = []
for xlevel in feature.sub_features:
exon_pos.append([xlevel.location._start.position + 1, xlevel.location._end.position])
if orient == '-':
if exon_pos != [] and len(exon_pos) != 1:
if exon_pos[0][0] > exon_pos[-1][0]:
exon_pos.reverse()
gene["exons"].append(exon_pos)
gid[feature.qualifiers['gene'][0]]=gene
else:
gene = init_gene()
gene['id'] = gene_cnt
gene['name'] = feature.qualifiers['gene'][0]
gene['chr'] = rec.id
gene['source'] = feature.qualifiers['source'][0]
orient = None
if feature.strand == 1:
orient = '+'
else:
orient = '-'
gene['strand'] = orient
gene['is_alt_spliced'] = 0
gene['transcripts'].append(feature.id)
exon_pos = []
for xlevel in feature.sub_features:
exon_pos.append([xlevel.location._start.position + 1, xlevel.location._end.position])
if orient == '-':
if exon_pos != [] and len(exon_pos) != 1:
if exon_pos[0][0] > exon_pos[-1][0]:
exon_pos.reverse()
gene["exons"].append(exon_pos)
gene_cnt += 1
gid[feature.qualifiers['gene'][0]]=gene
gfh.close()
for ent in gid.ordered_items():
cand = OrganizePacket(ent[1])
genes_data.append(cand)
return genes_data
def ParseGFF(fname):
"""get contents from a decent GFF file.
"""
smap = {1: '+', -1: '-'}
for cid in ['Chr1', 'Chr2', 'Chr3', 'Chr4', 'Chr5', 'ChrM',
'ChrC']: ## change according to the GFF file TODO
fh = open(fname, 'rU')
limit_info = dict(gff_id=[cid], gff_source=[
'TAIR10'
]) ## change the source TODO According to the file type
for rec in GFF.parse(fh, limit_info=limit_info):
for each_rec in rec.features:
if each_rec.type == 'gene':
for child in each_rec.sub_features:
print child.id, 'NULL', rec.id, smap[
child.
strand], child.type, child.location._start.position, child.location._end.position, each_rec.qualifiers[
'Note'][0]
cnt = 1
for cod in child.sub_features:
fid = None
if cod.type == "five_prime_UTR":
fid = child.id + '_' + str(cnt)
cod.type = 'UTR5'
elif cod.type == "three_prime_UTR":
fid = child.id + '_' + str(cnt)
cod.type = 'UTR3'
elif cod.type == "CDS":
fid = child.id + '_' + str(cnt)
if fid:
print fid, child.id, rec.id, smap[
cod.
strand], cod.type, cod.location._start.position, cod.location._end.position, 'NULL'
cnt += 1
break
fh.close()
def __main__():
try:
gff_file = sys.argv[1]
chrid = sys.argv[2]
source = sys.argv[3]
except:
sys.stderr.write('Access denied for a GFF file !\n')
sys.exit(-1)
#gff_source = ['rheMac2_ensGene', 'rheMac2_refGene', 'rheMac2_refSeqAnno', 'rheMac2_transMapAlnUcscGenes']
limit_parse = dict(gff_id=[chrid], gff_source=[source])
chrpos = dict()
fh = open(gff_file)
for rec in GFF.parse(fh, limit_info=limit_parse):
for element in rec.features:
chrpos[(element.location._start.position,
element.location._end.position)] = 1
fh.close()
sorted_chrpos = [sort_pos for sort_pos in sorted(chrpos)]
WriteSortedGFF(gff_file, limit_parse, sorted_chrpos)
def get_Feature(fname):
"""Extract genome annotation information from a provided GFF file.
"""
from Core import GFF
global te_featdb; global psd_featdb; global cg_featdb; global oth_featdb; global ribo_featdb
for cid in ['Chr1', 'Chr2', 'Chr3', 'Chr4', 'Chr5', 'ChrM', 'ChrC']: ## change according to the GFF file TODO According to the file type add chromosome number automatically.
