split sample id replicates on last _ (in case user sample_ids include underscores) (9f96a19f) · Commits · Chaos / Cutandrun

bin/lib/reports.py

+3 −3

Original line number	Diff line number	Diff line
		@@ -70,7 +70,7 @@ class Reports:
		dt_frag_i = pd.read_csv(dt_frag_list[i], sep='\t', header=None, names=['Size','Occurrences'])
		frag_base_i = os.path.basename(dt_frag_list[i])
		sample_id = frag_base_i.split(".")[0]
		sample_id_split = sample_id.split("_")
		sample_id_split = sample_id.rsplit("_", 1)
		rep_i = sample_id_split[len(sample_id_split)-1]
		group_i ="_".join(sample_id_split[0:(len(sample_id_split)-1)])

		@@ -133,7 +133,7 @@ class Reports:
		seacr_bed_i = pd.read_csv(seacr_bed_list[i], sep='\t', header=None, usecols=[0,1,2,3,4], names=['chrom','start','end','total_signal','max_signal'])
		bed_base_i = os.path.basename(seacr_bed_list[i])
		sample_id = bed_base_i.split(".")[0]
		sample_id_split = sample_id.split("_")
		sample_id_split = sample_id.rsplit("_", 1)
		rep_i = sample_id_split[len(sample_id_split)-1]
		group_i ="_".join(sample_id_split[0:(len(sample_id_split)-1)])
		seacr_bed_i['group'] = np.repeat(group_i, seacr_bed_i.shape[0])
		@@ -215,7 +215,7 @@ class Reports:
		self.bam_df_list.append(bam_now)
		bam_base = os.path.basename(bam)
		sample_id = bam_base.split(".")[0]
		[group_now,rep_now] = sample_id.split("_")
		[group_now,rep_now] = sample_id.rsplit("_", 1)
		self.frip.at[k, 'group'] = group_now
		self.frip.at[k, 'replicate'] = rep_now
		self.frip.at[k, 'mapped_frags'] = bam_now.shape[0]