def test_var_eff_pred_varseq():
if sys.version_info[0] == 2:
pytest.skip("rbp example not supported on python 2 ")
model_dir = "examples/var_seqlen_model/"
if INSTALL_REQ:
install_model_requirements(model_dir, "dir", and_dataloaders=True)
#
model = kipoi.get_model(model_dir, source="dir")
# The preprocessor
Dataloader = kipoi.get_dataloader_factory(model_dir, source="dir")
#
dataloader_arguments = {
"fasta_file": "example_files/hg38_chr22.fa",
"preproc_transformer": "dataloader_files/encodeSplines.pkl",
"gtf_file": "example_files/gencode_v25_chr22.gtf.pkl.gz",
"intervals_file": "example_files/variant_centered_intervals.tsv"
}
vcf_path = "example_files/variants.vcf"
out_vcf_fpath = "example_files/variants_generated.vcf"
ref_out_vcf_fpath = "example_files/variants_ref_out.vcf"
#
with cd(model.source_dir):
vcf_path = kipoi.postprocessing.variant_effects.ensure_tabixed_vcf(
vcf_path)
model_info = kipoi.postprocessing.variant_effects.ModelInfoExtractor(
model, Dataloader)
writer = kipoi.postprocessing.variant_effects.VcfWriter(
model, vcf_path, out_vcf_fpath)
vcf_to_region = None
with pytest.raises(Exception):
# This has to raise an exception as the sequence length is None.
vcf_to_region = kipoi.postprocessing.variant_effects.SnvCenteredRg(
model_info)
res = sp.predict_snvs(
model,
Dataloader,
vcf_path,
dataloader_args=dataloader_arguments,
evaluation_function=analyse_model_preds,
batch_size=32,
vcf_to_region=vcf_to_region,
evaluation_function_kwargs={'diff_types': {
'diff': Diff("mean")
}},
sync_pred_writer=writer)
writer.close()
# pass
# assert filecmp.cmp(out_vcf_fpath, ref_out_vcf_fpath)
compare_vcfs(out_vcf_fpath, ref_out_vcf_fpath)
os.unlink(out_vcf_fpath)
def test_var_eff_pred2():
if sys.version_info[0] == 2:
pytest.skip("rbp example not supported on python 2 ")
# Take the rbp model
model_dir = "examples/rbp/"
if INSTALL_REQ:
install_model_requirements(model_dir, "dir", and_dataloaders=True)
#
model = kipoi.get_model(model_dir, source="dir")
# The preprocessor
Dataloader = kipoi.get_dataloader_factory(model_dir, source="dir")
#
dataloader_arguments = {
"fasta_file": "example_files/hg38_chr22.fa",
"preproc_transformer": "dataloader_files/encodeSplines.pkl",
"gtf_file": "example_files/gencode_v25_chr22.gtf.pkl.gz",
}
#
# Run the actual predictions
vcf_path = "example_files/variants.vcf"
out_vcf_fpath = "example_files/variants_generated2.vcf"
ref_out_vcf_fpath = "example_files/variants_ref_out2.vcf"
restricted_regions_fpath = "example_files/restricted_regions.bed"
#
with cd(model.source_dir):
pbd = pb.BedTool(restricted_regions_fpath)
model_info = kipoi.postprocessing.variant_effects.ModelInfoExtractor(
model, Dataloader)
vcf_to_region = kipoi.postprocessing.variant_effects.SnvPosRestrictedRg(
model_info, pbd)
writer = kipoi.postprocessing.variant_effects.utils.io.VcfWriter(
model, vcf_path, out_vcf_fpath)
res = sp.predict_snvs(
model,
Dataloader,
vcf_path,
dataloader_args=dataloader_arguments,
evaluation_function=analyse_model_preds,
batch_size=32,
vcf_to_region=vcf_to_region,
evaluation_function_kwargs={'diff_types': {
'diff': Diff("mean")
}},
sync_pred_writer=writer)
writer.close()
# pass
#assert filecmp.cmp(out_vcf_fpath, ref_out_vcf_fpath)
compare_vcfs(out_vcf_fpath, ref_out_vcf_fpath)
os.unlink(out_vcf_fpath)
def test_predict_variants_example_single_model(file_format, tmpdir):
"""kipoi predict ...