print cid
fh = open(fname, 'rU')
limit_info = dict(gff_id=[cid], gff_source=['TAIR10']) ## change the source TODO According to the file type add source flag automatically
for rec in GFF.parse(fh, limit_info=limit_info):
for each_rec in rec.features:
if each_rec.type=='gene':
for child in each_rec.sub_features:
if child.type=='mRNA':
if cid in cg_featdb:
cg_featdb[cid][(int(each_rec.location._start.position),
int(each_rec.location._end.position))]=each_rec.strand
else:
cg_featdb[cid]={(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand}
elif each_rec.sub_features[0].type in ['miRNA', 'ncRNA', 'snoRNA', 'snRNA', 'tRNA']:
if cid in oth_featdb:
oth_featdb[cid][(int(each_rec.location._start.position),
int(each_rec.location._end.position))]=each_rec.strand
else:
oth_featdb[cid]={(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand}
elif each_rec.sub_features[0].type=='rRNA':
if cid in ribo_featdb:
ribo_featdb[cid][(int(each_rec.location._start.position),
int(each_rec.location._end.position))]=each_rec.strand
else:
ribo_featdb[cid]={(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand}
elif each_rec.type=='pseudogene':
if cid in psd_featdb:
psd_featdb[cid][(int(each_rec.location._start.position),
int(each_rec.location._end.position))]=each_rec.strand
else:
psd_featdb[cid]={(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand}
elif each_rec.type in ['transposable_element', 'transposable_element_gene']:
if cid in te_featdb:
te_featdb[cid][(int(each_rec.location._start.position),
int(each_rec.location._end.position))]=each_rec.strand
else:
te_featdb[cid]={(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand}
fh.close()
ribo_featdb['Chr3'][(14199917, 14203578)]=1 ## Unannotated rRNA from A thaliana genome.
ribo_featdb['Chr2'][(5784, 9683)]=1 ## Unannotated rRNA from A thaliana genome.
ribo_featdb['Chr2'][(2821, 3704)]=1 #
ribo_featdb['Chr3'][(14196614, 14197675)]=1 #
ribo_featdb['Chr3'][(14194052, 14194611)]=1 #
ribo_featdb['Chr3'][(14199498, 14199751)]=1 #
ribo_featdb['Chr3'][(14195564, 14195739)]=1 #
ribo_featdb['ChrM'][(11426, 11883)]=-1 #
ribo_featdb['ChrM'][(364594, 365124)]=1 #"""
return te_featdb, psd_featdb, cg_featdb, oth_featdb, ribo_featdb
def get_annotation(fname, rfname):
"""Parse genome annotation from GFF3 file.
"""
smap = {1: '+', -1: '-'}
from Core import GFF
te_featdb, teg_featdb, ribo_featdb, oth_featdb = dict(), dict(), dict(
), dict()
for cid in ['Chr1', 'Chr2', 'Chr3', 'Chr4', 'Chr5', 'ChrM', 'ChrC']:
sys.stderr.write(cid + ".....\n")
fh = open(fname, 'rU')
limit_info = dict(gff_id=[cid], gff_source=['TAIR10'])
for rec in GFF.parse(fh, limit_info=limit_info):
for each_rec in rec.features:
if each_rec.type == 'gene':
for child in each_rec.sub_features:
if child.type in [
'mRNA', 'miRNA', 'ncRNA', 'snoRNA', 'snRNA',
'tRNA'
]:
if cid in oth_featdb:
oth_featdb[cid][(
int(each_rec.location._start.position),
int(each_rec.location._end.position)
)] = smap[each_rec.strand]
else:
oth_featdb[cid] = {
(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
smap[each_rec.strand]
}
elif each_rec.type == 'transposable_element_gene':
if cid in teg_featdb:
teg_featdb[cid][(int(
each_rec.location._start.position),
int(each_rec.location._end.position)
)] = smap[each_rec.strand]
else:
teg_featdb[cid] = {
(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
smap[each_rec.strand]
}
elif each_rec.type == 'transposable_element':
if cid in te_featdb:
te_featdb[cid][(each_rec.id,
int(each_rec.location._start.position),
int(each_rec.location._end.position)
)] = smap[each_rec.strand]
else:
te_featdb[
cid] = {
(each_rec.id,
int(each_rec.location._start.position),
int(each_rec.location._end.position)):
smap[each_rec.strand]
}
elif each_rec.type == 'pseudogene':
if cid in oth_featdb:
oth_featdb[cid][(int(
each_rec.location._start.position),
int(each_rec.location._end.position)
)] = smap[each_rec.strand]
else:
oth_featdb[cid] = {
(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
smap[each_rec.strand]
}
fh.close()
## add additional rRNA related location from A. thaliana
fh = open(rfname, 'rU')
for line in fh:
line = line.strip('\n\r').split(' ')
if line[0] in ribo_featdb:
ribo_featdb[line[0]][(int(line[1]), int(line[2]))] = line[3]
else:
ribo_featdb[line[0]] = {(int(line[1]), int(line[2])): line[3]}
fh.close()
return te_featdb, teg_featdb, ribo_featdb, oth_featdb
def get_Feature(fname):
"""Extract genome annotation information from a provided GFF file.
