def find_isoform(gff3, genome_bam, isoform_gff3, tss_tes_stat, genomefa,
transcript_fa, downsample_ratio, config_dict,
raw_splice_isoform):
# find isoform
print "#### Read genne annotations"
chr_to_gene, transcript_dict, gene_to_transcript, transcript_to_exon = parse_gff_tree(
gff3)
transcript_to_junctions = {
tr: blocks_to_junctions(transcript_to_exon[tr])
for tr in transcript_to_exon
}
remove_similar_tr(gene_to_transcript, transcript_to_exon)
gene_dict = get_gene_flat(gene_to_transcript, transcript_to_exon)
chr_to_blocks = get_gene_blocks(gene_dict, chr_to_gene, gene_to_transcript)
# finding isoforms are required
print "#### find isoforms"
group_bam2isoform(genome_bam,
isoform_gff3,
tss_tes_stat,
"",
chr_to_blocks,
gene_dict,
transcript_to_junctions,
transcript_dict,
genomefa,
config=config_dict["isoform_parameters"],
downsample_ratio=downsample_ratio,
raw_gff3=None)
#raw_gff3=raw_splice_isoform if config_dict["global_parameters"]["generate_raw_isoform"] else None)
# get fasta
#print "### generate transcript fasta file", datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
chr_to_gene_i, transcript_dict_i, gene_to_transcript_i, transcript_to_exon_i = parse_gff_tree(
isoform_gff3)
ref_dict = {
"chr_to_gene": chr_to_gene,
"transcript_dict": transcript_dict,
"gene_to_transcript": gene_to_transcript,
"transcript_to_exon": transcript_to_exon
}
if not config_dict["realign_parameters"]["use_annotation"]:
ref_dict = None
get_transcript_seq(genomefa,
transcript_fa,
chr_to_gene_i,
transcript_dict_i,
gene_to_transcript_i,
transcript_to_exon_i,
ref_dict=ref_dict)
return {
"transcript_dict": transcript_dict,
"transcript_dict_i": transcript_dict_i
}
def get_splice_expr(isoform_gff, fsm_annotation, res_csv, tr_kept=10):
typ_cnt = Counter()
chr_to_gene, transcript_dict, gene_to_transcript, transcript_to_exon = parse_gff_tree(
isoform_gff)
transcript_to_splice = {}
for tr in transcript_to_exon: # convert to list
transcript_to_splice[tr] = []
for ex in transcript_to_exon[tr]:
transcript_to_splice[tr].append(ex[0])
transcript_to_splice[tr].append(ex[1])
tr_dict = {}
fsm2tr = {}
fsm_cnt = Counter()
gene2fsm = {}
for line in open(fsm_annotation):
if "gene_id" in line:
continue
its = line.strip().split(
",") # 0:tr_id, 1:gene_id, 2:FSM_id, 3:in_ref, 4:cnt
# filtered out in gff (low abundance)
if its[0] not in transcript_to_exon:
continue
tr_dict[its[0]] = (its[1], its[2], int(its[4]))
fsm_cnt[its[2]] += int(its[4])
fsm2tr.setdefault(its[2], []).append(its[0])
gene2fsm.setdefault(its[1], []).append(its[2])
for ge in gene2fsm:
gene2fsm[ge] = [(it, fsm_cnt[it]) for it in list(set(gene2fsm[ge]))]
if len(gene2fsm[ge]) == 1:
continue
gene2fsm[ge].sort(key=lambda x: x[1], reverse=True)
if len(gene2fsm[ge]) > tr_kept:
gene2fsm[ge] = gene2fsm[ge][:tr_kept]
out_f = open(res_csv, "w")
for ge in gene2fsm:
if len(gene2fsm[ge]) == 1:
continue
for i in range(len(gene2fsm[ge])):
for j in range(len(gene2fsm[ge])):
if i == j:
continue
if gene2fsm[ge][i][0] in transcript_to_splice:
tr1 = gene2fsm[ge][i][0]
else:
tr1 = fsm2tr[gene2fsm[ge][i][0]][0]
if gene2fsm[ge][j][0] in transcript_to_splice:
tr2 = gene2fsm[ge][j][0]
else:
tr2 = fsm2tr[gene2fsm[ge][j][0]][0]
typ = comp_two_splicing(transcript_to_splice[tr1],
transcript_to_splice[tr2])
typ = "::".join(typ)
typ_cnt[typ] += 1
out_f.write("{},{},{}\n".format(gene2fsm[ge][i][0],
gene2fsm[ge][j][0], typ))
out_f.close()
for i in typ_cnt.most_common(5):
print("\t", i)
def get_cage_coverage(isoform_gff, cage_f):
cage_dict = make_CAGE_dict(cage_f)
cage_cov_dict = {}
chr_to_gene, transcript_dict, gene_to_transcript, transcript_to_exon = parse_gff_tree(
isoform_gff)
for ch in chr_to_gene:
if ch not in cage_dict:
print((ch, "not in CAGE annotation file."))
