def _parse_ml_method(ml_method_id: str, ml_specification) -> tuple:
valid_class_values = ReflectionHandler.all_nonabstract_subclass_basic_names(MLMethod, "", "ml_methods/")
if type(ml_specification) is str:
ml_specification = {ml_specification: {}}
ml_specification = {**DefaultParamsLoader.load("ml_methods/", "MLMethod"), **ml_specification}
ml_specification_keys = list(ml_specification.keys())
ParameterValidator.assert_all_in_valid_list(list(ml_specification_keys), ["model_selection_cv", "model_selection_n_folds"] +
valid_class_values, "MLParser", ml_method_id)
non_default_keys = [key for key in ml_specification.keys() if key not in ["model_selection_cv", "model_selection_n_folds"]]
assert len(ml_specification_keys) == 3, f"MLParser: ML method {ml_method_id} was not correctly specified. Expected at least 1 key " \
f"(ML method name), got {len(ml_specification_keys) - 2} instead: " \
f"{str([key for key in non_default_keys])[1:-1]}."
ml_method_class_name = non_default_keys[0]
ml_method_class = ReflectionHandler.get_class_by_name(ml_method_class_name, "ml_methods/")
ml_specification[ml_method_class_name] = {**DefaultParamsLoader.load("ml_methods/", ml_method_class_name, log_if_missing=False),
**ml_specification[ml_method_class_name]}
method, params = MLParser.create_method_instance(ml_specification, ml_method_class, ml_method_id)
ml_specification[ml_method_class_name] = params
method.name = ml_method_id
return method, ml_specification
def _parse_to_enum_instances(params, location):
for key in params.keys():
class_name = DefaultParamsLoader._convert_to_camel_case(key)
if ReflectionHandler.exists(class_name, location):
cls = ReflectionHandler.get_class_by_name(class_name, location)
params[key] = cls[params[key].upper()]
return params
def parse(self,
key: str,
instruction: dict,
symbol_table: SymbolTable,
path: str = None) -> DatasetExportInstruction:
location = "DatasetExportParser"
ParameterValidator.assert_keys(list(instruction.keys()),
DatasetExportParser.VALID_KEYS,
location, key)
valid_formats = ReflectionHandler.all_nonabstract_subclass_basic_names(
DataExporter, "Exporter", 'dataset_export/')
ParameterValidator.assert_all_in_valid_list(
instruction["export_formats"], valid_formats, location,
"export_formats")
ParameterValidator.assert_all_in_valid_list(
instruction["datasets"],
symbol_table.get_keys_by_type(SymbolType.DATASET), location,
"datasets")
return DatasetExportInstruction(
datasets=[
symbol_table.get(dataset_key)
for dataset_key in instruction["datasets"]
],
exporters=[
ReflectionHandler.get_class_by_name(f"{key}Exporter",
"dataset_export/")
for key in instruction["export_formats"]
],
name=key)
def test_get_class_from_path(self):
filepath = EnvironmentSettings.root_path + "/source/util/KmerHelper.py"
cls = ReflectionHandler.get_class_from_path(filepath, "KmerHelper")
self.assertEqual(KmerHelper, cls)
cls = ReflectionHandler.get_class_from_path(filepath)
self.assertEqual(KmerHelper, cls)
def import_hp_setting(config_dir: str) -> Tuple[HPSetting, Label]:
config = MLMethodConfiguration()
config.load(f'{config_dir}ml_config.yaml')
ml_method = ReflectionHandler.get_class_by_name(
config.ml_method, 'ml_methods/')()
ml_method.load(config_dir)
encoder = MLImport.import_encoder(config, config_dir)
preprocessing_sequence = MLImport.import_preprocessing_sequence(
config, config_dir)
labels = list(config.labels_with_values.keys())
assert len(
labels
) == 1, "MLImport: Multiple labels set in a single ml_config file."
