`deeprvat.seed_gene_discovery.seed_gene_discovery`

Module Contents

`replace_in_array`
`get_caf`
`save_burdens`
`subset_matrix`
`center`	Mean centers genotype values, excluding missing values from computation.
`collapse_burden`	Collapses burdens with specified method.
`get_weights`
`calculate_beta_maf_weights`
`calculate_sift_polyphen_weights`
`get_anno`
`call_score`
`test_gene`
`run_association_`
`cli`
`_add_annotation_cols`
`update_config`
`make_dataset_`
`make_dataset`
`run_association`
`combine_results`

`logger`
`variant_weight_th_dict`

deeprvat.seed_gene_discovery.seed_gene_discovery.variant_weight_th_dict = None

exception deeprvat.seed_gene_discovery.seed_gene_discovery.GotNone: Bases: Exception

deeprvat.seed_gene_discovery.seed_gene_discovery.replace_in_array(arr, old_val, new_val)

deeprvat.seed_gene_discovery.seed_gene_discovery.save_burdens(GW_list, GW_full_list, split, chunk, out_dir)

deeprvat.seed_gene_discovery.seed_gene_discovery.subset_matrix(M: Any, train_proportion: int)

deeprvat.seed_gene_discovery.seed_gene_discovery.center(X, inplace=False)

Mean centers genotype values, excluding missing values from computation.

Parameters:: X (numpy.ndarray) – 2D array with dimensions \(n*m\) with \(n:=\) number of individuals and \(m:=\) number of SNVs.
Returns:: mean-centered array
Return type:: numpy.ndarray

deeprvat.seed_gene_discovery.seed_gene_discovery.collapse_burden(X, method='max')

Collapses burdens with specified method.

Parameters:

X (numpy.ndarray) – 2D array with dimensions \(n*m\) with \(n:=\) number of individuals and \(m:=\) number of SNVs with non-zero weight.
method (string) – collapsing method

Returns:

collapsed array \(n*1\)

Return type:

numpy.ndarray

deeprvat.seed_gene_discovery.seed_gene_discovery.get_weights(variant_ids, annotation_df, weight_cols, var_weight_function, maf_col)

deeprvat.seed_gene_discovery.seed_gene_discovery.calculate_beta_maf_weights(anno, maf_col, beta_weights=(1, 25))

deeprvat.seed_gene_discovery.seed_gene_discovery.calculate_sift_polyphen_weights(anno)

deeprvat.seed_gene_discovery.seed_gene_discovery.get_anno(G: numpy.ndarray, variant_ids: numpy.ndarray, annotation_df: pandas.DataFrame, weight_cols: List[str], var_weight_function: str, maf_col: str)

deeprvat.seed_gene_discovery.seed_gene_discovery.call_score(GV, null_model_score, pval_dict, test_type)

deeprvat.seed_gene_discovery.seed_gene_discovery.test_gene(G_full: scipy.sparse.spmatrix, gene: int, grouped_annotations: pandas.DataFrame, Y, weight_cols: List[str], null_model_score: seak.scoretest.ScoretestNoK, test_config: Dict, var_type, test_type, maf_col, min_mac) → Dict[str, Any]

deeprvat.seed_gene_discovery.seed_gene_discovery.run_association_(Y: numpy.ndarray, X: numpy.ndarray, gene_ids, G_full, grouped_annotations: pandas.DataFrame, dataset: deeprvat.data.DenseGTDataset, config: Dict[str, Any], var_type: str, test_type: str, persist_burdens: bool) → pandas.DataFrame

deeprvat.seed_gene_discovery.seed_gene_discovery._add_annotation_cols(annotations, config)

deeprvat.seed_gene_discovery.seed_gene_discovery.update_config(old_config_file: str, phenotype: Optional[str], simulated_phenotype_file: str, variant_type: Optional[str], rare_maf: Optional[float], maf_column: str, new_config_file: str)

deeprvat.seed_gene_discovery.seed_gene_discovery.make_dataset_(config: Dict, pickled_dataset_file: str = None, debug: bool = False, data_key='data') → torch.utils.data.Dataset

deeprvat.seed_gene_discovery.seed_gene_discovery.make_dataset(debug: bool, data_key: str, config_file: str, pickled_dataset_file: str, out_file: str)

deeprvat.seed_gene_discovery.seed_gene_discovery.run_association(debug: bool, dataset_file: Optional[deeprvat.data.DenseGTDataset], data_file: Optional[deeprvat.data.DenseGTDataset], config_file: str, var_type: str, test_type: str, out_path: str, persist_burdens: bool, n_chunks: Optional[int] = None, chunk: Optional[int] = None)

deeprvat.seed_gene_discovery.seed_gene_discovery.combine_results(result_files: Tuple[str], out_file: str)