def test_run_cat1(self):
history_id = self.gi.histories.create_history(
name="test_run_cat1 history")["id"]
dataset1_id = self._test_dataset(history_id, contents="1 2 3")
dataset2_id = self._test_dataset(history_id, contents="4 5 6")
dataset3_id = self._test_dataset(history_id, contents="7 8 9")
tool_inputs = inputs().set("input1", dataset(dataset1_id)).set(
"queries",
repeat().instance(inputs().set(
"input2", dataset(dataset2_id))).instance(inputs().set(
"input2", dataset(dataset3_id))))
tool_output = self.gi.tools.run_tool(history_id=history_id,
tool_id="cat1",
tool_inputs=tool_inputs)
self.assertEqual(len(tool_output["outputs"]), 1)
def test_run_cat1(self):
history_id = self.gi.histories.create_history(name="test_run_cat1 history")["id"]
dataset1_id = self._test_dataset(history_id, contents="1 2 3")
dataset2_id = self._test_dataset(history_id, contents="4 5 6")
dataset3_id = self._test_dataset(history_id, contents="7 8 9")
tool_inputs = (
inputs()
.set("input1", dataset(dataset1_id))
.set(
"queries",
repeat()
.instance(inputs().set("input2", dataset(dataset2_id)))
.instance(inputs().set("input2", dataset(dataset3_id))),
)
)
tool_output = self.gi.tools.run_tool(history_id=history_id, tool_id="cat1", tool_inputs=tool_inputs)
self.assertEqual(len(tool_output["outputs"]), 1)
def test_wait_for_job(self):
tool_inputs = inputs().set("input1", dataset(self.dataset_id))
tool_output = self.gi.tools.run_tool(history_id=self.history_id,
tool_id="cat1",
tool_inputs=tool_inputs)
job_id = tool_output['jobs'][0]['id']
job = self.gi.jobs.wait_for_job(job_id)
self.assertEqual(job['state'], 'ok')
def test_conditional():
# Build up example inputs for random_lines1
as_dict = inputs().set("num_lines", 5).set(
"input", dataset("encoded1")).set(
"seed_source",
conditional().set("seed_source_selector",
"set_seed").set("seed", "asdf")).to_dict()
assert as_dict["num_lines"] == 5
assert as_dict["input"]["src"] == "hda"
assert as_dict["input"]["id"] == "encoded1"
assert as_dict["seed_source|seed_source_selector"] == "set_seed"
assert as_dict["seed_source|seed"] == "asdf"
def test_repeat():
# Build up inputs for cat1
as_dict = inputs().set("input1", dataset("encoded1")).set(
"queries",
repeat().instance(inputs().set_dataset_param(
"input2", "encoded2")).instance(inputs().set_dataset_param(
"input2", "encoded3"))).to_dict()
assert as_dict["input1"]["src"] == "hda"
assert as_dict["input1"]["id"] == "encoded1"
assert as_dict["queries_0|input2"]["src"] == "hda"
assert as_dict["queries_0|input2"]["id"] == "encoded2"
assert as_dict["queries_1|input2"]["src"] == "hda"
assert as_dict["queries_1|input2"]["id"] == "encoded3"
def test_run_random_lines(self):
# Run second test case from randomlines.xml
history_id = self.gi.histories.create_history(name="test_run_random_lines history")["id"]
with open(get_abspath(os.path.join("data", "1.bed"))) as f:
contents = f.read()
dataset_id = self._test_dataset(history_id, contents=contents)
tool_inputs = (
inputs()
.set("num_lines", "1")
.set("input", dataset(dataset_id))
.set("seed_source", conditional().set("seed_source_selector", "set_seed").set("seed", "asdf"))
)
tool_output = self.gi.tools.run_tool(history_id=history_id, tool_id="random_lines1", tool_inputs=tool_inputs)
self.assertEqual(len(tool_output["outputs"]), 1)
def export_output(request, project, gi, file_id, tool_id="export_sbw"):
"""Export data in galaxy MetaGenSense output directory"""
"""add the name of project on file name"""
data = gi.datasets.show_dataset(dataset_id=file_id)
hist_id = data['history_id']
myinputs = inputs().set("prefix", project).set("input", dataset(file_id))
tool_outputs = gi.tools.run_tool(history_id=hist_id, tool_id=tool_id, tool_inputs=myinputs)
if tool_outputs:
messages.warning(request, "Export is in progress, your file will be available: " + project + '_' + data['name'])
return redirect('galaxy_history_detail', history_id=hist_id)
def test_run_random_lines(self):
# Run second test case from randomlines.xml
history_id = self.gi.histories.create_history(
name="test_run_random_lines history")["id"]
with open(test_util.get_abspath(os.path.join("data", "1.bed"))) as f:
contents = f.read()
dataset_id = self._test_dataset(history_id, contents=contents)
tool_inputs = inputs().set("num_lines", "1").set(
"input", dataset(dataset_id)).set(
