immuneML.data_model package

Subpackages

• immuneML.data_model.datasets package
  • Submodules
  • immuneML.data_model.datasets.Dataset module
    • Dataset
      • Dataset.PREPROCESSED
      • Dataset.SUBSAMPLED
      • Dataset.TEST
      • Dataset.TRAIN
      • Dataset.build_from_objects()
      • Dataset.clone()
      • Dataset.create_metadata_dict()
      • Dataset.dataset_file
      • Dataset.encoded_data
      • Dataset.get_data()
      • Dataset.get_data_from_index_range()
      • Dataset.get_example_count()
      • Dataset.get_example_ids()
      • Dataset.get_label_names()
      • Dataset.get_metadata()
      • Dataset.identifier
      • Dataset.labels
      • Dataset.make_subset()
      • Dataset.name
  • immuneML.data_model.datasets.ElementDataset module
    • ElementDataset
      • ElementDataset.bnp_dataclass
      • ElementDataset.buffer_type
      • ElementDataset.clone()
      • ElementDataset.create_metadata_dict()
      • ElementDataset.data
      • ElementDataset.dataset_file
      • ElementDataset.dynamic_fields
      • ElementDataset.element_count
      • ElementDataset.element_ids
      • ElementDataset.filename
      • ElementDataset.get_label_names()
    • ReceptorDataset
      • ReceptorDataset.build()
      • ReceptorDataset.build_from_objects()
      • ReceptorDataset.get_data()
      • ReceptorDataset.get_data_from_index_range()
      • ReceptorDataset.get_example_count()
      • ReceptorDataset.get_example_ids()
      • ReceptorDataset.get_metadata()
      • ReceptorDataset.make_subset()
    • SequenceDataset
      • SequenceDataset.build()
      • SequenceDataset.build_from_objects()
      • SequenceDataset.get_attribute()
      • SequenceDataset.get_data()
      • SequenceDataset.get_data_from_index_range()
      • SequenceDataset.get_example_count()
      • SequenceDataset.get_example_ids()
      • SequenceDataset.get_metadata()
      • SequenceDataset.make_subset()
    • fill_in_neutral_vals()
    • make_all_fields_dict_from_receptors()
    • make_all_fields_dict_from_sequences()
  • immuneML.data_model.datasets.RepertoireDataset module
    • RepertoireDataset
      • RepertoireDataset.add_encoded_data()
      • RepertoireDataset.build()
      • RepertoireDataset.build_from_objects()
      • RepertoireDataset.clone()
      • RepertoireDataset.create_metadata_dict()
      • RepertoireDataset.get_data()
      • RepertoireDataset.get_data_from_index_range()
      • RepertoireDataset.get_example_count()
      • RepertoireDataset.get_example_ids()
      • RepertoireDataset.get_filenames()
      • RepertoireDataset.get_label_names()
      • RepertoireDataset.get_metadata()
      • RepertoireDataset.get_metadata_fields()
      • RepertoireDataset.get_repertoire()
      • RepertoireDataset.get_repertoire_ids()
      • RepertoireDataset.get_subject_ids()
      • RepertoireDataset.make_subset()
  • Module contents

Submodules

immuneML.data_model.AIRRSequenceSet module

immuneML.data_model.EncodedData module

class immuneML.data_model.EncodedData.EncodedData(examples, labels: dict = None, example_ids: list = None, feature_names: list = None, feature_annotations: pandas.DataFrame = None, encoding: str = None, example_weights: list = None, info: dict = None, dimensionality_reduced_data: ndarray = None)

Bases: object

When a dataset is encoded, it is stored in an object of EncodedData class.

Parameters:

• examples – a design matrix containing the encoded data. This is typically a numpy array, although other matrix formats such as scipy sparse matrix, pandas dataframe or pytorch tensors are also permitted as long as the numpy matrix can be retrieved using ‘get_examples_as_np_matrix()’. The matrix is usually two-dimensional. The first dimension should be the examples, and the second (and higher) dimensions represent features.

• feature_names – a list of feature names. The length (dimensions) of this list should match the number of features in the examples matrix.