label = Label(labels[0], config.labels_with_values[labels[0]])
return HPSetting(
encoder=encoder,
encoder_params=config.encoding_parameters,
encoder_name=config.encoding_name,
ml_method=ml_method,
ml_method_name=config.ml_method_name,
ml_params={},
preproc_sequence=preprocessing_sequence,
preproc_sequence_name=config.preprocessing_sequence_name), label
def parse_object(specs,
valid_class_names: list,
class_name_ending: str,
class_path: str,
location: str,
key: str,
builder: bool = False,
return_params_dict: bool = False):
class_name = ObjectParser.get_class_name(specs, valid_class_names,
class_name_ending, location,
key)
ParameterValidator.assert_in_valid_list(class_name, valid_class_names,
location, key)
cls = ReflectionHandler.get_class_by_name(
f"{class_name}{class_name_ending}", class_path)
params = ObjectParser.get_all_params(specs, class_path, class_name,
key)
try:
if "name" not in inspect.signature(cls.__init__).parameters.keys():
del params["name"]
obj = cls.build_object(
**params) if builder and hasattr(cls, "build_object") else cls(
**params)
except TypeError as err:
raise AssertionError(
f"{location}: invalid parameter {err.args[0]} when specifying parameters in {specs} "
f"under key {key}. Valid parameter names are: "
f"{[name for name in inspect.signature(cls.__init__).parameters.keys()]}"
)
return (obj, {class_name: params}) if return_params_dict else obj
def make_simulation_docs(path):
instantiations = ReflectionHandler.all_nonabstract_subclasses(MotifInstantiationStrategy, "Instantiation", "motif_instantiation_strategy/")
instantiations = [DocumentationFormat(inst, inst.__name__.replace('Instantiation', ""), DocumentationFormat.LEVELS[2])
for inst in instantiations]
implanting_strategies = ReflectionHandler.all_nonabstract_subclasses(SignalImplantingStrategy, 'Implanting', 'signal_implanting_strategy/')
implanting_strategies = [DocumentationFormat(implanting, implanting.__name__.replace('Implanting', ""), DocumentationFormat.LEVELS[2])
for implanting in implanting_strategies]
classes_to_document = [DocumentationFormat(Motif, Motif.__name__, DocumentationFormat.LEVELS[1])] + instantiations + \
[DocumentationFormat(Signal, Signal.__name__, DocumentationFormat.LEVELS[1])] + implanting_strategies + \
[DocumentationFormat(Implanting, Implanting.__name__, DocumentationFormat.LEVELS[1])]
with open(path + "simulation.rst", "w") as file:
for doc_format in classes_to_document:
write_class_docs(doc_format, file)
def generate_docs(path):
inst_path = PathBuilder.build(f"{path}instructions/")
instructions = sorted(ReflectionHandler.all_nonabstract_subclasses(
Instruction, "Instruction", subdirectory='instructions/'),
key=lambda x: x.__name__)
inst_paths = {}
for instruction in instructions:
instruction_name = instruction.__name__[:-11]
if hasattr(InstructionParser,
f"make_{instruction_name.lower()}_docs"):
fn = getattr(InstructionParser,
f"make_{instruction_name.lower()}_docs")
file_path = fn(inst_path)
else:
file_path = InstructionParser.make_docs(
instruction, instruction_name, inst_path)
inst_paths[instruction_name] = file_path
with open(f'{inst_path}instructions.rst', 'w') as file:
for key, item in inst_paths.items():
lines = f"{key}\n---------------------------\n.. include:: {os.path.relpath(item, EnvironmentSettings.source_docs_path)}\n"
file.writelines(lines)
def _parse_motif(key: str, motif_item: dict) -> Motif:
motif_dict = copy.deepcopy(motif_item)
valid_values = ReflectionHandler.all_nonabstract_subclass_basic_names(
MotifInstantiationStrategy, "Instantiation",
"motif_instantiation_strategy/")
instantiation_object = ObjectParser.parse_object(
motif_item["instantiation"], valid_values, "Instantiation",
"motif_instantiation_strategy", "MotifParser", key)
motif_dict["instantiation"] = instantiation_object
motif_dict["identifier"] = key
if "name_chain1" in motif_item:
motif_dict["name_chain1"] = Chain[
motif_item["name_chain1"].upper()]
if "name_chain2" in motif_item:
motif_dict["name_chain2"] = Chain[
motif_item["name_chain2"].upper()]
assert "seed" in motif_dict or all(el in motif_dict for el in ["name_chain1", "name_chain2", "seed_chain1", "seed_chain2"]), \
"MotifParser: please check the documentation for motif definition. Either parameter `seed` has to be set (for simulation in single " \
"chain data) or all of the parameters `name_chain1`, `name_chain2`, `seed_chain1`, `seed_chain2` (for simulation for paired chain data)."
