#!/usr/bin/env python
import sys
import pygeneann
import sequtils
import pysam
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('cff_file', action='store', help='CFF file, can be .cff or cff.reann')
parser.add_argument('ensbed', action='store', help='Ensemble gene file')
parser.add_argument('ref_fa', action='store', help='Reference genome file')
args = parser.parse_args()
gene_ann = pygeneann.GeneAnnotation(args.ensbed)
ref = pysam.FastaFile(args.ref_fa)
def remove_underscores(gene):
return gene.replace("_",".")
seq_dict ={}
for line in open(args.cff_file, "r"):
fusion = pygeneann.CffFusion(line)
# in a downstream script, "_" is used as a field separator. Need to remove "_" from gene names
gene1 = remove_underscores(fusion.reann_gene1)
gene2 = remove_underscores(fusion.reann_gene2)
lib = fusion.library
fusion_id = fusion.fusion_id
parser.add_argument('gene_bed', action='store', help='Gene annotation bed file')
parser.add_argument('tmp_dir', action='store', help='Temp file directory')
args = parser.parse_args()
cff_file = args.cff_file
dna_bam_list = args.dna_bam_list
out_dir = args.tmp_dir
gene_ann_file = args.gene_bed
#dna_bam = pysam.AlignmentFile(dna_bam_file, "rb")
bam_dict = load_bam_dict(dna_bam_list)
gene_ann = pygeneann.GeneAnnotation(gene_ann_file)
win_size = 100000
rlen = 100
isize = 500
supp_cluster_num = -99 # No dna file: -1; gene not in annotation: -2; chr not in bam's refrerence: -3; confilicting windonw start and end: -4
for line in open(cff_file, "r"):
fusion = pygeneann.CffFusion(line)
if fusion.sample_name in bam_dict:
dna_bam_file = bam_dict[fusion.sample_name]
dna_bam = pysam.AlignmentFile(dna_bam_file, "rb")
else:
#print >> sys.stderr, fusion.sample_name, "has no dna file."
supp_cluster_num = -1
#print "Fusion:", line.strip(), supp_cluster_num
#!/usr/bin/env python
import sys
sys.path.append(
"/hpf/largeprojects/ccmbio/jiangyue/DIPG_analysis_by_samples/Scripts/pygeneann/pygenefusionann"
)
import pygeneann
import sequtils
import pysam
cff_file = sys.argv[1]
#ref_fa = sys.argv[2]
ensbed = sys.argv[2]
# gene order annotation test
ref = sys.argv[3]
gene_ann = pygeneann.GeneAnnotation(ensbed)
n = 1
for line in open(cff_file, "r"):
fusion = pygeneann.CffFusion(line)
fusion.ann_gene_order(gene_ann)
#annotate fusion id and seq
fusion.fusion_id = "F" + (str(n)).zfill(8)
pygeneann.get_fusion_seq(fusion, ref, 100)
fusion.check_codon(gene_ann, ref)
print fusion.tostring()
n += 1