Comparison of inflammatory molecular mechanisms between osteoarthritis and rheumatoid arthritis via gene microarrays.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39315289", "kind": "science-record", "revision": 3, "content_hash": "sha256:24c5e07a710038a0b72b41bdf9488c00d024ae09435a74ad2149b1dfab3b8e2b", "created_at": "2026-11-01T20:29:30Z", "updated_at": "2026-11-01T22:12:45Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Comparison of inflammatory molecular mechanisms between osteoarthritis and rheumatoid arthritis via gene microarrays.", "doi": "10.22099/mbrc.2024.49924.1963", "pmid": "39315289", "authors": ["Maziar Oveisee", "Akram Gholipour", "Mahshid Malakootian"], "journal": "Molecular biology research communications", "year": 2024, "abstract": "Osteoarthritis (OA) and rheumatoid arthritis (RA) treatment requires exact arthritis type diagnosis. We compared inflammatory molecular mechanisms between OA and RA to introduce reliable molecular biomarkers. The GSE55235 and GSE100786 microarray datasets were acquired from the GEO. Data preprocessing and differential expression analysis were conducted in OA and RA groups and their control groups applying GEO2R. Differentially expressed genes (DEGs) with a |LogFC|>1 and adj. p<0.05 were determined. Gene ontology (GO) and signaling pathway analysis were done utilizing PANTHER and Enrichr. The suitability of gene expression alterations as biomarkers was tested using the receiver operating characteristic (ROC) curve analysis. We found 2129 DEGs between the OA and control groups and 2494 DEGs between the RA and control groups. GO on the DEGs showed enrichment in binding, cellular processes, and cellular anatomical entities in molecular functions, biological processes, and cellular components, respectively. Enrichr found the cell differentiation pathways of Th1 and Th2 only in RA. The ROC curve analysis indicated HLA-DQA1 downregulation and MAPK8IP3 upregulation as reliable biomarkers to discriminate RA from OA in peripheral blood and bone marrow samples, respectively. We found more DEGs in patients with OA than those with RA and determined inflammatory pathways and genes unique to RA as reliable biomarkers to discriminate RA from OA. Gene expression alterations associated with Th1 and Th2 cell differentiation pathways, including HLA-DQA1 downregulation and MAPK8IP3 upregulation, could be novel molecular biomarkers to diagnose RA.", "claims": [{"id": "claim-method", "statement": "A ROC curve analysis was conducted to determine whether the DEGs in the GSE100786 dataset had enough sensitivity and specificity to discriminate RA from OA.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39315289", "locator": "sections[2] \"MATERIALS AND METHODS\" paragraph 7", "quote": "A ROC curve analysis was conducted to determine whether the DEGs in the GSE100786 dataset had enough sensitivity and specificity to discriminate RA from OA."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data source was a publicly available database with the following accession numbers: GSE55235 and GSE100786 (https://www.ncbi.nlm.nih.gov/geo/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39315289", "locator": "sections[8] \"Ethics approval and consent to participate:\" paragraph 2", "quote": "The data source was a publicly available database with the following accession numbers: GSE55235 and GSE100786 (https://www.ncbi.nlm.nih.gov/geo/)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The ROC curve analysis indicated HLA-DQA1 downregulation and MAPK8IP3 upregulation as reliable biomarkers to discriminate RA from OA in peripheral blood and bone marrow samples, respectively.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39315289", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The ROC curve analysis indicated HLA-DQA1 downregulation and MAPK8IP3 upregulation as reliable biomarkers to discriminate RA from OA in peripheral blood and bone marrow samples, respectively."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The ROC curve analysis indicated HLA-DQA1 downregulation and MAPK8IP3 upregulation as reliable biomarkers to discriminate RA from OA in peripheral blood and bone marrow samples, respectively.", "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:39315289"], "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:GSE100786"], "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:GSE100786"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39315289", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.22099/mbrc.2024.49924.1963", "sha256": "sha256:9395f1a644110b28fd6d4508fa794388ba88730ae7470ccf332126e8cb269435", "bytes": 34968, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.22099/mbrc.2024.49924.1963", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11416848", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE100786", "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=GSE100786", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE100786", "version": null, "note": "The data source was a publicly available database with the following accession numbers: GSE55235 and GSE100786 (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data source was a publicly available database with the following accession numbers: GSE55235 and GSE100786 (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2693242", "GSM2693243", "GSM2693244", "GSM2693245", "GSM2693246", "GSM2693247", "GSM2693248", "GSM2693249", "GSM2693250", "GSM2693251", "GSM2693252", "GSM2693253", "GSM2693254", "GSM2693255", "GSM2693256", "GSM2693257", "GSM2693258", "GSM2693259", "GSM2693260", "GSM2693261", "GSM2693262", "GSM2693263", "GSM2693264", "GSM2693265", "GSM2693266", "GSM2693267", "GSM2693268", "GSM2693269"], "sample_count": 28, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data of bone marrow and blood monocytes from patients with rheumatoid arthritis (RA) and osteoarthritis (OA)", "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 source was a publicly available database with the following accession numbers: GSE55235 and GSE100786 (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data source was a publicly available database with the following accession numbers: GSE55235 and GSE100786 (https://www.ncbi.nlm.nih.gov/geo/).", "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}}], "gaps": ["asset:data:geo:GSE100786 not downloaded", "asset:data:geo:GSE100786 licence not read", "asset:data:geo:GSE55235 not downloaded", "asset:data:geo:GSE55235 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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-2", "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"}}, {"id": "method-3", "family": null, "specific": null, "label": "Receiver operating characteristic (ROC) curve analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "A ROC curve analysis was conducted to determine whether the DEGs in the GSE100786 dataset had enough sensitivity and specificity to discriminate RA from OA."}}], "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": ["pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pathway_enrichment."}, "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": ["GSE55235", "GSE100786"], "resolved_accessions": ["GSE55235", "GSE100786"], "statements": ["The data source was a publicly available database with the following accession numbers: GSE55235 and GSE100786 (https://www.ncbi.nlm.nih.gov/geo/)."], "basis": "The paper names GSE55235, GSE100786 in National Center for Biotechnology Information’s Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pathway_enrich"], "assets": ["source:pmid:39315289", "data:geo:GSE100786"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE100786"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:32:36Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 10738, "completion_tokens": 1339, "cached_tokens": 256}}, "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:39315289", "type": "paper", "label": "pmid:39315289"}, {"id": "source:pmid:39315289", "type": "manuscript", "label": "PMID 39315289 full text"}, {"id": "data:geo:GSE100786", "type": "dataset", "label": "GEO GSE100786"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39315289", "type": "paper", "label": "pmid:39315289"}, {"id": "source:pmid:39315289", "type": "manuscript", "label": "PMID 39315289 full text"}, {"id": "data:geo:GSE100786", "type": "dataset", "label": "GEO GSE100786"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39315289", "type": "extraction", "used": ["source:pmid:39315289"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE100786", "type": "accession_resolution", "used": ["data:geo:GSE100786"], "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:39315289", "parent_hash": "sha256:933728018592baad5b593520f3727d1b1bc0e824bb188add07b16b5c9eeb88fd", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE100786 licence not read", "asset:data:geo:GSE100786 not downloaded", "asset:data:geo:GSE55235 licence not read", "asset:data:geo:GSE55235 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": ["pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["GO enrichment"], "order_basis": "analysis_only", "id": "assay:1"}]}