{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30854058", "kind": "science-record", "revision": 8, "content_hash": "sha256:9298f043f3e7f0bd1e6381ec91a3eea7fbf4b5a3d7b95af17d327384f6bb4300", "created_at": "2026-11-01T15:40:43Z", "updated_at": "2026-11-01T22:43:51Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of B-cell translocation gene 1-controlled gene networks in diffuse large B-cell lymphoma: A study based on bioinformatics analysis.", "doi": "10.3892/ol.2019.9900", "pmid": "30854058", "authors": ["Wei Yan", "Shawn Xiang Li", "Hongyu Gao", "Wei Yang"], "journal": "Oncology letters", "year": 2019, "abstract": "B-cell translocation gene 1 (BTG1) is a member of the BTG/transducer of Erb family. The present study evaluated the impact of BTG1 gene expression on the clinical outcome of diffuse large B-cell lymphoma (DLBCL) and investigated potential mechanisms using the Gene Expression Omnibus (GEO) database. The gene expression profile datasets GSE31312, GSE10846, GSE65420 and GSE87371 were downloaded from the GEO database. BTG1 expression and clinicopathological data were obtained from the GSE31312 dataset. In 498 cases, the expression of BTG1 in DLBCL was associated with treatment response (χ2=19.020; P<0.001) and International Prognostic Index score (χ2=5.320; P=0.025). Using the Kaplan-Meier method, it was identified that the expression of BTG1 was associated with overall survival (OS) and progression-free survival (PFS) times. Univariate and multivariate Cox regression analysis demonstrated that BTG1 was an independent predictive factor for OS and PFS. From the overlapping analysis of 407 BTG1-associated genes and 22,187 DLBCL-associated genes, 401 genes were identified as BTG1-associated DLBCL genes. Pathway analysis revealed that BTG1-associated DLBCL genes were associated with cancer progression and DLBCL signaling pathways. Subsequently, a protein-protein interaction network was constructed of the BTG1-associated genes, which consisted of 235 genes and 601 interactions. Additionally, 24 genes with high degrees in the network were identified as hub genes, which included genes associated with 'ribosome' [ribosomal protein (RP) L11, RPL3, RPS29, RPL19, RPL15 and RPL12], 'cell cycle' (ubiquitin carboxyl extension protein 52, ATM and Ras homolog family member H), 'mitogen-activated protein kinase pathway' (mitogen-activated protein kinase 1), 'histone modification' (ASH1-like protein) and 'transcription/translation' (eukaryotic translation initiation factor 3 subunit E, eukaryotic translation elongation factor 1 δ, transcription termination factor 1, cAMP responsive element binding protein 1 and RNA polymerase II subunit F). In conclusion, BTG1 may serve as a predictive biomarker for DLBCL prognosis. Additionally, bioinformatics analysis indicated that BTG1 may exhibit key functions in the progression and development of DLBCL.", "claims": [{"id": "claim-method", "statement": "Associations between BTG1 expression and clinical parameters were examined with the χ2 test. Survival analysis was performed using the Kaplan-Meier method and differences were analyzed by log-rank test. Univariate and multivariate Cox proportional hazards regression analyses were performed to identify independent predictors.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30854058", "locator": "sections[4] \"Patient characteristics from the Gene Expression Omnibus (GEO) database and statistical analysis\" paragraph 2", "quote": "Associations between BTG1 expression and clinical parameters were examined with the χ2 test. Survival analysis was performed using the Kaplan-Meier method and differences were analyzed by log-rank test. Univariate and multivariate Cox proportional hazards regression analyses were performed to identify independent predictors."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets analyzed during the current study are available from the GEO database (http://www.ncbi.nlm.nih.gov/geo). All clinicopathological data analyzed during this study are included in the published GEO dataset, GSE31312 (25).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30854058", "locator": "sections[20] \"Availability of data and material\" paragraph 2", "quote": "The datasets analyzed during the current study are available from the GEO database (http://www.ncbi.nlm.nih.gov/geo). All clinicopathological data analyzed during this study are included in the published GEO dataset, GSE31312 (25)."