def test_run(self):
path = EnvironmentSettings.tmp_test_path / "galaxy_api_dataset_generation/"
PathBuilder.build(path)
yaml_path = path / "specs.yaml"
result_path = path / "results/"
PathBuilder.build(path)
self.prepare_specs(yaml_path)
run_immuneML(
Namespace(
**{
"specification_path": yaml_path,
"result_path": result_path,
'tool': "DatasetGenerationTool"
}))
self.assertTrue(
os.path.isfile(result_path / "result/dataset_metadata.csv"))
self.assertTrue(
os.path.isfile(result_path / "result/dataset.iml_dataset"))
self.assertEqual(
200,
len([
name
for name in os.listdir(result_path / "result/repertoires/")
if os.path.isfile(
os.path.join(result_path / "result/repertoires/", name))
]))
shutil.rmtree(path)
def test_run(self):
path = EnvironmentSettings.tmp_test_path / "galaxy_api_dataset_simulation/"
PathBuilder.build(path)
yaml_path = path / "specs.yaml"
result_path = path / "results/"
specs = {'definitions': {
"datasets": {
"d1": {
"format": "RandomRepertoireDataset",
"params": {
"repertoire_count": 100,
"sequence_count_probabilities": {
100: 1
},
"sequence_length_probabilities": {
10: 1
},
"labels": {}
}
}
}
},
"instructions": {
"inst1": {"type": "DatasetExport", "export_formats": ["ImmuneML"], "datasets": ["d1"]}
}
}
with open(yaml_path, "w") as file:
yaml.dump(specs, file)
PathBuilder.build(path)
run_immuneML(Namespace(**{"specification_path": yaml_path, "result_path": result_path, 'tool': "DataSimulationTool"}))
self.assertTrue(os.path.isfile(result_path / "result/dataset_metadata.csv"))
self.assertTrue(os.path.isfile(result_path / "result/dataset.iml_dataset"))
self.assertEqual(200, len([name for name in os.listdir(result_path / "result/repertoires/")
if os.path.isfile(os.path.join(result_path / "result/repertoires/", name))]))
shutil.rmtree(path)
def test_run1(self):
path = PathBuilder.build(EnvironmentSettings.tmp_test_path / "api_galaxy_yaml_tool1/")
result_path = path / "result/"
dataset = RandomDatasetGenerator.generate_repertoire_dataset(10, {10: 1}, {12: 1}, {}, result_path)
dataset.name = "d1"
ImmuneMLExporter.export(dataset, result_path)
specs = {
"definitions": {
"datasets": {
"new_d1": {
"format": "ImmuneML",
"params": {
"metadata_file": str(result_path / "d1_metadata.csv")
}
}
},
},
"instructions": {
"inst1": {
"type": "DatasetExport",
"datasets": ["new_d1"],
"export_formats": ["AIRR"]
}
}
}
specs_path = path / "specs.yaml"
with open(specs_path, "w") as file:
yaml.dump(specs, file)
run_immuneML(Namespace(**{"specification_path": specs_path, "result_path": result_path / 'result/', 'tool': "GalaxyYamlTool"}))
self.assertTrue(os.path.exists(result_path / "result/inst1/dataset/AIRR"))
shutil.rmtree(path)
def test_run(self):
path = PathBuilder.build(EnvironmentSettings.tmp_test_path /
"api_galaxy_trainmlmodel_tool/")
result_path = path / "result/"
specs = {
"definitions": {
"datasets": {
"d2": {
"format": "RandomRepertoireDataset",
"params": {
"repertoire_count": 50,
"sequence_length_probabilities": {
10: 1
},
'sequence_count_probabilities': {
10: 1
},
'labels': {
"CD": {
True: 0.5,
False: 0.5
}
}
}
}
},
"encodings": {
"e1": {
"Word2Vec": {
"k": 3,
"model_type": "sequence",
"vector_size": 8,
}
},
"e2": {
"Word2Vec": {
"k": 3,
"model_type": "sequence",
"vector_size": 10,
}
},
},
"ml_methods": {
"simpleLR": {
"LogisticRegression": {
"penalty": "l1"
},
"model_selection_cv": False,
"model_selection_n_folds": -1,
}
},
},
"instructions": {
"inst2": {
"type":
"TrainMLModel",
"settings": [{
"encoding": "e1",
"ml_method": "simpleLR"
}, {
"encoding": "e2",
"ml_method": "simpleLR"
}],
"assessment": {
"split_strategy": "random",
"split_count": 1,
"training_percentage": 0.7
},
"selection": {
"split_strategy": "random",
"split_count": 2,
"training_percentage": 0.7
},
"labels": ["CD"],
"dataset":
"d2",
"strategy":
"GridSearch",
"metrics": ["accuracy", "auc"],
"reports": [],
"number_of_processes":
10,
"optimization_metric":
"accuracy",
'refit_optimal_model':
False,
"store_encoded_data":
False
}
}
}
specs_path = path / "specs.yaml"
with open(specs_path, "w") as file:
yaml.dump(specs, file)
run_immuneML(
Namespace(
**{
"specification_path": specs_path,
"result_path": result_path,
'tool': "GalaxyTrainMLModel"
}))
self.assertTrue(
os.path.exists(result_path / "exported_models/ml_model_CD.zip"))
self.assertTrue(os.path.exists(result_path / "index.html"))
shutil.rmtree(path)
def test_run(self):
path = PathBuilder.build(EnvironmentSettings.tmp_test_path / "api_galaxy_simulation_tool/")
result_path = path / "result"
specs = {
"definitions": {
"datasets": {
"d1": {
"format": "RandomRepertoireDataset",
"params": {
"repertoire_count": 50,
"sequence_length_probabilities": {10: 1},
'sequence_count_probabilities': {10: 1},
'labels': {
"CD": {
True: 0.5,
False: 0.5
}
}
}
}
},
"motifs": {
"motif1": {
"seed": "E/E",
"instantiation": {
"GappedKmer": {
"max_gap": 1
},
}
},
"motif2": {
"seed": "TTT",
"instantiation": "GappedKmer"
}
},
"signals": {
"signal1": {
"motifs": ["motif1", "motif2"],
"implanting": "HealthySequence",
"sequence_position_weights": None
}
},
"simulations": {
"sim1": {
"var1": {
"signals": ["signal1"],
"dataset_implanting_rate": 0.5,
"repertoire_implanting_rate": 0.5
}
}
},
},
"instructions": {
"inst1": {
"type": "Simulation",
"dataset": "d1",
"simulation": "sim1",
"export_formats": ["AIRR"]
},
}
}
specs_path = path / "specs.yaml"
with open(specs_path, "w") as file:
yaml.dump(specs, file)
run_immuneML(Namespace(**{"specification_path": specs_path, "result_path": result_path / 'result/', 'tool': "GalaxySimulationTool"}))
shutil.rmtree(path)