Osteoarthritis related epigenetic variations in miRNA expression and DNA methylation.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37434153", "kind": "science-record", "revision": 4, "content_hash": "sha256:50cf3292574b964806dbe7c69bfac330b48adbba52ff297ec0318d0849ca6a0d", "created_at": "2026-11-01T19:02:12Z", "updated_at": "2026-11-01T22:09:52Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Osteoarthritis related epigenetic variations in miRNA expression and DNA methylation.", "doi": "10.1186/s12920-023-01597-6", "pmid": "37434153", "authors": ["Lingpeng Jin", "Jun Ma", "Zhen Chen", "Fei Wang", "Zhikuan Li", "Ziqi Shang", "Jiangtao Dong"], "journal": "BMC medical genomics", "year": 2023, "abstract": "Osteoarthritis (OA) is chronic arthritis characterized by articular cartilage degradation. However, a comprehensive regulatory network for OA-related microRNAs and DNA methylation modifications has yet to be established. Thus, we aimed to identify epigenetic changes in microRNAs and DNA methylation and establish the regulatory network between miRNAs and DNA methylation. The mRNA, miRNA, and DNA methylation expression profiles of healthy or osteoarthritis articular cartilage samples were downloaded from Gene Expression Omnibus (GEO) database, including GSE169077, GSE175961, and GSE162484. The differentially expressed genes (DEGs), differentially expressed miRNAs (DEMs), and differentially methylated genes (DMGs) were analyzed by the online tool GEO2R. DAVID and STRING databases were applied for functional enrichment analysis and protein-protein interaction (PPI) network. Potential therapeutic compounds for the treatment of OA were identified by Connectivity map (CMap) analysis. A total of 1424 up-regulated DEGs, 1558 down-regulated DEGs, 5 DEMs with high expression, 6 DEMs with low expression, 1436 hypermethylated genes, and 455 hypomethylated genes were selected. A total of 136 up-regulated and 65 downregulated genes were identified by overlapping DEGs and DEMs predicted target genes which were enriched in apoptosis and circadian rhythm. A total of 39 hypomethylated and 117 hypermethylated genes were obtained by overlapping DEGs and DMGs, which were associated with ECM receptor interactions and cellular metabolic processes, cell connectivity, and transcription. Moreover, The PPI network showed COL5A1, COL6A1, LAMA4, T3GAL6A, and TP53 were the most connective proteins. After overlapping of DEGs, DMGs and DEMs predicted targeted genes, 4 up-regulated genes and 11 down-regulated genes were enriched in the Axon guidance pathway. The top ten genes ranked by PPI network connectivity degree in the up-regulated and downregulated overlapping genes of DEGs and DMGs were further analyzed by the CMap database, and nine chemicals were predicted as potential drugs for the treatment of OA. In conclusion, TP53, COL5A1, COL6A1, LAMA4, and ST3GAL6 may play important roles in OA genesis and development.", "claims": [{"id": "claim-method", "statement": "Through GEO2R online tool, differentially expressed mRNAs (DEGs), miRNAs (DEMs), and methylated CpG probes (DMPs) were identified. DEGs, DEMs, and DMPs were filtered out using the following criteria: p < 0.05 and | t |> 2.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37434153", "locator": "sections[4] \"Identification of DEGs, DEMs, and DMPs\" paragraph 2", "quote": "Through GEO2R online tool, differentially expressed mRNAs (DEGs), miRNAs (DEMs), and methylated CpG probes (DMPs) were identified. DEGs, DEMs, and DMPs were filtered out using the following criteria: p < 0.05 and | t |> 2."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data (expression profiles: GSE169077, GSE175961, and GSE162484) used in this study are public and available from the GEO database (https://www.ncbi.nlm.nih.gov).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37434153", "locator": "sections[24] \"Availability of data and materials\" paragraph 2", "quote": "The data (expression profiles: GSE169077, GSE175961, and GSE162484) used in this study are public and available from the GEO database (https://www.ncbi.nlm.nih.gov)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Using GEO2R analysis of GEO expression and methylation data, the study selected 1424 up-regulated DEGs, 1558 down-regulated DEGs, 5 highly expressed DEMs, 6 lowly expressed DEMs, 1436 hypermethylated genes, and 455 hypomethylated genes.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37434153", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "A total of 1424 up-regulated DEGs, 1558 down-regulated DEGs, 5 DEMs with high expression, 6 DEMs with low expression, 1436 hypermethylated genes, and 455 hypomethylated genes were selected."}, {"asset": "source:pmid:37434153", "locator": "sections[4] \"Identification of DEGs, DEMs, and DMPs\" paragraph 2", "quote": "Through GEO2R online tool, differentially expressed mRNAs (DEGs), miRNAs (DEMs), and methylated CpG probes (DMPs) were identified."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Using GEO2R analysis of GEO expression and methylation data, the study selected 1424 up-regulated DEGs, 1558 down-regulated DEGs, 5 highly expressed DEMs, 6 lowly expressed DEMs, 1436 hypermethylated genes, and 455 hypomethylated genes.", "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:37434153"], "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:GSE162484"], "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:GSE162484"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37434153", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12920-023-01597-6", "sha256": "sha256:8844ce2ad50dfa63916767429302360b0ddfa8511720a7d55e0513e4aaf07ffb", "bytes": 45843, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12920-023-01597-6", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10337191", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE162484", "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=GSE162484", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE162484", "version": null, "note": "The data (expression profiles: GSE169077, GSE175961, and GSE162484) used in this study are public and available from the GEO database (https://www.ncbi.nlm.nih.gov).