}], "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:30854058"], "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:GSE10846"], "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:GSE10846"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30854058", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3892/ol.2019.9900", "sha256": "sha256:bd66a65a28e45869fa1b3cc8529b79310a1e3ab2310c4872f90bd7a91e1fb462", "bytes": 40063, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3892/ol.2019.9900", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6365947", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE10846", "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=GSE10846", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE10846", "version": null, "note": "The datasets analyzed during the current study are available from the GEO database (http://www.ncbi.nlm.nih.gov/geo). All clinicopathological data analyzed during this study are included in the published GEO dataset, GSE31312 (25).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed during the current study are available from the GEO database (http://www.ncbi.nlm.nih.gov/geo). All clinicopathological data analyzed during this study are included in the published GEO dataset, GSE31312 (25).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM274895", "GSM274896", "GSM274897", "GSM274898", "GSM274899", "GSM274900", "GSM274901", "GSM274902", "GSM274903", "GSM274904", "GSM274905", "GSM274906", "GSM274907", "GSM274908", "GSM274909", "GSM274910", "GSM274911", "GSM274912", "GSM274913", "GSM274914", "GSM274915", "GSM274916", "GSM274917", "GSM274918", "GSM274919", "GSM274920", "GSM274921", "GSM274922", "GSM274923", "GSM274924", "GSM274925", "GSM274926", "GSM274927", "GSM274928", "GSM274929", "GSM274930", "GSM274931", "GSM274932", "GSM274933", "GSM274934", "GSM274935", "GSM274936", "GSM274937", "GSM274938", "GSM274939", "GSM274940", "GSM274941", "GSM274942", "GSM274943", "GSM274944", "GSM274945", "GSM274946", "GSM274947", "GSM274948", "GSM274949", "GSM274950", "GSM274951", "GSM274952", "GSM274953", "GSM274954", "GSM274955", "GSM274956", "GSM274957", "GSM274958", "GSM274959", "GSM274960", "GSM274961", "GSM274962", "GSM274963", "GSM274964", "GSM274965", "GSM274966", "GSM274967", "GSM274968", "GSM274969", "GSM274970", "GSM274971", "GSM274972", "GSM274973", "GSM274974", "GSM274975", "GSM274976", "GSM274977", "GSM274978", "GSM274979", "GSM274980", "GSM274981", "GSM274982", "GSM274983", "GSM274984", "GSM274985", "GSM274986", "GSM274987", "GSM274988", "GSM274989", "GSM274990", "GSM274991", "GSM274992", "GSM274993", "GSM274994", "GSM274995", "GSM274996", "GSM274997", "GSM274998", "GSM274999", "GSM275000", "GSM275001", "GSM275002", "GSM275003", "GSM275004", "GSM275005", "GSM275006", "GSM275007", "GSM275008", "GSM275009", "GSM275010", "GSM275011", "GSM275012", "GSM275013", "GSM275014", "GSM275015", "GSM275016", "GSM275017", "GSM275018", "GSM275019", "GSM275020", "GSM275021", "GSM275022", "GSM275023", "GSM275024", "GSM275025", "GSM275026", "GSM275027", "GSM275028", "GSM275029", "GSM275030", "GSM275031", "GSM275032", "GSM275033", "GSM275034", "GSM275035", "GSM275036", "GSM275037", "GSM275038", "GSM275039", "GSM275040", "GSM275041", "GSM275042", "GSM275043", "GSM275044", "GSM275045", "GSM275046", "GSM275047", "GSM275048", "GSM275049", "GSM275050", "GSM275051", "GSM275052", "GSM275053", "GSM275054", "GSM275055", "GSM275056", "GSM275057", "GSM275058", "GSM275059", "GSM275060", "GSM275061", "GSM275062", "GSM275063", "GSM275064", "GSM275065", "GSM275066", "GSM275067", "GSM275068", "GSM275069", "GSM275070", "GSM275071", "GSM275072", "GSM275073", "GSM275074", "GSM275075", "GSM275076", "GSM275077", "GSM275078", "GSM275079", "GSM275080", "GSM275081", "GSM275082", "GSM275083", "GSM275084", "GSM275085", "GSM275086", "GSM275087", "GSM275088", "GSM275089", "GSM275090", "GSM275091", "GSM275092", "GSM275093", "GSM275094", "GSM275095", "GSM275096", "GSM275097", "GSM275098", "GSM275099", "GSM275100", "GSM275101", "GSM275102", "GSM275103", "GSM275104", "GSM275105", "GSM275106", "GSM275107", "GSM275108", "GSM275109", "GSM275110", "GSM275111", "GSM275112", "GSM275113", "GSM275114", "GSM275115", "GSM275116", "GSM275117", "GSM275118", "GSM275119", "GSM275120", "GSM275121", "GSM275122", "GSM275123", "GSM275124", "GSM275125", "GSM275126", "GSM275127", "GSM275128", "GSM275129", "GSM275130", "GSM275131", "GSM275132", "GSM275133", "GSM275134", "GSM275135", "GSM275136", "GSM275137", "GSM