continue
cage_cov_dict[ch] = []
cage_tmp = dict((it[0], it) for it in cage_dict[ch])
cage_left = [it[0] for it in cage_dict[ch]]
for ge in chr_to_gene[ch]:
for tr in gene_to_transcript[ge]:
tss_pos = transcript_dict[tr].start if transcript_dict[
tr].strand == "+" else transcript_dict[tr].end
min_idx = max(0, bisect_right(cage_left, tss_pos) - 1)
#min_idx = min(range(len(cage_dict[ch])), key=lambda i: min(abs(cage_dict[ch][i][0]-tss_pos),abs(cage_dict[ch][i][1]-tss_pos)) )
if tss_pos >= cage_dict[ch][min_idx][
0] and tss_pos <= cage_dict[ch][min_idx][1]:
cage_cov_dict[ch].append((tr, tss_pos, 0))
elif tss_pos < cage_dict[ch][min_idx][0]:
if min_idx == 0:
cage_cov_dict[ch].append(
(tr, tss_pos, cage_dict[ch][min_idx][0] - tss_pos))
else:
cage_cov_dict[ch].append(
(tr, tss_pos,
min(tss_pos - cage_dict[ch][min_idx - 1][1],
cage_dict[ch][min_idx][0] - tss_pos)))
else: # tss_pos>cage_dict[ch][min_idx][1]
if min_idx == len(cage_dict[ch]) - 1:
cage_cov_dict[ch].append(
(tr, tss_pos, tss_pos - cage_dict[ch][min_idx][1]))
else:
cage_cov_dict[ch].append(
(tr, tss_pos,
min(tss_pos - cage_dict[ch][min_idx][1],
cage_dict[ch][min_idx + 1][0] - tss_pos)))
return cage_cov_dict
# write header
al_stat.write(
"chr,position,REF,ALT,REF_frequency,REF_frequency_in_short_reads,hypergeom_test_p_value,sequence_entrophy,INDEL_frequency,mean_base_quality\n")
for rec in reporting_summary:
al_stat.write(",".join(str(it) for it in rec)+"\n")
pct_bin, pt = np.histogram(acc_pct, bins=500, range=(0, 1))
with open(os.path.join(out_dir, "mutation", "MT_freq_summary.csv"), "w") as cov_bin_out:
for ix in range(500):
cov_bin_out.write("{},{}\n".format(pt[ix], pct_bin[ix]))
if __name__ == "__main__":
known_position_dict = {("chr18", 63318364): 0}
fa_f = "/stornext/General/data/user_managed/grpu_mritchie_1/LuyiTian/Index/GRCh38.primary_assembly.genome.fa"
gff_f = "/stornext/General/data/user_managed/grpu_mritchie_1/LuyiTian/Index/gencode.v33.annotation.gff3"
chr_to_gene, transcript_dict, gene_to_transcript, transcript_to_exon = parse_gff_tree(
gff_f)
gene_dict = get_gene_flat(gene_to_transcript, transcript_to_exon)
chr_to_blocks = get_gene_blocks(gene_dict, chr_to_gene, gene_to_transcript)
# CLL141 capture
cb_seq_dict = dict((it.strip().split("-")[0], it.strip().split("-")[0]) for it in open(
"/stornext/General/data/user_managed/grpu_mritchie_1/RachelThijssen/sclr_data/Illumina_data/Thijssen_count80/outs/filtered_feature_bc_matrix/barcodes.tsv"))
bam_short = "/stornext/General/data/user_managed/grpu_mritchie_1/hongkePeng/Rachel/all_fastq/CLL141-CLL-cells_S8_Rsubread.sorted.bam"
iso_dir = "/stornext/Genomics/data/CLL_venetoclax/single_cell_data/capture_test/isoform_out"
bam_in = os.path.join(iso_dir, "align2genome.bam")
gff_f = os.path.join(iso_dir, "isoform_annotated.gff3")
chr_to_gene, transcript_dict, gene_to_transcript, transcript_to_exon = parse_gff_tree(
gff_f)
gene_dict = get_gene_flat(gene_to_transcript, transcript_to_exon)
chr_to_blocks = get_gene_blocks(gene_dict, chr_to_gene, gene_to_transcript)
get_all_SNV_table(bam_in, chr_to_blocks, transcript_to_exon,
fa_f, iso_dir, cb_seq_dict, bam_short, known_position_dict)
def annotate_filter_gff(isoform_gff,ref_gff,isoform_out,anno_out,tr_cnt,min_sup_reads,verbose=True):
"""