"""
from Core import GFF
te_featdb, psd_featdb, cg_featdb, oth_featdb, ribo_featdb = dict(), dict(
), dict(), dict(), dict()
for cid in [
'Chr1', 'Chr2', 'Chr3', 'Chr4', 'Chr5', 'ChrM', 'ChrC'
]: ## change according to the GFF file TODO According to the file type add chromosome number automatically.
print cid
fh = open(fname, 'rU')
limit_info = dict(
gff_id=[cid], gff_source=['TAIR10']
) ## change the source TODO According to the file type add source flag automatically
for rec in GFF.parse(fh, limit_info=limit_info):
for each_rec in rec.features:
if each_rec.type == 'gene':
for child in each_rec.sub_features:
if child.type == 'mRNA':
if cid in cg_featdb:
cg_featdb[cid][(
int(each_rec.location._start.position),
int(each_rec.location._end.position)
)] = each_rec.strand
else:
cg_featdb[cid] = {
(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand
}
elif each_rec.sub_features[0].type in [
'miRNA', 'ncRNA', 'snoRNA', 'snRNA', 'tRNA'
]:
if cid in oth_featdb:
oth_featdb[cid][(
int(each_rec.location._start.position),
int(each_rec.location._end.position)
)] = each_rec.strand
else:
oth_featdb[cid] = {
(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand
}
elif each_rec.sub_features[0].type == 'rRNA':
if cid in ribo_featdb:
ribo_featdb[cid][(
int(each_rec.location._start.position),
int(each_rec.location._end.position)
)] = each_rec.strand
else:
ribo_featdb[cid] = {
(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand
}
elif each_rec.type == 'pseudogene':
if cid in psd_featdb:
psd_featdb[cid][(int(
each_rec.location._start.position),
int(each_rec.location._end.position)
)] = each_rec.strand
else:
psd_featdb[cid] = {
(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand
}
elif each_rec.type in [
'transposable_element', 'transposable_element_gene'
]:
if cid in te_featdb:
te_featdb[cid][(int(each_rec.location._start.position),
int(each_rec.location._end.position)
)] = each_rec.strand
else:
te_featdb[cid] = {
(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand
}
fh.close()
return te_featdb, psd_featdb, cg_featdb, oth_featdb, ribo_featdb
def WriteSortedGFF(fname, limit_parse, sorted_pos):
fgh = open(fname)
for rec in GFF.parse(fgh, limit_info=limit_parse):
for sort_pos in sorted_pos:
for feature in rec.features:
if sort_pos == (feature.location._start.position, feature.location._end.position):
orient = None
if feature.strand == 1:
orient = '+'
else:
orient = '-'
gline = [rec.id,
feature.qualifiers['source'][0],
feature.type,
str(feature.location._start.position + 1),
str(feature.location._end.position),
'.',
orient,
'.',
'ID=' + feature.qualifiers['ID'][0] + ';Name=' + feature.qualifiers['Name'][0]
]
print '\t'.join(gline)
for slevel in feature.sub_features: ## second level feature
orient = None
if slevel.strand == 1:
orient = '+'
else:
orient = '-'
tline = [rec.id,
slevel.qualifiers['source'][0],
slevel.type,
str(slevel.location._start.position + 1),
str(slevel.location._end.position),
str(float(slevel.qualifiers['score'][0])),
orient,
'.',
'ID=' + slevel.qualifiers['ID'][0] + ';Parent=' + slevel.qualifiers['Parent'][0]
]
print '\t'.join(tline)
for tlevel in slevel.sub_features:
orient = None
if tlevel.strand == 1:
orient = '+'
else:
orient = '-'
xline = []
if tlevel.type == 'CDS':
xline = [rec.id,
tlevel.qualifiers['source'][0],
tlevel.type,
str(tlevel.location._start.position + 1),
str(tlevel.location._end.position),
'.',
orient,
tlevel.qualifiers['phase'][0],
'Parent=' + tlevel.qualifiers['Parent'][0]
]
else:
xline = [rec.id,
tlevel.qualifiers['source'][0],
tlevel.type,
str(tlevel.location._start.position + 1),
str(tlevel.location._end.position),
'.',
orient,
'.',
'Parent=' + tlevel.qualifiers['Parent'][0]
]
print '\t'.join(xline)
#break
#break ## one sorted position
fgh.close()
def WriteSortedGFF(fname, limit_parse, sorted_pos):
fgh = open(fname)
for rec in GFF.parse(fgh, limit_info=limit_parse):
for sort_pos in sorted_pos:
for feature in rec.features:
if sort_pos == (feature.location._start.position,
feature.location._end.position):
orient = None
if feature.strand == 1:
orient = '+'
