{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32788627", "kind": "science-record", "revision": 9, "content_hash": "sha256:e78ad0eec16092062071f0910e1becd2d399cc13da7a08e2a557c704da14d7ed", "created_at": "2026-11-01T15:41:07Z", "updated_at": "2026-11-01T22:45:11Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of potential diagnostic gene biomarkers in patients with osteoarthritis.", "doi": "10.1038/s41598-020-70596-9", "pmid": "32788627", "authors": ["Xinling Wang", "Yang Yu", "Yong Huang", "Mingshuang Zhu", "Rigao Chen", "Zhanghui Liao", "Shipeng Yang"], "journal": "Scientific reports", "year": 2020, "abstract": "The current study was aimed to identify diagnostic gene signature for osteoarthritis (OA). The differentially expressed genes (DEGs) in synovial membrane samples and blood samples were respectively identified from the GEO dataset. The intersection DEGs between synovial membrane and blood were further screened out, followed by the functional annotation of these common DEGs. The optimal intersection gene biomarkers for OA diagnostics were determined. The GSE51588 dataset of articular cartilage was used for expression validation and further diagnostic analysis validation of identified gene biomarkers for OA diagnostics. There were 379 intersection DEGs were obtained between the synovial membrane and blood samples of OA. 22 DEGs had a diagnostic value for OA. After further screening, a total of 9 DEGs including TLR7, RTP4, CRIP1, ZNF688, TOP1, EIF1AY, RAB2A, ZNF281 and UIMC1 were identified for OA diagnostic. The identified DEGs could be considered as potential diagnostic biomarkers for OA.", "claims": [{"id": "claim-method", "statement": "The limma package in R software was used to identify the DEGs in OA synovial membrane and blood samples. Benjamini and Hochberg test was used to adjust the p value. The p < 0.05 was considered as the cutoff criterion.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32788627", "locator": "sections[4] \"Data processing and identification of DEGs\" paragraph 2", "quote": "The limma package in R software was used to identify the DEGs in OA synovial membrane and blood samples. Benjamini and Hochberg test was used to adjust the p value. The p < 0.05 was considered as the cutoff criterion."}], "state": "complete"}, {"id": "claim-data-access", "statement": "4 datasets of synovial membrane including GSE82107, GSE55457, GSE55235 and GSE12021 and 2 datasets of blood including GSE63359 and GSE48556 were used for gene expression profiles analysis. All these datasets were downloaded from the GEO database, which based on GPL 570, GPL96 and GPL6947 platforms.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32788627", "locator": "sections[3] \"Microarray data information\" paragraph 2", "quote": "4 datasets of synovial membrane including GSE82107, GSE55457, GSE55235 and GSE12021 and 2 datasets of blood including GSE63359 and GSE48556 were used for gene expression profiles analysis. All these datasets were downloaded from the GEO database, which based on GPL 570, GPL96 and GPL6947 platforms."}], "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:32788627"], "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:32788627", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-020-70596-9", "sha256": "sha256:9b86f124905cdf3dbe153c95d51764ab597d6c76b8c9d5c61257af720f2e5127", "bytes": 27667, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-020-70596-9", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7424510", "source": "europe_pmc_fulltext", "coverage": "whole_body", "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": "4 datasets of synovial membrane including GSE82107, GSE55457, GSE55235 and GSE12021 and 2 datasets of blood including GSE63359 and GSE48556 were used for gene expression profiles analysis. All these datasets were downloaded from the GEO database, which based on GPL 570, GPL96 and GPL6947 platforms.