{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34350180", "kind": "science-record", "revision": 7, "content_hash": "sha256:caa6aacf7ce1ea816afc79f370ef2893096bb9e216d306e57a283d479f0dd75e", "created_at": "2026-11-01T15:41:47Z", "updated_at": "2026-11-01T22:04:25Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "RPL19 Is a Prognostic Biomarker and Promotes Tumor Progression in Hepatocellular Carcinoma.", "doi": "10.3389/fcell.2021.686547", "pmid": "34350180", "authors": ["Benchen Rao", "Jianhao Li", "Tong Ren", "Jing Yang", "Guizhen Zhang", "Liwen Liu", "Haiyu Wang", "Maoxin Huang", "Zhigang Ren", "Zujiang Yu"], "journal": "Frontiers in cell and developmental biology", "year": 2021, "abstract": "BACKGROUND: Hepatocellular carcinoma (HCC) is one of the most common malignancies, and the therapeutic outcome remains undesirable due to its recurrence and metastasis. Gene dysregulation plays a pivotal role in the occurrence and progression of cancer, and the molecular mechanisms are largely unknown.\nMETHODS: The differentially expressed genes of HCC screened from the GSE39791 dataset were used to conduct weighted gene co-expression network analysis. The selected hub genes were validated in The Cancer Genome Atlas (TCGA) database and 11 HCC datasets from the Gene Expression Omnibus (GEO) database. Then, a tissue microarray comprising 90 HCC specimens and 90 adjacent normal specimens was used to validate the hub genes. Moreover, the Hallmark, Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) databases were used to identify enriched pathways. Then, we conducted the immune infiltration analysis.\nRESULTS: A total of 17 co-expression modules were obtained by weighted gene co-expression network analysis. The green, blue, and purple modules were the most relevant to HCC samples. Four hub genes, RPL19, RPL35A, RPL27A, and RPS12, were identified. Interestingly, we found that all four genes were highly expressed in HCC and that their high expression was related to a poor prognosis by analyzing the TCGA and GEO databases. Furthermore, we investigated RPL19 in HCC tissue microarrays and demonstrated that RPL19 was overexpressed in tumor tissues compared with non-tumor tissues (p = 0.016). Moreover, overexpression of RPL19 predicted a poor prognosis in hepatocellular carcinoma (p < 0.0007). Then, enrichment analysis revealed that cell cycle pathways were significantly enriched, and bile acid metabolism-related pathways were significantly down-regulated when RPL19 was highly expressed. Furthermore, immune infiltration analysis showed that immune response was suppressed.\nCONCLUSION: Our study demonstrates that RPL19 may play an important role in promoting tumor progression and is correlated with a poor prognosis in HCC. RPL19 may serve as a promising biomarker and therapeutic target for the precise diagnosis and treatment of HCC in the future.", "claims": [{"id": "claim-method", "statement": "The overall survival (OS), relapse-free survival (RFS), and progress-free survival (PFS) of HCC patients were calculated with Kaplan–Meier curves and log-rank tests.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34350180", "locator": "sections[9] \"Statistical Analysis\" paragraph 2", "quote": "The overall survival (OS), relapse-free survival (RFS), and progress-free survival (PFS) of HCC patients were calculated with Kaplan–Meier curves and log-rank tests."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34350180", "locator": "sections[18] \"Data Availability Statement\" paragraph 2", "quote": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material."}], "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:34350180"], "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:GSE102083"], "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:GSE102083"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34350180", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fcell.2021.686547", "sha256": "sha256:f9e250064cd4621ad53a0fbe698ca0bb101d541b44d3c3c562b8439e394f450a", "bytes": 57248, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fcell.2021.686547", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8327752", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE102083", "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=GSE102083", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE102083", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2723148", "GSM2723149", "GSM2723150", "GSM2723151", "GSM2723152", "GSM2723153", "GSM2723154", "GSM2723155", "GSM2723156", "GSM2723157", "GSM2723158", "GSM2723159", "GSM2723160", "GSM2723161", "GSM2723162", "GSM2723163", "GSM2723164", "GSM2723165", "GSM2723166", "GSM2723167", "GSM2723168", "GSM2723169", "GSM2723170", "GSM2723171", "GSM2723172", "GSM2723173", "GSM2723174", "GSM2723175", "GSM2723176", "GSM2723177", "GSM2723178", "GSM2723179", "GSM2723180", "GSM2723181", "GSM2723182", "GSM2723183", "GSM2723184", "GSM2723185", "GSM2723186", "GSM2723187", "GSM2723188", "GSM2723189", "GSM2723190", "GSM2723191", "GSM2723192", "GSM2723193", "GSM2723194", "GSM2723195", "GSM2723196", "GSM2723197", "GSM2723198", "GSM2723199", "GSM2723200", "GSM2723201", "GSM2723202", "GSM2723203", "GSM2723204", "GSM2723205", "GSM2723206", "GSM2723