Control of dataset bias in combined Affymetrix cohorts of triple negative breast cancer.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26484129", "kind": "science-record", "revision": 3, "content_hash": "sha256:fbce9a3e47dd748d1a66c0abb9d60edaf8075e935c67ad46a8392ee563b80d52", "created_at": "2026-11-01T15:40:11Z", "updated_at": "2026-11-01T21:20:09Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Control of dataset bias in combined Affymetrix cohorts of triple negative breast cancer.", "doi": "10.1016/j.gdata.2014.09.014", "pmid": "26484129", "authors": ["Thomas Karn", "Achim Rody", "Volkmar Müller", "Marcus Schmidt", "Sven Becker", "Uwe Holtrich", "Lajos Pusztai"], "journal": "Genomics data", "year": 2014, "abstract": "Heterogenous subtypes of breast cancer need to be analyzed separately. Pooling of datasets can provide reasonable sample sizes but dataset bias is an important concern. We assembled a combined dataset of 579 Affymetrix microarrays from triple negative breast cancer (TNBC) in Gene Expression Omnibus (GEO) series GSE31519. We developed a method for selecting comparable datasets and to control for the amount of dataset bias of individual probesets.", "claims": [{"id": "claim-method", "statement": "To assess dataset bias, we used Kruskal–Wallis statistic comparing the expression of each probeset with the primary dataset vector across the 394 TNBCs.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26484129", "locator": "sections[8] \"Control for biased probesets\" paragraph 2", "quote": "To assess dataset bias, we used Kruskal–Wallis statistic comparing the expression of each probeset with the primary dataset vector across the 394 TNBCs."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The normalized data are available under the following link:\nhttp://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE31519&format=file&file=GSE31519%5Fcomplete%5Fdataset%2Etxt%2Egz", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26484129", "locator": "sections[5] \"Dataset\" paragraphs 1-9", "quote": "The normalized data are available under the following link:\nhttp://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE31519&format=file&file=GSE31519%5Fcomplete%5Fdataset%2Etxt%2Egz"}], "state": "complete"}, {"id": "claim-target-result", "statement": "The paper assembled a combined cohort of 579 TNBC microarrays from GEO series GSE31519 and developed a two-part statistical method that selects comparable datasets and controls dataset-biased probesets.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:26484129", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We assembled a combined dataset of 579 Affymetrix microarrays from triple negative breast cancer (TNBC) in Gene Expression Omnibus (GEO) series GSE31519."}, {"asset": "source:pmid:26484129", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We developed a method for selecting comparable datasets and to control for the amount of dataset bias of individual probesets."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The paper assembled a combined cohort of 579 TNBC microarrays from GEO series GSE31519 and developed a two-part statistical method that selects comparable datasets and controls dataset-biased probesets.", "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:26484129"], "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": "complete", "blocked_on": null, "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": ["data:geo:GSE31519"], "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": ["data:geo:GSE31519"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26484129", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.gdata.2014.09.014", "sha256": "sha256:07e3d68a4714430678b006d8a0a8900da2fd8c1c7dd2f2f0a0ebe5b2e51f0487", "bytes": 9975, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.gdata.2014.09.014", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4535974", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE31519", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31519", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31519", "version": null, "note": "The normalized data are available under the following link:\nhttp://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE31519&format=file&file=GSE31519%5Fcomplete%5Fdataset%2Etxt%2Egz", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The normalized data are available under the following link:\nhttp://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE31519&format=file&file=GSE31519%5Fcomplete%5Fdataset%2Etxt%2Egz", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM782523", "GSM782524", "GSM782525", "GSM782526", "GSM782527", "GSM782528", "GSM782529", "GSM782530", "GSM782531", "GSM782532", "GSM782533", "GSM782534", "GSM782535", "GSM782536", "GSM782537", "GSM782538", "GSM782539", "GSM782540", "GSM782541", "GSM782542", "GSM782543", "GSM782544", "GSM782545", "GSM782546", "GSM782547", "GSM782548", "GSM782549", "GSM782550", "GSM782551", "GSM782552", "GSM782553", "GSM782554", "GSM782555", "GSM782556", "GSM782557", "GSM782558", "GSM782559", "GSM782560", "GSM782561", "GSM782562", "GSM782563", "GSM782564", "GSM782565", "GSM782566", "GSM782567", "GSM782568", "GSM782569", "GSM782570", "GSM782571", "GSM782572", "GSM782573", "GSM782574", "GSM782575", "GSM782576", "GSM782577", "GSM782578", "GSM782579", "GSM782580", "GSM782581", "GSM782582", "GSM782583", "GSM782584", "GSM782585", "GSM782586", "GSM782587", "GSM782588", "GSM782589"], "sample_count": 67, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "A Clinically Relevant Gene Signature in Triple-Negative and Basal-Like Breast Cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE31519 not downloaded", "asset:data:geo:GSE31519 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Kruskal–Wallis statistic", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To assess dataset bias, we used Kruskal–Wallis statistic comparing the expression of each probeset with the primary dataset vector across the 394 TNBCs."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Kruskal–Wallis statistic), 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": "R1", "reachable": true, "accessions": ["GSE31519"], "resolved_accessions": ["GSE31519"], "statements": ["The normalized data are available under the following link:\nhttp://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE31519&format=file&file=GSE31519%5Fcomplete%5Fdataset%2Etxt%2Egz"], "basis": "The paper names GSE31519 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:26484129", "data:geo:GSE31519"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE31519"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:25:10Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 25198, "completion_tokens": 3777, "cached_tokens": 1544}}, "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:26484129", "type": "paper", "label": "pmid:26484129"}, {"id": "source:pmid:26484129", "type": "manuscript", "label": "PMID 26484129 full text"}, {"id": "data:geo:GSE31519", "type": "dataset", "label": "GEO GSE31519"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26484129", "type": "paper", "label": "pmid:26484129"}, {"id": "source:pmid:26484129", "type": "manuscript", "label": "PMID 26484129 full text"}, {"id": "data:geo:GSE31519", "type": "dataset", "label": "GEO GSE31519"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26484129", "type": "extraction", "used": ["source:pmid:26484129"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE31519", "type": "accession_resolution", "used": ["data:geo:GSE31519"], "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": "pmid:26484129", "parent_hash": "sha256:a447d9914eb030108e6a2511d26da21722d2991d08506c33fb428edb28c60671", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE31519 licence not read", "asset:data:geo:GSE31519 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Control of dataset bias in combined Affymetrix cohorts of triple negative breast cancer.", "cern. We assembled a combined dataset of 579 Affymetrix microarrays from triple negative breast canc"], "order_basis": "paper_text_order:0", "id": "assay:1"}]}