From e5f2ea34d0b5876de4ad9a43679561281ea1fb89 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?M=C3=A1t=C3=A9=20Balajti?= Date: Tue, 29 Oct 2024 11:52:21 +0100 Subject: [PATCH] update docstrings for get_source_expression --- htsinfer/get_library_source.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/htsinfer/get_library_source.py b/htsinfer/get_library_source.py index 3ee5b9d..5fcf945 100644 --- a/htsinfer/get_library_source.py +++ b/htsinfer/get_library_source.py @@ -247,7 +247,7 @@ def run_kallisto_quantification( def get_source_expression( kallisto_dir: Path, ) -> DataFrame: - """Return percentages of total expression per read source. + """Return percentages of total estimated counts per read source. Args: kallisto_dir: Directory containing Kallisto quantification results. @@ -255,9 +255,9 @@ def get_source_expression( Returns: Data frame with columns `source_ids` (a tuple of source short name and taxon identifier, e.g., `("hsapiens", 9606)`) and - `est_counts`, signifying the percentages of total expression - per read source. The data frame is sorted by total expression - in descending order. + `est_counts`, signifying the percentages of total estimated + counts per read source. The data frame is sorted by total + estimated counts in descending order. Raises: FileProblem: Kallisto quantification results could not be @@ -285,7 +285,7 @@ def get_source_expression( # handle case where no alignments are found dat.est_counts.fillna(0, inplace=True) - # aggregate expression by source identifiers + # aggregate counts by source identifiers dat[[ 'gene_symbol', 'gene_id',