else:
orient = '-'
gline = [
rec.id, feature.qualifiers['source'][0], feature.type,
str(feature.location._start.position + 1),
str(feature.location._end.position), '.', orient, '.',
'ID=' + feature.qualifiers['ID'][0] + ';Name=' +
feature.qualifiers['Name'][0]
]
print '\t'.join(gline)
for slevel in feature.sub_features: ## second level feature
orient = None
if slevel.strand == 1:
orient = '+'
else:
orient = '-'
tline = [
rec.id, slevel.qualifiers['source'][0],
slevel.type,
str(slevel.location._start.position + 1),
str(slevel.location._end.position),
str(float(slevel.qualifiers['score'][0])), orient,
'.', 'ID=' + slevel.qualifiers['ID'][0] +
';Parent=' + slevel.qualifiers['Parent'][0]
]
print '\t'.join(tline)
for tlevel in slevel.sub_features:
orient = None
if tlevel.strand == 1:
orient = '+'
else:
orient = '-'
xline = []
if tlevel.type == 'CDS':
xline = [
rec.id, tlevel.qualifiers['source'][0],
tlevel.type,
str(tlevel.location._start.position + 1),
str(tlevel.location._end.position), '.',
orient, tlevel.qualifiers['phase'][0],
'Parent=' + tlevel.qualifiers['Parent'][0]
]
else:
xline = [
rec.id, tlevel.qualifiers['source'][0],
tlevel.type,
str(tlevel.location._start.position + 1),
str(tlevel.location._end.position), '.',
orient, '.',
'Parent=' + tlevel.qualifiers['Parent'][0]
]
print '\t'.join(xline)
#break
#break ## one sorted position
fgh.close()
def get_Feature(fname):
"""Extract genome annotation information from a provided GFF file.
"""
from Core import GFF
global te_featdb
global psd_featdb
global cg_featdb
global oth_featdb
global ribo_featdb
for cid in [
'Chr1', 'Chr2', 'Chr3', 'Chr4', 'Chr5', 'ChrM', 'ChrC'
]: ## change according to the GFF file TODO According to the file type add chromosome number automatically.
print cid
fh = open(fname, 'rU')
limit_info = dict(
gff_id=[cid], gff_source=['TAIR10']
) ## change the source TODO According to the file type add source flag automatically
for rec in GFF.parse(fh, limit_info=limit_info):
for each_rec in rec.features:
if each_rec.type == 'gene':
for child in each_rec.sub_features:
if child.type == 'mRNA':
if cid in cg_featdb:
cg_featdb[cid][(
int(each_rec.location._start.position),
int(each_rec.location._end.position)
)] = each_rec.strand
else:
cg_featdb[cid] = {
(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand
}
elif each_rec.sub_features[0].type in [
'miRNA', 'ncRNA', 'snoRNA', 'snRNA', 'tRNA'
]:
if cid in oth_featdb:
oth_featdb[cid][(
int(each_rec.location._start.position),
int(each_rec.location._end.position)
)] = each_rec.strand
else:
oth_featdb[cid] = {
(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand
}
elif each_rec.sub_features[0].type == 'rRNA':
if cid in ribo_featdb:
ribo_featdb[cid][(
int(each_rec.location._start.position),
int(each_rec.location._end.position)
)] = each_rec.strand
else:
ribo_featdb[cid] = {
(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand
}
elif each_rec.type == 'pseudogene':
if cid in psd_featdb:
psd_featdb[cid][(int(
each_rec.location._start.position),
int(each_rec.location._end.position)
)] = each_rec.strand
else:
psd_featdb[cid] = {
(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand
}
elif each_rec.type in [
'transposable_element', 'transposable_element_gene'
]:
if cid in te_featdb:
te_featdb[cid][(int(each_rec.location._start.position),
int(each_rec.location._end.position)
)] = each_rec.strand
else:
te_featdb[cid] = {
(int(each_rec.location._start.position),
int(each_rec.location._end.position)):
each_rec.strand
}
fh.close()
ribo_featdb['Chr3'][(
14199917, 14203578)] = 1 ## Unannotated rRNA from A thaliana genome.
ribo_featdb['Chr2'][(
5784, 9683)] = 1 ## Unannotated rRNA from A thaliana genome.
ribo_featdb['Chr2'][(2821, 3704)] = 1 #
ribo_featdb['Chr3'][(14196614, 14197675)] = 1 #
ribo_featdb['Chr3'][(14194052, 14194611)] = 1 #
ribo_featdb['Chr3'][(14199498, 14199751)] = 1 #
ribo_featdb['Chr3'][(14195564, 14195739)] = 1 #
ribo_featdb['ChrM'][(11426, 11883)] = -1 #
ribo_featdb['ChrM'][(364594, 365124)] = 1 #"""
return te_featdb, psd_featdb, cg_featdb, oth_featdb, ribo_featdb