jan-gruszczynski-publications/stainology-paper: 1.1.0

Stainology Database This repository accompanies the paper: Ovarian Stainology: Database of evidence-based immunohistochemical antigen expression in ovarian tumorsGruszczyński et al., Scientific Data (2026)https://www.nature.com/articles/s41597-026-07776-1 It provides all scripts and pipeline components used to extract, process, and structure immunohistochemistry (IHC) data from published scientific literature. Project website (database, documentation, more details):https://stainology.cs.put.poznan.pl/ --- Version Current: v1.1.0 — post-publication release with bug fixes to the deduplication step and extensive updates to stain and expression type nomenclature variation dictionaries. To reproduce results exactly as published, use Release 1.0.1:https://github.com/jan-gruszczynski-publications/stainology-paper/releases/tag/v1.0.1 --- Repository Structure /data_extraction/Contains all scripts used to identify relevant publications and extract IHC information from abstracts and tables. /post_processing/Houses the implementation of pipeline modules used to clean, filter, normalize, and harmonize the raw extracted data. Includes:- Pipeline sub-modules used to implement post-processing steps.- The full pipeline logic used to generate the final version of the dataset.