Whole-genome mRNA expression profiling identifies functional and prognostic signatures in patients with mesenchymal glioblastoma multiforme.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:23663361", "kind": "science-record", "revision": 3, "content_hash": "sha256:c84c7824cf3c775fe617dfad648fc7522b169d479ec09edc080bfc1d4813aec9", "created_at": "2026-11-01T15:40:03Z", "updated_at": "2026-11-01T21:19:41Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Whole-genome mRNA expression profiling identifies functional and prognostic signatures in patients with mesenchymal glioblastoma multiforme.", "doi": "10.1111/cns.12118", "pmid": "23663361", "authors": ["Zhao-Shi Bao", "Chuan-Bao Zhang", "Hong-Jun Wang", "Wei Yan", "Yan-Wei Liu", "Ming-Yang Li", "Wei Zhang"], "journal": "CNS neuroscience & therapeutics", "year": 2013, "abstract": "BACKGROUND: The Cancer Genome Atlas (TCGA) has divided patients with glioblastoma multiforme (GBM) into four subtypes based on mRNA expression microarray. The mesenchymal subtype, with a larger proportion, is considered a more lethal one. Clinical outcome prediction is required to better guide more personalized treatment for these patients.\nAIMS: The objective of this study was to identify a mRNA expression signature to improve outcome prediction for patients with mesenchymal GBM.\nRESULTS: For signature identification and validation, we downloaded mRNA expression microarray data from TCGA as training set and data from Rembrandt and GSE16011 as validation set. Cox regression and risk-score analysis were used to develop the 4 signatures, which were function and prognosis associated as revealed by Gene Ontology (GO) analysis and Gene Set Variation Analysis (GSVA). Patients who had high-risk scores according to the signatures had poor overall survival compared with patients who had low-risk scores.\nCONCLUSIONS: The signatures were identified as risk predictors that patients who had a high-risk score tended to have unfavorable outcome, demonstrating their potential for personalizing cancer management.", "claims": [{"id": "claim-target-result", "statement": "The study used Cox regression and risk-score analysis to develop four mRNA expression signatures for mesenchymal GBM outcome prediction, with TCGA as the training source and Rembrandt and GSE16011 as validation sources; no numerical performance result for this methodological target is reported in the abstract.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:23663361", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "For signature identification and validation, we downloaded mRNA expression microarray data from TCGA as training set and data from Rembrandt and GSE16011 as validation set."}, {"asset": "source:pmid:23663361", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Cox regression and risk‐score analysis were used to develop the 4 signatures, which were function and prognosis associated as revealed by Gene Ontology (GO) analysis and Gene Set Variation Analysis (GSVA)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The study used Cox regression and risk-score analysis to develop four mRNA expression signatures for mesenchymal GBM outcome prediction, with TCGA as the training source and Rembrandt and GSE16011 as validation sources; no numerical performance result for this methodological target is reported in the abstract.", "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:23663361"], "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:23663361", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1111/cns.12118", "sha256": "sha256:96a8ef1ebbeeca20579b6e22d385f88f86658fef62b3036dbe58b5eced372a7d", "bytes": 1188, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1111/cns.12118", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6493663", "source": "ncbi_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Cox regression"}}], "targets": [], "gaps": []}, "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": "R1", "expressible": true, "required_operations": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["cox_ph"], "assets": ["source:pmid:23663361"], "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": "2026-10-31T18:21:23Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": null}, "calls": 2, "usage": {"prompt_tokens": 1438, "completion_tokens": 605, "cached_tokens": 520}}, "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:23663361", "type": "paper", "label": "pmid:23663361"}, {"id": "source:pmid:23663361", "type": "manuscript", "label": "PMID 23663361 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:23663361", "type": "paper", "label": "pmid:23663361"}, {"id": "source:pmid:23663361", "type": "manuscript", "label": "PMID 23663361 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-23663361", "type": "extraction", "used": ["source:pmid:23663361"], "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:23663361", "parent_hash": "sha256:b2853bc6725f3ab5db6e5fbd4b21eca8ecd114aced3c01b13d0bc46df99c5d62", "fork_of": null, "generation": 2}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Cox regression"], "order_basis": "analysis_only", "id": "assay:1"}]}