275138", "GSM275139", "GSM275140", "GSM275141", "GSM275142", "GSM275143", "GSM275144", "GSM275145", "GSM275146", "GSM275147", "GSM275148", "GSM275149", "GSM275150", "GSM275151", "GSM275152", "GSM275153", "GSM275154", "GSM275155", "GSM275156", "GSM275157", "GSM275158", "GSM275159", "GSM275160", "GSM275161", "GSM275162", "GSM275163", "GSM275164", "GSM275165", "GSM275166", "GSM275167", "GSM275168", "GSM275169", "GSM275170", "GSM275171", "GSM275172", "GSM275173", "GSM275174", "GSM275175", "GSM275176", "GSM275177", "GSM275178", "GSM275179", "GSM275180", "GSM275181", "GSM275182", "GSM275183", "GSM275184", "GSM275185", "GSM275186", "GSM275187", "GSM275188", "GSM275189", "GSM275190", "GSM275191", "GSM275192", "GSM275193", "GSM275194", "GSM275195", "GSM275196", "GSM275197", "GSM275198", "GSM275199", "GSM275200", "GSM275201", "GSM275202", "GSM275203", "GSM275204", "GSM275205", "GSM275206", "GSM275207", "GSM275208", "GSM275209", "GSM275210", "GSM275211", "GSM275212", "GSM275213", "GSM275214", "GSM275215", "GSM275216", "GSM275217", "GSM275218", "GSM275219", "GSM275220", "GSM275221", "GSM275222", "GSM275223", "GSM275224", "GSM275225", "GSM275226", "GSM275227", "GSM275228", "GSM275229", "GSM275230", "GSM275231", "GSM275232", "GSM275233", "GSM275234", "GSM275235", "GSM275236", "GSM275237", "GSM275238", "GSM275239", "GSM275240", "GSM275241", "GSM275242", "GSM275243", "GSM275244", "GSM275245", "GSM275246", "GSM275247", "GSM275248", "GSM275249", "GSM275250", "GSM275251", "GSM275252", "GSM275253", "GSM275254", "GSM275255", "GSM275256", "GSM275257", "GSM275258", "GSM275259", "GSM275260", "GSM275261", "GSM275262", "GSM275263", "GSM275264", "GSM275265", "GSM275266", "GSM275267", "GSM275268", "GSM275269", "GSM275270", "GSM275271", "GSM275272", "GSM275273", "GSM275274", "GSM275275", "GSM275276", "GSM275277", "GSM275278", "GSM275279", "GSM275280", "GSM275281", "GSM275282", "GSM275283", "GSM275284", "GSM275285", "GSM275286", "GSM275287", "GSM275288", "GSM275289", "GSM275290", "GSM275291", "GSM275292", "GSM275293", "GSM275294", "GSM275295", "GSM275296", "GSM275297", "GSM275298", "GSM275299", "GSM275300", "GSM275301", "GSM275302", "GSM275303", "GSM275304", "GSM275305", "GSM275306", "GSM275307", "GSM275308", "GSM361239", "GSM361240", "GSM361241", "GSM361242", "GSM361243", "GSM361244"], "sample_count": 420, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Prediction of survival in diffuse large B cell lymphoma treated with chemotherapy plus Rituximab", "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:GSE31312", "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=GSE31312", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31312", "version": null, "note": "The datasets analyzed during the current study are available from the GEO database (http://www.ncbi.nlm.nih.gov/geo). All clinicopathological data analyzed during this study are included in the published GEO dataset, GSE31312 (25).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed during the current study are available from the GEO database (http://www.ncbi.nlm.nih.gov/geo). All clinicopathological data analyzed during this study are included in the published GEO dataset, GSE31312 (25).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM775979", "GSM775980", "GSM775981", "GSM775982", "GSM775983", "GSM775984", "GSM775985", "GSM775986", "GSM775987", "GSM775988", "GSM775989", "GSM775990", "GSM775991", "GSM775992", "GSM775993", "GSM775994", "GSM775995", "GSM775996", "GSM775997", "GSM775998", "GSM775999", "GSM776000", "GSM776001", "GSM776002", "GSM776003", "GSM776004", "GSM776005", "GSM776006", "GSM776007", "GSM776008", "GSM776009", "GSM776010", "GSM776011", "GSM776012", "GSM776013", "GSM776014", "GSM776015", "GSM776016", "GSM776017", "GSM776018", "GSM776019", "GSM776020", "GSM776021", "GSM776022", "GSM776023", "GSM776024", "GSM776025", "GSM776026", "GSM776027", "GSM776028", "GSM776029", "GSM776030", "GSM776031", "GSM776032", "GSM776033", "GSM776034", "GSM776035", "GSM776036", "GSM776037", "GSM776038", "GSM776039", "GSM776040", "GSM776041", "GSM776042", "GSM776043", "GSM776044", "GSM776045", "GSM776046", "GSM776047", "GSM776048", "GSM776049", "GSM776050", "GSM776051", "GSM776052", "GSM776053", "GSM776054", "GSM776055", "GSM776056", "GSM776057", "GSM776058", "GSM776059", "GSM776060", "GSM776061", "GSM776062", "GSM776063", "GSM776064", "GSM776065", "GSM776066", "GSM776067", "GSM776068", "GSM776069", "GSM776070", "GSM776071", "GSM776072", "GSM776073", "GSM776074", "GSM776075", "GSM776076", "GSM776077", "GSM776078", "GSM776079", "GSM776080", "GSM776081", "GSM776082", "GSM776083", "GSM776084", "GSM776085", "GSM776086", "GSM776087", "GSM776088", "GSM776089", "GSM776090", "GSM776091", "GSM776092", "GSM776093", "GSM776094", "GSM776095", "GSM776096", "GSM776097", "GSM776098", "GSM776099", "GSM776100", "GSM776101", "GSM776102", "GSM776103", "GSM776104", "GSM776105", "GSM776106", "GSM776107", "GSM776108", "GSM776109", "GSM776110", "GSM776111", "GSM776112", "GSM776113", "GSM776114", "GSM776115", "GSM776116", "GSM776117", "GSM776118", "GSM776119", "GSM776120", "GSM776121", "GSM776122", "GSM776123", "GSM776124", "GSM776125", "GSM776126", "GSM776127", "GSM776128", "GSM776129", "GSM776130", "GSM776131", "GSM776132", "GSM776133", "GSM776134", "GSM776135", "GSM776136", "GSM776137", "GSM776138", "GSM776139", "GSM776140", "GSM776141", "GSM776142", "GSM776143", "GSM776144", "GSM776145", "GSM776146", "GSM776147", "GSM776148", "GSM776149", "GSM776150", "GSM776151", "GSM776152", "GSM776153", "GSM776154", "GSM776155", "GSM776156", "GSM776157", "GSM776158", "GSM776159", "GSM776160", "GSM776161", "GSM776162", "GSM776163", "GSM776164", "GSM776165", "GSM776166", "GSM776167", "GSM776168", "GSM776169", "GSM776170", "GSM776171", "GSM776172", "GSM776173", "GSM776174", "GSM776175", "GSM776176", "GSM776177", "GSM776178", "GSM776179", "GSM776180", "GSM776181", "GSM776182", "GSM776183", "GSM776184", "GSM776185", "GSM776186", "GSM776187", "GSM776188", "GSM776189", "GSM776190", "GSM776191", "GSM776192", "GSM776193", "GSM776194", "GSM776195", "GSM776196", "GSM776197", "GSM776198", "GSM776199", "GSM776200", "GSM776201", "GSM776202", "GSM776203", "GSM776204", "GSM776205", "GSM776206", "GSM776207", "GSM776208", "GSM776209", "GSM776210", "GSM776211", "GSM776212", "GSM776213", "GSM776214", "GSM776215", "GSM776216", "GSM776217", "GSM776218", "GSM776219", "GSM776220", "GSM776221", "GSM776222", "GSM776223", "GSM776224", "GSM776225", "GSM776226", "GSM776227", "GSM776228", "GSM776229", "GSM776230", "GSM776231", "GSM776232", "GSM776233", "GSM776234", "GSM776235", "GSM776236", "GSM776237", "GSM776238", "GSM776239", "GSM776240", "GSM776241", "GSM776242", "GSM776243", "GSM776244", "GSM776245", "GSM776246", "GSM776247", "GSM776248", "GSM776249", "GSM776250", "GSM776251", "GSM776252", "GSM776253", "GSM776254", "GSM776255", "GSM776256", "GSM776257", "GSM776258", "GSM776259", "GSM776260", "GSM776261", "GSM776262", "GSM776263", "GSM776264", "GSM776265", "GSM776266", "GSM776267", "GSM776268", "GSM776269", "GSM776270", "GSM776271", "GSM776272", "GSM776273", "GSM776274", "GSM776275", "GSM776276", "GSM776277", "GSM776278", "GSM776279", "GSM776280", "GSM776281", "GSM776282", "GSM776283", "GSM776284", "GSM776285", "GSM776286", "GSM776287", "GSM776288", "GSM776289", "GSM776290", "GSM776291", "GSM776292", "GSM776293", "GSM776294", "GSM776295", "GSM776296", "GSM776297", "GSM776298", "GSM776299", "GSM776300", "GSM776301", "GSM776302", "GSM776303", "GSM776304", "GSM776305", "GSM776306", "GSM776307", "GSM776308", "GSM776309", "GSM776310", "GSM776311", "GSM776312", "GSM776313", "GSM776314", "GSM776315", "GSM776316", "GSM776317", "GSM776318", "GSM776319", "GSM776320", "GSM776321", "GSM776322", "GSM776323", "GSM776324", "GSM776325", "GSM776326", "GSM776327", "GSM776328", "GSM776329", "GSM776330", "GSM776331", "GSM776332", "GSM776333", "GSM776334", "GSM776335", "GSM776336", "GSM776337", "GSM776338", "GSM776339", "GSM776340", "GSM776341", "GSM776342", "GSM776343", "GSM776344", "GSM776345", "GSM776346", "GSM776347", "GSM776348", "GSM776349", "GSM776350", "GSM776351", "GSM776352", "GSM776353", "GSM776354", "GSM776355", "GSM776356", "GSM776357", "GSM776358", "GSM776359", "GSM776360", "GSM776361", "GSM776362", "GSM776363", "GSM776364", "GSM776365", "GSM776366", "GSM776367", "GSM776368", "GSM776369", "GSM776370", "GSM776371", "GSM776372", "GSM776373", "GSM776374", "GSM776375", "GSM776376", "GSM776377", "GSM776378", "GSM776379", "GSM776380", "GSM776381", "GSM776382", "GSM776383", "GSM776384", "GSM776385", "GSM776386", "GSM776387", "GSM776388", "GSM776389", "GSM776390", "GSM776391", "GSM776392", "GSM776393", "GSM776394", "GSM776395", "GSM776396", "GSM776397", "GSM776398", "GSM776399", "GSM776400", "GSM776401", "GSM776402", "GSM776403", "GSM776404", "GSM776405", "GSM776406", "GSM776407", "GSM776408", "GSM776409", "GSM776410", "GSM776411", "GSM776412", "GSM776413", "GSM776414", "GSM776415", "GSM776416", "GSM776417", "GSM776418", "GSM776419