Exploring heat shock protein-related biomarkers and subgroups in osteoarthritis using Gene Expression Omnibus data sets.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40474128", "kind": "science-record", "revision": 4, "content_hash": "sha256:c19bfc2aec6b63acb84684c3ee6bee10d6455949a9372bb0a4bc94537d7a994f", "created_at": "2026-11-01T20:30:35Z", "updated_at": "2026-11-01T22:56:37Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Exploring heat shock protein-related biomarkers and subgroups in osteoarthritis using Gene Expression Omnibus data sets.", "doi": "10.1186/s12891-025-08827-1", "pmid": "40474128", "authors": ["Weixin Cai", "Boxin Yan", "Hanbing Song", "Jiaxing Liu", "Geqiang Wang", "Yichang Jiang"], "journal": "BMC musculoskeletal disorders", "year": 2025, "abstract": "Osteoarthritis (OA) is a degenerative joint disease marked by cartilage deterioration. Recent studies suggest that heat shock proteins (HSPs) may play a role in the pathophysiology of OA. This study explores the role of heat shock protein-related genes (HSRs) in OA using GEO datasets (GSE12021, GSE55457, GSE55235). Differential expression analysis identified 34 HSRs with significant changes in OA. Protein-protein interaction (PPI) network analysis highlighted central HSRs, including HSPA5, HSPA6, HSPA1L, HSPA12 A, and HSPH1, indicating their key roles in OA. Enrichment analysis revealed that HSRs are involved in protein folding, chaperone activities, and endoplasmic reticulum stress. A nomogram developed from HSR expression profiles demonstrated high accuracy in predicting OA risk. Clustering analysis identified two distinct HSR-related subgroups with unique gene expression and immune profiles. Variations in immune cell infiltration and immune pathway activities were observed between these subgroups. Overall, the study underscores the significance of HSRs in OA pathogenesis and suggests potential personalized therapeutic strategies based on distinct HSR-related subgroups.", "claims": [{"id": "claim-method", "statement": "We employed the limma package to identify differentially expressed genes (DEGs) between the healthy controls (HC) and OA groups.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40474128", "locator": "sections[4] \"Identification of genes with differential expression\" paragraph 2", "quote": "We employed the limma package to identify differentially expressed genes (DEGs) between the healthy controls (HC) and OA groups."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data utilized in this study were sourced from the GEO database, accessible at https://www.ncbi.nlm.nih.gov/geo/. The corresponding accession numbers are: GSE55457, GSE12021, and GSE55235.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40474128", "locator": "sections[27] \"notes\" paragraph 1", "quote": "The data utilized in this study were sourced from the GEO database, accessible at https://www.ncbi.nlm.nih.gov/geo/. The corresponding accession numbers are: GSE55457, GSE12021, and GSE55235."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Integrated analysis of three GEO datasets identified 34 heat shock-related genes with significant changes in osteoarthritis.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40474128", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Differential expression analysis identified 34 HSRs with significant changes in OA."}, {"asset": "source:pmid:40474128", "locator": "sections[3] \"Data acquisition and data preparation\" paragraph 2", "quote": "The data sets for our research were sourced from the NCBI Gene Expression Omnibus (GEO) database."}, {"asset": "source:pmid:40474128", "locator": "sections[3] \"Data acquisition and data preparation\" paragraph 2", "quote": "We specifically employed three OA data sets (GSE12021, GSE55457, and GSE55235) [16, 17]."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Integrated analysis of three GEO datasets identified 34 heat shock-related genes with significant changes in osteoarthritis.", "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:40474128"], "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:GSE12021"], "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:GSE12021"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40474128", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12891-025-08827-1", "sha256": "sha256:8b9182448af4658bf7debe9dc9af1130377732cc2e8fd98c06ef6fe8ed3e5519", "bytes": 37225, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12891-025-08827-1", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12139309", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE12021", "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=GSE12021", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE12021", "version": null, "note": "The data utilized in this study were sourced from the GEO database, accessible at https://www.ncbi.nlm.nih.gov/geo/. The corresponding accession numbers are: GSE55457, GSE12021, and GSE55235.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data utilized in this study were sourced from the GEO database, accessible at https://www.ncbi.nlm.nih.gov/geo/. The corresponding accession numbers are: GSE55457, GSE12021, and GSE55235.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM302859", "GSM302864", "GSM302866", "GSM302870", "GSM302872", "GSM302874", "GSM302876", "GSM302878", "GSM302880", "GSM302881", "GSM302882", "GSM302895", "GSM302896", "GSM302897", "GSM302900", "GSM302905", "GSM302924", "GSM302926", "GSM302927", "GSM302929", "GSM302930", "GSM302932", "GSM302933", "GSM302934", "GSM302943", "GSM302944", "GSM303326", "GSM303339", "GSM303341", "GSM303355", "GSM303356", "GSM303357", "GSM303358", "GSM303359", "GSM303360", "GSM303361", "GSM303362", "GSM303363", "GSM303364", "GSM303365", "GSM303366", "GSM303367", "GSM303368", "GSM303369", "GSM303370", "GSM303377", "GSM303520", "GSM303521", "GSM303522", "GSM303523", "GSM303524", "GSM303525", "GSM303530", "GSM303531", "GSM303532", "GSM303533", "GSM303534"], "sample_count": 57, "group_sizes": null, "group_sizes_basis": null, "platform": "96;97", "taxon": "Homo sapiens", "title": "Identification of inter-individual and gene-specific variances in mRNA expression profiles in the RA SM", "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:GSE55235", "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=GSE55235", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE55235", "version": null, "note": "The data utilized in this study were sourced from the GEO database, accessible at https://www.ncbi.nlm.nih.gov/geo/. The corresponding accession numbers are: GSE55457, GSE12021, and GSE55235.