BioSamples database: the global hub for sample metadata and multi-omics integration.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41231754", "kind": "science-record", "revision": 1, "content_hash": "sha256:f29ffa29b50aaef6d37b055ac7807bbdcd296906dc523f6034174280fc1f506b", "created_at": "2026-11-01T20:31:16Z", "updated_at": "2026-11-01T20:31:16Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "BioSamples database: the global hub for sample metadata and multi-omics integration.", "doi": "10.1093/nar/gkaf1133", "pmid": "41231754", "authors": ["Dipayan Gupta", "Isuru Liyanage", "Yasset Perez-Riverol", "Enrique Sapena Ventura", "Wei Kheng Teh", "Tim Van Den Bossche", "Senthilnathan Vijayaraja", "Amnon Khen", "Ugis Sarkans", "Tony Burdett", "Jeena Rajan"], "journal": "Nucleic acids research", "year": 2026, "abstract": "The BioSamples database (https://www.ebi.ac.uk/biosamples/) at the European Bioinformatics Institute (EMBL-EBI) is a core infrastructure resource that provides a centralized platform for the storage, curation, and dissemination of biological sample metadata. BioSamples holds sample descriptions across diverse datasets, enhancing their reusability and integrability in accordance with the FAIR (findable, accessible, interoperable, and reusable) principles. BioSamples serves as the central place to store the sample metadata for multiple repositories and archives at EMBL-EBI, including the European Nucleotide Archive, ArrayExpress, and the European Phenome-Genome Archive. In this article, we outline technical updates made to support increased sample registration and provide a better user experience. We describe four use cases whereby different communities have leveraged BioSamples to connect multi-omics data and enable the creation of public data portals and data status trackers. BioSamples is freely available, and its content is distributed under the EMBL-EBI Terms of Use available at https://www.ebi.ac.uk/about/terms-of-use. The BioSamples code is available at https://github.com/EBIBioSamples/biosamples-v4 and https://doi.org/10.5281/zenodo.17304021 and is distributed under the Apache 2.0 license.", "claims": [{"id": "claim-data-access", "statement": "The BioSamples database is freely available, and its content is distributed under the EMBL-EBI Terms of Use available at https://www.ebi.ac.uk/about/terms-of-use. The BioSamples code is available at https://github.com/EBIBioSamples/biosamples-v4 and https://doi.org/10.5281/zenodo.17304021 and distributed under the Apache 2.0 license.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41231754", "locator": "sections[19] \"Data availability\" paragraph 2", "quote": "The BioSamples database is freely available, and its content is distributed under the EMBL-EBI Terms of Use available at https://www.ebi.ac.uk/about/terms-of-use. The BioSamples code is available at https://github.com/EBIBioSamples/biosamples-v4 and https://doi.org/10.5281/zenodo.17304021 and distributed under the Apache 2.0 license."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:41231754"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:accession_absent", "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41231754", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/nar/gkaf1133", "sha256": "sha256:0ce7e19ac850e14278e5f8f5335d4231f2ea2ce6cfcac3acdfbd98088f1e8171", "bytes": 33657, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/nar/gkaf1133", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12807758", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (not named), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["The BioSamples database is freely available, and its content is distributed under the EMBL-EBI Terms of Use available at https://www.ebi.ac.uk/about/terms-of-use. The BioSamples code is available at https://github.com/EBIBioSamples/biosamples-v4 and https://doi.org/10.5281/zenodo.17304021 and distributed under the Apache 2.0 license."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:41231754"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:05:41Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9205, "completion_tokens": 644, "cached_tokens": 264}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:41231754", "type": "paper", "label": "pmid:41231754"}, {"id": "source:pmid:41231754", "type": "manuscript", "label": "PMID 41231754 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41231754", "type": "paper", "label": "pmid:41231754"}, {"id": "source:pmid:41231754", "type": "manuscript", "label": "PMID 41231754 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41231754", "type": "extraction", "used": ["source:pmid:41231754"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": null, "parent_hash": null, "fork_of": null, "generation": 0}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]}