Restructured GEO: restructuring Gene Expression Omnibus metadata for genome dynamics analysis.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30649296", "kind": "science-record", "revision": 2, "content_hash": "sha256:b1da259798a5d8bfd04ec851358a54a3966aba14ed2a9009703ac52310d419aa", "created_at": "2026-11-01T15:40:40Z", "updated_at": "2026-11-01T18:50:16Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Restructured GEO: restructuring Gene Expression Omnibus metadata for genome dynamics analysis.", "doi": "10.1093/database/bay145", "pmid": "30649296", "authors": ["Guocai Chen", "Juan Camilo Ramírez", "Nan Deng", "Xing Qiu", "Canglin Wu", "W Jim Zheng", "Hulin Wu"], "journal": "Database : the journal of biological databases and curation", "year": 2019, "abstract": "Motivation: Gene Expression Omnibus (GEO) and other publicly available data store their metadata in the format of unstructured English text, which is very difficult for automated reuse.\nResults: We employed text mining techniques to analyze the metadata of GEO and developed Restructured GEO database (ReGEO). ReGEO reorganizes and categorizes GEO series and makes them searchable by two new attributes extracted automatically from each series' metadata. These attributes are the number of time points tested in the experiment and the disease being investigated. ReGEO also makes series searchable by other attributes available in GEO, such as platform organism, experiment type, associated PubMed ID as well as general keywords in the study's description. Our approach greatly expands the usability of GEO data, demonstrating a credible approach to improve the utility of vast amount of publicly available data in the era of Big Data research.", "claims": [{"id": "claim-data-access", "statement": "We obtained metadata and the titles of samples for Gene Series Expression (GSE) data from GEO and GEOmetadb (14).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30649296", "locator": "sections[3] \"Data source and workflow\" paragraph 2", "quote": "We obtained metadata and the titles of samples for Gene Series Expression (GSE) data from GEO and GEOmetadb (14)."}], "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:30649296"], "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:30649296", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/database/bay145", "sha256": "sha256:bff12a7b2bb245caaf77de0e6ef32588d5689bd6c5756f2b86f2e27462548649", "bytes": 25045, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/database/bay145", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6333964", "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": ["We obtained metadata and the titles of samples for Gene Series Expression (GSE) data from GEO and GEOmetadb (14)."], "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:30649296"], "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": "2026-10-31T18:13:25Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": null}, "calls": 3, "usage": {"prompt_tokens": 18459, "completion_tokens": 2281, "cached_tokens": 792}}, "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:30649296", "type": "paper", "label": "pmid:30649296"}, {"id": "source:pmid:30649296", "type": "manuscript", "label": "PMID 30649296 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30649296", "type": "paper", "label": "pmid:30649296"}, {"id": "source:pmid:30649296", "type": "manuscript", "label": "PMID 30649296 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30649296", "type": "extraction", "used": ["source:pmid:30649296"], "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:30649296", "parent_hash": "sha256:0cfcd5a64a85ced7bc4967b82d61faeca66c94e450ed616bb6f9d41ac10ab8b3", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]}