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

Jump to bottom

Fix filter bam naming bug #112

Merged
merged 2 commits into from
Apr 9, 2024
Merged

Fix filter bam naming bug #112

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d600745
fix filter bam using original reads name instead of qc reads name
AroneyS Apr 9, 2024
d2916f6
double unmapping group threads to 32
AroneyS Apr 9, 2024
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
10 changes: 5 additions & 5 deletions binchicken/workflow/coassemble.smk
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -473,7 +473,7 @@ rule qc_reads:
quality_cutoff = 15,
unqualified_percent_limit = 40,
min_length = 80,
threads: 16
threads: 32
resources:
mem_mb=get_mem_mb,
runtime = lambda wildcards, attempt: 4*60*attempt,
Expand Down Expand Up @@ -520,7 +520,7 @@ rule map_reads:
output:
dir = temp(directory(output_dir + "/mapping/{read}_coverm")),
group: "unmapping"
threads: 16
threads: 32
resources:
mem_mb=get_mem_mb,
runtime = lambda wildcards, attempt: 12*60*attempt,
Expand All @@ -547,10 +547,10 @@ rule filter_bam_files:
group: "unmapping"
params:
genomes = "{read}_reference.fna",
reads_1 = lambda wildcards: os.path.basename(config["reads_1"][wildcards.read]),
reads_1 = lambda wildcards: os.path.basename(config["reads_1"][wildcards.read]) if not config["run_qc"] else wildcards.read + "_1.fastq.gz",
sequence_identity = config["unmapping_max_identity"],
alignment_percent = config["unmapping_max_alignment"],
threads: 16
threads: 32
resources:
mem_mb=get_mem_mb,
runtime = lambda wildcards, attempt: 4*60*attempt,
Expand All @@ -577,7 +577,7 @@ rule bam_to_fastq:
reads_1 = output_dir + "/mapping/{read}_unmapped.1.fq.gz",
reads_2 = output_dir + "/mapping/{read}_unmapped.2.fq.gz",
group: "unmapping"
threads: 16
threads: 32
resources:
mem_mb=get_mem_mb,
runtime = lambda wildcards, attempt: 4*60*attempt,
Expand Down
61 changes: 61 additions & 0 deletions test/test_coassemble.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -345,6 +345,67 @@ def test_coassemble_taxa_of_interest(self):
with open(recover_path) as f:
self.assertEqual(expected, f.read())

def test_coassemble_unmap_runqc(self):
with in_tempdir():
cmd = (
f"binchicken coassemble "
f"--assemble-unmapped "
f"--run-qc "
f"--forward {SAMPLE_READS_FORWARD} "
f"--reverse {SAMPLE_READS_REVERSE} "
f"--genomes {GENOMES} "
f"--genome-transcripts {GENOME_TRANSCRIPTS} "
f"--sample-singlem {SAMPLE_SINGLEM} "
f"--sample-read-size {SAMPLE_READ_SIZE} "
f"--genome-singlem {GENOME_SINGLEM} "
f"--singlem-metapackage {METAPACKAGE} "
f"--output test "
f"--conda-prefix {path_to_conda} "
)
extern.run(cmd)

config_path = os.path.join("test", "config.yaml")
self.assertTrue(os.path.exists(config_path))

edges_path = os.path.join("test", "coassemble", "target", "targets.tsv")
self.assertTrue(os.path.exists(edges_path))

edges_path = os.path.join("test", "coassemble", "target", "elusive_edges.tsv")
self.assertTrue(os.path.exists(edges_path))

cluster_path = os.path.join("test", "coassemble", "target", "elusive_clusters.tsv")
self.assertTrue(os.path.exists(cluster_path))

qc_sample_1F_path = os.path.join("test", "coassemble", "qc", "sample_1_1.fastq.gz")
self.assertTrue(os.path.exists(qc_sample_1F_path))
qc_sample_1R_path = os.path.join("test", "coassemble", "qc", "sample_1_2.fastq.gz")
self.assertTrue(os.path.exists(qc_sample_1R_path))

qc_sample_2F_path = os.path.join("test", "coassemble", "qc", "sample_2_1.fastq.gz")
self.assertTrue(os.path.exists(qc_sample_2F_path))
qc_sample_2R_path = os.path.join("test", "coassemble", "qc", "sample_2_2.fastq.gz")
self.assertTrue(os.path.exists(qc_sample_2R_path))

qc_sample_3F_path = os.path.join("test", "coassemble", "qc", "sample_3_1.fastq.gz")
self.assertTrue(os.path.exists(qc_sample_3F_path))
qc_sample_3R_path = os.path.join("test", "coassemble", "qc", "sample_3_2.fastq.gz")
self.assertTrue(os.path.exists(qc_sample_3R_path))

map_sample_1F_path = os.path.join("test", "coassemble", "mapping", "sample_1_unmapped.1.fq.gz")
self.assertTrue(os.path.exists(map_sample_1F_path))
map_sample_1R_path = os.path.join("test", "coassemble", "mapping", "sample_1_unmapped.2.fq.gz")
self.assertTrue(os.path.exists(map_sample_1R_path))

map_sample_2F_path = os.path.join("test", "coassemble", "mapping", "sample_2_unmapped.1.fq.gz")
self.assertTrue(os.path.exists(map_sample_2F_path))
map_sample_2R_path = os.path.join("test", "coassemble", "mapping", "sample_2_unmapped.2.fq.gz")
self.assertTrue(os.path.exists(map_sample_2R_path))

map_sample_3F_path = os.path.join("test", "coassemble", "mapping", "sample_3_unmapped.1.fq.gz")
self.assertTrue(os.path.exists(map_sample_3F_path))
map_sample_3R_path = os.path.join("test", "coassemble", "mapping", "sample_3_unmapped.2.fq.gz")
self.assertTrue(os.path.exists(map_sample_3R_path))

def test_coassemble_query_input(self):
with in_tempdir():
cmd = (
Expand Down
Loading