• feature_annotations – a data frame consisting of additional annotations for each feature. This can be used to add more information fields if feature_names is not sufficient. This data field is not used for machine learning, but may be used by some Reports.

• example_ids – a list of example (repertoire/sequence/receptor) IDs; it must be the same length as the example_count in the examples matrix. These can be retrieved using Dataset.get_example_ids()

• labels – a dict of labels where label names are keys and the values are lists of values for the label across examples: {‘disease1’: [‘sick’, ‘healthy’, ‘sick’]} During encoding, the labels can be computed using EncoderHelper.encode_dataset_labels()

get_examples_as_np_matrix()

immuneML.data_model.SequenceParams module

class immuneML.data_model.SequenceParams.Chain(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)

Bases: Enum

ALPHA = 'TRA'

BETA = 'TRB'

DELTA = 'TRD'

GAMMA = 'TRG'

HEAVY = 'IGH'

KAPPA = 'IGK'

LIGHT = 'IGL'

static get_chain(item: str)

static get_chain_value(item: str)

to_string()

class immuneML.data_model.SequenceParams.ChainPair(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)

Bases: Enum

IGH_IGK = ('IGH', 'IGK')

IGH_IGL = ('IGH', 'IGL')

TRA_TRB = ('TRA', 'TRB')

TRG_TRD = ('TRG', 'TRD')

static get_chain_pair(chains: List[Chain])

Given a list of 2 chain objects, returns the relevant ChainPair

class immuneML.data_model.SequenceParams.RegionType(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)

Bases: Enum

FULL_SEQUENCE = 'full_sequence'

IMGT_CDR1 = 'cdr1'

IMGT_CDR2 = 'cdr2'

IMGT_CDR3 = 'cdr3'

IMGT_FR1 = 'fwr1'

IMGT_FR2 = 'fwr2'

IMGT_FR3 = 'fwr3'

IMGT_FR4 = 'fwr4'

IMGT_JUNCTION = 'junction'

classmethod get_object(rt)

to_string()

immuneML.data_model.SequenceSet module

class immuneML.data_model.SequenceSet.Receptor(chain_pair: immuneML.data_model.SequenceParams.ChainPair, chain_1: immuneML.data_model.SequenceSet.ReceptorSequence, chain_2: immuneML.data_model.SequenceSet.ReceptorSequence, receptor_id: str = None, cell_id: str = None, metadata: dict = <factory>)

Bases: object

cell_id: str = None

chain_1: ReceptorSequence

chain_2: ReceptorSequence

chain_pair: ChainPair

metadata: dict

receptor_id: str = None

class immuneML.data_model.SequenceSet.ReceptorSequence(sequence_id: str = '', sequence: AlphabetEncoding('ACGT') = '', sequence_aa: AlphabetEncoding('ACDEFGHIKLMNPQRSTVWY*') = '', productive: str = 'T', vj_in_frame: str = 'T', stop_codon: str = 'F', locus: str = '', locus_species: str = '', v_call: str = '', d_call: str = '', j_call: str = '', c_call: str = '', metadata: dict = <factory>, duplicate_count: int = -1, cell_id: str = '')

Bases: object

c_call: str = ''

cell_id: str = ''

d_call: str = ''

duplicate_count: int = -1

get_attribute(attr_name)

get_sequence(sequence_type: SequenceType = SequenceType.AMINO_ACID)

j_call: str = ''

locus: str = ''

locus_species: str = ''

metadata: dict

productive: str = 'T'

sequence: AlphabetEncoding('ACGT') = ''

sequence_aa: AlphabetEncoding('ACDEFGHIKLMNPQRSTVWY*') = ''

sequence_id: str = ''

stop_codon: str = 'F'

v_call: str = ''

property v_gene

vj_in_frame: str = 'T'

class immuneML.data_model.SequenceSet.Repertoire(data_filename: pathlib.Path = None, metadata_filename: pathlib.Path = None, metadata: dict = None, identifier: str = None, dynamic_fields: dict = None, element_count: int = None, _bnp_dataclass: bytes = None, _buffer_type: bytes = None)