combine FLAMES ouput with reference and filter out transcript by
realignment result
"""
gff3_fmt = "{_ch}\t{_sr}\t{_ty}\t{_st}\t{_en}\t{_sc}\t{_stnd}\t{_ph}\t{_attr}"
chr_to_gene, transcript_dict, gene_to_transcript, transcript_to_exon = parse_gff_tree(isoform_gff)
chr_to_gene_ref, transcript_dict_ref, gene_to_transcript_ref, transcript_to_exon_ref = parse_gff_tree(ref_gff)
prt = "\tFiltering and combining isoforms from realigned bam file:\n\tBefore filtering: {} isoforms in count matrix. {} isoforms in reference annotation. {} isoforms in FLAMES raw output.".format(
len(tr_cnt),
len(transcript_to_exon_ref),
len(transcript_to_exon)
)
if verbose:
print(prt)
gff_rec = []
iso_rm=0
iso_kp=0
for ch in chr_to_gene:
new_ge_list = copy.deepcopy(chr_to_gene[ch])
new_ge_list.extend(chr_to_gene_ref[ch])
new_ge_list = list(set(new_ge_list))
for ge in new_ge_list:
gff_tmp = []
total_cnt = 0
mi = 99999999999
ma = -1
if ge in gene_to_transcript:
for tr in gene_to_transcript[ge]:
if (tr in tr_cnt) and (tr_cnt[tr]>=min_sup_reads):
gff_tmp.append(gff3_fmt.format(_ch=ch,_sr="FLAMES",_ty="transcript",
_st=transcript_to_exon[tr][0][0]+1,
_en=transcript_to_exon[tr][-1][1],
_sc=".",_stnd=transcript_dict[tr].strand, _ph=".",
_attr="ID=transcript:{};transcript_id={};Parent=gene:{};support_count={}".format(tr,tr, ge, tr_cnt[tr])))
total_cnt += tr_cnt[tr]
mi = min(mi,transcript_to_exon[tr][0][0])
ma = max(ma,transcript_to_exon[tr][-1][1])
exon_idx = 1
for ex in transcript_to_exon[tr]:
gff_tmp.append(gff3_fmt.format(_ch=ch,_sr="FLAMES",_ty="exon",_st=ex[0]+1,_en=ex[1], # `+1` because gff is 1-based
_sc=".",_stnd=transcript_dict[tr].strand, _ph=".",
_attr="exon_id=exon:{}_{};Parent=transcript:{};rank={}".format(ex[0]+1, ex[1],tr, exon_idx )))
exon_idx += 1
iso_kp += 1
else:
iso_rm += 1
if ge in gene_to_transcript_ref:
for tr in gene_to_transcript_ref[ge]:
if (tr not in transcript_dict) and (tr in tr_cnt) and (tr_cnt[tr]>=min_sup_reads): # not in FLAMES output but in tr count
gff_tmp.append(gff3_fmt.format(_ch=ch,_sr="reference",_ty="transcript",
_st=transcript_to_exon_ref[tr][0][0]+1,
_en=transcript_to_exon_ref[tr][-1][1],
_sc=".",_stnd=transcript_dict_ref[tr].strand, _ph=".",
_attr="ID=transcript:{};transcript_id={};Parent=gene:{};support_count={}".format(tr,tr, ge, tr_cnt[tr])))
total_cnt += tr_cnt[tr]
mi = min(mi,transcript_to_exon_ref[tr][0][0])
ma = max(ma,transcript_to_exon_ref[tr][-1][1])
exon_idx = 1
for ex in transcript_to_exon_ref[tr]:
gff_tmp.append(gff3_fmt.format(_ch=ch,_sr="reference",_ty="exon",_st=ex[0]+1,_en=ex[1], # `+1` because gff is 1-based
_sc=".",_stnd=transcript_dict_ref[tr].strand, _ph=".",
_attr="exon_id=exon:{}_{};Parent=transcript:{};rank={}".format(ex[0]+1, ex[1],tr, exon_idx )))
exon_idx += 1
iso_kp += 1
if len(gff_tmp)>0 and ge in gene_to_transcript:
gff_tmp.insert(0,gff3_fmt.format(_ch=ch,_sr="FLAMES",_ty="gene",
_st=mi+1,
_en=ma,
_sc=".",_stnd=transcript_dict[gene_to_transcript[ge][0]].strand, _ph=".",
_attr="ID=gene:{};gene_id={};support_count={}".format(ge, ge, total_cnt)))
gff_rec.extend(gff_tmp)
elif len(gff_tmp)>0:
gff_tmp.insert(0,gff3_fmt.format(_ch=ch,_sr="FLAMES",_ty="gene",
_st=mi+1,
_en=ma,
_sc=".",_stnd=transcript_dict_ref[gene_to_transcript_ref[ge][0]].strand, _ph=".",