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data (expression profiles: GSE169077, GSE175961, and GSE162484) used in this study are public and available from the GEO database (https://www.ncbi.nlm.nih.gov).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4952732", "GSM4952733", "GSM4952734", "GSM4952735", "GSM4952736", "GSM4952737", "GSM4952738", "GSM4952739", "GSM4952740", "GSM4952741", "GSM4952742", "GSM4952743", "GSM4952744", "GSM4952745", "GSM4952746"], "sample_count": 15, "group_sizes": null, "group_sizes_basis": null, "platform": "13534", "taxon": "Homo sapiens", "title": "Genome-Wide Differentially Methylated Region Analysis to Reveal Epigenetic Differences of Articular Cartilage in Kashin-Beck Disease and Osteoarthritis", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE169077", "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=GSE169077", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE169077", "version": null, "note": "The data (expression profiles: GSE169077, GSE175961, and GSE162484) used in this study are public and available from the GEO database (https://www.ncbi.nlm.nih.gov).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data (expression profiles: GSE169077, GSE175961, and GSE162484) used in this study are public and available from the GEO database (https://www.ncbi.nlm.nih.gov).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5176138", "GSM5176139", "GSM5176140", "GSM5176141", "GSM5176142", "GSM5176143", "GSM5176144", "GSM5176145", "GSM5176146", "GSM5176147", "GSM5176148"], "sample_count": 11, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Dysregulated gene expression in human osteoarthritis cartilage", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE175961", "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=GSE175961", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE175961", "version": null, "note": "The data (expression profiles: GSE169077, GSE175961, and GSE162484) used in this study are public and available from the GEO database (https://www.ncbi.nlm.nih.gov).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data (expression profiles: GSE169077, GSE175961, and GSE162484) used in this study are public and available from the GEO database (https://www.ncbi.nlm.nih.gov).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5352048", "GSM5352049", "GSM5352050", "GSM5352051", "GSM5352052", "GSM5352053"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "20712", "taxon": "Homo sapiens", "title": "Microarray and differential expression analysis were used to identify the noncoding RNAs (ncRNAs) and mRNAs that were expressed abnormally between the cartilage from KOA patients and healthy controls (miRNA).", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE162484 not downloaded", "asset:data:geo:GSE162484 licence not read", "asset:data:geo:GSE169077 not downloaded", "asset:data:geo:GSE169077 licence not read", "asset:data:geo:GSE175961 not downloaded", "asset:data:geo:GSE175961 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": "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": "pathway enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "GEO2R online tool with differential features filtered using p < 0.05 and |t| > 2", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Through GEO2R online tool, differentially expressed mRNAs (DEGs), miRNAs (DEMs), and methylated CpG probes (DMPs) were identified. DEGs, DEMs, and DMPs were filtered out using the following criteria: p < 0.05 and | t |> 2."}}], "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": ["GSE169077", "GSE175961", "GSE162484"], "resolved_accessions": ["GSE169077", "GSE175961", "GSE162484"], "statements": ["The data (expression profiles: GSE169077, GSE175961, and GSE162484) used in this study are public and available from the GEO database (https://www.ncbi.nlm.nih.gov)."], "basis": "The paper names GSE169077, GSE175961, GSE162484 in Gene Expression Omnibus (GEO) database 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:37434153", "data:geo:GSE162484"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE162484"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:46:30Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 14327, "completion_tokens": 1833, "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:37434153", "type": "paper", "label": "pmid:37434153"}, {"id": "source:pmid:37434153", "type": "manuscript", "label": "PMID 37434153 full text"}, {"id": "data:geo:GSE162484", "type": "dataset", "label": "GEO GSE162484"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37434153", "type": "paper", "label": "pmid:37434153"}, {"id": "source:pmid:37434153", "type": "manuscript", "label": "PMID 37434153 full text"}, {"id": "data:geo:GSE162484", "type": "dataset", "label": "GEO GSE162484"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37434153", "type": "extraction", "used": ["source:pmid:37434153"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE162484", "type": "accession_resolution", "used": ["data:geo:GSE162484"], "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:37434153", "parent_hash": "sha256:ab6bc80fc52d8dd8c0c4b9c7bb31943c8caae0c8136a595f5b810a9f9a89c5c2", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE162484 licence not read", "asset:data:geo:GSE162484 not downloaded", "asset:data:geo:GSE169077 licence not read", "asset:data:geo:GSE169077 not downloaded", "asset:data:geo:GSE175961 licence not read", "asset:data:geo:GSE175961 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.69, "evidence": ["redicted target genes which were enriched in apoptosis and circadian rhythm. A total of 39 hypometh"], "order_basis": "paper_text_order:1369", "id": "assay:1"}, {"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": "consumes_earlier_output", "id": "assay:2"}]}