Identification of genes and pathways associated with subchondral bone in osteoarthritis via bioinformatic analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32925767", "kind": "science-record", "revision": 14, "content_hash": "sha256:ab49690f0dbba94f76b8352119301a5da3f66c53012660fc0b1d00b38f9bb40d", "created_at": "2026-11-01T15:41:10Z", "updated_at": "2026-11-01T23:42:39Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of genes and pathways associated with subchondral bone in osteoarthritis via bioinformatic analysis.", "doi": "10.1097/MD.0000000000022142", "pmid": "32925767", "authors": ["Zhanyu Yang", "Jiangdong Ni", "Letian Kuang", "Yongquan Gao", "Shibin Tao"], "journal": "Medicine", "year": 2020, "abstract": "Osteoarthritis (OA) is a high prevalent musculoskeletal problem, which can cause severe pain, constitute a huge social and economic burden, and seriously damage the quality of life. This study was intended to identify genetic characteristics of subchondral bone in patients with OA and to elucidate the potential molecular mechanisms involved. Data of gene expression profiles (GSE51588), which contained 40 OA samples and 10 normal samples, was obtained from the Gene Expression Omnibus (GEO). The raw data were integrated to obtain differentially expressed genes (DEGs) and were further analyzed with bioinformatic analysis. The protein-protein interaction (PPI) networks were built and analyzed via Search Tool for the Retrieval of Interacting Genes (STRING). The significant modules and hub genes were identified via Cytoscape. Moreover, Gene Ontology (GO) and Kyoto Encyclopaedia of Genes and Genomes (KEGG) enrichment analysis were performed. Totally 235 DEGs were differentially expressed in the subchondral bone from OA patients compared with those of normal individuals, of which 78 were upregulated and 157 were downregulated. Eight hub genes were identified, including DEFA4, ARG1, LTF, RETN, PGLYRP1, OLFM4, ORM1, and BPI. The enrichment analyses of the DEGs and significant modules indicated that DEGs were mainly involved in inflammatory response, extracellular space, RAGE receptor binding, and amoebiasis pathway. The present study provides a novel and in-depth understanding of pathogenesis of the OA subchondral bone at molecular level. DEFA4, ARG1, LTF, RETN, PGLYRP1, OLFM4, ORM1, and BPI may be the new candidate targets for diagnosis and therapies on patients with OA in the future.", "claims": [{"id": "claim-method", "statement": "DEGs were identified using classical t test and statistically significant DEGs were defined with the criteria of |Log2(FC)| > 2 and adj. P < .05.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32925767", "locator": "sections[4] \"DEGs screening and hierarchical clustering analysis\" paragraph 2", "quote": "DEGs were identified using classical t test and statistically significant DEGs were defined with the criteria of |Log2(FC)| > 2 and adj. P < .05."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data sharing not applicable to this article as no datasets were generated or analyzed during the present study.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32925767", "locator": "sections[16] \"Footnotes\" paragraph 2", "quote": "Data sharing not applicable to this article as no datasets were generated or analyzed during the present study."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "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:32925767"], "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:GSE51588"], "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:GSE51588"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32925767", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1097/MD.0000000000022142", "sha256": "sha256:1c5ce0829c1b6bfffef10e6ee7a233b243cbe20b72fb118c9e24ca65100ece45", "bytes": 32467, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1097/MD.0000000000022142", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7489699", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE51588", "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=GSE51588", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE51588", "version": null, "note": "Data sharing not applicable to this article as no datasets were generated or analyzed during the present study.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sharing not applicable to this article as no datasets were generated or analyzed during the present study.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1248759", "GSM1248760", "GSM1248761", "GSM1248762", "GSM1248763", "GSM1248764", "GSM1248765", "GSM1248766", "GSM1248767", "GSM1248768", "GSM1248769", "GSM1248770", "GSM1248771", "GSM1248772", "GSM1248773", "GSM1248774", "GSM1248775", "GSM1248776", "GSM1248777", "GSM1248778", "GSM1248779", "GSM1248780", "GSM1248781", "GSM1248782", "GSM1248783", "GSM1248784", "GSM1248785", "GSM1248786", "GSM1248787", "GSM1248788", "GSM1248789", "GSM1248790", "GSM1248791", "GSM1248792", "GSM1248793", "GSM1248794", "GSM1248795", "GSM1248796", "GSM1248797", "GSM1248798", "GSM1248799", "GSM1248800", "GSM1248801", "GSM1248802", "GSM1248803", "GSM1248804", "GSM1248805", "GSM1248806", "GSM1248807", "GSM1248808"], "sample_count": 50, "group_sizes": null, "group_sizes_basis": null, "platform": "13497", "taxon": "Homo sapiens", "title": "Genome-wide Expression Profiles of Subchondral Bone in Osteoarthritis", "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:GSE511588", "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=GSE511588", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE511588", "version": null, "note": "Data sharing not applicable to this article as no datasets were generated or analyzed during the present study.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sharing not applicable to this article as no datasets were generated or analyzed during the present study.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-11-01T23:38:31Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32925767:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a46a4a03407df8490fa444cdd2c1cd913fce9e6f54cdbd904fc17ad844236652", "bytes": 178, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "Characteristics of the samples.", "structure": {"pmcid": "PMC7489699", "section_index": 3, "section_title": "Data source and data preprocessing", "row_count": 0, "column_count": 0}, "table": {"label": "Table 1", "caption": "Characteristics of the samples.