207", "GSM2723208", "GSM2723209", "GSM2723210", "GSM2723211", "GSM2723212", "GSM2723213", "GSM2723214", "GSM2723215", "GSM2723216", "GSM2723217", "GSM2723218", "GSM2723219", "GSM2723220", "GSM2723221", "GSM2723222", "GSM2723223", "GSM2723224", "GSM2723225", "GSM2723226", "GSM2723227", "GSM2723228", "GSM2723229", "GSM2723230", "GSM2723231", "GSM2723232", "GSM2723233", "GSM2723234", "GSM2723235", "GSM2723236", "GSM2723237", "GSM2723238", "GSM2723239", "GSM2723240", "GSM2723241", "GSM2723242", "GSM2723243", "GSM2723244", "GSM2723245", "GSM2723246", "GSM2723247", "GSM2723248", "GSM2723249", "GSM2723250", "GSM2723251", "GSM2723252", "GSM2723253", "GSM2723254", "GSM2723255", "GSM2723256", "GSM2723257", "GSM2723258", "GSM2723259", "GSM2723260", "GSM2723261", "GSM2723262", "GSM2723263", "GSM2723264", "GSM2723265", "GSM2723266", "GSM2723267", "GSM2723268", "GSM2723269", "GSM2723270", "GSM2723271", "GSM2723272", "GSM2723273", "GSM2723274", "GSM2723275", "GSM2723276", "GSM2723277", "GSM2723278", "GSM2723279", "GSM2723280", "GSM2723281", "GSM2723282", "GSM2723283", "GSM2723284", "GSM2723285", "GSM2723286", "GSM2723287", "GSM2723288", "GSM2723289", "GSM2723290", "GSM2723291", "GSM2723292", "GSM2723293", "GSM2723294", "GSM2723295", "GSM2723296", "GSM2723297", "GSM2723298", "GSM2723299", "GSM2723300", "GSM2723301", "GSM2723302", "GSM2723303", "GSM2723304", "GSM2723305", "GSM2723306", "GSM2723307", "GSM2723308", "GSM2723309", "GSM2723310", "GSM2723311", "GSM2723312", "GSM2723313", "GSM2723314", "GSM2723315", "GSM2723316", "GSM2723317", "GSM2723318", "GSM2723319", "GSM2723320", "GSM2723321", "GSM2723322", "GSM2723323", "GSM2723324", "GSM2723325", "GSM2723326", "GSM2723327", "GSM2723328", "GSM2723329", "GSM2723330", "GSM2723331", "GSM2723332", "GSM2723333", "GSM2723334", "GSM2723335", "GSM2723336", "GSM2723337", "GSM2723338", "GSM2723339", "GSM2723340", "GSM2723341", "GSM2723342", "GSM2723343", "GSM2723344", "GSM2723345", "GSM2723346", "GSM2723347", "GSM2723348", "GSM2723349", "GSM2723350", "GSM2723351", "GSM2723352", "GSM2723353", "GSM2723354", "GSM2723355", "GSM2723356", "GSM2723357", "GSM2723358", "GSM2723359", "GSM2723360", "GSM2723361", "GSM2723362", "GSM2723363", "GSM2723364", "GSM2723365", "GSM2723366", "GSM2723367", "GSM2723368", "GSM2723369", "GSM2723370", "GSM2723371", "GSM2723372", "GSM2723373", "GSM2723374", "GSM2723375", "GSM2723376", "GSM2723377", "GSM2723378", "GSM2723379", "GSM2723380", "GSM2723381", "GSM2723382", "GSM2723383", "GSM2723384", "GSM2723385", "GSM2723386", "GSM2723387", "GSM2723388", "GSM2723389", "GSM2723390", "GSM2723391", "GSM2723392", "GSM2723393", "GSM2723394", "GSM2723395", "GSM2723396", "GSM2723397", "GSM2723398", "GSM2723399", "GSM2723400", "GSM2723401", "GSM2723402", "GSM2723403", "GSM2723404", "GSM2723405", "GSM2723406", "GSM2723407", "GSM2723408", "GSM2723409", "GSM2723410", "GSM2723411", "GSM2723412", "GSM2723413", "GSM2723414", "GSM2723415", "GSM2723416"], "sample_count": 269, "group_sizes": null, "group_sizes_basis": null, "platform": "10787;570", "taxon": "Homo sapiens; Mus musculus", "title": "FABP4 overexpressed in intratumoral hepatic stellate cells within hepatocellular carcinoma with metabolic risk factors", "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:GSE14520", "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=GSE14520", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE14520", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM362947", "GSM362948", "GSM362949", "GSM362950", "GSM362951", "GSM362952", "GSM362953", "GSM362954", "GSM362955", "GSM362956", "GSM362957", "GSM362958", "GSM362959", "GSM362960", "GSM362961", "GSM362962", "GSM362963", "GSM362964", "GSM362965", "GSM362966", "GSM362967", "GSM362968", "GSM362969", "GSM362970", "GSM362971", "GSM362972", "GSM362973", "GSM362974", "GSM362975", "GSM362976", "GSM362977", "GSM362978", "GSM362979", "GSM362980", "GSM362981", "GSM362982", "GSM362983", "GSM362984", "GSM362985", "GSM362986", "GSM362987", "GSM362988", "GSM362989", "GSM362990", "GSM362991", "GSM362992", "GSM362993", "GSM362994", "GSM362995", "GSM362996", "GSM362997", "GSM362998", "GSM362999", "GSM363000", "GSM363001", "GSM363002", "GSM363003", "GSM363004", "GSM363005", "GSM363006", "GSM363007", "GSM363008", "GSM363009", "GSM363010", "GSM363011", "GSM363012", "GSM363013", "GSM363014", "GSM363015", "GSM363016", "GSM363017", "GSM363018", "GSM363019", "GSM363020", "GSM363021", "GSM363022", "GSM363023", "GSM363024", "GSM363025", "GSM363026", "GSM363027", "GSM363028", "GSM363029", "GSM363030", "GSM363031", "GSM363032", "GSM363033", "GSM363034", "GSM363035", "GSM363036", "GSM363037", "GSM363038", "GSM363039", "GSM363040", "GSM363041", "GSM363042", "GSM363043", "GSM363044", "GSM363045", "GSM363046", "GSM363047", "GSM363048", "GSM363049", "GSM363050", "GSM363051", "GSM363052", "GSM363053", "GSM363054", "GSM363055", "GSM363056", "GSM363057", "GSM363058", "GSM363059", "GSM363060", "GSM363061", "GSM363062", "GSM363063", "GSM363064", "GSM363065", "GSM363066", "GSM363067", "GSM363068", "GSM363069", "GSM363070", "GSM363071", "GSM363072", "GSM363073", "GSM363074", "GSM363075", "GSM363076", "GSM363077", "GSM363078", "GSM363079", "GSM363080", "GSM363081", "GSM363082", "GSM363083", "GSM363084", "GSM363085", "GSM363086", "