motif = Motif(**motif_dict)
return motif
def get_class(specs, valid_class_names, class_name_ending, class_path,
location, key):
class_name = ObjectParser.get_class_name(specs, valid_class_names,
class_name_ending, location,
key)
cls = ReflectionHandler.get_class_by_name(
f"{class_name}{class_name_ending}", class_path)
return cls
def build_object(dataset=None, **params):
try:
prepared_parameters = MatchedSequencesEncoder._prepare_parameters(**params)
encoder = ReflectionHandler.get_class_by_name(MatchedSequencesEncoder.dataset_mapping[dataset.__class__.__name__],
"reference_encoding/")(**prepared_parameters)
except ValueError:
raise ValueError("{} is not defined for dataset of type {}.".format(MatchedSequencesEncoder.__name__,
dataset.__class__.__name__))
return encoder
def parse_instruction(key: str, instruction: dict,
symbol_table: SymbolTable, path) -> tuple:
ParameterValidator.assert_keys_present(list(instruction.keys()),
["type"],
InstructionParser.__name__, key)
valid_instructions = [
cls[:-6]
for cls in ReflectionHandler.discover_classes_by_partial_name(
"Parser", "dsl/instruction_parsers/")
]
ParameterValidator.assert_in_valid_list(instruction["type"],
valid_instructions,
"InstructionParser", "type")
parser = ReflectionHandler.get_class_by_name(
"{}Parser".format(instruction["type"]), "instruction_parsers/")()
instruction_object = parser.parse(key, instruction, symbol_table, path)
symbol_table.add(key, SymbolType.INSTRUCTION, instruction_object)
return instruction, symbol_table
def build_object(dataset=None, **params):
try:
prepared_params = Word2VecEncoder._prepare_parameters(**params)
encoder = ReflectionHandler.get_class_by_name(
Word2VecEncoder.dataset_mapping[dataset.__class__.__name__],
"word2vec/")(**prepared_params)
except ValueError:
raise ValueError(
"{} is not defined for dataset of type {}.".format(
Word2VecEncoder.__name__, dataset.__class__.__name__))
return encoder
def parse(self, key: str, instruction: dict, symbol_table: SymbolTable, path: str = None) -> SubsamplingInstruction:
valid_keys = ["type", "dataset", "subsampled_dataset_sizes", "dataset_export_formats"]
ParameterValidator.assert_keys(instruction.keys(), valid_keys, SubsamplingParser.__name__, key)
dataset_keys = symbol_table.get_keys_by_type(SymbolType.DATASET)
ParameterValidator.assert_in_valid_list(instruction['dataset'], dataset_keys, SubsamplingParser.__name__, f'{key}/dataset')
dataset = symbol_table.get(instruction['dataset'])
ParameterValidator.assert_type_and_value(instruction['subsampled_dataset_sizes'], list, SubsamplingParser.__name__, f'{key}/subsampled_dataset_sizes')
ParameterValidator.assert_all_type_and_value(instruction['subsampled_dataset_sizes'], int, SubsamplingParser.__name__,
f'{key}/subsampled_dataset_sizes', 1, dataset.get_example_count())
valid_export_formats = ReflectionHandler.all_nonabstract_subclass_basic_names(DataExporter, 'Exporter', "dataset_export/")
ParameterValidator.assert_type_and_value(instruction['dataset_export_formats'], list, SubsamplingParser.__name__, f"{key}/dataset_export_formats")