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data utilized in this study were sourced from the GEO database, accessible at https://www.ncbi.nlm.nih.gov/geo/. The corresponding accession numbers are: GSE55457, GSE12021, and GSE55235.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1332201", "GSM1332202", "GSM1332203", "GSM1332204", "GSM1332205", "GSM1332206", "GSM1332207", "GSM1332208", "GSM1332209", "GSM1332210", "GSM1332211", "GSM1332212", "GSM1332213", "GSM1332214", "GSM1332215", "GSM1332216", "GSM1332217", "GSM1332218", "GSM1332219", "GSM1332220", "GSM1332221", "GSM1332222", "GSM1332223", "GSM1332224", "GSM1332225", "GSM1332226", "GSM1332227", "GSM1332228", "GSM1332229", "GSM1332230"], "sample_count": 30, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Identification of rheumatoid arthritis and osteoarthritis patients by transcriptome-based rule set generation", "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:GSE55457", "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=GSE55457", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE55457", "version": null, "note": "The data utilized in this study were sourced from the GEO database, accessible at https://www.ncbi.nlm.nih.gov/geo/. The corresponding accession numbers are: GSE55457, GSE12021, and GSE55235.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data utilized in this study were sourced from the GEO database, accessible at https://www.ncbi.nlm.nih.gov/geo/. The corresponding accession numbers are: GSE55457, GSE12021, and GSE55235.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1337304", "GSM1337305", "GSM1337306", "GSM1337307", "GSM1337308", "GSM1337309", "GSM1337310", "GSM1337311", "GSM1337312", "GSM1337313", "GSM1337314", "GSM1337315", "GSM1337316", "GSM1337317", "GSM1337318", "GSM1337319", "GSM1337320", "GSM1337321", "GSM1337322", "GSM1337323", "GSM1337324", "GSM1337325", "GSM1337326", "GSM1337327", "GSM1337328", "GSM1337329", "GSM1337330", "GSM1337331", "GSM1337332", "GSM1337333", "GSM1337334", "GSM1337335", "GSM1337336"], "sample_count": 33, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Identification of rheumatoid arthritis and osteoarthritis patients by transcriptome-based rule set generation [Jena]", "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:GSE12021 not downloaded", "asset:data:geo:GSE12021 licence not read", "asset:data:geo:GSE55235 not downloaded", "asset:data:geo:GSE55235 licence not read", "asset:data:geo:GSE55457 not downloaded", "asset:data:geo:GSE55457 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": "We employed the limma package to identify differentially expressed genes (DEGs) between the healthy controls (HC) and OA groups."}}, {"id": "method-2", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {"p_value": "est was employed, and a p-value of less than 0"}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Wilcoxon"}}, {"id": "method-3", "family": "clustering", "specific": "hierarchical", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "hierarchical clustering"}}, {"id": "method-4", "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-5", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "GO enrichment"}}, {"id": "method-6", "family": "network_analysis", "specific": "centrality", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "centrality"}}], "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": ["GSE12021", "GSE55457", "GSE55235"], "resolved_accessions": ["GSE12021", "GSE55457", "GSE55235"], "statements": ["The data utilized in this study were sourced from the GEO database, accessible at https://www.ncbi.nlm.nih.gov/geo/. The corresponding accession numbers are: GSE55457, GSE12021, and GSE55235."], "basis": "The paper names GSE12021, GSE55457, GSE55235 in NCBI 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:40474128", "data:geo:GSE12021"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE12021"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:53:55Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9512, "completion_tokens": 1877, "cached_tokens": 264}}, "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:40474128", "type": "paper", "label": "pmid:40474128"}, {"id": "source:pmid:40474128", "type": "manuscript", "label": "PMID 40474128 full text"}, {"id": "data:geo:GSE12021", "type": "dataset", "label": "GEO GSE12021"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40474128", "type": "paper", "label": "pmid:40474128"}, {"id": "source:pmid:40474128", "type": "manuscript", "label": "PMID 40474128 full text"}, {"id": "data:geo:GSE12021", "type": "dataset", "label": "GEO GSE12021"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40474128", "type": "extraction", "used": ["source:pmid:40474128"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE12021", "type": "accession_resolution", "used": ["data:geo:GSE12021"], "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:40474128", "parent_hash": "sha256:c53807f8906ca2e33ddb1f723c282dfb10a5b4fd9c5aa4cf02c4850e1c46f2fd", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE12021 licence not read", "asset:data:geo:GSE12021 not downloaded", "asset:data:geo:GSE55235 licence not read", "asset:data:geo:GSE55235 not downloaded", "asset:data:geo:GSE55457 licence not read", "asset:data:geo:GSE55457 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["Following this, qRT-PCR was performed on the Real-Time PCR System (Applied Biosystems, USA) utilizing S"], "order_basis": "paper_text_order:2004", "id": "assay:1"}, {"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": ["We employed the limma package to identify differentially expressed genes (DEGs) between the healthy controls (HC) and OA groups."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}