Metabolic and immune heterogeneity in stroke: Insights into subtype identification and biomarker discovery.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40397919", "kind": "science-record", "revision": 3, "content_hash": "sha256:39c5892d20cd26edd2d7c3b8f337cafa66eb88d4a021c9d06c81ffacb6d92343", "created_at": "2026-11-01T20:30:32Z", "updated_at": "2026-11-01T22:14:05Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Metabolic and immune heterogeneity in stroke: Insights into subtype identification and biomarker discovery.", "doi": "10.1371/journal.pone.0323172", "pmid": "40397919", "authors": ["Wei Wang", "Qiuyang Qian", "Ziye Guo", "Fangyi Lin", "Weiming Lin", "Zhigang Yuan", "Mei Shen"], "journal": "PloS one", "year": 2025, "abstract": "Stroke is a leading cause of mortality and long-term disability worldwide, characterized by substantial molecular and clinical heterogeneity. This study aimed to investigate the metabolic and immune-related mechanisms underlying stroke subtypes using transcriptomic data and advanced computational tools. Gene expression data from two GEO datasets (GSE16561 and GSE58294) were preprocessed, batch-corrected, and integrated. Consensus clustering based on 2,752 metabolism-related genes identified three distinct subtypes with significant differences in metabolic activity. GSVA analysis revealed subtype-specific variations in key pathways, such as the citrate cycle, glycolysis, and glycosaminoglycan biosynthesis, highlighting their metabolic diversity.", "claims": [{"id": "claim-method", "statement": "Consensus clustering was performed using a published list of 2,752 metabolism-related genes encoding known human metabolic enzymes and transporters.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40397919", "locator": "sections[4] \"2. Disease subtype identification\" paragraph 2", "quote": "Consensus clustering was performed using a published list of 2,752 metabolism-related genes encoding known human metabolic enzymes and transporters."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Gene expression data for stroke patients were obtained from the Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/). Two datasets, GSE16561 and GSE58294, were selected for analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40397919", "locator": "sections[20] \"Data Availability\" paragraph 2", "quote": "Gene expression data for stroke patients were obtained from the Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/). Two datasets, GSE16561 and GSE58294, were selected for analysis."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Consensus clustering based on 2,752 metabolism-related genes identified three distinct subtypes with significant differences in metabolic activity.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40397919", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Consensus clustering based on 2,752 metabolism-related genes identified three distinct subtypes with significant differences in metabolic activity."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Consensus clustering based on 2,752 metabolism-related genes identified three distinct subtypes with significant differences in metabolic activity.", "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:40397919"], "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:GSE16561"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:group_comparison_wilcoxon", "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:GSE16561"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:group_comparison_wilcoxon"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40397919", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0323172", "sha256": "sha256:1007ccaa4b295fd44f34f075886e3f402fceafeeb13ed29f1d3122d7d9332948", "bytes": 33985, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0323172", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12094752", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE16561", "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=GSE16561", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE16561", "version": null, "note": "Gene expression data for stroke patients were obtained from the Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/). Two datasets, GSE16561 and GSE58294, were selected for analysis.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene expression data for stroke patients were obtained from the Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/). Two datasets, GSE16561 and GSE58294, were selected for analysis.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM416528", "GSM416529", "GSM416530", "GSM416531", "GSM416532", "GSM416533", "GSM416534", "GSM416535", "GSM416536", "GSM416537", "GSM416538", "GSM416539", "GSM416540", "GSM416541", "GSM416542", "GSM416543", "GSM416544", "GSM416545", "GSM416546", "GSM416547", "GSM416548", "GSM416549", "GSM416550", "GSM416551", "GSM416552", "GSM416553", "GSM416554", "GSM416555", "GSM416556", "GSM416557", "GSM416558", "GSM416559", "GSM416560", "GSM416561", "GSM416562", "GSM416563", "GSM416564", "GSM416565", "GSM416566", "GSM416567", "GSM416568", "GSM416569", "GSM416570", "GSM416571", "GSM416572", "GSM416573", "GSM416574", "GSM416575", "GSM416576", "GSM416577", "GSM416578", "GSM416579", "GSM416580", "GSM416581", "GSM416582", "GSM416583", "GSM416584", "GSM416585", "GSM416586", "GSM416587", "GSM416588", "GSM416589", "GSM416590"], "sample_count": 63, "group_sizes": null, "group_sizes_basis": null, "platform": "6883", "taxon": "Homo sapiens", "title": "Gene expression analysis of peripheral whole blood RNA following ischemic stroke", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE58294", "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=GSE58294", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE58294", "version": null, "note": "Gene expression data for stroke patients were obtained from the Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/). Two datasets, GSE16561 and GSE58294, were selected for analysis.