Bases: object

property bnp_dataclass

property buffer_type

classmethod build(path: Path, metadata: dict, filename_base: str = None, identifier: str = None, **kwargs)

classmethod build_from_dc_object(path: Path, metadata: dict, filename_base: str = None, identifier: str = None, data=None, type_dict: dict = None)

classmethod build_from_sequences(sequences: List[ReceptorSequence], result_path: Path, filename_base: str = None, metadata: dict = None, region_type: RegionType = RegionType.IMGT_CDR3)

classmethod build_like(repertoire: Repertoire, indices_to_keep, result_path: Path, filename_base: str)

property data: AIRRSequenceSet

data_filename: Path = None

dynamic_fields: dict = None

element_count: int = None

get_element_count()

identifier: str = None

metadata: dict = None

metadata_filename: Path = None

receptors(region_type: RegionType) → List[Receptor]

sequences(region_type: RegionType = RegionType.IMGT_CDR3) → List[ReceptorSequence]

immuneML.data_model.SequenceSet.build_dynamic_airr_sequence_set_dataclass(all_fields_dict: Dict[str, Any])

immuneML.data_model.SequenceSet.get_sequence_value(el: AIRRSequenceSet, region_type: RegionType = RegionType.IMGT_CDR3)

immuneML.data_model.SequenceSet.make_airr_seq_set_object_from_sequences(sequences: List[ReceptorSequence], region_type: RegionType = RegionType.IMGT_CDR3)

immuneML.data_model.SequenceSet.make_receptors_from_data(data: AIRRSequenceSet, dynamic_fields: dict, location, region_type: RegionType = RegionType.IMGT_CDR3)

immuneML.data_model.SequenceSet.make_sequences_from_data(data, dynamic_fields: dict, region_type: RegionType = RegionType.IMGT_CDR3)

immuneML.data_model.bnp_util module

immuneML.data_model.bnp_util.add_neutral_values(field_values: dict, types: dict) → dict

immuneML.data_model.bnp_util.bnp_read_from_file(filename: Path, buffer_type: DelimitedBuffer = None, dataclass=None)

immuneML.data_model.bnp_util.bnp_write_to_file(filename: Path, bnp_object)

immuneML.data_model.bnp_util.build_dynamic_bnp_dataclass(all_fields_dict: Dict[str, Any])

immuneML.data_model.bnp_util.build_dynamic_bnp_dataclass_obj(all_fields_dict: Dict[str, Any])

immuneML.data_model.bnp_util.convert_enums_to_str(field_values: dict) → dict

immuneML.data_model.bnp_util.convert_to_expected_types(all_fields_dict, types) → dict

immuneML.data_model.bnp_util.extend_dataclass_with_dynamic_fields(cls, fields: List[Tuple[str, type]], cls_name: str = None)

immuneML.data_model.bnp_util.get_field_type_from_values(values)

immuneML.data_model.bnp_util.get_row_by_index(self, index) → dict

immuneML.data_model.bnp_util.get_rows_by_indices(self, index1, index2) → dict

immuneML.data_model.bnp_util.get_sequence_field_name(region_type: RegionType = RegionType.IMGT_CDR3, sequence_type: SequenceType = SequenceType.AMINO_ACID)

immuneML.data_model.bnp_util.get_single_row_value(self, attr_name: str)

immuneML.data_model.bnp_util.get_type_dict_from_bnp_object(bnp_object) → dict

immuneML.data_model.bnp_util.load_type_dict(full_dict: dict) → dict

immuneML.data_model.bnp_util.make_buffer_type_from_dataset_file(dataset_file: Path)

immuneML.data_model.bnp_util.make_element_dataset_objects(bnp_object, class_name) → list

immuneML.data_model.bnp_util.make_full_airr_seq_set_df(df)

immuneML.data_model.bnp_util.merge_dataclass_objects(objects: list, fill_unmatched: bool = False)

immuneML.data_model.bnp_util.prepare_values_for_bnp(field_values: dict, types: dict) → dict

immuneML.data_model.bnp_util.read_yaml(filename: Path) → dict

immuneML.data_model.bnp_util.write_dataset_yaml(filename: Path, yaml_dict)

immuneML.data_model.bnp_util.write_yaml(filename: Path, yaml_dict)

Module contents