GSM363087", "GSM363088", "GSM363089", "GSM363090", "GSM363091", "GSM363092", "GSM363093", "GSM363094", "GSM363095", "GSM363096", "GSM363097", "GSM363098", "GSM363099", "GSM363100", "GSM363101", "GSM363102", "GSM363103", "GSM363104", "GSM363105", "GSM363106", "GSM363107", "GSM363108", "GSM363109", "GSM363110", "GSM363111", "GSM363112", "GSM363113", "GSM363114", "GSM363115", "GSM363116", "GSM363117", "GSM363118", "GSM363119", "GSM363120", "GSM363121", "GSM363122", "GSM363123", "GSM363124", "GSM363125", "GSM363126", "GSM363127", "GSM363128", "GSM363129", "GSM363130", "GSM363131", "GSM363132", "GSM363133", "GSM363134", "GSM363135", "GSM363136", "GSM363137", "GSM363138", "GSM363139", "GSM363140", "GSM363141", "GSM363142", "GSM363143", "GSM363144", "GSM363145", "GSM363146", "GSM363147", "GSM363148", "GSM363149", "GSM363150", "GSM363151", "GSM363152", "GSM363153", "GSM363154", "GSM363155", "GSM363156", "GSM363157", "GSM363158", "GSM363159", "GSM363160", "GSM363161", "GSM363162", "GSM363163", "GSM363164", "GSM363165", "GSM363166", "GSM363167", "GSM363168", "GSM363169", "GSM363170", "GSM363171", "GSM363172", "GSM363173", "GSM363174", "GSM363175", "GSM363176", "GSM363177", "GSM363178", "GSM363179", "GSM363180", "GSM363181", "GSM363182", "GSM363183", "GSM363184", "GSM363185", "GSM363186", "GSM363187", "GSM363188", "GSM363189", "GSM363190", "GSM363191", "GSM363192", "GSM363193", "GSM363194", "GSM363195", "GSM363196", "GSM363197", "GSM363198", "GSM363199", "GSM363200", "GSM363201", "GSM363202", "GSM363203", "GSM363204", "GSM363205", "GSM363206", "GSM363207", "GSM363208", "GSM363209", "GSM363210", "GSM363211", "GSM363212", "GSM363213", "GSM363214", "GSM363215", "GSM363216", "GSM363217", "GSM363218", "GSM363219", "GSM363220", "GSM363221", "GSM363222", "GSM363223", "GSM363224", "GSM363225", "GSM363226", "GSM363227", "GSM363228", "GSM363229", "GSM363230", "GSM363231", "GSM363232", "GSM363233", "GSM363234", "GSM363235", "GSM363236", "GSM363237", "GSM363238", "GSM363239", "GSM363240", "GSM363241", "GSM363242", "GSM363243", "GSM363244", "GSM363245", "GSM363246", "GSM363247", "GSM363248", "GSM363249", "GSM363250", "GSM363251", "GSM363252", "GSM363253", "GSM363254", "GSM363255", "GSM363256", "GSM363257", "GSM363258", "GSM363259", "GSM363260", "GSM363261", "GSM363262", "GSM363263", "GSM363264", "GSM363265", "GSM363266", "GSM363267", "GSM363268", "GSM363269", "GSM363270", "GSM363271", "GSM363272", "GSM363273", "GSM363274", "GSM363275", "GSM363276", "GSM363277", "GSM363278", "GSM363279", "GSM363280", "GSM363281", "GSM363282", "GSM363283", "GSM363284", "GSM363285", "GSM363286", "GSM363287", "GSM363288", "GSM363289", "GSM363290", "GSM363291", "GSM363292", "GSM363293", "GSM363294", "GSM363295", "GSM363296", "GSM363297", "GSM363298", "GSM363299", "GSM363300", "GSM363301", "GSM363302", "GSM363303", "GSM363304", "GSM363305", "GSM363306", "GSM363307", "GSM363308", "GSM363309", "GSM363310", "GSM363311", "GSM363312", "GSM363313", "GSM363314", "GSM363315", "GSM363316", "GSM363317", "GSM363318", "GSM363319", "GSM363320", "GSM363321", "GSM363322", "GSM363323", "GSM363324", "GSM363325", "GSM363326", "GSM363327", "GSM363328", "GSM363329", "GSM363330", "GSM363331", "GSM363332", "GSM363333", "GSM363334", "GSM363335", "GSM363336", "GSM363337", "GSM363338", "GSM363339", "GSM363340", "GSM363341", "GSM363342", "GSM363343", "GSM363344", "GSM363345", "GSM363346", "GSM363347", "GSM363348", "GSM363349", "GSM363350", "GSM363351", "GSM363352", "GSM363353", "GSM363354", "GSM363355", "GSM363356", "GSM363357", "GSM363358", "GSM363359", "GSM363360", "GSM363361", "GSM363362", "GSM363363", "GSM363364", "GSM363365", "GSM363366", "GSM363367", "GSM363368", "GSM363369", "GSM363370", "GSM363371", "GSM363372", "GSM363373", "GSM363374", "GSM363375", "GSM363376", "GSM363378", "GSM363380", "GSM363381", "GSM363382", "GSM363384", "GSM363386", "GSM363388", "GSM363391", "GSM363393", "GSM363397", "GSM363400", "GSM363402", "GSM363404", "GSM363407", "GSM363417", "GSM363420", "GSM363421", "GSM363422", "GSM363423", "GSM363424", "GSM363425", "GSM363426", "GSM363427", "GSM363428", "GSM363429", "GSM363430", "GSM363431", "GSM363432", "GSM363433", "GSM363434", "GSM363435", "GSM363436", "GSM363437", "GSM363438", "GSM363439", "GSM363440", "GSM363441", "GSM363442", "GSM363443", "GSM363444", "GSM363445", "GSM363446", "GSM363447", "GSM363448", "GSM363449", "GSM363450", "GSM363451", "GSM712532", "GSM712533", "GSM712534", "GSM712535", "GSM712536", "GSM712537", "GSM712538", "GSM712539", "GSM712540", "GSM712541", "GSM712542"], "sample_count": 488, "group_sizes": null, "group_sizes_basis": null, "platform": "3921;571", "taxon": "Homo sapiens", "title": "Gene expression data of human hepatocellular carcinoma (HCC)", "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:GSE39791", "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=GSE39791", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE39791", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM979051", "GSM979052", "GSM979053", "GSM979054", "GSM979055", "GSM979056", "GSM979057", "GSM979058", "GSM979059", "GSM979060", "GSM979061", "GSM979062", "GSM979063", "GSM979064", "GSM979065", "GSM979066", "GSM979067", "GSM979068", "GSM979069", "GSM979070", "GSM979071", "GSM979072", "GSM979073", "GSM979074", "GSM979075", "GSM979076", "GSM979077", "GSM979078", "GSM979079", "GSM979080", "GSM979081", "GSM979082", "GSM979083", "GSM979084", "GSM979085", "GSM979086", "GSM979087", "GSM979088", "GSM979089", "GSM979090", "GSM979091", "GSM979092", "GSM979093", "GSM979094", "GSM979095", "GSM979096", "GSM979097", "GSM979098", "GSM979099", "GSM979100", "GSM979101", "GSM979102", "GSM979103", "GSM979104", "GSM979105", "GSM979106", "GSM979107", "GSM979108", "GSM979109", "GSM979110", "GSM979111", "GSM979112", "GSM979113", "GSM979114", "GSM979115", "GSM979116", "GSM979117", "GSM979118", "GSM979119", "GSM979120", "GSM979121", "GSM979122", "GSM979123", "GSM979124", "GSM979125", "GSM979126", "GSM979127", "GSM979128", "GSM979129", "GSM979130", "GSM979131", "GSM979132", "GSM979133", "GSM979134", "GSM979135", "GSM979136", "GSM979137", "GSM979138", "GSM979139", "GSM979140", "GSM979141", "GSM979142", "GSM979143", "GSM979144", "GSM979145", "GSM979146", "GSM979147", "GSM979148", "GSM979149", "GSM979150", "GSM979151", "GSM979152", "GSM979153", "GSM979154", "GSM979155", "GSM979156", "GSM979157", "GSM979158", "GSM979159", "GSM979160", "GSM979161", "GSM979162", "GSM979163", "GSM979164", "GSM979165", "GSM979166", "GSM979167", "GSM979168", "GSM979169", "GSM979170", "GSM979171", "GSM979172", "GSM979173", "GSM979174", "GSM979175", "GSM979176", "GSM979177", "GSM979178", "GSM979179", "GSM979180", "GSM979181", "GSM979182", "GSM979183", "GSM979184", "GSM979185", "GSM979186", "GSM979187", "GSM979188", "GSM979189", "GSM979190", "GSM979191", "GSM979192", "GSM979193", "GSM979194"], "sample_count": 144, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Hepatic regeneration gene expression signature predicts late recurrence of hepatocellular carcinoma", "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:GSE45436", "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=GSE45436", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE45436", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1100370", "GSM1100371", "GSM1100372", "GSM1100373", "GSM1100374", "GSM1100375", "GSM1100376", "GSM1100377", "GSM1100378", "GSM1100379", "GSM1100380", "GSM1100381", "GSM1100382", "GSM1100383", "GSM1100384", "GSM1100385", "GSM1100386", "GSM1100387", "GSM1100388", "GSM1100389", "GSM1100390", "GSM1100391", "GSM1100392", "GSM1100393", "GSM1100394", "GSM1100395", "GSM1100396", "GSM1100397", "GSM1100398", "GSM1100399", "GSM1100400", "GSM1100401", "GSM1100402", "GSM1100403", "GSM1100404", "GSM1100405", "GSM1100406", "GSM1100407", "GSM1100408", "GSM1100409", "GSM1100410", "GSM1100411", "GSM1100412", "GSM1100413", "GSM1100414", "GSM1100415", "GSM1100416", "GSM1100417", "GSM1100418", "GSM1100419", "GSM1100420", "GSM1100421", "GSM1100422", "GSM1100423", "GSM1100424", "GSM1100425", "GSM1100426", "GSM1100427", "GSM1100428", "GSM1100429", "GSM1100430", "GSM1100431", "GSM1100432", "GSM1100433", "GSM1100434", "GSM1100435", "GSM1100436", "GSM1100437", "GSM1100438", "GSM1100439", "GSM1100440", "GSM1100441", "GSM1100442", "GSM1100443", "GSM1100444", "GSM1100445", "GSM1100446", "GSM1100447", "GSM1100448", "GSM1100449", "GSM1100450", "GSM1100451", "GSM1100452", "GSM1100453", "GSM1100454", "GSM1100455", "GSM1100456", "GSM1104153", "GSM1104154", "GSM1104155", "GSM1104156", "GSM1104157", "GSM1104158", "GSM1104159", "GSM1104160", "GSM1104161", "GSM1104162", "GSM1104163", "GSM1104164", "GSM1104165", "GSM1104166", "GSM1104167", "GSM1104168", "GSM1104169", "GSM1104170", "GSM1104171", "GSM1104172", "GSM1104173", "GSM1104174", "GSM1104175", "GSM1104176", "GSM1104177", "GSM1104178", "GSM1104179", "GSM1104180", "GSM1104181", "GSM1104182", "GSM1104183", "GSM1104184", "GSM1104185", "GSM1104186", "GSM1104187", "GSM1104188", "GSM1104189", "GSM1104190", "GSM1104191", "GSM1104192", "GSM1104193", "GSM1104194", "GSM1104195", "GSM1104196", "GSM1104197", "GSM1104198", "GSM1104199"], "sample_count": 134, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profiles of human hepatocellular carcinoma", "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:GSE54236", "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=GSE54236", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE54236", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1310570", "GSM1310571", "GSM1310572", "GSM1310573", "GSM1310574", "GSM1310575", "GSM1310576", "GSM1310577", "GSM1310578", "GSM1310579", "GSM1310580", "GSM1310581", "GSM1310582", "GSM1310583", "GSM1310584", "GSM1310585", "GSM1310586", "GSM1310587", "GSM1310588", "GSM1310589", "GSM1310590", "GSM1310591", "GSM1310592", "GSM1310593", "GSM1310594", "GSM1310595", "GSM1310596", "GSM1310597", "GSM1310598", "GSM1310599", "GSM1310600", "GSM1310601", "GSM1310602", "GSM1310603", "GSM1310604", "GSM1310605", "GSM1310606", "GSM1310607", "GSM1310608", "GSM1310609", "GSM1310610", "GSM1310611", "GSM1310612", "GSM1310613", "GSM1310614", "GSM1310615", "GSM1310616", "GSM1310617", "GSM1310618", "GSM1310619", "GSM1310620", "GSM1310621", "GSM1310622", "GSM1310623", "GSM1310624", "GSM1310625", "GSM1310626", "GSM1310627", "GSM1310628", "GSM1310629", "GSM1310630", "GSM1310631", "GSM1310632", "GSM1310633", "GSM1310634", "GSM1310635", "GSM1310636", "GSM1310637", "GSM1310638", "GSM1310639", "GSM1310640", "GSM1310641", "GSM1310642", "GSM1310643", "GSM