", "GSM776420", "GSM776421", "GSM776422", "GSM776423", "GSM776424", "GSM776425", "GSM776426", "GSM776427", "GSM776428", "GSM776429", "GSM776430", "GSM776431", "GSM776432", "GSM776433", "GSM776434", "GSM776435", "GSM776436", "GSM776437", "GSM776438", "GSM776439", "GSM776440", "GSM776441", "GSM776442", "GSM776443", "GSM776444", "GSM776445", "GSM776446", "GSM776447", "GSM776448", "GSM776449", "GSM776450", "GSM776451", "GSM776452", "GSM776453", "GSM776454", "GSM776455", "GSM776456", "GSM776457", "GSM776458", "GSM776459", "GSM776460", "GSM776461", "GSM776462", "GSM776463", "GSM776464", "GSM776465", "GSM776466", "GSM776467", "GSM776468", "GSM776469", "GSM776470", "GSM776471", "GSM776472", "GSM776473", "GSM776474", "GSM776475", "GSM776476"], "sample_count": 498, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Development and application of a new immunophenotypic algorithm for molecular subtype classification of Diffuse Large B-Cell Lymphoma (DLBCL): Report from an International DLBCL Rituximab-CHOP Consortium Program Study", "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:GSE65420", "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=GSE65420", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE65420", "version": null, "note": "The datasets analyzed during the current study are available from the GEO database (http://www.ncbi.nlm.nih.gov/geo). All clinicopathological data analyzed during this study are included in the published GEO dataset, GSE31312 (25).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed during the current study are available from the GEO database (http://www.ncbi.nlm.nih.gov/geo). All clinicopathological data analyzed during this study are included in the published GEO dataset, GSE31312 (25).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1595839", "GSM1595840", "GSM1595841", "GSM1595842", "GSM1595843", "GSM1595844", "GSM1595845", "GSM1595846", "GSM1595847", "GSM1595848", "GSM1595849", "GSM1595850", "GSM1595851", "GSM1595852", "GSM1595853", "GSM1595854", "GSM1595855", "GSM1595856", "GSM1595857", "GSM1595858", "GSM1595859", "GSM1595860", "GSM1595861", "GSM1595862", "GSM1595863", "GSM1595864", "GSM1595865", "GSM1595866", "GSM1595867"], "sample_count": 29, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Genetic and drug perturbation of components in the NFkB signaling pathway in 11-18 cells", "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:GSE65720", "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=GSE65720", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE65720", "version": null, "note": "The datasets analyzed during the current study are available from the GEO database (http://www.ncbi.nlm.nih.gov/geo). All clinicopathological data analyzed during this study are included in the published GEO dataset, GSE31312 (25).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed during the current study are available from the GEO database (http://www.ncbi.nlm.nih.gov/geo). All clinicopathological data analyzed during this study are included in the published GEO dataset, GSE31312 (25).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1603750", "GSM1603751", "GSM1603752", "GSM1603753", "GSM1603754", "GSM1603755", "GSM1603756", "GSM1603757", "GSM1603758", "GSM1603759", "GSM1603760", "GSM1603761", "GSM1603762", "GSM1603763", "GSM1603764", "GSM1603765", "GSM1603766", "GSM1603767", "GSM1603768", "GSM1603769", "GSM1603770", "GSM1603771", "GSM1603772", "GSM1603773", "GSM1603774", "GSM1603775", "GSM1603776", "GSM1603777", "GSM1603778", "GSM1603779", "GSM1603780", "GSM1603781", "GSM1603782", "GSM1603783", "GSM1603784", "GSM1603785", "GSM1603786", "GSM1603787", "GSM1603788", "GSM1603789", "GSM1603790", "GSM1603791", "GSM1603792", "GSM1603793", "GSM1603794", "GSM1603795", "GSM1603796", "GSM1603797", "GSM1603798", "GSM1603799", "GSM1603800", "GSM1603801", "GSM1603802", "GSM2144368", "GSM2144369", "GSM2144370", "GSM2144371", "GSM2144372", "GSM2144373", "GSM2144374", "GSM2144375", "GSM2144376"], "sample_count": 62, "group_sizes": null, "group_sizes_basis": null, "platform": "10150;10123", "taxon": "Homo sapiens", "title": "Clonal relationship of relapsing diffuse large B-cell lymphoma", "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:GSE87371", "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=GSE87371", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE87371", "version": null, "note": "The datasets analyzed during the current study are available from the GEO database (http://www.ncbi.nlm.nih.gov/geo). All clinicopathological data analyzed during this study are included in the published GEO dataset, GSE31312 (25).