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "4 datasets of synovial membrane including GSE82107, GSE55457, GSE55235 and GSE12021 and 2 datasets of blood including GSE63359 and GSE48556 were used for gene expression profiles analysis. All these datasets were downloaded from the GEO database, which based on GPL 570, GPL96 and GPL6947 platforms.", "access_statement_kind": "repository_route_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:GSE48556", "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=GSE48556", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE48556", "version": null, "note": "4 datasets of synovial membrane including GSE82107, GSE55457, GSE55235 and GSE12021 and 2 datasets of blood including GSE63359 and GSE48556 were used for gene expression profiles analysis. All these datasets were downloaded from the GEO database, which based on GPL 570, GPL96 and GPL6947 platforms.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "4 datasets of synovial membrane including GSE82107, GSE55457, GSE55235 and GSE12021 and 2 datasets of blood including GSE63359 and GSE48556 were used for gene expression profiles analysis. All these datasets were downloaded from the GEO database, which based on GPL 570, GPL96 and GPL6947 platforms.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1182186", "GSM1182187", "GSM1182188", "GSM1182189", "GSM1182190", "GSM1182191", "GSM1182192", "GSM1182193", "GSM1182194", "GSM1182195", "GSM1182196", "GSM1182197", "GSM1182198", "GSM1182199", "GSM1182200", "GSM1182201", "GSM1182202", "GSM1182203", "GSM1182204", "GSM1182205", "GSM1182206", "GSM1182207", "GSM1182208", "GSM1182209", "GSM1182210", "GSM1182211", "GSM1182212", "GSM1182213", "GSM1182214", "GSM1182215", "GSM1182216", "GSM1182217", "GSM1182218", "GSM1182219", "GSM1182220", "GSM1182221", "GSM1182222", "GSM1182223", "GSM1182224", "GSM1182225", "GSM1182226", "GSM1182227", "GSM1182228", "GSM1182229", "GSM1182230", "GSM1182231", "GSM1182232", "GSM1182233", "GSM1182234", "GSM1182235", "GSM1182236", "GSM1182237", "GSM1182238", "GSM1182239", "GSM1182240", "GSM1182241", "GSM1182242", "GSM1182243", "GSM1182244", "GSM1182245", "GSM1182246", "GSM1182247", "GSM1182248", "GSM1182249", "GSM1182250", "GSM1182251", "GSM1182252", "GSM1182253", "GSM1182254", "GSM1182255", "GSM1182256", "GSM1182257", "GSM1182258", "GSM1182259", "GSM1182260", "GSM1182261", "GSM1182262", "GSM1182263", "GSM1182264", "GSM1182265", "GSM1182266", "GSM1182267", "GSM1182268", "GSM1182269", "GSM1182270", "GSM1182271", "GSM1182272", "GSM1182273", "GSM1182274", "GSM1182275", "GSM1182276", "GSM1182277", "GSM1182278", "GSM1182279", "GSM1182280", "GSM1182281", "GSM1182282", "GSM1182283", "GSM1182284", "GSM1182285", "GSM1182286", "GSM1182287", "GSM1182288", "GSM1182289", "GSM1182290", "GSM1182291", "GSM1182292", "GSM1182293", "GSM1182294", "GSM1182295", "GSM1182296", "GSM1182297", "GSM1182298", "GSM1182299", "GSM1182300", "GSM1182301", "GSM1182302", "GSM1182303", "GSM1182304", "GSM1182305", "GSM1182306", "GSM1182307", "GSM1182308", "GSM1182309", "GSM1182310", "GSM1182311", "GSM1182312", "GSM1182313", "GSM1182314", "GSM1182315", "GSM1182316", "GSM1182317", "GSM1182318", "GSM1182319", "GSM1182320", "GSM1182321", "GSM1182322", "GSM1182323", "GSM1182324"], "sample_count": 139, "group_sizes": null, "group_sizes_basis": null, "platform": "6947", "taxon": "Homo sapiens", "title": "Gene expression profiles from peripheral blood mononuclear cells (PBMCs) of osteoarthritis patients and healthy controls", "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: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": "4 datasets of synovial membrane including GSE82107, GSE55457, GSE55235 and GSE12021 and 2 datasets of blood including GSE63359 and GSE48556 were used for gene expression profiles analysis. All these datasets were downloaded from the GEO database, which based on GPL 570, GPL96 and GPL6947 platforms.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "4 datasets of synovial membrane including GSE82107, GSE55457, GSE55235 and GSE12021 and 2 datasets of blood including GSE63359 and GSE48556 were used for gene expression profiles analysis. All these datasets were downloaded from the GEO database, which based on GPL 570, GPL96 and GPL6947 platforms.", "access_statement_kind": "repository_route_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: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": "4 datasets of synovial membrane including GSE82107, GSE55457, GSE55235 and GSE12021 and 2 datasets of blood including GSE63359 and GSE48556 were used for gene expression profiles analysis. All these datasets were downloaded from the GEO database, which based on GPL 570, GPL96 and GPL6947 platforms.