diff --git a/deeprvat/annotations/annotations.py b/deeprvat/annotations/annotations.py index ba08e5a2..2ca4f2f8 100644 --- a/deeprvat/annotations/annotations.py +++ b/deeprvat/annotations/annotations.py @@ -1082,7 +1082,7 @@ def aggregate_abscores( delayed(process_chunk)( i, abs_splice_res_dir, tissues_to_exclude, tissue_agg_function, ca_shortened ) - for i in tqdm(os.listdir(abs_splice_res_dir)) + for i in tqdm(sorted(os.listdir(abs_splice_res_dir))) ) all_absplice_scores = list(output_generator) @@ -1751,6 +1751,10 @@ def process_vep( assert vep_file.pos.isna().sum() == 0 assert vep_file.ref.isna().sum() == 0 assert vep_file.alt.isna().sum() == 0 + assert ( + vep_file[["chrom", "pos", "ref", "alt"]].drop_duplicates().shape + == vcf_df[["chrom", "pos", "ref", "alt"]].drop_duplicates().shape + ) if "pos" in vep_file.columns: vep_file["pos"] = vep_file["pos"].astype(int) diff --git a/tests/annotations/test_data/merge_annotations/merge_annotations_mixedIDs/expected/merged_annotations_expected.parquet b/tests/annotations/test_data/merge_annotations/merge_annotations_mixedIDs/expected/merged_annotations_expected.parquet index 3e645640..507fc519 100644 Binary files a/tests/annotations/test_data/merge_annotations/merge_annotations_mixedIDs/expected/merged_annotations_expected.parquet and b/tests/annotations/test_data/merge_annotations/merge_annotations_mixedIDs/expected/merged_annotations_expected.parquet differ diff --git a/tests/annotations/test_data/merge_annotations/merge_annotations_small/expected/merged_annotations_expected.parquet b/tests/annotations/test_data/merge_annotations/merge_annotations_small/expected/merged_annotations_expected.parquet index 3e645640..6ea8c2d8 100644 Binary files a/tests/annotations/test_data/merge_annotations/merge_annotations_small/expected/merged_annotations_expected.parquet and b/tests/annotations/test_data/merge_annotations/merge_annotations_small/expected/merged_annotations_expected.parquet differ