def gatk_test_lanes():
genome_human = mbf_genomes.EnsemblGenome("Homo_sapiens", 96)
input_samples = [
[
mbf_align.AlignedSample(
"Test1GATK",
"/project/code/mvariants/data/base_raw_test_hg36_Subread_gatk_rg.bam",
genome_human,
is_paired=False,
vid=None,
)
],
[
mbf_align.AlignedSample(
"Test2GATK",
"data/base_raw_test_hg3612_Subread_gatk_rg.bam",
genome_human,
is_paired=False,
vid=None,
)
],
]
return input_samples
work_dir = Path("_benchmark_read_counting")
work_dir.mkdir(exist_ok=True)
os.chdir(work_dir)
bam_name = (Path("results") / "aligned" / "STAR_2.6.1d" /
"Drosophila_melanogaster_94" / "ERR2984187" / "ERR2984187.bam")
if not bam_name.exists():
# leverage pipeline to get some sample data
import mbf_align
import mbf_externals
ppg.new_pipegraph()
genome = mbf_genomes.EnsemblGenome("Drosophila_melanogaster", 94)
aligner = mbf_externals.aligners.STAR()
# just some random drospohila lane.
samples = {"ERR2984187": "ERR2984187"}
raw = {
name: mbf_align.Sample(
name,
mbf_align.strategies.FASTQsFromAccession(err),
reverse_reads=False,
pairing="only_first",
)
for name, err in samples.items()
}
aligned = {
def gatk_preprocessor(tmpdir):
genome_human = mbf_genomes.EnsemblGenome("Homo_sapiens", 96)
preprocessor = GATKPreprocess(genome=genome_human,
name="TestGATK_Preprocessor",
cache_dir=tmpdir)
return preprocessor
def test_mutect_init():
with pytest.raises(ValueError):
Mutect2("this has no genome")
genome_human = mbf_genomes.EnsemblGenome("Homo_sapiens", 96)
Mutect2(genome=genome_human)
import mbf_genomes
import subprocess
genome = mbf_genomes.EnsemblGenome('Homo_sapiens', 94)
allowed = set(['22'])
genes = genome.df_genes[genome.df_genes['chr'].isin(allowed)]
transcripts = genome.df_transcripts[genome.df_transcripts['chr'].isin(allowed)]
genes.to_msgpack("hs_22_genes.msgpack")
transcripts.to_msgpack("hs_22_transcripts.msgpack")
subprocess.check_call(['gzip', 'hs_22_genes.msgpack'])
subprocess.check_call(['gzip', 'hs_22_transcripts.msgpack'])