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "4 datasets of synovial membrane including GSE82107, GSE55457, GSE55235 and GSE12021 and 2 datasets of blood including GSE63359 and GSE48556 were used for gene expression profiles analysis. All these datasets were downloaded from the GEO database, which based on GPL 570, GPL96 and GPL6947 platforms.", "access_statement_kind": "repository_route_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": "4 datasets of synovial membrane including GSE82107, GSE55457, GSE55235 and GSE12021 and 2 datasets of blood including GSE63359 and GSE48556 were used for gene expression profiles analysis. All these datasets were downloaded from the GEO database, which based on GPL 570, GPL96 and GPL6947 platforms.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "4 datasets of synovial membrane including GSE82107, GSE55457, GSE55235 and GSE12021 and 2 datasets of blood including GSE63359 and GSE48556 were used for gene expression profiles analysis. All these datasets were downloaded from the GEO database, which based on GPL 570, GPL96 and GPL6947 platforms.", "access_statement_kind": "repository_route_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}}, {"id": "data:geo:GSE63359", "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=GSE63359", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE63359", "version": null, "note": "4 datasets of synovial membrane including GSE82107, GSE55457, GSE55235 and GSE12021 and 2 datasets of blood including GSE63359 and GSE48556 were used for gene expression profiles analysis. All these datasets were downloaded from the GEO database, which based on GPL 570, GPL96 and GPL6947 platforms.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "4 datasets of synovial membrane including GSE82107, GSE55457, GSE55235 and GSE12021 and 2 datasets of blood including GSE63359 and GSE48556 were used for gene expression profiles analysis. All these datasets were downloaded from the GEO database, which based on GPL 570, GPL96 and GPL6947 platforms.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1546587", "GSM1546588", "GSM1546589", "GSM1546590", "GSM1546591", "GSM1546592", "GSM1546593", "GSM1546594", "GSM1546595", "GSM1546596", "GSM1546597", "GSM1546598", "GSM1546599", "GSM1546600", "GSM1546601", "GSM1546602", "GSM1546603", "GSM1546604", "GSM1546605", "GSM1546606", "GSM1546607", "GSM1546608", "GSM1546609", "GSM1546610", "GSM1546611", "GSM1546612", "GSM1546613", "GSM1546614", "GSM1546615", "GSM1546616", "GSM1546617", "GSM1546618", "GSM1546619", "GSM1546620", "GSM1546621", "GSM1546622", "GSM1546623", "GSM1546624", "GSM1546625", "GSM1546626", "GSM1546627", "GSM1546628", "GSM1546629", "GSM1546630", "GSM1546631", "GSM1546632", "GSM1546633", "GSM1546634", "GSM1546635", "GSM1546636", "GSM1546637", "GSM1546638", "GSM1546639", "GSM1546640", "GSM1546641", "GSM1546642", "GSM1546643", "GSM1546644", "GSM1546645", "GSM1546646", "GSM1546647", "GSM1546648", "GSM1546649", "GSM1546650", "GSM1546651", "GSM1546652", "GSM1546653", "GSM1546654", "GSM1546655", "GSM1546656", "GSM1546657", "GSM1546658"], "sample_count": 72, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Expression data for peripheral human blood leukocytes gene expression", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE82107", "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=GSE82107", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE82107", "version": null, "note": "4 datasets of synovial membrane including GSE82107, GSE55457, GSE55235 and GSE12021 and 2 datasets of blood including GSE63359 and GSE48556 were used for gene expression profiles analysis. All these datasets were downloaded from the GEO database, which based on GPL 570, GPL96 and GPL6947 platforms.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "4 datasets of synovial membrane including GSE82107, GSE55457, GSE55235 and GSE12021 and 2 datasets of blood including GSE63359 and GSE48556 were used for gene expression profiles analysis. All these datasets were downloaded from the GEO database, which based on GPL 570, GPL96 and GPL6947 platforms.