def test_pruning_plotjob(self, new_pipegraph):
jobA = register_qc(ppg.PlotJob("c.png", lambda: None, lambda: None))
assert not jobA._pruned
prune_qc()
assert jobA._pruned
assert jobA.cache_job._pruned
assert jobA.table_job._pruned
def test_registration_and_pruning(self, new_pipegraph):
with pytest.raises(TypeError):
register_qc("shu")
jobA = ppg.FileGeneratingJob("a",
lambda: Path("a").write_text("hello"))
register_qc(jobA)
print(list(get_qc_jobs()))
assert jobA in list(get_qc_jobs())
assert not jobA._pruned
jobc = register_qc(
ppg.FileGeneratingJob("c", lambda: Path("b").write_text("hello")))
def check_prune(job):
return job.job_id.lower()[-1] == "c"
prune_qc(check_prune)
assert jobc in list(get_qc_jobs())
assert not jobc._pruned
jobB = register_qc(
ppg.FileGeneratingJob("b", lambda: Path("b").write_text("hello")))
assert jobB in list(get_qc_jobs())
assert jobB._pruned
jobC = register_qc(
ppg.FileGeneratingJob("C", lambda: Path("b").write_text("hello")))
assert not jobC._pruned
assert len(list(get_qc_jobs())) == 4
prune_qc()
assert jobA._pruned
assert jobB._pruned
assert jobc._pruned
assert jobC._pruned
for j in get_qc_jobs():
assert j._pruned
def test_volcano_plot(self):
ppg.util.global_pipegraph.quiet = False
import mbf_sampledata
pasilla_data = pd.read_csv(
mbf_sampledata.get_sample_path(
"mbf_comparisons/pasillaCount_deseq2.tsv.gz"),
sep=" ",
)
# pasilla_data = pasilla_data.set_index('Gene')
pasilla_data.columns = [str(x) for x in pasilla_data.columns]
treated = [x for x in pasilla_data.columns if x.startswith("treated")]
untreated = [
x for x in pasilla_data.columns if x.startswith("untreated")
]
pasilla_data = DelayedDataFrame("pasilla", pasilla_data)
comp = Comparisons(pasilla_data, {
"treated": treated,
"untreated": untreated
}).a_vs_b("treated", "untreated", TTest())
comp.filter([("log2FC", "|>=", 2.0), ("FDR", "<=", 0.05)])
prune_qc(lambda job: "volcano" in job.job_id)
run_pipegraph()
qc_jobs = list(get_qc_jobs())
qc_jobs = [x for x in qc_jobs if not x._pruned]
print(qc_jobs)
assert len(qc_jobs) == 1
assert_image_equal(qc_jobs[0].filenames[0])
def test_align_and_extract_umis(new_pipegraph):
from mbf_align.post_process import AnnotateFastqBarcodes
for folder in [
get_sample_path(Path("mbf_align/sample_extract_barcodes")),
get_sample_path(Path("mbf_align/sample_extract_barcodes_gz")),
]:
new_pipegraph.new_pipegraph()
genome = get_human_22_fake_genome()
mbf_qualitycontrol.prune_qc(lambda _: False)
r = Sample("test",
str(folder),
False,
pairing="only_second",
vid="AA123")
al = AlignedSample("test", str(folder / "test.bam"), genome, False,
"AA123")
x = al.post_process(
AnnotateFastqBarcodes(r, {
"XC": [0, 4],
"XM": [7, 7 + 4]
}))
ppg.run_pipegraph()
f = x.get_bam()
r = next(f.fetch())
print(r.tags)
assert r.get_tag("XC") == "AGTC"
assert r.get_tag("XM") == "TGAC"
def test_subtraction_by_read(self):
from mbf_sampledata import get_human_22_fake_genome
genome = get_human_22_fake_genome()
lane = mbf_align.AlignedSample(
"test_lane",
get_sample_data(Path("mbf_align/rnaseq_spliced_chr22.bam")),
genome,
False,
"AA123",
) # index creation is automatic
lane2 = mbf_align.AlignedSample(
"test_lane2",
get_sample_data(Path("mbf_align/rnaseq_spliced_chr22.bam")),
genome,
False,
"AA124",