"seed_source",
conditional().set("seed_source_selector",
"set_seed").set("seed", "asdf"))
tool_output = self.gi.tools.run_tool(history_id=history_id,
tool_id="random_lines1",
tool_inputs=tool_inputs)
self.assertEqual(len(tool_output["outputs"]), 1)
def test_repeat():
# Build up inputs for cat1
as_dict = inputs().set(
"input1", dataset("encoded1")
).set(
"queries", repeat().instance(
inputs().set_dataset_param("input2", "encoded2")
).instance(
inputs().set_dataset_param("input2", "encoded3")
)
).to_dict()
assert as_dict["input1"]["src"] == "hda"
assert as_dict["input1"]["id"] == "encoded1"
assert as_dict["queries_0|input2"]["src"] == "hda"
assert as_dict["queries_0|input2"]["id"] == "encoded2"
assert as_dict["queries_1|input2"]["src"] == "hda"
assert as_dict["queries_1|input2"]["id"] == "encoded3"
def test_conditional():
# Build up example inputs for random_lines1
as_dict = inputs().set(
"num_lines", 5
).set(
"input", dataset("encoded1")
).set(
"seed_source", conditional().set(
"seed_source_selector", "set_seed"
).set(
"seed", "asdf"
)
).to_dict()
assert as_dict["num_lines"] == 5
assert as_dict["input"]["src"] == "hda"
assert as_dict["input"]["id"] == "encoded1"
assert as_dict["seed_source|seed_source_selector"] == "set_seed"
assert as_dict["seed_source|seed"] == "asdf"
def create_run_definition(dataset_id, tool_dict):
'''define jobs for galaxy'''
filtering_runs = [{
'tool':
tool_dict['paired_fastq_filtering'],
'inputs':
OrderedDict([('A', dataset(dataset_id['fq1'])),
('B', dataset(dataset_id['fq2']))])
}, {
'tool':
tool_dict['paired_fastq_filtering'],
'inputs':
OrderedDict([('A', dataset(dataset_id['fq1'])),
('B', dataset(dataset_id['fq2'])),
('sampling',
conditional().set('sequence_sampling',
'true').set('sample_size', 500))])
}, {
'tool':
tool_dict['single_fastq_filtering'],
'inputs':
OrderedDict([('A', dataset(dataset_id['fq1'])),
('sampling',
conditional().set('sequence_sampling',
'true').set('sample_size', 500))])
}]
affixer_runs = [{
'tool':
tool_dict['fasta_affixer'],
'inputs':
OrderedDict([('input', dataset(dataset_id['input_fasta'])),
('prefix', "PREFIX"), ('suffix', 'SUFFIX')])
}, {
'tool':
tool_dict['names_affixer'],
'inputs':
OrderedDict([('input', dataset(dataset_id['fq1'])),
('prefix', "PREFIX"), ('suffix', 'SUFFIX')])
}]
various_utils = [{
'tool':
tool_dict['sampler'],
'inputs':
OrderedDict([('input', dataset(dataset_id['input_fasta'])),
('number', 500)])
}, {
'tool':
tool_dict['fasta_interlacer'],
'inputs':
OrderedDict([('A', dataset(dataset_id['fastaA'])),
('B', dataset(dataset_id['fastaB']))])
}, {
'tool':
tool_dict['rename_sequences'],
'inputs':
OrderedDict([('input', dataset(dataset_id['fastaA'])),
('prefix_length', 3)])
}, {
'tool':
tool_dict['chip_seq_ratio'],
'inputs':
OrderedDict([('ChipFile', dataset(dataset_id['chip_fasta'])),
('InputFile', dataset(dataset_id['input_fasta'])),
('ContigFile', dataset(dataset_id['clustering_contigs']))
])
}, {
'tool':
tool_dict['pair_scan'],
'inputs':
OrderedDict([('fasta_input', dataset(dataset_id['interlaced_fasta']))])
}]
dante_runs = [{
'tool':
tool_dict['dante'],
'inputs':
OrderedDict([('input_type', conditional().set(
'input_type_selector',
'fasta').set('input_sequences',
dataset(dataset_id['gepy_genome'])))])
}, {
'tool':
tool_dict['dante'],
'inputs':
OrderedDict([
('input_type',
conditional().set('input_type_selector',
'aln').set('input_sequences',
dataset(dataset_id['aln_contigs'])))
])
}, {
'tool':
tool_dict['domain_filter'],
'inputs':
OrderedDict([('DomGff', dataset(dataset_id['gff_dante']))])
}, {
'tool':
tool_dict['gff_to_tabular'],
'inputs':
OrderedDict([('inputgff', dataset(dataset_id['gff_dante']))])
}, {
'tool':
tool_dict['gff_extract'],
'inputs':
OrderedDict([('input_dna', dataset(dataset_id['gepy_genome'])),
('domains_gff', dataset(dataset_id['gff_dante']))])
}, {
'tool':
tool_dict['gff_summary'],
'inputs':
OrderedDict([('group', "Name"),
('inputgff', dataset(dataset_id['gff_dante']))])
}]
repex_runs = [{
'tool':
tool_dict['repeatexplorer2'],
'inputs':
OrderedDict([('FastaFile', dataset(dataset_id['LAS_interlaced_fasta']))
])
}, {
'tool':
tool_dict['tarean'],
'inputs':
OrderedDict([('FastaFile', dataset(dataset_id['LAS_interlaced_fasta']))
])
}]
runs = affixer_runs + filtering_runs + dante_runs + various_utils + repex_runs
return runs