"""
if sys.version_info[0] == 2:
pytest.skip(
"Only rbp example testable at the moment, which only runs on py3")
examples = "rbp", "non_bedinput_model"
example_dirs = ["tests/models/{0}/".format(ex) for ex in examples]
main_example_dir = example_dirs[1]
tmpdir_here = tmpdir.mkdir("example")
# non_bedinput_model is not compatible with restricted bed files as
# alterations in region generation have no influence on that model
tmpfile = str(tmpdir_here.join("out.{0}".format(file_format)))
vcf_tmpfile = str(tmpdir_here.join("out.{0}".format("vcf")))
dataloader_kwargs = {
"fasta_file": "example_files/hg38_chr22.fa",
"preproc_transformer": "dataloader_files/encodeSplines.pkl",
"gtf_file": "example_files/gencode_v25_chr22.gtf.pkl.gz",
"intervals_file": "example_files/variant_intervals.tsv"
}
dataloader_kwargs = {
k: main_example_dir + v
for k, v in dataloader_kwargs.items()
}
import json
dataloader_kwargs_str = json.dumps(dataloader_kwargs)
args = [
"python",
os.path.abspath("./kipoi_veff/cli.py"),
"score_variants",
# "./", # directory
example_dirs[1],
"--source=dir",
"--batch_size=4",
"--dataloader_args='%s'" % dataloader_kwargs_str,
"--input_vcf",
main_example_dir + "/example_files/variants.vcf",
# this one was now gone in the master?!
"--output_vcf",
vcf_tmpfile,
"--extra_output",
tmpfile
]
# run the
if INSTALL_FLAG:
args.append(INSTALL_FLAG)
# run the command
kipoi_veff.cli.cli_score_variants('score_variants', args[3:])
for example_dir in example_dirs[1:2]:
# assert filecmp.cmp(example_dir + "/example_files/variants_ref_out.vcf", vcf_tmpfile)
model_name_safe = example_dir.replace("/", "_")
vcf_tmpfile_model = vcf_tmpfile
assert os.path.exists(vcf_tmpfile_model)
compare_vcfs(example_dir + "/example_files/variants_ref_out.vcf",
vcf_tmpfile_model)
ending = tmpfile.split('.')[-1]
extra_output = tmpfile
assert os.path.exists(extra_output)
if file_format == "hdf5":
data = HDF5Reader.load(extra_output)
else:
data = pd.read_table(extra_output)
def test_predict_variants_example_multimodel(file_format, tmpdir):
"""kipoi predict ...
"""
if sys.version_info[0] == 2:
pytest.skip(
"Only rbp example testable at the moment, which only runs on py3")
examples = "rbp", "non_bedinput_model"
example_dirs = ["examples/{0}/".format(ex) for ex in examples]
main_example_dir = example_dirs[1]
tmpdir_here = tmpdir.mkdir("example")
# non_bedinput_model is not compatible with restricted bed files as
# alterations in region generation have no influence on that model
tmpfile = str(tmpdir_here.join("out.{0}".format(file_format)))
vcf_tmpfile = str(tmpdir_here.join("out.{0}".format("vcf")))
dataloader_kwargs = {
"fasta_file": "example_files/hg38_chr22.fa",
"preproc_transformer": "dataloader_files/encodeSplines.pkl",
"gtf_file": "example_files/gencode_v25_chr22.gtf.pkl.gz",
"intervals_file": "example_files/variant_intervals.tsv"
}
dataloader_kwargs = {
k: main_example_dir + v
for k, v in dataloader_kwargs.items()
}
import json
dataloader_kwargs_str = json.dumps(dataloader_kwargs)
args = [
"python",
os.path.abspath("./kipoi/__main__.py"),
"postproc",
"score_variants",
# "./", # directory
example_dirs[0],
example_dirs[1],
"--source=dir",
"--batch_size=4",
"--dataloader_args='%s'" % dataloader_kwargs_str,
"--input_vcf",
main_example_dir + "/example_files/variants.vcf",
# this one was now gone in the master?!
"--output_vcf",
vcf_tmpfile,
"--extra_output",
tmpfile
]
# run the
if INSTALL_FLAG:
args.append(INSTALL_FLAG)
returncode = subprocess.call(args=args,
cwd=os.path.realpath(main_example_dir) +
"/../../")
assert returncode == 0
assert os.path.exists(tmpfile)
for example_dir in example_dirs:
# assert filecmp.cmp(example_dir + "/example_files/variants_ref_out.vcf", vcf_tmpfile)
vcf_tmpfile_model = vcf_tmpfile[:-4] + example_dir.replace(
"/", "_") + ".vcf"
assert os.path.exists(vcf_tmpfile_model)
compare_vcfs(example_dir + "/example_files/variants_ref_out.vcf",
vcf_tmpfile_model)
if file_format == "hdf5":
data = HDF5Reader.load(tmpfile)
else:
table_labels = []
table_starts = []
table_ends = []
tables = {}
head_line_id = "KPVEP_"
with open(tmpfile, "r") as ifh:
for i, l in enumerate(ifh):
if head_line_id in l:
if (len(table_starts) > 0):
table_ends.append(i - 1)
table_labels.append(l.rstrip()[len(head_line_id):])
table_starts.append(i + 1)
table_ends.append(i)
for label, start, end in zip(table_labels, table_starts, table_ends):
tables[label] = pd.read_csv(tmpfile,
sep="\t",
skiprows=start,
nrows=end - start,
index_col=0)
def test_predict_variants_example(example, restricted_bed, file_format,
new_dataloader_kwargs_format, tmpdir):
"""kipoi predict ...
