Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Remove sample name parsing which doesn't work when directories have .… #100

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Remove sample name parsing which doesn't work when directories have .… #100

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d9d617a
Remove sample name parsing which doesn't work when directories have .…
ericenns Nov 28, 2017
c5bff33
Added in missing )
ericenns Dec 14, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions scripts/srst2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -311,7 +311,7 @@ def parse_fai(fai_file,db_type,delimiter):
return size, gene_clusters, unique_gene_symbols, unique_allele_symbols, gene_cluster_symbols


def read_pileup_data(pileup_file, size, prob_err, consensus_file = ""):
def read_pileup_data(pileup_file, size, prob_err, sample_name, consensus_file = ""):
with open(pileup_file) as pileup:
prob_success = 1 - prob_err # Set by user, default is prob_err = 0.01
hash_alignment = {}
Expand Down Expand Up @@ -450,7 +450,7 @@ def read_pileup_data(pileup_file, size, prob_err, consensus_file = ""):
elif consensus_file.split(".")[-2] == "all_consensus_alleles":
consensus_type = "consensus"
with open(consensus_file, "a") as consensus_outfile:
consensus_outfile.write(">{0}.{1} {2}\n".format(allele, consensus_type, pileup_file.split(".")[1].split("__")[1]))
consensus_outfile.write(">{0}.{1} {2}\n".format(allele, consensus_type, sample_name)
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

typo: missing )

outstring = consensus_seq + "\n"
consensus_outfile.write(outstring)

Expand Down Expand Up @@ -942,7 +942,7 @@ def dict_of_dicts_inverted_ind(dd):
def parse_scores(run_type,args,scores, hash_edge_depth,
avg_depth_allele, coverage_allele, mismatch_allele, indel_allele,
missing_allele, size_allele, next_to_del_depth_allele,
unique_cluster_symbols,unique_allele_symbols, pileup_file):
unique_cluster_symbols,unique_allele_symbols, pileup_file, sample_name):

# sort into hash for each gene locus
scores_by_gene = group_allele_dict_by_gene(dict( (allele,val) for (allele,val) in scores.items() \
Expand Down Expand Up @@ -1018,11 +1018,11 @@ def parse_scores(run_type,args,scores, hash_edge_depth,
if args.report_new_consensus or args.report_all_consensus:
new_alleles_filename = args.output + ".new_consensus_alleles.fasta"
allele_pileup_file = create_allele_pileup(results[gene][0], pileup_file)
read_pileup_data(allele_pileup_file, size_allele, args.prob_err, consensus_file = new_alleles_filename)
read_pileup_data(allele_pileup_file, size_allele, args.prob_err, sample_name, consensus_file = new_alleles_filename)
if args.report_all_consensus:
new_alleles_filename = args.output + ".all_consensus_alleles.fasta"
allele_pileup_file = create_allele_pileup(results[gene][0], pileup_file)
read_pileup_data(allele_pileup_file, size_allele, args.prob_err, consensus_file = new_alleles_filename)
read_pileup_data(allele_pileup_file, size_allele, args.prob_err, sample_name, consensus_file = new_alleles_filename)

return results # (allele, diffs, depth_problem, divergence)

Expand Down Expand Up @@ -1419,7 +1419,7 @@ def map_fileSet_to_db(args, sample_name, fastq_inputs, db_name, fasta, size, gen
logging.info(' Processing SAMtools pileup...')
hash_alignment, hash_max_depth, hash_edge_depth, avg_depth_allele, coverage_allele, \
mismatch_allele, indel_allele, missing_allele, size_allele, next_to_del_depth_allele= \
read_pileup_data(pileup_file, size, args.prob_err)
read_pileup_data(pileup_file, size, args.prob_err, sample_name)

# Generate scores for all alleles (prints these and associated info if verbose)
# result = dict, with key=allele, value=score
Expand All @@ -1437,7 +1437,7 @@ def map_fileSet_to_db(args, sample_name, fastq_inputs, db_name, fasta, size, gen
allele_scores = parse_scores(run_type, args, scores, \
hash_edge_depth, avg_depth_allele, coverage_allele, mismatch_allele, \
indel_allele, missing_allele, size_allele, next_to_del_depth_allele,
unique_gene_symbols, unique_allele_symbols, pileup_file)
unique_gene_symbols, unique_allele_symbols, pileup_file, sample_name)

# REPORT/RECORD RESULTS

Expand Down