The impact of inflammation and iron metabolism on gene expression alterations in ischemic stroke: a bioinformatics approach.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40307317", "kind": "science-record", "revision": 4, "content_hash": "sha256:4a6af50bd136fbaf0244c4accfd2c160a08d5fef2496363f7a4f0c9043602df4", "created_at": "2026-11-01T20:30:27Z", "updated_at": "2026-11-01T22:56:27Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "The impact of inflammation and iron metabolism on gene expression alterations in ischemic stroke: a bioinformatics approach.", "doi": "10.1038/s41598-025-00369-9", "pmid": "40307317", "authors": ["Shengwu Wang", "Xuemei Li", "Youcai Bi", "Chao Yan", "Yunbo Chen"], "journal": "Scientific reports", "year": 2025, "abstract": "This study explores the differential expression of inflammation and iron metabolism-related genes (IIMRDEGs) in Ischemic Stroke (IS), a major contributor to global morbidity and mortality. Using the Gene Expression Omnibus (GEO) query tool, we integrated gene expression datasets GSE22255 and GSE16561. We identified 56 differentially expressed genes (DEGs), including 42 that were upregulated and 14 downregulated, according to criteria of |logFC| > 0.5 and p < 0.05. An intersection with known IIMRDEGs revealed 16 genes with significant relevance to IS, such as SLC22A4 and DUSP1. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses indicated that these genes are mainly involved in leukocyte chemotaxis and responses to bacterial molecules, in addition to IL-17 and TNF signaling pathways. A protein-protein interaction (PPI) network of 12 IIMRDEGs identified 8 hub genes, including IL7R and ADM, which exhibited significant expression differences (p < 0.001) and potential diagnostic utility with AUC values between 0.7 and 0.9 in ROC curve analysis. Furthermore, immune infiltration analysis showed notable differences in 7 immune cell types between IS and control samples. Our findings advance the understanding of ischemic stroke mechanisms and present potential biomarkers for improving diagnosis and therapeutic strategies.", "claims": [{"id": "claim-method", "statement": "To analyze the differences in gene expression values between the IS samples and control samples in the combined GEO datasets, the R package limma was used for differential analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40307317", "locator": "sections[5] \"Cerebral infarction-related inflammation and iron metabolism related differentially expressed genes\" paragraph 2", "quote": "To analyze the differences in gene expression values between the IS samples and control samples in the combined GEO datasets, the R package limma was used for differential analysis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data is provided within the manuscript and supplementary information files.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40307317", "locator": "sections[27] \"notes\" paragraph 1", "quote": "Data is provided within the manuscript and supplementary information files."}], "state": "complete"}, {"id": "claim-target-result", "statement": "An intersection with known IIMRDEGs revealed 16 genes with significant relevance to IS, such as SLC22A4 and DUSP1.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40307317", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "An intersection with known IIMRDEGs revealed 16 genes with significant relevance to IS, such as SLC22A4 and DUSP1."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "An intersection with known IIMRDEGs revealed 16 genes with significant relevance to IS, such as SLC22A4 and DUSP1.", "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:40307317"], "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": "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": ["data:geo:GSE16561"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40307317", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-025-00369-9", "sha256": "sha256:3007cb4a40e8be06f6ce9401fe17badce32ff6501479b7ec612f65d6e3035c65", "bytes": 56973, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-025-00369-9", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12044060", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "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": "Data is provided within the manuscript and supplementary information files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data is provided within the manuscript and supplementary information files.", "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:GSE22255", "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=GSE22255", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE22255", "version": null, "note": "Data is provided within the manuscript and supplementary information files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data is provided within the manuscript and supplementary information files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM554014", "GSM554015", "GSM554016", "GSM554017", "GSM554018", "GSM554019", "GSM554020", "GSM554021", "GSM554022", "GSM554023", "GSM554024", "GSM554025", "GSM554026", "GSM554027", "GSM554028", "GSM554029", "GSM554030", "GSM554031", "GSM554032", "GSM554033", "GSM554034", "GSM554035", "GSM554036", "GSM554037", "GSM554038", "GSM554039", "GSM554040", "GSM554041", "GSM554042", "GSM554043", "GSM554044", "GSM554045", "GSM554046", "GSM554047", "GSM554048", "GSM554049", "GSM554050", "GSM554051", "GSM554052", "GSM554053"], "sample_count": 40, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Blood genomic expression profile for ischemic stroke (IS)", "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:GSE22255 not downloaded", "asset:data:geo:GSE22255 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "To analyze the differences in gene expression values between the IS samples and control samples in the combined GEO datasets, the R package limma was used for differential analysis."}}, {"id": "method-2", "family": "group_comparison", "specific": "mann_whitney", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_mann_whitney"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Mann-Whitney"}}, {"id": "method-3", "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-4", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Spearman correlation"}}, {"id": "method-5", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-6", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.7, "band": "medium", "quote": "ROC curve"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE22255", "GSE16561"], "resolved_accessions": ["GSE22255", "GSE16561"], "statements": ["Data is provided within the manuscript and supplementary information files."], "basis": "The paper names GSE22255, GSE16561 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:40307317", "data:geo:GSE16561"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "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": "2026-11-01T19:51:28Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 14857, "completion_tokens": 1067, "cached_tokens": 128}}, "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:40307317", "type": "paper", "label": "pmid:40307317"}, {"id": "source:pmid:40307317", "type": "manuscript", "label": "PMID 40307317 full text"}, {"id": "data:geo:GSE16561", "type": "dataset", "label": "GEO GSE16561"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40307317", "type": "paper", "label": "pmid:40307317"}, {"id": "source:pmid:40307317", "type": "manuscript", "label": "PMID 40307317 full text"}, {"id": "data:geo:GSE16561", "type": "dataset", "label": "GEO GSE16561"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40307317", "type": "extraction", "used": ["source:pmid:40307317"], "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:40307317", "parent_hash": "sha256:5e9d254fcc082cf86b7d05553761a79f7f5704a6b5a9628117c252db9fc07d2e", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE16561 licence not read", "asset:data:geo:GSE16561 not downloaded", "asset:data:geo:GSE22255 licence not read", "asset:data:geo:GSE22255 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["To analyze the differences in gene expression values between the IS samples and control samples in the combined GEO datasets, the R package limma was used for differential analysis."], "order_basis": "analysis_only", "id": "assay:1"}]}