1310644", "GSM1310645", "GSM1310646", "GSM1310647", "GSM1310648", "GSM1310649", "GSM1310650", "GSM1310651", "GSM1310652", "GSM1310653", "GSM1310654", "GSM1310655", "GSM1310656", "GSM1310657", "GSM1310658", "GSM1310659", "GSM1310660", "GSM1310661", "GSM1310662", "GSM1310663", "GSM1310664", "GSM1310665", "GSM1310666", "GSM1310667", "GSM1310668", "GSM1310669", "GSM1310670", "GSM1310671", "GSM1310672", "GSM1310673", "GSM1310674", "GSM1310675", "GSM1310676", "GSM1310677", "GSM1310678", "GSM1310679", "GSM1310680", "GSM1310681", "GSM1310682", "GSM1310683", "GSM1310684", "GSM1310685", "GSM1310686", "GSM1310687", "GSM1310688", "GSM1310689", "GSM1310690", "GSM1310691", "GSM1310692", "GSM1310693", "GSM1310694", "GSM1310695", "GSM1310696", "GSM1310697", "GSM1310698", "GSM1310699", "GSM1310700", "GSM1310701", "GSM1310702", "GSM1310703", "GSM1310704", "GSM1310705", "GSM1310706", "GSM1310707", "GSM1310708", "GSM1310709", "GSM1310710", "GSM1310711", "GSM1310712", "GSM1310713", "GSM1310714", "GSM1310715", "GSM1310716", "GSM1310717", "GSM1310718", "GSM1310719", "GSM1310720", "GSM1310721", "GSM1310722", "GSM1310723", "GSM1310724", "GSM1310725", "GSM1310726", "GSM1310727", "GSM1310728", "GSM1310729", "GSM1310730"], "sample_count": 161, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Prospective gene expression analysis of  human RNA samples from Hepatocellular Carcinoma in relation with growth rate and survival", "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:GSE57957", "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=GSE57957", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE57957", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1398645", "GSM1398646", "GSM1398647", "GSM1398648", "GSM1398649", "GSM1398650", "GSM1398651", "GSM1398652", "GSM1398653", "GSM1398654", "GSM1398655", "GSM1398656", "GSM1398657", "GSM1398658", "GSM1398659", "GSM1398660", "GSM1398661", "GSM1398662", "GSM1398663", "GSM1398664", "GSM1398665", "GSM1398666", "GSM1398667", "GSM1398668", "GSM1398669", "GSM1398670", "GSM1398671", "GSM1398672", "GSM1398673", "GSM1398674", "GSM1398675", "GSM1398676", "GSM1398677", "GSM1398678", "GSM1398679", "GSM1398680", "GSM1398681", "GSM1398682", "GSM1398683", "GSM1398684", "GSM1398685", "GSM1398686", "GSM1398687", "GSM1398688", "GSM1398689", "GSM1398690", "GSM1398691", "GSM1398692", "GSM1398693", "GSM1398694", "GSM1398695", "GSM1398696", "GSM1398697", "GSM1398698", "GSM1398699", "GSM1398700", "GSM1398701", "GSM1398702", "GSM1398703", "GSM1398704", "GSM1398705", "GSM1398706", "GSM1398707", "GSM1398708", "GSM1398709", "GSM1398710", "GSM1398711", "GSM1398712", "GSM1398713", "GSM1398714", "GSM1398715", "GSM1398716", "GSM1398717", "GSM1398718", "GSM1398719", "GSM1398720", "GSM1398721", "GSM1398722"], "sample_count": 78, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Expression profile of Hepatocellular Carcinoma", "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:GSE60502", "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=GSE60502", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE60502", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1481292", "GSM1481293", "GSM1481294", "GSM1481295", "GSM1481296", "GSM1481297", "GSM1481298", "GSM1481299", "GSM1481300", "GSM1481301", "GSM1481302", "GSM1481303", "GSM1481304", "GSM1481305", "GSM1481306", "GSM1481307", "GSM1481308", "GSM1481309", "GSM1481310", "GSM1481311", "GSM1481312", "GSM1481313", "GSM1481314", "GSM1481315", "GSM1481316", "GSM1481317", "GSM1481318", "GSM1481319", "GSM1481320", "GSM1481321", "GSM1481322", "GSM1481323", "GSM1481324", "GSM1481325", "GSM1481326", "GSM1481327"], "sample_count": 36, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Gene expression profiling of 18 hepatocellular carcinoma and adjacent non-tumorous liver tissue", "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:GSE62232", "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=GSE62232", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE62232", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1523329", "GSM1523330", "GSM1523331", "GSM1523332", "GSM1523333", "GSM1523334", "GSM1523335", "GSM1523336", "GSM1523337", "GSM1523338", "GSM1523339", "GSM1523340", "GSM1523341", "GSM1523342", "GSM1523343", "GSM1523344", "GSM1523345", "GSM1523346", "GSM1523347", "GSM1523348", "GSM1523349", "GSM1523350", "GSM1523351", "GSM1523352", "GSM1523353", "GSM1523354", "GSM1523355", "GSM1523356", "GSM1523357", "GSM1523358", "GSM1523359", "GSM1523360", "GSM1523361", "GSM1523362", "GSM1523363", "GSM1523364", "GSM1523365", "GSM1523366", "GSM1523367", "GSM1523368", "GSM1523369", "GSM1523370", "GSM1523371", "GSM1523372", "GSM1523373", "GSM1523374", "GSM1523375", "GSM1523376", "GSM1523377", "GSM1523378", "GSM1523379", "GSM1523380", "GSM1523381", "GSM1523382", "GSM1523383", "GSM1523384", "GSM1523385", "GSM1523386", "GSM1523387", "GSM1523388", "GSM1523389", "GSM1523390", "GSM1523391", "GSM1523392", "GSM1523393", "GSM1523394", "GSM1523395", "GSM1523396", "GSM1523397", "GSM1523398", "GSM1523399", "GSM1523400", "GSM1523401", "GSM1523402", "GSM1523403", "GSM1523404", "GSM1523405", "GSM1523406", "GSM1523407", "GSM1523408", "GSM1523409", "GSM1523410", "GSM1523411", "GSM1523412", "GSM1523413", "GSM1523414", "GSM1523415", "GSM1523416", "GSM1523417", "GSM1523418", "GSM1523419"], "sample_count": 91, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Large-scale gene expression profiling  of 81 hepatocellular carcinomas", "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:GSE64041", "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=GSE64041", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE64041", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2052455", "GSM2052456", "GSM2052457", "GSM2052458", "GSM2052459", "GSM2052460", "GSM2052461", "GSM2052462", "GSM2052463", "GSM2052464", "GSM2052465", "GSM2052466", "GSM2052467", "GSM2052468", "GSM2052469", "GSM2052470", "GSM2052471", "GSM2052472", "GSM2052473", "GSM2052474", "GSM2052475", "GSM2052476", "GSM2052477", "GSM2052478", "GSM2052479", "GSM2052480", "GSM2052481", "GSM2052482", "GSM2052483", "GSM2052484", "GSM2052485", "GSM2052486", "GSM2052487", "GSM2052488", "GSM2052489", "GSM2052490", "GSM2052491", "GSM2052492", "GSM2052493", "GSM2052494", "GSM2052495", "GSM2052496", "GSM2052497", "GSM2052498", "GSM2052499", "GSM2052500", "GSM2052501", "GSM2052502", "GSM2052503", "GSM2052504", "GSM2052505", "GSM2052506", "GSM2052507", "GSM2052508", "GSM2052509", "GSM2052510", "GSM2052511", "GSM2052512", "GSM2052513", "GSM2052514", "GSM2052515", "GSM2052516", "GSM2052517", "GSM2052518", "GSM2052519", "GSM2052520", "GSM2052521", "GSM2052522", "GSM2052523", "GSM2052524", "GSM2052525", "GSM2052526", "GSM2052527", "GSM2052528", "GSM2052529", "GSM2052530", "GSM2052531", "GSM2052532", "GSM2052533", "GSM2052534", "GSM2052535", "GSM2052536", "GSM2052537", "GSM2052538", "GSM2052539", "GSM2052540", "GSM2052541", "GSM2052542", "GSM2052543", "GSM2052544", "GSM2052545", "GSM2052546", "GSM2052547", "GSM2052548", "GSM2052549", "GSM2052550", "GSM2052551", "GSM2052552", "GSM2052553", "GSM2052554", "GSM2052555", "GSM2052556", "GSM2052557", "GSM2052558", "GSM2052559", "GSM2052560", "GSM2052561", "GSM2052562", "GSM2052563", "GSM2052564", "GSM2052565", "GSM2052566", "GSM2052567", "GSM2052568", "GSM2052569", "GSM2052570", "GSM2052571", "GSM2052572", "GSM2052573", "GSM2052574", "GSM2052575", "GSM2052576", "GSM2052577", "GSM2052578", "GSM2052579"], "sample_count": 125, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Gene expression profiling in paired human hepatocellular carcinoma and liver parenchyma biopsies and normal liver biopsies.", "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:GSE76297", "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=GSE76297", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE76297", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1979367", "GSM1979368", "GSM1979369", "GSM1979370", "GSM1979371", "GSM1979372", "GSM1979373", "GSM1979374", "GSM1979375", "GSM1979376", "GSM1979377", "GSM1979378", "GSM1979379", "GSM1979380", "GSM1979381", "GSM1979382", "GSM1979383", "GSM1979384", "GSM1979385", "GSM1979386", "GSM1979387", "GSM1979388", "GSM1979389", "GSM1979390", "GSM1979391", "GSM1979392", "GSM1979393", "GSM1979394", "GSM1979395", "GSM1979396", "GSM1979397", "GSM1979398", "GSM1979399", "GSM1979400", "GSM1979401", "GSM1979402", "GSM1979403", "GSM1979404", "GSM1979405", "GSM1979406", "GSM1979407", "GSM1979408", "GSM1979409", "GSM1979410", "GSM1979411", "GSM1979412", "GSM1979413", "GSM1979414", "GSM1979415", "GSM1979416", "GSM1979417", "GSM1979418", "GSM1979419", "GSM1979420", "GSM1979421", "GSM1979422", "GSM1979423", "GSM1979424", "GSM1979425", "GSM1979426", "GSM1979427", "GSM1979428", "GSM1979429", "GSM1979430", "GSM1979431", "GSM1979432", "GSM1979433", "GSM1979434", "GSM1979435", "GSM1979436", "GSM1979437", "GSM1979438", "GSM1979439", "GSM1979440", "GSM1979441", "GSM1979442", "GSM1979443", "GSM1979444", "GSM1979445", "GSM1979446", "GSM1979447", "GSM1979448", "GSM1979449", "GSM1979450", "GSM1979451", "GSM1979452", "GSM1979453", "GSM1979454", "GSM1979455", "GSM1979456", "GSM1979457", "GSM1979458", "GSM1979459", "GSM1979460", "GSM1979461", "GSM1979462", "GSM1979463", "GSM1979464", "GSM1979465", "GSM1979466", "GSM1979467", "GSM1979468", "GSM1979469", "GSM1979470", "GSM1979471", "GSM1979472", "GSM1979473", "GSM1979474", "GSM1979475", "GSM1979476", "GSM1979477", "GSM1979478", "GSM1979479", "GSM1979480", "GSM1979481", "GSM1979482", "GSM1979483", "GSM1979484", "GSM1979485", "GSM1979486", "GSM1979487", "GSM1979488", "GSM1979489", "GSM1979490", "GSM1979491", "GSM1979492", "GSM1979493", "GSM1979494", "GSM1979495", "GSM1979496", "GSM1979497", "GSM1979498", "GSM1979499", "GSM1979500", "GSM1979501", "GSM1979502", "GSM1979503", "GSM1979504", "GSM1979505", "GSM1979506", "GSM1979507", "GSM1979508", "GSM1979509", "GSM1979510", "GSM1979511", "GSM1979512", "GSM1979513", "GSM1979514", "GSM1979515", "GSM1979516", "GSM1979517", "GSM1979518", "GSM1979519", "GSM1979520", "GSM1979521", "GSM1979522", "GSM1979523", "GSM1979524", "GSM1979525", "GSM1979526", "GSM1979527", "GSM1979528", "GSM1979529", "GSM1979530", "GSM1979531", "GSM1979532", "GSM1979533", "GSM1979534", "GSM1979535", "GSM1979536", "GSM1979537", "GSM1979538", "GSM1979539", "GSM1979540", "GSM1979541", "GSM1979542", "GSM1979543", "GSM1979544", "GSM1979545", "GSM1979546", "GSM1979547", "GSM1979548", "GSM1979549", "GSM1979550", "GSM1979551", "GSM1979552", "GSM1979553", "GSM1979554", "GSM