Mercurial > repos > dvanzessen > bcbio_nextgen_emc

comparison script.py @ 8:2e5223259a56 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author dvanzessen
date Tue, 21 Apr 2020 11:38:36 +0000
parents 2ed60a09d6b6
children
comparison
equal deleted inserted replaced
7:7d5b46d41ff0 8:2e5223259a56
37 bed_file_path = bed_new_file_path 37 bed_file_path = bed_new_file_path
38 38
39 input_files = [] 39 input_files = []
40 phenotype_counter = Counter() 40 phenotype_counter = Counter()
41 for input_file in input_files_raw: 41 for input_file in input_files_raw:
42 if input_file.find(":"): 42 if input_file.count(":") == 1: # single end
43 forward_file, phenotype = input_file.split(":")
44 phenotype_counter.update(phenotype)
45 phenotype_count = phenotype_counter[phenotype]
46
47 forward_new_name = "{phenotype}_{phenotype_count}.fastq.gz".format(phenotype=phenotype, phenotype_count=phenotype_count)
48 forward_new_file_path = os.path.join(
49 workdir,
50 forward_new_name
51 )
52 os.symlink(forward_file, forward_new_file_path)
53
54 input_files.append(
55 {
56 "forward": forward_new_file_path,
57 "description": "{phenotype}_{phenotype_index}".format(phenotype=phenotype, phenotype_index=phenotype_count),
58 "phenotype": phenotype
59 }
60 )
61
62 elif input_file.count(":") == 2: # paired end
43 forward_file, reverse_file, phenotype = input_file.split(":") 63 forward_file, reverse_file, phenotype = input_file.split(":")
44 phenotype_counter.update(phenotype) 64 phenotype_counter.update(phenotype)
45 phenotype_count = phenotype_counter[phenotype] 65 phenotype_count = phenotype_counter[phenotype]
46 66
47 forward_new_name = "{phenotype}_{phenotype_count}_R1.fastq.gz".format(phenotype=phenotype, phenotype_count=phenotype_count) 67 forward_new_name = "{phenotype}_{phenotype_count}_R1.fastq.gz".format(phenotype=phenotype, phenotype_count=phenotype_count)