Methodologies for extracting functional pharmacogenomic experiments from international repository.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:18693879", "kind": "science-record", "revision": 3, "content_hash": "sha256:68ab5c77189c6a10ff5b7179ac7c4e343a77b596fb9a42828ec15b849d6aff90", "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": "partial", "title": "Methodologies for extracting functional pharmacogenomic experiments from international repository.", "doi": null, "pmid": "18693879", "authors": ["Yi-An Lin", "Annie Chiang", "Ray Lin", "Peggy Yao", "Rong Chen", "Atul Janardhan Butte"], "journal": "AMIA ... Annual Symposium proceedings. AMIA Symposium", "year": 2007, "abstract": "Pharmacogenomic studies are studies designed to elucidate the relationships between drugs and genes on the genomic scale. Given the rapidly increasing amount of microarray data in international repositories, and the implicit drug information contained in PubMed, MeSH and UMLS, we propose automatic methods for identifying drug-related microarray experiments from NCBI GEO by the semantic connections between these data resources. In our study, we find that 51.5% of microarray experiments are associated with at least one PubMed identifier, 22.1% of these contain a MeSH term that relates to the UMLS Pharmacologic Substances semantic sub-tree. Our work shows an abundance of publicly available gene expression data available to enable the discovery of novel drug indications, drug classifications and other pharmacogenomic studies.", "claims": [{"id": "claim-target-result", "statement": "The study used automatic semantic-connection methods to identify drug-related NCBI GEO microarray experiments by linking GEO data with PubMed identifiers and MeSH/UMLS information, finding that 51.5% of experiments had a PubMed identifier and 22.1% of those contained a relevant MeSH term.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:18693879", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Given the rapidly increasing amount of microarray data in international repositories, and the implicit drug information contained in PubMed, MeSH and UMLS, we propose automatic methods for identifying drug-related microarray experiments from NCBI GEO by the semantic connections between these data resources."}, {"asset": "source:pmid:18693879", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "In our study, we find that 51.5% of microarray experiments are associated with at least one PubMed identifier, 22.1% of these contain a MeSH term that relates to the UMLS Pharmacologic Substances semantic sub-tree."}], "state": "complete"}], "gaps": ["doi"]}, "experiment": {"state": "partial", "objective": "The study used automatic semantic-connection methods to identify drug-related NCBI GEO microarray experiments by linking GEO data with PubMed identifiers and MeSH/UMLS information, finding that 51.5% of experiments had a PubMed identifier and 22.1% of those contained a relevant MeSH term.", "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:18693879"], "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:18693879", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": null, "sha256": "sha256:e71443a7382d464f2cb95170f20f47397691cde1956220230ff38d30caad529b", "bytes": 846, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "18693879", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC2655846", "source": "ncbi_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": [], "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:18693879"], "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": "2026-10-31T18:20:36Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": null}, "calls": 2, "usage": {"prompt_tokens": 1316, "completion_tokens": 729, "cached_tokens": 528}}, "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:18693879", "type": "paper", "label": "pmid:18693879"}, {"id": "source:pmid:18693879", "type": "manuscript", "label": "PMID 18693879 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:18693879", "type": "paper", "label": "pmid:18693879"}, {"id": "source:pmid:18693879", "type": "manuscript", "label": "PMID 18693879 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-18693879", "type": "extraction", "used": ["source:pmid:18693879"], "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:18693879", "parent_hash": "sha256:a7dc4b78ef02810344779d3bfc80600e2c10bb60f121e499d020495579964232", "fork_of": null, "generation": 2}, "gaps": ["doi", "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": ["cale. Given the rapidly increasing amount of microarray data in international repositories, and the", "tomatic methods for identifying drug-related microarray experiments from NCBI GEO by the semantic co", "sources. In our study, we find that 51.5% of microarray experiments are associated with at least one"], "order_basis": "paper_text_order:215", "id": "assay:1"}]}