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2183532", "GSM2183533", "GSM2183534", "GSM2183535", "GSM2183536", "GSM2183537", "GSM2183538", "GSM2183539", "GSM2183540", "GSM2183541", "GSM2183542", "GSM2183543", "GSM2183544", "GSM2183545", "GSM2183546", "GSM2183547", "GSM2183548"], "sample_count": 17, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Synovial biopsies of osteoarthritis patients", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32788627:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6cc27f771c5d035e7557fe36f56d4f6ee15944650bbac505a06a655cb9fd7206", "bytes": 783, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab1", "version": null, "note": "Six datasets used for gene expression profiles analysis.", "structure": {"pmcid": "PMC7424510", "section_index": 3, "section_title": "Microarray data information", "row_count": 7, "column_count": 7}, "table": {"label": "Table 1", "caption": "Six datasets used for gene expression profiles analysis.", "rows": [["GEO ID", "Author", "Platform", "Samples", "Year", "Type", "Omics"], ["GSE82107", "Marieke de Vries", "GPL 570", "OA: Normal = 10:7", "2016", "Synovial membrane", "mRNA"], ["GSE55457", "Woetzel D", "GPL 96", "OA: Normal = 10:10", "2014", "Synovial membrane", "mRNA"], ["GSE55235", "Woetzel D", "GPL 96", "OA: Normal = 10:10", "2014", "Synovial membrane", "mRNA"], ["GSE12021", "Huber R", "GPL 96", "OA: Normal = 10:9", "2008", "Synovial membrane", "mRNA"], ["GSE63359", "Attur M", "GPL 96", "OA: Normal = 44:26", "2017", "Blood", "mRNA"], ["GSE48556", "Ramos YF", "GPL 6,947", "OA: Normal = 106:33", "2013", "Blood", "mRNA"]], "row_count": 7, "column_count": 7, "numeric_cells": 24, "header_rows": 1, "locator": "section[3]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:32788627:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8e9bd315b4a2464379892c6d79f01645c6c66b02ccf8143c81eb6996bc3518eb", "bytes": 1167, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[2]#Tab2", "version": null, "note": "The clinical information of patients in datasets.", "structure": {"pmcid": "PMC7424510", "section_index": 3, "section_title": "Microarray data information", "row_count": 38, "column_count": 3}, "table": {"label": "Table 2", "caption": "The clinical information of patients in datasets.", "rows": [["", "OA", "Normal"], ["GSE82107", "10", "7"], ["Age, years (mean ± SD)", "NA", "NA"], ["Sex"], ["Male", "NA", "NA"], ["Female", "NA", "NA"], ["GSE55457", "10", "10"], ["Age, years (mean ± SD)", "72.4 ± 5.9", "51.0 ± 19.7"], ["Sex"], ["Male", "2", "8"], ["Female", "8", "2"], ["GSE55235", "10", "10"], ["Sex"], ["Male", "2", "7"], ["Female", "8", "3"], ["GSE12021", "10", "9"], ["Age, years (mean ± SD)", "71.9 ± 2.0", "49.9 ± 6.7"], ["Sex"], ["Male", "2", "7"], ["Female", "8", "2"], ["Disease duration, years (mean ± SD)", "6.2 ± 2.7", "0.4 ± 0.3"], ["CRP(mg/L)", "7.6 ± 2.9", "NA"], ["GSE63359", "46", "26"], ["Age, years (mean ± SD)", "65.6 ± 10.7", "54.6 ± 9.5"], ["Sex"], ["Male", "14", "7"], ["Female", "32", "19"], ["BMI (mean ± SD)", "27.4 ± 4.1", "24.9 ± 3.9"], ["GSE48556", "106", "33"], ["Age, years (mean ± SD)", "58.2 ± 7.6", "60.9 ± 7.7"], ["Sex"], ["Male", "1", "9"], ["Female", "105", "24"], ["GSE51588", "40", "10"], ["Age, years (mean ± SD)", "69.7 ± 8.8", "38.4 ± 12.7"], ["Sex"], ["Male", "18", "4"], ["Female", "22", "6"]], "row_count": 38, "column_count": 3, "numeric_cells": 60, "header_rows": 1, "locator": "section[3]/table-wrap[2]#Tab2"}}, {"id": "asset:table:pmid:32788627:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d2d6b4cc9b09ebf8012b193700043854d70150f80246656b41f1426e6e48df18", "bytes": 1367, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#Tab3", "version": null, "note": "The clinical information of OA patients normal individuals in QRT-PCR.", "structure": {"pmcid": "PMC7424510", "section_index": 14, "section_title": "QRT-PCR validation of diagnostic gene biomarkers", "row_count": 9, "column_count": 11}, "table": {"label": "Table 3", "caption": "The clinical information of OA patients normal individuals in QRT-PCR.", "rows": [["", "Age", "Gender", "BMI", "Duration of disease", "Kellgren-Lawrance classification", "Site", "White blood cell count (cells/ml)", "Platelet count (cells/ml)", "C-reactive protein (mg/l)", "X-ray results"], ["OA", "55", "Female", "25.4", "30 years", "I", "Left knee", "5.83 × 109", "2.55 × 1011", "< 0.5", "Mild degeneration of the left knee joint"], ["29", "Male", "24.8", "2 months", "I", "Left knee", "4.58 × 109", "3.07 × 1011", "< 0.5", "Mild degeneration of the left knee joint"], ["65", "Female", "20", "1 month", "I", "Left knee", "2.01 × 109", "1.35 × 1011", "< 