) # index creation is automatic
lane3 = mbf_align.AlignedSample(
"test_lane3",
get_sample_data(Path("mbf_align/chipseq_chr22.bam")),
genome,
False,
"AA123",
) # index creation is automatic
lane3_subset = mbf_align.AlignedSample(
"test_lane3_subset",
get_sample_data(Path("mbf_align/chipseq_chr22_subset.bam")),
genome,
False,
"AA123",
) # index creation is automatic
lane_empty = lane.post_process(
mbf_align.post_process.SubtractOtherLane(lane2), new_name="empty")
lane_full = lane.post_process(
mbf_align.post_process.SubtractOtherLane(lane3), new_name="full")
lane_some = lane3.post_process(
mbf_align.post_process.SubtractOtherLane(lane3_subset),
result_dir="results/aligned/shu",
)
qc_jobs = [
lane_some.post_processor_qc_jobs, lane_full.post_processor_qc_jobs
]
prune_qc(lambda job: job in qc_jobs)
ppg.run_pipegraph()
assert Path(lane_empty.get_bam_names()[1]).exists()
assert Path(lane_full.get_bam_names()[1]).exists()
assert lane_empty.mapped_reads() == 0
assert lane_full.mapped_reads() == lane.mapped_reads()
assert lane.mapped_reads() != 0
assert (lane_some.mapped_reads() == lane3.mapped_reads() -
lane3_subset.mapped_reads())
assert lane3_subset.mapped_reads(
) # make sure there was something to subtract
assert "shu" in lane_some.get_bam_names()[0]
assert_image_equal(qc_jobs[0].filenames[0], "_result_dir")
assert_image_equal(qc_jobs[0].filenames[0])
def _test_qc_plots(self, filename, remaining_job_count, chdir="."):
lane = self.prep_lane()
prune_qc(lambda job: filename in job.job_id)
not_pruned_count = sum([1 for x in get_qc_jobs() if not x._pruned])
assert not_pruned_count == remaining_job_count # plot cache, plot_table, plot
ppg.run_pipegraph()
if chdir == '..':
fn = lane.result_dir / chdir / filename
else:
fn = lane.result_dir / chdir / f"{lane.name}_{filename}"
assert_image_equal(fn, suffix="_" + filename)
def test_ma_plot(self):
ppg.util.global_pipegraph.quiet = False
pasilla_data, treated, untreated = get_pasilla_data_subset()
import numpy
numpy.random.seed(500)
comp = Comparisons(pasilla_data, {
"treated": treated,
"untreated": untreated
}).a_vs_b("treated", "untreated", TTest(), laplace_offset=1)
comp.filter([
("log2FC", "|>=", 2.0),
# ('FDR', '<=', 0.05),
])
prune_qc(lambda job: "ma_plot" in job.job_id)
run_pipegraph()
qc_jobs = list(get_qc_jobs())
qc_jobs = [x for x in qc_jobs if not x._pruned]
assert len(qc_jobs) == 1
assert_image_equal(qc_jobs[0].filenames[0])
def test_correlation(self):
ppg.util.global_pipegraph.quiet = False
import mbf_sampledata
pasilla_data = pd.read_csv(
mbf_sampledata.get_sample_path(
"mbf_comparisons/pasillaCount_deseq2.tsv.gz"),
sep=" ",
)
# pasilla_data = pasilla_data.set_index('Gene')
pasilla_data.columns = [str(x) for x in pasilla_data.columns]
treated = [x for x in pasilla_data.columns if x.startswith("treated")]
untreated = [
x for x in pasilla_data.columns if x.startswith("untreated")
]
pasilla_data = DelayedDataFrame("pasilla", pasilla_data)
Comparisons(pasilla_data, {"treated": treated, "untreated": untreated})
prune_qc(lambda job: "correlation" in job.job_id)
run_pipegraph()
qc_jobs = list(get_qc_jobs())
qc_jobs = [x for x in qc_jobs if not x._pruned]
print(qc_jobs)
assert len(qc_jobs) == 1
assert_image_equal(qc_jobs[0].filenames[0])