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed during the current study are available from the GEO database (http://www.ncbi.nlm.nih.gov/geo). All clinicopathological data analyzed during this study are included in the published GEO dataset, GSE31312 (25).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2328918", "GSM2328919", "GSM2328920", "GSM2328921", "GSM2328922", "GSM2328923", "GSM2328924", "GSM2328925", "GSM2328926", "GSM2328927", "GSM2328928", "GSM2328929", "GSM2328930", "GSM2328931", "GSM2328932", "GSM2328933", "GSM2328934", "GSM2328935", "GSM2328936", "GSM2328937", "GSM2328938", "GSM2328939", "GSM2328940", "GSM2328941", "GSM2328942", "GSM2328943", "GSM2328944", "GSM2328945", "GSM2328946", "GSM2328947", "GSM2328948", "GSM2328949", "GSM2328950", "GSM2328951", "GSM2328952", "GSM2328953", "GSM2328954", "GSM2328955", "GSM2328956", "GSM2328957", "GSM2328958", "GSM2328959", "GSM2328960", "GSM2328961", "GSM2328962", "GSM2328963", "GSM2328964", "GSM2328965", "GSM2328966", "GSM2328967", "GSM2328968", "GSM2328969", "GSM2328970", "GSM2328971", "GSM2328972", "GSM2328973", "GSM2328974", "GSM2328975", "GSM2328976", "GSM2328977", "GSM2328978", "GSM2328979", "GSM2328980", "GSM2328981", "GSM2328982", "GSM2328983", "GSM2328984", "GSM2328985", "GSM2328986", "GSM2328987", "GSM2328988", "GSM2328989", "GSM2328990", "GSM2328991", "GSM2328992", "GSM2328993", "GSM2328994", "GSM2328995", "GSM2328996", "GSM2328997", "GSM2328998", "GSM2328999", "GSM2329000", "GSM2329001", "GSM2329002", "GSM2329003", "GSM2329004", "GSM2329005", "GSM2329006", "GSM2329007", "GSM2329008", "GSM2329009", "GSM2329010", "GSM2329011", "GSM2329012", "GSM2329013", "GSM2329014", "GSM2329015", "GSM2329016", "GSM2329017", "GSM2329018", "GSM2329019", "GSM2329020", "GSM2329021", "GSM2329022", "GSM2329023", "GSM2329024", "GSM2329025", "GSM2329026", "GSM2329027", "GSM2329028", "GSM2329029", "GSM2329030", "GSM2329031", "GSM2329032", "GSM2329033", "GSM2329034", "GSM2329035", "GSM2329036", "GSM2329037", "GSM2329038", "GSM2329039", "GSM2329040", "GSM2329041", "GSM2329042", "GSM2329043", "GSM2329044", "GSM2329045", "GSM2329046", "GSM2329047", "GSM2329048", "GSM2329049", "GSM2329050", "GSM2329051", "GSM2329052", "GSM2329053", "GSM2329054", "GSM2329055", "GSM2329056", "GSM2329057", "GSM2329058", "GSM2329059", "GSM2329060", "GSM2329061", "GSM2329062", "GSM2329063", "GSM2329064", "GSM2329065", "GSM2329066", "GSM2329067", "GSM2329068", "GSM2329069", "GSM2329070", "GSM2329071", "GSM2329072", "GSM2329073", "GSM2329074", "GSM2329075", "GSM2329076", "GSM2329077", "GSM2329078", "GSM2329079", "GSM2329080", "GSM2329081", "GSM2329082", "GSM2329083", "GSM2329084", "GSM2329085", "GSM2329086", "GSM2329087", "GSM2329088", "GSM2329089", "GSM2329090", "GSM2329091", "GSM2329092", "GSM2329093", "GSM2329094", "GSM2329095", "GSM2329096", "GSM2329097", "GSM2329098", "GSM2329099", "GSM2329100", "GSM2329101", "GSM2329102", "GSM2329103", "GSM2329104", "GSM2329105", "GSM2329106", "GSM2329107", "GSM2329108", "GSM2329109", "GSM2329110", "GSM2329111", "GSM2329112", "GSM2329113", "GSM2329114", "GSM2329115", "GSM2329116", "GSM2329117", "GSM2329118", "GSM2329119", "GSM2329120", "GSM2329121", "GSM2329122", "GSM2329123", "GSM2329124", "GSM2329125", "GSM2329126", "GSM2329127", "GSM2329128", "GSM2329129", "GSM2329130", "GSM2329131", "GSM2329132", "GSM2329133", "GSM2329134", "GSM2329135", "GSM2329136", "GSM2329137", "GSM2329138", "GSM2329139", "GSM2329140"], "sample_count": 223, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from Diffuse Large B Cell Lymphoma (DLBCL) 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:30854058:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:577a5de699f9d262cc3065389abd6dd3379a805d7ab214f70a87b03291dc3979", "bytes": 1615, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#tI-ol-0-0-9900", "version": null, "note": "Association between BTG1 expression level and clinical characteristics obtained from the GSE31312 dataset.", "structure": {"pmcid": "PMC6365947", "section_index": 10, "section_title": "Patient characteristics from the GSE31312 dataset", "row_count": 33, "column_count": 6}, "table": {"label": "Table I.", "caption": "Association between BTG1 expression level and clinical characteristics obtained from the GSE31312 dataset.", "rows": [["Characteristic", "Case, n (%)", "Low BTG1 expression, n", "High BTG1 expression, n", "χ2 value", "P-value"], ["Sex", "", "", "", "0.218", "0.709"], ["Male", "199 (42.3)", "138", "133", "", ""], ["Female", "271 (57.7)", "97", "102", "", ""], ["Age, years", "", "", "", "0.690", "0.460"], ["<63", "229 (48.7)", "110", "119", "", ""], ["≥63", "241 (51.3)", "125", "116", "", ""], ["Stage", "", "", "", "0.000", "1.000"], ["I/II", "220 (46.8)", "110", "110", "", ""], ["III/IV", "250 (53.2)", "125", "125", "", ""], ["ECOG score", "", "", "", "0.209", "0.732"], ["Low", "374 (79.6)", "185", "189", "", ""], ["High", "96 (20.4)", "50", "46", "", ""], ["Subtype", "", "", "", "0.034", "0.926"], ["Non-GCB", "222 (47.2)", "112", "110", "", ""], ["GCB", "248 (52.8)", "123", "125", "", ""], ["IPI score", "", "", "", "5.320", "0.025"], ["Low", "274 (64.6)", "135", "139", "", ""], ["High", "150 (35.4)", "79", "71", "", ""], ["B symptom", "", "", "", "0.513", "0.526"], ["No", "276 (67.6)", "138", "138", "", ""], ["Yes", "132 (32.4)", "61", "71", "", ""], ["Bulky disease", "", "", "", "0.141", "0.724"], ["No", "268 (73.2)", "129", "139", "", ""], ["Yes", "98 (26.8)", "45", "53", "", ""], ["LDH level", "", "", "", "0.071", "0.839"], ["Normal", "148 (34.7)", "76", "72", "", ""], ["High", "278 (65.3)", "139", "139", "", ""], ["Treatment response", "", "", "", "19.020", "<0.001"], ["CR", "354 (75.3)", "157", "197", "", ""], ["PR", "72 (15.3)", "48", "24", "", ""], ["PD", "24 (5.1)", "15", "9", "", ""], ["SD", "20 (4.3)", "15", "5", "", ""]], "row_count": 33, "column_count": 6, "numeric_cells": 89, "header_rows": 1, "locator": "section[10]/table-wrap[1]#tI-ol-0-0-9900"}}, {"id": "asset:table:pmid:30854058:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4b3bac3067196bc52a7f4f829afbb39204e6ff2651f44676e64f8963baade190", "bytes": 2386, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#tII-ol-0-0-9900", "version": null, "note": "Univariate and multivariate Cox regression analysis for patients with diffuse large B-cell lymphoma.", "structure": {"pmcid": "PMC6365947", "section_index": 12, "section_title": "Prognostic performance of BTG1 for DLBCL", "row_count": 34, "column_count": 5}, "table": {"label": "Table II.", "caption": "Univariate and multivariate Cox regression analysis for patients with diffuse large B-cell lymphoma.", "rows": [["A, Overall survival"], [""], ["", "Univariate analysis", "Multivariate analysis"], ["", "", ""], ["Variable", "HR (95% CI)", "P-value", "HR (95% CI)", "P-value"], ["Sex (males vs. females)", "1.050 (0.775–1.423)", "0.752", "", ""], ["Age (≥63 vs. <63), years", "1.697 (1.246–2.312)", "0.752", "1.742 (1.244–2.441)", "0.001"], ["Stage (low vs. high)", "2.307 (1.668–3.189)", "<0.001", "1.594 (1.103–2.302)", "0.013"], ["ECOG score (low vs. high)", "2.021 (1.450–2.818)", "<0.001", "1.978 (1.376–2.844)", "<0.001"], ["Subtype (non-GCB vs. GCB)", "0.668 (0.494–0.904)", "0.009", "1.978 (1.376–2.844)", "<0.001"], ["IPI score (low vs. high)", "1.411 (1.026–1.940)", "0.034", "", ""], ["B symptom (no vs. yes)", "1.105 (1.787–1.551)", "0.565", "", ""], ["LDH (normal vs. high)", "1.120 (0.803–1.563)", "0.503", "", ""], ["Bulky disease (no vs. yes)", "1.051 (0.732–1.509)", "0.787", "", ""], ["Treatment response (CR+PR vs. PD+SD)", "2.605 (2.828–2.990)", "<0.001", "2.612 (2.214–3.081)", "<0.001"], ["BTG1 expression (low vs. high)", "2.066 (1.508–2.829)", "<0.001", "1.692 (1.193–2.401)", "0.003"], [""], ["B, Progression free survival"], [""], ["", "Univariate analysis", "Multivariate analysis"], ["", "", ""], ["Variable", "HR (95% CI)", "P-value", "HR (95% CI)", "P-value"], [""], ["Sex (males vs. females)", "0.864 (0.639–1.169)", "0.343", "", ""], ["Age (≥63 vs. <63), years", "1.156 (0.855–1.563)", "0.346", "", ""], ["Stage (low vs. high)", "2.469 (1.781–3.422)", "<0.001", "1.538 (1.063–2.226)", "0.022"], ["ECOG score (low vs. high)", "1.678 (1.191–2.366)", "0.003", "1.187 (0.815–1.729)", "0.371"], ["Subtype (non-GCB vs. GCB)", "0.624 (0.461–0.846)", "0.002", "0.563 (0.406–0.782)", "0.001"], ["IPI score (low vs. high)", "1.545 (1.124–2.124)", "0.007", "", ""], ["B symptom (no vs. yes)", "1.261 (0.902–1.763)", "0.125", "", ""], ["LDH (normal vs. high)", "1.078 (0.774–1.501)", "0.659", "", ""], ["Bulky disease (no vs. yes)", "1.175 (0.820–1.682)", "0.379", "", ""], ["Treatment response (CR+PR vs. PD+SD)", "2.401 (2.095–2.751)", "<0.001", "2.220 (1.889–2.607)", "<0.001"], ["BTG1 expression (low vs. high)", "1.801 (1.324–2.449)", "<0.001", "1.403 (1.004–1.960)", "0.047"]], "row_count": 34, "column_count": 5, "numeric_cells": 72, "header_rows": 5, "locator": "section[12]/table-wrap[1]#tII-ol-0-0-9900"}}], "gaps": ["asset:data:geo:GSE10846 not downloaded", "asset:data:geo:GSE10846 licence not read", "asset:data:geo:GSE31312 not downloaded", "asset:data:geo:GSE31312 licence not read", "asset:data:geo:GSE65420 not downloaded", "asset:data:geo:GSE65420 licence not read", "asset:data:geo:GSE65720 not downloaded", "asset:data:geo:GSE65720 licence not read", "asset:data:geo:GSE87371 not downloaded", "asset:data:geo:GSE87371 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Associations between BTG1 expression and clinical parameters were examined with the χ2 test. Survival analysis was performed using the Kaplan-Meier method and differences were analyzed by log-rank test. Univariate and multivariate Cox proportional hazards regression analyses were performed to identify independent predictors."}}, {"id": "method-2", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Cox regression"}}, {"id": "method-3", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}, {"id": "method-4", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-5", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.7, "band": "medium", "quote": "χ2"}}], "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": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE31312", "GSE10846", "GSE87371", "GSE65420", "GSE65720"], "resolved_accessions": ["GSE31312", "GSE10846", "GSE87371", "GSE65420", "GSE65720"], "statements": ["The datasets analyzed during the current study are available from the GEO database (http://www.ncbi.nlm.nih.gov/geo). All clinicopathological data analyzed during this study are included in the published GEO dataset, GSE31312 (25)."], "basis": "The paper names GSE31312, GSE10846, GSE87371, GSE65420, GSE65720 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": ["survival_km"], "assets": ["source:pmid:30854058", "data:geo:GSE10846", "asset:table:pmid:30854058:1", "asset:table:pmid:30854058:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE10846"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:14:15Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 34362, "completion_tokens": 2294, "cached_tokens": 792}}, "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:30854058", "type": "paper", "label": "pmid:30854058"}, {"id": "source:pmid:30854058", "type": "manuscript", "label": "PMID 30854058 full text"}, {"id": "data:geo:GSE10846", "type": "dataset", "label": "GEO GSE10846"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30854058", "type": "paper", "label": "pmid:30854058"}, {"id": "source:pmid:30854058", "type": "manuscript", "label": "PMID 30854058 full text"}, {"id": "data:geo:GSE10846", "type": "dataset", "label": "GEO GSE10846"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30854058", "type": "extraction", "used": ["source:pmid:30854058"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE10846", "type": "accession_resolution", "used": ["data:geo:GSE10846"], "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:30854058", "parent_hash": "sha256:43ab694a9a7db5a64c1c9cebb8b4bd2e004db135adcc31a018133a1e2e8eee97", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE10846 licence not read", "asset:data:geo:GSE10846 not downloaded", "asset:data:geo:GSE31312 licence not read", "asset:data:geo:GSE31312 not downloaded", "asset:data:geo:GSE65420 licence not read", "asset:data:geo:GSE65420 not downloaded", "asset:data:geo:GSE65720 licence not read", "asset:data:geo:GSE65720 not downloaded", "asset:data:geo:GSE87371 licence not read", "asset:data:geo:GSE87371 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["cate a statistically significant difference. Microarray data and data processing Expression levels o", "ch were sequenced using the GPL570 platform (Affymetrix Human Genome U133 Plus 2.0 Array). GSE31312"], "order_basis": "paper_text_order:2725", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Associations between BTG1 expression and clinical parameters were examined with the χ2 test. Survival analysis was performed using the Kaplan-Meier method and differences were analyzed by log-rank test. Univariate and multivariate Cox proportional hazards regression analyses were performed to identify independent predictors."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T03:10:37+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}}}