ParameterValidator.assert_all_in_valid_list(instruction['dataset_export_formats'], valid_export_formats, SubsamplingParser.__name__, f"{key}/dataset_export_formats")
return SubsamplingInstruction(dataset=dataset, subsampled_dataset_sizes=instruction['subsampled_dataset_sizes'],
dataset_export_formats=[ReflectionHandler.get_class_by_name(export_format + "Exporter", "dataset_export/")
for export_format in instruction['dataset_export_formats']], name=key)
def _parse_dataset(key: str, dataset_specs: dict, symbol_table: SymbolTable, result_path: str) -> SymbolTable:
location = "ImportParser"
ParameterValidator.assert_keys(list(dataset_specs.keys()), ImportParser.valid_keys, location, f"datasets:{key}", False)
valid_formats = ReflectionHandler.all_nonabstract_subclass_basic_names(DataImport, "Import", "IO/dataset_import/")
ParameterValidator.assert_in_valid_list(dataset_specs["format"], valid_formats, location, "format")
import_cls = ReflectionHandler.get_class_by_name("{}Import".format(dataset_specs["format"]))
params = ImportParser._prepare_params(dataset_specs, result_path, key)
if "is_repertoire" in params:
ParameterValidator.assert_type_and_value(params["is_repertoire"], bool, location, "is_repertoire")
if params["is_repertoire"] == True:
if import_cls != IReceptorImport:
assert "metadata_file" in params, f"{location}: Missing parameter: metadata_file under {key}/params/"
ParameterValidator.assert_type_and_value(params["metadata_file"], str, location, "metadata_file")
if params["is_repertoire"] == False:
assert "paired" in params, f"{location}: Missing parameter: paired under {key}/params/"
ParameterValidator.assert_type_and_value(params["paired"], bool, location, "paired")
if params["paired"] == True:
assert "receptor_chains" in params, f"{location}: Missing parameter: receptor_chains under {key}/params/"
ParameterValidator.assert_in_valid_list(params["receptor_chains"], ["_".join(cp.value) for cp in ChainPair], location, "receptor_chains")
try:
dataset = import_cls.import_dataset(params, key)
dataset.name = key
symbol_table.add(key, SymbolType.DATASET, dataset)
except KeyError as key_error:
raise KeyError(f"{key_error}\n\nAn error occurred during parsing of dataset {key}. "
f"The keyword {key_error.args[0]} was missing. This either means this argument was "
f"not defined under definitions/datasets/{key}/params, or this column was missing from "
f"an input data file. ")
except Exception as ex:
raise Exception(f"{ex}\n\nAn error occurred while parsing the dataset {key}. See the log above for more details.")
return symbol_table
def get_documentation():
doc = str(SubsamplingInstruction.__doc__)
valid_strategy_values = ReflectionHandler.all_nonabstract_subclass_basic_names(
DataExporter, "Exporter", "dataset_export/")
valid_strategy_values = str(valid_strategy_values)[1:-1].replace(
"'", "`")
mapping = {
"Valid formats are class names of any non-abstract class inheriting "
":py:obj:`~source.IO.dataset_export.DataExporter.DataExporter`.":
f"Valid values are: {valid_strategy_values}."
