exon_num = int(options.exon_num)
start_time = time.time()
print "Run start:"
#######################################
make_dir(out_dir)
#gtf_outdir=out_dir+'/'+'gtf'
#tid_gid_file=gtf_outdir+"/"+"tid_gid"
#make_dir(gtf_outdir)
snc_gtf = out_dir + "/" + 'filter_out_noncoding.gtf'
lnc_gtf = out_dir + "/" + 'novel_lincRNA.gtf'
coding_gtf = out_dir + "/" + 'novel_coding.gtf'
cnc_gtf = out_dir + "/" + 'ambiguous_genes.gtf'
Gene_Info = out_dir + '/compare_2_infor.txt'
###################################
gtf = Gtf(gtf_input)
tid_gid = gtf.get_tid_gid()
#index_content=Table(index_file,0,False)
#index_content.write_to_file('index_content')
#transform_index_content=index_content.cal(index_transform,'row')
#transform_index=Table.build_table(1,['tid','cnc_type','score','start','end','length'],transform_index_content)
transform_index = Table(index_file, 1, True)
transform_index.left_join(1, tid_gid, 1)
gid_cnctype = transform_index.get_col('gid', 'index')
gid_cnctype = gid_cnctype.de_redundency()
gid_cnctype = gid_cnctype.key_by('gid', 'index')
elif overlap_noncoding!="":
return overlap_noncoding
else:
return "-"
else:
return "-"
(coding_ref_input,noncoding_ref_input,out_dir,combined_gtf_input)=fetch_args()
start_time=time.time()
print "Classification start:"
(cuffcompare_outdir,gtf_outdir)=prepare_dirs(out_dir)
(coding_ref,noncoding_ref,combined_gtf)=fetch_gtfs(
coding_ref_input, noncoding_ref_input,
combined_gtf_input, cuffcompare_outdir)
gtf=Gtf.simple_read(combined_gtf_input)
tid_gid=gtf.get_tid_gid()
gid_tid=tid_gid.key_by([2],[1])
all_gids=gid_tid.getCol(1)
print "Input genes: ", len(all_gids)
print "Running Cuffcompare ..."
strand_coding_tmap=cuffcompare(coding_ref_input,combined_gtf_input,cuffcompare_outdir+'/strandc')
strand_coding_tmap.update_col('cuff_gene_id',gtf.get_gid(strand_coding_tmap.getCol('cuff_id')))
strand_noncoding_tmap=cuffcompare(noncoding_ref_input,combined_gtf_input,cuffcompare_outdir+'/strandnc')
strand_noncoding_tmap.update_col('cuff_gene_id',gtf.get_gid(strand_noncoding_tmap.getCol('cuff_id')))
coding_tmap=cuffcompare(coding_ref,combined_gtf,cuffcompare_outdir+'/coding')
coding_tmap.update_col('cuff_gene_id',gtf.get_gid(coding_tmap.getCol('cuff_id')))
exon_num=int(options.exon_num)
start_time = time.time()
print "Run start:"
#######################################
make_dir(out_dir)
#gtf_outdir=out_dir+'/'+'gtf'
#tid_gid_file=gtf_outdir+"/"+"tid_gid"
#make_dir(gtf_outdir)
snc_gtf=out_dir+"/"+'filter_out_noncoding.gtf'
lnc_gtf=out_dir+"/"+'novel_lincRNA.gtf'
coding_gtf=out_dir+"/"+'novel_coding.gtf'
cnc_gtf=out_dir+"/"+'ambiguous_genes.gtf'
Gene_Info = out_dir + '/compare_2_infor.txt'
###################################
gtf=Gtf(gtf_input)
tid_gid=gtf.get_tid_gid()
#index_content=Table(index_file,0,False)
#index_content.write_to_file('index_content')
#transform_index_content=index_content.cal(index_transform,'row')
#transform_index=Table.build_table(1,['tid','cnc_type','score','start','end','length'],transform_index_content)
transform_index=Table(index_file,1,True)
transform_index.left_join(1,tid_gid,1)
gid_cnctype=transform_index.get_col('gid','index')
gid_cnctype=gid_cnctype.de_redundency()
return overlap_noncoding
else:
return "-"
else:
return "-"
(coding_ref_input, noncoding_ref_input, out_dir,
combined_gtf_input) = fetch_args()
start_time = time.time()
print "Classification start:"
(cuffcompare_outdir, gtf_outdir) = prepare_dirs(out_dir)
(coding_ref, noncoding_ref,
combined_gtf) = fetch_gtfs(coding_ref_input, noncoding_ref_input,
combined_gtf_input, cuffcompare_outdir)
gtf = Gtf.simple_read(combined_gtf_input)
tid_gid = gtf.get_tid_gid()
gid_tid = tid_gid.key_by([2], [1])
all_gids = gid_tid.getCol(1)
print "Input genes: ", len(all_gids)
print "Running Cuffcompare ..."
strand_coding_tmap = cuffcompare(coding_ref_input, combined_gtf_input,
cuffcompare_outdir + '/strandc')
strand_coding_tmap.update_col(
'cuff_gene_id', gtf.get_gid(strand_coding_tmap.getCol('cuff_id')))
strand_noncoding_tmap = cuffcompare(noncoding_ref_input, combined_gtf_input,
cuffcompare_outdir + '/strandnc')
strand_noncoding_tmap.update_col(
'cuff_gene_id', gtf.get_gid(strand_noncoding_tmap.getCol('cuff_id')))