"""
if (example not in {"rbp", "non_bedinput_model"}) or (sys.version_info[0]
== 2):
pytest.skip(
"Only rbp example testable at the moment, which only runs on py3")
example_dir = "tests/models/{0}/".format(example)
tmpdir_here = tmpdir.mkdir("example")
# non_bedinput_model is not compatible with restricted bed files as
# alterations in region generation have no influence on that model
if restricted_bed and (example != "rbp"):
pytest.skip("Resticted_bed only available for rbp_eclip")
tmpfile = str(tmpdir_here.join("out.{0}".format(file_format)))
vcf_tmpfile = str(tmpdir_here.join("out.{0}".format("vcf")))
dataloader_kwargs = {
"fasta_file": "example_files/hg38_chr22.fa",
"preproc_transformer": "dataloader_files/encodeSplines.pkl",
"gtf_file": "example_files/gencode_v25_chr22.gtf.pkl.gz",
"intervals_file": "example_files/variant_intervals.tsv"
}
dataloader_kwargs = {
k: example_dir + v
for k, v in dataloader_kwargs.items()
}
if not new_dataloader_kwargs_format:
import json
dataloader_kwargs_str = json.dumps(dataloader_kwargs)
args = [
"python",
os.path.abspath("./kipoi_veff/cli.py"),
"score_variants",
# "./", # directory
example_dir,
"--source=dir",
"--batch_size=4",
"--dataloader_args='%s'" % dataloader_kwargs_str,
"--input_vcf",
temp(example_dir + "/example_files/variants.vcf", tmpdir),
# this one was now gone in the master?!
"--output_vcf",
vcf_tmpfile,
"--extra_output",
tmpfile
]
else:
dataloader_kwargs_list = [
"{0}={1}".format(key, val)
for key, val in dataloader_kwargs.items()
]
args = [
"python",
os.path.abspath("./kipoi_veff/cli.py"),
"score_variants",
# "./", # directory
example_dir,
"--source=dir",
"--batch_size=4",
"--dataloader_args"
] + dataloader_kwargs_list + [
"--input_vcf",
temp(example_dir + "/example_files/variants.vcf", tmpdir),
# this one was now gone in the master?!
"--output_vcf",
vcf_tmpfile,
"--extra_output",
tmpfile
]
# run the
if INSTALL_FLAG:
args.append(INSTALL_FLAG)
if restricted_bed:
args += [
"--restriction_bed",
example_dir + "/example_files/restricted_regions.bed"
]
returncode = subprocess.call(args=args, cwd=".")
assert returncode == 0
assert os.path.exists(tmpfile)
assert os.path.exists(vcf_tmpfile)
if restricted_bed:
# assert filecmp.cmp(example_dir + "/example_files/variants_ref_out2.vcf", vcf_tmpfile)
compare_vcfs(example_dir + "/example_files/variants_ref_out2.vcf",
vcf_tmpfile)
else:
# assert filecmp.cmp(example_dir + "/example_files/variants_ref_out.vcf", vcf_tmpfile)
compare_vcfs(example_dir + "/example_files/variants_ref_out.vcf",
vcf_tmpfile)
if file_format == "hdf5":
data = HDF5Reader.load(tmpfile)
else:
table_labels = []
table_starts = []
table_ends = []
tables = {}
head_line_id = "KPVEP_"
with open(tmpfile, "r") as ifh:
for i, l in enumerate(ifh):
if head_line_id in l:
if (len(table_starts) > 0):
table_ends.append(i - 1)
table_labels.append(l.rstrip()[len(head_line_id):])
table_starts.append(i + 1)
table_ends.append(i)
for label, start, end in zip(table_labels, table_starts, table_ends):
tables[label] = pd.read_csv(tmpfile,
sep="\t",
skiprows=start,
nrows=end - start,
index_col=0)