BRB-ArrayTools Data Archive for human cancer gene expression: a unique and efficient data sharing resource.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:19259398", "kind": "science-record", "revision": 3, "content_hash": "sha256:5f6712426cbe6e8487d4b1081075a4620bec0745417e207ea935aa464a7e2544", "created_at": "2026-11-01T15:14:33Z", "updated_at": "2026-11-01T18:46:44Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "BRB-ArrayTools Data Archive for human cancer gene expression: a unique and efficient data sharing resource.", "doi": "10.4137/cin.s448", "pmid": "19259398", "authors": ["Yingdong Zhao", "Richard Simon"], "journal": "Cancer informatics", "year": 2008, "abstract": "The explosion of available microarray data on human cancer increases the urgency for developing methods for effectively sharing this data among clinical cancer investigators. Lack of a smooth interface between the databases and statistical analysis tools limits the potential benefits of sharing the publicly available microarray data. To facilitate the efficient sharing and use of publicly available microarray data among cancer investigators, we have built a BRB-ArrayTools Data Archive including over one hundred human cancer microarray projects for 28 cancer types. Expression array data and clinical descriptors have been imported into BRB-ArrayTools and are stored as BRB-ArrayTools project folders on the archive. The data archive can be accessed from: http://linus.nci.nih.gov/~brb/DataArchive.html Our BRB-ArrayTools data archive and GEO importer represent ongoing efforts to provide effective tools for efficiently sharing and utilizing human cancer microarray data.", "claims": [{"id": "claim-data-access", "statement": "The GEO importer therefore serves us as an efficient pipeline to collect the most recent publicly available data in the GEO database.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:19259398", "locator": "sections[7] \"Discussion\" paragraph 2", "quote": "The GEO importer therefore serves us as an efficient pipeline to collect the most recent publicly available data in the GEO database."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": null, "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:19259398"], "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:19259398", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.4137/cin.s448", "sha256": "sha256:ca488546e2c2a4b3589e58cdd411d20bbb7b30016489fc1a10638ea922944452", "bytes": 17107, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.4137/cin.s448", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC2623314", "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 GEO importer therefore serves us as an efficient pipeline to collect the most recent publicly available data in the GEO database."], "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:19259398"], "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": null, "independence": "same_provider"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 0, "usage": {}}, "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:19259398", "type": "paper", "label": "pmid:19259398"}, {"id": "source:pmid:19259398", "type": "manuscript", "label": "PMID 19259398 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:19259398", "type": "paper", "label": "pmid:19259398"}, {"id": "source:pmid:19259398", "type": "manuscript", "label": "PMID 19259398 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-19259398", "type": "extraction", "used": ["source:pmid:19259398"], "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": "pmid:19259398", "parent_hash": "sha256:1bdc17b2de2921f7e7fe69b4a6c8c058d5c58772b53f7e8fc9d0e5608e725389", "fork_of": null, "generation": 2}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "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": ["The explosion of available microarray data on human cancer increases the urgency f", "hive including over one hundred human cancer microarray projects for 28 cancer types. Expression arr", "ficiently sharing and utilizing human cancer microarray data.", "l benefits of sharing the publicly available microarray data. To facilitate the efficient sharing an"], "order_basis": "paper_text_order:108", "id": "assay:1"}]}