_attr="ID=gene:{};gene_id={};support_count={}".format(ge, ge, total_cnt)))
gff_rec.extend(gff_tmp)
iso_annotated = open(isoform_out,"w")
iso_annotated.write("##gff-version 3\n")
iso_annotated.write("\n".join(gff_rec))
iso_annotated.close()
prt = "\tAfter filtering: kept {} isoforms. removed {} isoforms.".format(
iso_kp,
iso_rm
)
if verbose:
print(prt)
annotate_full_splice_match(transcript_to_exon,transcript_to_exon_ref,transcript_dict,transcript_dict_ref,anno_out,tr_cnt,min_sup_reads)
def sc_long_pipeline(args):
# parse configuration file
if os.path.isfile(args.config_file):
print("Use config file: {}".format(args.config_file))
config_dict = parse_json_config(args.config_file)
elif os.path.isfile(os.path.join(sys.path[0], args.config_file)):
print("Use config file: {}".format(os.path.join(sys.path[0], args.config_file)))
config_dict = parse_json_config(os.path.join(sys.path[0], args.config_file))
else:
print("Cannot find config file in current directory or script depository: {}".format(args.config_file))
exit()
print_config(config_dict)
# check if files exist
if args.downsample_ratio>1 or args.downsample_ratio<=0:
print("downsample_ratio shoulw between 0 and 1: {}".format(args.downsample_ratio))
exit()
if not (os.path.isfile(args.infq) and os.path.isfile(args.gff3) and os.path.isfile(args.genomefa)):
print("make sure all file exists:")
print(args.infq)
print(args.gff3)
print(args.genomefa)
exit()
if not os.path.exists(args.outdir):
os.makedirs(args.outdir)
print("output directory not exist, create one:")
print(args.outdir)
if args.inbam != "" and (not os.path.isfile(args.inbam)):
print("make sure input inbam file exists:")
print(args.inbam)
exit()
# output files:
isoform_gff3 = os.path.join(args.outdir, "isoform_annotated.gff3")
isoform_gff3_f = os.path.join(args.outdir, "isoform_annotated.filtered.gff3")
FSM_anno_out = os.path.join(args.outdir, "isoform_FSM_annotation.csv")
raw_splice_isoform = os.path.join(args.outdir, "splice_raw.gff3")
tss_tes_stat = os.path.join(args.outdir, "tss_tes.bedgraph")
transcript_fa = os.path.join(args.outdir, "transcript_assembly.fa")
transcript_fa_idx = os.path.join(args.outdir, "transcript_assembly.fa.fai")
tmp_bam = os.path.join(args.outdir, "tmp.align.bam")
tmp_bed = os.path.join(args.outdir, "tmp.splice_anno.bed12")
genome_bam = os.path.join(args.outdir, "align2genome.bam")
realign_bam = os.path.join(args.outdir, "realign2transcript.bam")
tr_cnt_csv = os.path.join(args.outdir, "transcript_count.csv.gz")
tr_badcov_cnt_csv = os.path.join(args.outdir, "transcript_count.bad_coverage.csv.gz")
print "Input parameters:"
print "\tgene annotation:", args.gff3
print "\tgenome fasta:", args.genomefa
if args.inbam != "":
print "\tinput bam:", args.inbam
genome_bam = args.inbam
else:
print "\tinput fastq:", args.infq
print "\toutput directory:", args.outdir
print "\tdirectory contains minimap2:", args.minimap2_dir
# align reads to genome
if args.inbam == "" and config_dict["pipeline_parameters"]["do_genome_alignment"]:
print "### align reads to genome using minimap2", datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
if config_dict["alignment_parameters"]["use_junctions"]:
gff3_to_bed12(args.minimap2_dir, args.gff3, tmp_bed)