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene expression data for stroke patients were obtained from the Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/). Two datasets, GSE16561 and GSE58294, were selected for analysis.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1406033", "GSM1406034", "GSM1406035", "GSM1406036", "GSM1406037", "GSM1406038", "GSM1406039", "GSM1406040", "GSM1406041", "GSM1406042", "GSM1406043", "GSM1406044", "GSM1406045", "GSM1406046", "GSM1406047", "GSM1406048", "GSM1406049", "GSM1406050", "GSM1406051", "GSM1406052", "GSM1406053", "GSM1406054", "GSM1406055", "GSM1406056", "GSM1406057", "GSM1406058", "GSM1406059", "GSM1406060", "GSM1406061", "GSM1406062", "GSM1406063", "GSM1406064", "GSM1406065", "GSM1406066", "GSM1406067", "GSM1406068", "GSM1406069", "GSM1406070", "GSM1406071", "GSM1406072", "GSM1406073", "GSM1406074", "GSM1406075", "GSM1406076", "GSM1406077", "GSM1406078", "GSM1406079", "GSM1406080", "GSM1406081", "GSM1406082", "GSM1406083", "GSM1406084", "GSM1406085", "GSM1406086", "GSM1406087", "GSM1406088", "GSM1406089", "GSM1406090", "GSM1406091", "GSM1406092", "GSM1406093", "GSM1406094", "GSM1406095", "GSM1406096", "GSM1406097", "GSM1406098", "GSM1406099", "GSM1406100", "GSM1406101", "GSM1406102", "GSM1406103", "GSM1406104", "GSM1406105", "GSM1406106", "GSM1406107", "GSM1406108", "GSM1406109", "GSM1406110", "GSM1406111", "GSM1406112", "GSM1406113", "GSM1406114", "GSM1406115", "GSM1406116", "GSM1406117", "GSM1406118", "GSM1406119", "GSM1406120", "GSM1406121", "GSM1406122", "GSM1406123", "GSM1406124"], "sample_count": 92, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene Expression Following Cardioembolic Stroke", "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:GSE16561 not downloaded", "asset:data:geo:GSE16561 licence not read", "asset:data:geo:GSE58294 not downloaded", "asset:data:geo:GSE58294 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Wilcoxon"}}, {"id": "method-2", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.8, "band": "high", "quote": "limma"}}, {"id": "method-3", "family": "model_calibration", "specific": "decision_curve", "label": "Model calibration / clinical utility", "dsl_operations": ["calibration_bins", "net_benefit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictions_and_outcomes"], "evidence": {"score": 0.8, "band": "high", "quote": "decision curve analysis"}}, {"id": "method-4", "family": null, "specific": null, "label": "Consensus clustering", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Consensus clustering was performed using a published list of 2,752 metabolism-related genes encoding known human metabolic enzymes and transporters."}}], "targets": [], "gaps": ["method.reader_named_unmapped", "method.group_comparison_wilcoxon"]}, "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": false, "required_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: wilcoxon."}, "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": ["GSE16561", "GSE58294"], "resolved_accessions": ["GSE16561", "GSE58294"], "statements": ["Gene expression data for stroke patients were obtained from the Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo/). Two datasets, GSE16561 and GSE58294, were selected for analysis."], "basis": "The paper names GSE16561, GSE58294 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:40397919", "data:geo:GSE16561"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "group_comparison_wilcoxon", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE16561"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:52:50Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9466, "completion_tokens": 1161, "cached_tokens": 0}}, "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:40397919", "type": "paper", "label": "pmid:40397919"}, {"id": "source:pmid:40397919", "type": "manuscript", "label": "PMID 40397919 full text"}, {"id": "data:geo:GSE16561", "type": "dataset", "label": "GEO GSE16561"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40397919", "type": "paper", "label": "pmid:40397919"}, {"id": "source:pmid:40397919", "type": "manuscript", "label": "PMID 40397919 full text"}, {"id": "data:geo:GSE16561", "type": "dataset", "label": "GEO GSE16561"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40397919", "type": "extraction", "used": ["source:pmid:40397919"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE16561", "type": "accession_resolution", "used": ["data:geo:GSE16561"], "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:40397919", "parent_hash": "sha256:a783e26793d58134b60295fb6bfd075f4a72e25385dea2285b4beb9a3b1fd38e", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE16561 licence not read", "asset:data:geo:GSE16561 not downloaded", "asset:data:geo:GSE58294 licence not read", "asset:data:geo:GSE58294 not downloaded", "execution.not_run", "method.group_comparison_wilcoxon", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:group_comparison_wilcoxon"], "assays": [{"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Wilcoxon"], "order_basis": "analysis_only", "id": "assay:1"}]}