The abstract is read at the publisher; the summary is JClub's.
SRAscout integrates NCBI SRA run metadata with BioProject records to enable semantic retrieval across about 714,000 BioProjects using BioBERT embeddings.
- Why it matters: Public sequencing repositories contain tens of millions of runs, but incomplete and inconsistent metadata make keyword-only search difficult and limit efficient dataset discovery and reuse.
- What they did: SRAscout harmonizes sample attributes (e.g., cell line, tissue, age, sex, treatment) into a consistent schema and embeds BioProject title/name/organism/description with a BioBERT-based model.
- The result: Users can search by DOI/PubMed ID, free text, or BioProject/SRA accessions, then download harmonized metadata tables and scripts to fetch files from ENA via a public API.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.