minimap2_align(args.minimap2_dir, args.genomefa, args.infq, tmp_bam, no_flank=config_dict["alignment_parameters"]["no_flank"], bed12_junc=tmp_bed if config_dict["alignment_parameters"]["use_junctions"] else None)
samtools_sort_index(tmp_bam, genome_bam)
os.remove(tmp_bam)
if config_dict["alignment_parameters"]["use_junctions"]:
os.remove(tmp_bed)
else:
print "### skip aligning reads to genome", datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
# find isoform
print "### read gene annotation", datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
chr_to_gene, transcript_dict, gene_to_transcript, transcript_to_exon = parse_gff_tree(args.gff3)
transcript_to_junctions = {tr: blocks_to_junctions(transcript_to_exon[tr]) for tr in transcript_to_exon}
remove_similar_tr(transcript_dict, gene_to_transcript, transcript_to_exon)
gene_dict = get_gene_flat(gene_to_transcript, transcript_to_exon)
chr_to_blocks = get_gene_blocks(gene_dict, chr_to_gene, gene_to_transcript)
if config_dict["pipeline_parameters"]["do_isoform_identification"]:
print "### find isoforms", datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
group_bam2isoform(genome_bam, isoform_gff3, tss_tes_stat, "", chr_to_blocks, gene_dict, transcript_to_junctions, transcript_dict, args.genomefa,
config=config_dict["isoform_parameters"],
downsample_ratio=args.downsample_ratio,
raw_gff3=raw_splice_isoform if config_dict["global_parameters"]["generate_raw_isoform"] else None)
else:
print "### skip finding isoforms", datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
# get fasta
#print "### generate transcript fasta file", datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
chr_to_gene_i, transcript_dict_i, gene_to_transcript_i, transcript_to_exon_i = parse_gff_tree(isoform_gff3)
ref_dict = {"chr_to_gene":chr_to_gene, "transcript_dict":transcript_dict, "gene_to_transcript":gene_to_transcript, "transcript_to_exon":transcript_to_exon}
if not config_dict["realign_parameters"]["use_annotation"]:
ref_dict = None
get_transcript_seq(args.genomefa, transcript_fa, chr_to_gene_i, transcript_dict_i, gene_to_transcript_i, transcript_to_exon_i,ref_dict=ref_dict)
# realign to transcript using minimap2
if config_dict["pipeline_parameters"]["do_read_realignment"]:
print "### realign to transcript using minimap2", datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
minimap2_tr_align(args.minimap2_dir, transcript_fa, args.infq, tmp_bam)
samtools_sort_index(tmp_bam, realign_bam)
os.remove(tmp_bam)
else:
print "### skip read realignment", datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
# quantification
if config_dict["pipeline_parameters"]["do_transcript_quantification"]:
print "### generate transcript count matrix", datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
bc_tr_count_dict, bc_tr_badcov_count_dict, tr_kept = parse_realigned_bam(realign_bam, transcript_fa_idx, config_dict["isoform_parameters"]["Min_sup_cnt"], config_dict["transcript_counting"]["min_tr_coverage"], config_dict["transcript_counting"]["min_read_coverage"])
#realigned_bam_coverage(realign_bam, transcript_fa_idx, args.outdir)
tr_cnt = wrt_tr_to_csv(bc_tr_count_dict, transcript_dict_i, tr_cnt_csv, transcript_dict, config_dict["global_parameters"]["has_UMI"])