}
doc = update_docs_per_mapping(doc, mapping)
return doc
def _get_implanting_strategy(key: str, signal: dict) -> SignalImplantingStrategy:
valid_strategies = [cls[:-10] for cls in
ReflectionHandler.discover_classes_by_partial_name("Implanting", "simulation/signal_implanting_strategy/")]
ParameterValidator.assert_in_valid_list(signal["implanting"], valid_strategies, "SignalParser", key)
defaults = DefaultParamsLoader.load("signal_implanting_strategy/", f"{signal['implanting']}Implanting")
signal = {**defaults, **signal}
ParameterValidator.assert_keys_present(list(signal.keys()), ["motifs", "implanting", "sequence_position_weights"], SignalParser.__name__, key)
implanting_comp = None
if 'implanting_computation' in signal:
implanting_comp = signal['implanting_computation'].lower()
ParameterValidator.assert_in_valid_list(implanting_comp, [el.name.lower() for el in ImplantingComputation], SignalParser.__name__,
'implanting_computation')
implanting_comp = ImplantingComputation[implanting_comp.upper()]
implanting_strategy = ReflectionHandler.get_class_by_name(f"{signal['implanting']}Implanting")(GappedMotifImplanting(),
signal["sequence_position_weights"],
implanting_comp)
return implanting_strategy
def __init__(self,
distance_metric: DistanceMetricType,
attributes_to_match: list,
sequence_batch_size: int,
context: dict = None,
name: str = None):
self.distance_metric = distance_metric
self.distance_fn = ReflectionHandler.import_function(
self.distance_metric.value, DistanceMetrics)
self.attributes_to_match = attributes_to_match
self.sequence_batch_size = sequence_batch_size
self.context = context
self.name = name
self.comparison = None
def get_documentation():
initial_doc = str(Signal.__doc__)
valid_implanting_values = str(
ReflectionHandler.all_nonabstract_subclass_basic_names(
SignalImplantingStrategy, 'Implanting',
'signal_implanting_strategy/'))[1:-1].replace("'", "`")
docs_mapping = {
"Valid values for this argument are class names of different signal implanting strategies.":
f"Valid values are: {valid_implanting_values}"
}
doc = update_docs_per_mapping(initial_doc, docs_mapping)
return doc
def make_reports_docs(path):
filename = "reports.rst"
open(path + filename, "w").close()
for report_type_class in [DataReport, EncodingReport, MLReport, TrainMLModelReport, MultiDatasetReport]:
with open(path + filename, "a") as file:
doc_format = DocumentationFormat(cls=report_type_class,
cls_name=f"**{report_type_class.get_title()}**",
level_heading=DocumentationFormat.LEVELS[1])
write_class_docs(doc_format, file)
subdir = DefaultParamsLoader.convert_to_snake_case(report_type_class.__name__) + "s"
classes = ReflectionHandler.all_nonabstract_subclasses(report_type_class, "", f"reports/{subdir}/")
make_docs(path, classes, filename, "", "a")
def _parse_report(key: str, params: dict, symbol_table: SymbolTable):
valid_values = ReflectionHandler.all_nonabstract_subclass_basic_names(
Report, "", "reports/")
report_object, params = ObjectParser.parse_object(
params,
valid_values,
"",
"reports/",
"ReportParser",
key,
builder=True,
return_params_dict=True)
symbol_table.add(key, SymbolType.REPORT, report_object)
return symbol_table, params
def get_documentation():
doc = str(Motif.__doc__)
valid_strategy_values = ReflectionHandler.all_nonabstract_subclass_basic_names(
MotifInstantiationStrategy, "Instantiation",
"motif_instantiation_strategy/")
valid_strategy_values = str(valid_strategy_values)[1:-1].replace(
"'", "`")
chain_values = str([name for name in Chain])[1:-1].replace("'", "`")
mapping = {
"It should be one of the classes inheriting MotifInstantiationStrategy.":
f"Valid values are: {valid_strategy_values}.",
"The value should be an instance of :py:obj:`~source.data_model.receptor.receptor_sequence.Chain.Chain`.":
f"Valid values are: {chain_values}."