1979555", "GSM1979556", "GSM1979557", "GSM1979558", "GSM1979559", "GSM1979560", "GSM1979561", "GSM1979562", "GSM1979563", "GSM1979564", "GSM1979565", "GSM1979566", "GSM1979567", "GSM1979568", "GSM1979569", "GSM1979570", "GSM1979571", "GSM1979572", "GSM1979573", "GSM1979574", "GSM1979575", "GSM1979576", "GSM1979577", "GSM1979578", "GSM1979579", "GSM1979580", "GSM1979581", "GSM1979582", "GSM1979583", "GSM1979584", "GSM1979585", "GSM1979586", "GSM1979587", "GSM1979588", "GSM1979589", "GSM1979590", "GSM1979591", "GSM1979592", "GSM1979593", "GSM1979594", "GSM1979595", "GSM1979596", "GSM1979597", "GSM1979598", "GSM1979599", "GSM1979600", "GSM1979601", "GSM1979602", "GSM1979603", "GSM1979604", "GSM1979605", "GSM1979606", "GSM1979607", "GSM1979608", "GSM1979609", "GSM1979610", "GSM1979611", "GSM1979612", "GSM1979613", "GSM1979614", "GSM1979615", "GSM1979616", "GSM1979617", "GSM1979618", "GSM1979619", "GSM1979620", "GSM1979621", "GSM1979622", "GSM1979623", "GSM1979624", "GSM1979625", "GSM1979626", "GSM1979627", "GSM1979628", "GSM1979629", "GSM1979630", "GSM1979631", "GSM1979632", "GSM1979633", "GSM1979634", "GSM1979635", "GSM1979636", "GSM1979637", "GSM1979638", "GSM1979639", "GSM1979640", "GSM1979641", "GSM1979642", "GSM1979643", "GSM1979644", "GSM1979645", "GSM1979646", "GSM1979647", "GSM1979648", "GSM1979649", "GSM1979650", "GSM1979651", "GSM1979652", "GSM1979653", "GSM1979654", "GSM1979655", "GSM1979656", "GSM1979657", "GSM1979658", "GSM1979659", "GSM1979660", "GSM1979661", "GSM1979662", "GSM1979663", "GSM1979664", "GSM1979665", "GSM1979666", "GSM1979667", "GSM1979668", "GSM1979669", "GSM1979670"], "sample_count": 304, "group_sizes": null, "group_sizes_basis": null, "platform": "17586", "taxon": "Homo sapiens", "title": "Gene expression data of human hepatocellular carcinoma (HCC) and Cholangiocarcinoma (CCA) from Thailand Initiative in Genomics and Expression Research for Liver Cancer (TIGER-LC)", "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:GSE76427", "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=GSE76427", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE76427", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2011285", "GSM2011286", "GSM2011287", "GSM2011288", "GSM2011289", "GSM2011290", "GSM2011291", "GSM2011292", "GSM2011293", "GSM2011294", "GSM2011295", "GSM2011296", "GSM2011297", "GSM2011298", "GSM2011299", "GSM2011300", "GSM2011301", "GSM2011302", "GSM2011303", "GSM2011304", "GSM2011305", "GSM2011306", "GSM2011307", "GSM2011308", "GSM2011309", "GSM2011310", "GSM2011311", "GSM2011312", "GSM2011313", "GSM2011314", "GSM2011315", "GSM2011316", "GSM2011317", "GSM2011318", "GSM2011319", "GSM2011320", "GSM2011321", "GSM2011322", "GSM2011323", "GSM2011324", "GSM2011325", "GSM2011326", "GSM2011327", "GSM2011328", "GSM2011329", "GSM2011330", "GSM2011331", "GSM2011332", "GSM2011333", "GSM2011334", "GSM2011335", "GSM2011336", "GSM2011337", "GSM2011338", "GSM2011339", "GSM2011340", "GSM2011341", "GSM2011342", "GSM2011343", "GSM2011344", "GSM2011345", "GSM2011346", "GSM2011347", "GSM2011348", "GSM2011349", "GSM2011350", "GSM2011351", "GSM2011352", "GSM2011353", "GSM2011354", "GSM2011355", "GSM2011356", "GSM2011357", "GSM2011358", "GSM2011359", "GSM2011360", "GSM2011361", "GSM2011362", "GSM2011363", "GSM2011364", "GSM2011365", "GSM2011366", "GSM2011367", "GSM2011368", "GSM2011369", "GSM2011370", "GSM2011371", "GSM2011372", "GSM2011373", "GSM2011374", "GSM2011375", "GSM2011376", "GSM2011377", "GSM2011378", "GSM2011379", "GSM2011380", "GSM2011381", "GSM2011382", "GSM2011383", "GSM2011384", "GSM2011385", "GSM2011386", "GSM2011387", "GSM2011388", "GSM2011389", "GSM2011390", "GSM2011391", "GSM2011392", "GSM2011393", "GSM2011394", "GSM2011395", "GSM2011396", "GSM2011397", "GSM2011398", "GSM2011399", "GSM2011400", "GSM2011401", "GSM2011402", "GSM2011403", "GSM2011404", "GSM2011405", "GSM2011406", "GSM2011407", "GSM2011408", "GSM2011409", "GSM2011410", "GSM2011411", "GSM2011412", "GSM2011413", "GSM2011414", "GSM2011415", "GSM2011416", "GSM2011417", "GSM2011418", "GSM2011419", "GSM2011420", "GSM2011421", "GSM2011422", "GSM2011423", "GSM2011424", "GSM2011425", "GSM2011426", "GSM2011427", "GSM2011428", "GSM2011429", "GSM2011430", "GSM2011431", "GSM2011432", "GSM2011433", "GSM2011434", "GSM2011435", "GSM2011436", "GSM2011437", "GSM2011438", "GSM2011439", "GSM2011440", "GSM2011441", "GSM2011442", "GSM2011443", "GSM2011444", "GSM2011445", "GSM2011446", "GSM2011447", "GSM2011448", "GSM2011449", "GSM2011450", "GSM2011451"], "sample_count": 167, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Microarray expression data for tumor and adjacent non-tumor tissues from hepatocellular carcinoma 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:34350180:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:aa888e2dca8e2422df9a175c7d3b8d66534178e97e1297c5a6ef5cfc682933c3", "bytes": 950, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "HCC expression profile cohorts used in this study.", "structure": {"pmcid": "PMC8327752", "section_index": 3, "section_title": "Datasets", "row_count": 14, "column_count": 6}, "table": {"label": "TABLE 1", "caption": "HCC expression profile cohorts used in this study.", "rows": [["Cohort ID", "Platforms", "HCC tissue", "Paracancerous