wrt_tr_to_csv(bc_tr_badcov_count_dict, transcript_dict_i, tr_badcov_cnt_csv, transcript_dict, config_dict["global_parameters"]["has_UMI"])
annotate_filter_gff(isoform_gff3,args.gff3,isoform_gff3_f,FSM_anno_out,tr_cnt,config_dict["isoform_parameters"]["Min_sup_cnt"])
else:
print "### skip transcript quantification", datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
def annotate_filter_gff(isoform_gff,ref_gff,isoform_out,anno_out,tr_cnt,min_sup_reads):
"""
combine FLAMES ouput with reference and filter out transcript by
realignment result
"""
gff3_fmt = "{_ch}\t{_sr}\t{_ty}\t{_st}\t{_en}\t{_sc}\t{_stnd}\t{_ph}\t{_attr}"
chr_to_gene, transcript_dict, gene_to_transcript, transcript_to_exon = parse_gff_tree(isoform_gff)
_, transcript_dict_ref, gene_to_transcript_ref, transcript_to_exon_ref = parse_gff_tree(ref_gff)
gff_rec = []
for ch in chr_to_gene:
for ge in chr_to_gene[ch]:
gff_tmp = []
total_cnt = 0
mi = 99999999999
ma = -1
for tr in gene_to_transcript[ge]:
if (tr in tr_cnt) and (tr_cnt[tr]>=min_sup_reads):
gff_tmp.append(gff3_fmt.format(_ch=ch,_sr="FLAMES",_ty="transcript",
_st=transcript_to_exon[tr][0][0]+1,
_en=transcript_to_exon[tr][-1][1],
_sc=".",_stnd=transcript_dict[tr].strand, _ph=".",
_attr="ID=transcript:{};transcript_id={};Parent=gene:{};support_count={}".format(tr,tr, ge, tr_cnt[tr])))
total_cnt += tr_cnt[tr]
mi = min(mi,transcript_to_exon[tr][0][0])
ma = max(ma,transcript_to_exon[tr][-1][1])
exon_idx = 1
for ex in transcript_to_exon[tr]:
gff_tmp.append(gff3_fmt.format(_ch=ch,_sr="FLAMES",_ty="exon",_st=ex[0]+1,_en=ex[1], # `+1` because gff is 1-based
_sc=".",_stnd=transcript_dict[tr].strand, _ph=".",
_attr="exon_id=exon:{}_{};Parent=transcript:{};rank={}".format(ex[0]+1, ex[1],tr, exon_idx )))
exon_idx += 1
if ge in gene_to_transcript_ref:
for tr in gene_to_transcript_ref[ge]:
if (tr not in transcript_dict) and (tr in tr_cnt) and (tr_cnt[tr]>=min_sup_reads): # not in FLAMES output but in tr count
gff_tmp.append(gff3_fmt.format(_ch=ch,_sr="reference",_ty="transcript",
_st=transcript_to_exon_ref[tr][0][0]+1,
_en=transcript_to_exon_ref[tr][-1][1],
_sc=".",_stnd=transcript_dict_ref[tr].strand, _ph=".",
_attr="ID=transcript:{};transcript_id={};Parent=gene:{};support_count={}".format(tr,tr, ge, tr_cnt[tr])))
total_cnt += tr_cnt[tr]
mi = min(mi,transcript_to_exon_ref[tr][0][0])
ma = max(ma,transcript_to_exon_ref[tr][-1][1])
exon_idx = 1
for ex in transcript_to_exon_ref[tr]:
gff_tmp.append(gff3_fmt.format(_ch=ch,_sr="reference",_ty="exon",_st=ex[0]+1,_en=ex[1], # `+1` because gff is 1-based
_sc=".",_stnd=transcript_dict_ref[tr].strand, _ph=".",
_attr="exon_id=exon:{}_{};Parent=transcript:{};rank={}".format(ex[0]+1, ex[1],tr, exon_idx )))
exon_idx += 1
if len(gff_tmp)>0:
gff_tmp.insert(0,gff3_fmt.format(_ch=ch,_sr="FLAMES",_ty="gene",
_st=mi+1,
_en=ma,
_sc=".",_stnd=transcript_dict[gene_to_transcript[ge][0]].strand, _ph=".",
_attr="ID=gene:{};gene_id={};support_count={}".format(ge, ge, total_cnt)))
gff_rec.extend(gff_tmp)
iso_annotated = open(isoform_out,"w")
iso_annotated.write("##gff-version 3\n")
iso_annotated.write("\n".join(gff_rec))
iso_annotated.close()
annotate_full_splice_match(transcript_to_exon,transcript_to_exon_ref,transcript_dict,transcript_dict_ref,anno_out,tr_cnt,min_sup_reads)