}
doc = update_docs_per_mapping(doc, mapping)
return doc
def _parse_sequence(key: str, preproc_sequence: list,
symbol_table: SymbolTable) -> SymbolTable:
sequence = []
valid_preprocessing_classes = ReflectionHandler.all_nonabstract_subclass_basic_names(
Preprocessor, "", "preprocessing/")
for item in preproc_sequence:
for step_key, step in item.items():
obj, params = ObjectParser.parse_object(
step, valid_preprocessing_classes, "", "preprocessing/",
"PreprocessingParser", step_key, True, True)
step = params
sequence.append(obj)
symbol_table.add(key, SymbolType.PREPROCESSING, sequence)
return symbol_table
def parse_encoder(key: str, specs: dict):
class_path = "encodings"
valid_encoders = ReflectionHandler.all_nonabstract_subclass_basic_names(
DatasetEncoder, "Encoder", class_path)
encoder = ObjectParser.get_class(specs, valid_encoders, "Encoder",
class_path, "EncodingParser", key)
params = ObjectParser.get_all_params(specs, class_path,
encoder.__name__[:-7], key)
required_params = [
p for p in list(
inspect.signature(encoder.__init__).parameters.keys())
if p != "self"
]
ParameterValidator.assert_all_in_valid_list(
params.keys(), required_params, "EncoderParser",
f"{key}/{encoder.__name__.replace('Encoder', '')}")
return encoder, params
def run_immuneML(namespace: argparse.Namespace):
if os.path.isdir(namespace.result_path) and len(
os.listdir(namespace.result_path)) != 0:
raise ValueError(
f"Directory {namespace.result_path} already exists. Please specify a new output directory for the analysis."
)
PathBuilder.build(namespace.result_path)
logging.basicConfig(filename=namespace.result_path + "/log.txt",
level=logging.INFO,
format='%(asctime)s %(levelname)s: %(message)s')
warnings.showwarning = lambda message, category, filename, lineno, file=None, line=None: logging.warning(
message)
if namespace.tool is None:
app = ImmuneMLApp(namespace.specification_path, namespace.result_path)
else:
app_cls = ReflectionHandler.get_class_by_name(namespace.tool, "api/")
app = app_cls(**vars(namespace))
app.run()
def prepare_reference(reference_params: dict, location: str, paired: bool):
ParameterValidator.assert_keys(list(reference_params.keys()),
["format", "params"], location,
"reference")
seq_import_params = reference_params[
"params"] if "params" in reference_params else {}
assert os.path.isfile(seq_import_params["path"]), f"{location}: the file {seq_import_params['path']} does not exist. " \
f"Specify the correct path under reference."
if "paired" in seq_import_params:
assert seq_import_params[
"paired"] == paired, f"{location}: paired must be {paired} for SequenceImport"
else:
seq_import_params["paired"] = paired
format_str = reference_params["format"]
if format_str == "IRIS": # todo refactor this when refactoring IRISSequenceImport
receptors = IRISSequenceImport.import_items(**seq_import_params)
else:
import_class = ReflectionHandler.get_class_by_name(
"{}Import".format(format_str))
params = DefaultParamsLoader.load(
EnvironmentSettings.default_params_path + "datasets/",
DefaultParamsLoader.convert_to_snake_case(format_str))
for key, value in seq_import_params.items():
params[key] = value
params["paired"] = paired
processed_params = DatasetImportParams.build_object(**params)
receptors = ImportHelper.import_items(
import_class, reference_params["params"]["path"],
processed_params)
return receptors
def get_documentation():
doc = str(TrainMLModelInstruction.__doc__)
valid_values = str([metric.name.lower()
for metric in Metric])[1:-1].replace("'", "`")
valid_strategies = str(ReflectionHandler.all_nonabstract_subclass_basic_names(HPOptimizationStrategy, "",
"hyperparameter_optimization/strategy/"))[1:-1]\
.replace("'", "`")
mapping = {
"dataset (Dataset)":
"dataset",
"hp_strategy (HPOptimizationStrategy)":
"strategy",
"hp_settings":
"settings",
"assessment (SplitConfig)":
"assessment",
"selection (SplitConfig)":
"selection",
"optimization_metric (Metric)":
"optimization_metric",
"label_configuration (LabelConfiguration)":
"labels (list)",
"data_reports":
"reports",
"a list of metrics":
f"a list of metrics ({valid_values})",
"a metric to use for optimization":
f"a metric to use for optimization (one of {valid_values})",
"Valid values are objects of any class inheriting :py:obj:`~source.hyperparameter_optimization.strategy."