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[3]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:32925767:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4b057fc123c9b7d9e69bd1cf987c1e53abe090167cc7e464406f91ae63e4498a", "bytes": 220, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T2", "version": null, "note": "Five significant modules from the protein–protein interaction network.", "structure": {"pmcid": "PMC7489699", "section_index": 6, "section_title": "PPI network and module analyses", "row_count": 0, "column_count": 0}, "table": {"label": "Table 2", "caption": "Five significant modules from the protein–protein interaction network.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[12]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:32925767:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:15ddfd2aee1a4e81b6ab05321c11d88694d1b705c8434ece60297069bc18948a", "bytes": 219, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#T3", "version": null, "note": "GO and KEGG pathway enrichment analysis of DEGs in significant modules.", "structure": {"pmcid": "PMC7489699", "section_index": 6, "section_title": "PPI network and module analyses", "row_count": 0, "column_count": 0}, "table": {"label": "Table 3", "caption": "GO and KEGG pathway enrichment analysis of DEGs in significant modules.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[12]/table-wrap[2]#T3"}}, {"id": "asset:table:pmid:32925767:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4b057fc123c9b7d9e69bd1cf987c1e53abe090167cc7e464406f91ae63e4498a", "bytes": 220, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T2", "version": null, "note": "Five significant modules from the protein–protein interaction network.", "structure": {"pmcid": "PMC7489699", "section_index": 12, "section_title": "PPI network and module analyses", "row_count": 0, "column_count": 0}, "table": {"label": "Table 2", "caption": "Five significant modules from the protein–protein interaction network.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[12]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:32925767:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:15ddfd2aee1a4e81b6ab05321c11d88694d1b705c8434ece60297069bc18948a", "bytes": 219, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#T3", "version": null, "note": "GO and KEGG pathway enrichment analysis of DEGs in significant modules.", "structure": {"pmcid": "PMC7489699", "section_index": 12, "section_title": "PPI network and module analyses", "row_count": 0, "column_count": 0}, "table": {"label": "Table 3", "caption": "GO and KEGG pathway enrichment analysis of DEGs in significant modules.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[12]/table-wrap[2]#T3"}}, {"id": "asset:table:pmid:32925767:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a703614da741a551fd7a821e8bc6d03a873631090c67a10c63ff754b36437e8b", "bytes": 180, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T4", "version": null, "note": "Functional roles of 8 hub genes.", "structure": {"pmcid": "PMC7489699", "section_index": 13, "section_title": "Hub gene selection and analysis", "row_count": 0, "column_count": 0}, "table": {"label": "Table 4", "caption": "Functional roles of 8 hub genes.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[13]/table-wrap[1]#T4"}}], "gaps": ["asset:data:geo:GSE51588 not downloaded", "asset:data:geo:GSE51588 licence not read", "asset:data:geo:GSE511588 not downloaded", "asset:data:geo:GSE511588 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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-2", "family": null, "specific": null, "label": "classical t test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "DEGs were identified using classical t test and statistically significant DEGs were defined with the criteria of |Log2(FC)| > 2 and adj. P < .05."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "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": ["GSE51588", "GSE511588"], "resolved_accessions": ["GSE51588"], "statements": ["Data sharing not applicable to this article as no datasets were generated or analyzed during the present study."], "basis": "The paper names GSE51588 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": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:32925767", "data:geo:GSE51588", "asset:table:pmid:32925767:1", "asset:table:pmid:32925767:2", "asset:table:pmid:32925767:3", "asset:table:pmid:32925767:4", "asset:table:pmid:32925767:5", "asset:table:pmid:32925767:6"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE51588"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:22:44Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 24311, "completion_tokens": 1598, "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:32925767", "type": "paper", "label": "pmid:32925767"}, {"id": "source:pmid:32925767", "type": "manuscript", "label": "PMID 32925767 full text"}, {"id": "data:geo:GSE51588", "type": "dataset", "label": "GEO GSE51588"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32925767", "type": "paper", "label": "pmid:32925767"}, {"id": "source:pmid:32925767", "type": "manuscript", "label": "PMID 32925767 full text"}, {"id": "data:geo:GSE51588", "type": "dataset", "label": "GEO GSE51588"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32925767", "type": "extraction", "used": ["source:pmid:32925767"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE51588", "type": "accession_resolution", "used": ["data:geo:GSE51588"], "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:32925767", "parent_hash": "sha256:5aab01bff21fcf1fcafc080e7495eb12ed6ca7a44a53f3a0694d30c973e72354", "fork_of": null, "generation": 13}, "gaps": ["asset:data:geo:GSE511588 licence not read", "asset:data:geo:GSE511588 not downloaded", "asset:data:geo:GSE51588 licence not read", "asset:data:geo:GSE51588 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "analysis_only", "id": "assay:1"}]}