0.5", "Mild degeneration of the left knee joint"], ["76", "Male", "28.3", "5 years", "III", "Right knee", "8.36 × 109", "2.16 × 1011", "< 0.5", "Degenerative changes in both knees"], ["NA", "60", "Female", "24", "3 days", "I", "Left knee", "5.33 × 109", "9.5 × 1011", "9.5", "Patellar fractures"], ["48", "Male", "22", "5 days", "Normal", "Right knee", "7.8 × 109", "1.54 × 1011", "11.1", "Fracture of the upper tibia"], ["45", "Male", "27", "1 days", "Normal", "Right knee", "8.8 × 109", "1.87 × 1011", "14.2", "Platform fractures"], ["37", "Female", "24", "1 days", "Normal", "Left knee", "9.1 × 109", "2.01 × 1011", "11.9", "Patellar fractures"]], "row_count": 9, "column_count": 11, "numeric_cells": 48, "header_rows": 1, "locator": "section[14]/table-wrap[1]#Tab3"}}], "gaps": ["asset:data:geo:GSE12021 not downloaded", "asset:data:geo:GSE12021 licence not read", "asset:data:geo:GSE48556 not downloaded", "asset:data:geo:GSE48556 licence not read", "asset:data:geo:GSE51588 not downloaded", "asset:data:geo:GSE51588 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", "asset:data:geo:GSE63359 not downloaded", "asset:data:geo:GSE63359 licence not read", "asset:data:geo:GSE82107 not downloaded", "asset:data:geo:GSE82107 licence not read"]}, "analysis": {"state": "complete", "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": "The limma package in R software was used to identify the DEGs in OA synovial membrane and blood samples. Benjamini and Hochberg test was used to adjust the p value. The p < 0.05 was considered as the cutoff criterion."}}], "targets": [], "gaps": []}, "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": ["GSE82107", "GSE55457", "GSE55235", "GSE12021", "GSE63359", "GSE48556", "GSE51588"], "resolved_accessions": ["GSE82107", "GSE55457", "GSE55235", "GSE12021", "GSE63359", "GSE48556", "GSE51588"], "statements": ["4 datasets of synovial membrane including GSE82107, GSE55457, GSE55235 and GSE12021 and 2 datasets of blood including GSE63359 and GSE48556 were used for gene expression profiles analysis. All these datasets were downloaded from the GEO database, which based on GPL 570, GPL96 and GPL6947 platforms."], "basis": "The paper names GSE82107, GSE55457, GSE55235, GSE12021, GSE63359, GSE48556, 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:32788627", "data:geo:GSE12021", "asset:table:pmid:32788627:1", "asset:table:pmid:32788627:2", "asset:table:pmid:32788627:3"], "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": "2026-10-31T18:21:50Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 22793, "completion_tokens": 2228, "cached_tokens": 785}}, "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:32788627", "type": "paper", "label": "pmid:32788627"}, {"id": "source:pmid:32788627", "type": "manuscript", "label": "PMID 32788627 full text"}, {"id": "data:geo:GSE12021", "type": "dataset", "label": "GEO GSE12021"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32788627", "type": "paper", "label": "pmid:32788627"}, {"id": "source:pmid:32788627", "type": "manuscript", "label": "PMID 32788627 full text"}, {"id": "data:geo:GSE12021", "type": "dataset", "label": "GEO GSE12021"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32788627", "type": "extraction", "used": ["source:pmid:32788627"], "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:32788627", "parent_hash": "sha256:ad556ce177bca8712ac754dd2af74429fe4c83230b8c8758ec1a0731a1a7a37c", "fork_of": null, "generation": 8}, "gaps": ["asset:data:geo:GSE12021 licence not read", "asset:data:geo:GSE12021 not downloaded", "asset:data:geo:GSE48556 licence not read", "asset:data:geo:GSE48556 not downloaded", "asset:data:geo:GSE51588 licence not read", "asset:data:geo:GSE51588 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", "asset:data:geo:GSE63359 licence not read", "asset:data:geo:GSE63359 not downloaded", "asset:data:geo:GSE82107 licence not read", "asset:data:geo:GSE82107 not downloaded", "execution.not_run", "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": ["The limma package in R software was used to identify the DEGs in OA synovial membrane and blood samples. Benjamini and Hochberg test was used to adjust the p value. The p < 0.05 was considered as the cutoff criterion."], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:51:13+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}