diff --git a/helical/models/uce/model.py b/helical/models/uce/model.py index 8616507f..049b30fc 100644 --- a/helical/models/uce/model.py +++ b/helical/models/uce/model.py @@ -102,7 +102,7 @@ def process_data(self, list_of_mariana = [1,2,3] if 1 in list_of_mariana: # do my change - + if gene_column_name != "index": data.var.index = data.var[gene_column_name] @@ -139,6 +139,7 @@ def process_data(self, pe_row_idxs = get_protein_embeddings_idxs(files_config["offset_pkl_path"], species, species_to_all_gene_symbols, filtered_adata) dataset_chroms, dataset_start = get_positions(Path(files_config["spec_chrom_csv_path"]), species, filtered_adata) + if not (len(dataset_chroms) == len(dataset_start) == num_genes == pe_row_idxs.shape[0]): LOGGER.error(f'Invalid input dimensions for the UCEDataset! ' f'dataset_chroms: {len(dataset_chroms)}, '