"HPOptimizationStrategy.HPOptimizationStrategy`.":
f"Valid values are: {valid_strategies}.",
"the reports to be specified here have to be :py:obj:`source.reports.train_ml_model_reports.TrainMLModelReport.TrainMLModelReport` reports.":
f"the reports that can be provided here are :ref:`{TrainMLModelReport.get_title()}`."
}
doc = update_docs_per_mapping(doc, mapping)
return doc
def parse_commandline_arguments(args):
ReflectionHandler.get_classes_by_partial_name("", "ml_methods/")
ml_method_names = [
cl.__name__
for cl in ReflectionHandler.all_nonabstract_subclasses(MLMethod)
] + ["SimpleLogisticRegression"]
parser = argparse.ArgumentParser(
description="tool for building immuneML Galaxy YAML from arguments")
parser.add_argument(
"-o",
"--output_path",
required=True,
help="Output location for the generated yaml file (directiory).")
parser.add_argument(
"-f",
"--file_name",
default="specs.yaml",
help=
"Output file name for the yaml file. Default name is 'specs.yaml' if not specified."
)
parser.add_argument(
"-l",
"--labels",
required=True,
help=
"Which metadata labels should be predicted for the dataset (separated by comma)."
)
parser.add_argument(
"-m",
"--ml_methods",
nargs="+",
choices=ml_method_names,
required=True,
help="Which machine learning methods should be applied.")
parser.add_argument("-t",
"--training_percentage",
type=float,
required=True,
help="The percentage of data used for training.")
parser.add_argument(
"-c",
"--split_count",
type=int,
required=True,
help=
"The number of times to repeat the training process with a different random split of the data."
)
parser.add_argument(
"-s",
"--sequence_type",
choices=["complete", "subsequence"],
default=["subsequence"],
nargs="+",
help="Whether complete CDR3 sequences are used, or k-mer subsequences."
)
parser.add_argument(
"-p",
"--position_type",
choices=["invariant", "positional"],
nargs="+",
help=
"Whether IMGT-positional information is used for k-mers, or the k-mer positions are position-invariant."
)
parser.add_argument("-g",
"--gap_type",
choices=["gapped", "ungapped"],
nargs="+",
help="Whether the k-mers contain gaps.")
parser.add_argument("-k", "--k", type=int, nargs="+", help="K-mer size.")
parser.add_argument("-kl",
"--k_left",
type=int,
nargs="+",
help="Length before gap when k-mers are used.")
parser.add_argument("-kr",
"--k_right",
type=int,
nargs="+",
help="Length after gap when k-mers are used.")
parser.add_argument("-gi",
"--min_gap",
type=int,
nargs="+",
help="Minimal gap length when gapped k-mers are used.")
parser.add_argument("-ga",
"--max_gap",
type=int,
nargs="+",
help="Maximal gap length when gapped k-mers are used.")
parser.add_argument(
"-r",
"--reads",
choices=[ReadsType.UNIQUE.value, ReadsType.ALL.value],
nargs="+",
default=[ReadsType.UNIQUE.value],
help=
"Whether k-mer counts should be scaled by unique clonotypes or all observed receptor sequences"
)
return parser.parse_args(args)
def import_encoder(config: MLMethodConfiguration, config_dir: str):
encoder_class = ReflectionHandler.get_class_by_name(
config.encoding_class)
encoder = encoder_class.load_encoder(config_dir + config.encoding_file)
return encoder
def parse_encoder_internal(short_class_name: str, encoder_params: dict):
encoder_class = ReflectionHandler.get_class_by_name(
f"{short_class_name}Encoder", "encodings")
params = ObjectParser.get_all_params(
{short_class_name: encoder_params}, "encodings", short_class_name)
return encoder_class, params, params