tissue", "Year", "Country"], ["TCGA", "Illumina", "369", "50", "2009", "United States"], ["GSE14520", "Affymetrix", "225", "220", "2010", "United States"], ["GSE39791", "Illumina", "72", "72", "2014", "United States"], ["GSE76297", "Affymetrix", "153", "151", "2017", "United States"], ["GSE54236", "Agilent", "81", "80", "2014", "Italy"], ["GSE62232", "Affymetrix", "81", "10", "2014", "France"], ["E", "Affymetrix", "95", "39", "2014", "Taiwan"], ["GSE60502", "Affymetrix", "18", "18", "2015", "Taiwan"], ["GSE57957", "Illumina", "39", "39", "2014", "Singapore"], ["GSE76427", "Illumina", "115", "52", "2017", "Singapore"], ["e", "Affymetrix", "60", "65", "2016", "Switzerland"], ["GSE102083", "Affymetrix", "156", "105", "2018", "Japan"], ["Total", "", "1464", "901", "", ""]], "row_count": 14, "column_count": 6, "numeric_cells": 47, "header_rows": 1, "locator": "section[3]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:34350180:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d7d24f2a0b4519843167259d4699c36b154aec72c2060911ce52662fc4cd02e7", "bytes": 684, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T2", "version": null, "note": "Screened cancer-specific genes.", "structure": {"pmcid": "PMC8327752", "section_index": 12, "section_title": "Identification of the Four Hub Genes by the Human Protein–Protein Interaction Network", "row_count": 5, "column_count": 8}, "table": {"label": "TABLE 2", "caption": "Screened cancer-specific genes.", "rows": [["Gene symbol", "Number of co-expression neighborhood gene", "Number of neighborhood gene", "Number of co-expression gene", "Number of network gene", "Co-expression neighborhood gene per", "Fisher’s exact test p-value", "FDR"], ["RPL19", "34", "158", "1148", "17381", "0.177083", "1.18E−07", "0.000137"], ["RPS12", "26", "115", "1148", "17381", "0.184397", "1.61E−06", "0.00185"], ["RPL27A", "29", "145", "1148", "17381", "0.166667", "3.51E−06", "0.004005"], ["RPL35A", "20", "86", "1148", "17381", "0.188679", "1.76E−05", "0.01978"]], "row_count": 5, "column_count": 8, "numeric_cells": 32, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:34350180:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:71d653fb774815d2143b5285a7f892092cdea1c7bc8084bfd35ff144a6c91411", "bytes": 764, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#T3", "version": null, "note": "Relationship between RPL19 expression and the clinicopathological features of hepatocellular carcinoma patients.", "structure": {"pmcid": "PMC8327752", "section_index": 14, "section_title": "RPL19 Is Closely Related to the Tumor Progress and the Poor Prognosis of HCC", "row_count": 13, "column_count": 6}, "table": {"label": "TABLE 3", "caption": "Relationship between RPL19 expression and the clinicopathological features of hepatocellular carcinoma patients.", "rows": [["Clinicopathological feature", "No. of patients (%)", "RPL19 expression level", "P-value"], ["", "", "", "", ""], ["", "", "Low", "High", ""], ["Age (years)", "≤50", "40", "25", "15", "0.883"], ["", ">50", "50", "32", "18", ""], ["Sex", "Female", "10", "4", "6", "0.104"], ["", "Male", "80", "53", "27", ""], ["TNM", "I", "63", "44", "19", "0.050*"], ["", "II-IV", "27", "13", "14", ""], ["Tumor size", "≤3 cm", "36", "23", "13", "0.929"], ["", ">3 cm", "54", "34", "20", ""], ["AFP", "≤300 μg/L", "48", "36", "12", "0.014*"], ["", ">300 μg/L", "42", "21", "21", ""]], "row_count": 13, "column_count": 6, "numeric_cells": 42, "header_rows": 3, "locator": "section[14]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:34350180:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0668cf8684926d33b9f032cc1149d8f91a8e6290a72450f0bfee258fcc33c147", "bytes": 750, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[2]#T4", "version": null, "note": "Univariate and multivariate analyses of the overall survival of hepatocellular carcinoma patients.", "structure": {"pmcid": "PMC8327752", "section_index": 14, "section_title": "RPL19 Is Closely Related to the Tumor Progress and the Poor Prognosis of HCC", "row_count": 9, "column_count": 7}, "table": {"label": "TABLE 4", "caption": "Univariate and multivariate analyses of the overall survival of hepatocellular carcinoma patients.", "rows": [["Clinicopathological feature", "Univariate analysis", "Multivariate analysis"], ["", "", ""], ["", "HR", "95% (CI)", "P-value", "HR", "95% (CI)", "P-value"], ["Age (years)", "1.018", "0.987–1.049", "0.255", "", "", ""], ["Sex", "1.472", "0.455–4.754", "0.519", "", "", ""], ["TNM stage", "1.707", "1.039–2.807", "0.035*", "", "", ""], ["Tumor size", "1.082", "0.982–1.193", "0.112", "", "", ""], ["AFP", "1.377", "1.092–1.736", "0.007**", "", "", ""], ["RPL19 expression", "1.921", "1.39–2.656", "<0.001**", "1.693", "1.189–2.411", "0.003**"]], "row_count": 9, "column_count": 7, "numeric_cells": 24, "header_rows": 3, "locator": "section[14]/table-wrap[2]#T4"}}], "gaps": ["asset:data:geo:GSE102083 not downloaded", "asset:data:geo:GSE102083 licence not read", "asset:data:geo:GSE14520 not downloaded", "asset:data:geo:GSE14520 licence not read", "asset:data:geo:GSE39791 not downloaded", "asset:data:geo:GSE39791 licence not read", "asset:data:geo:GSE45436 not downloaded", "asset:data:geo:GSE45436 licence not read", "asset:data:geo:GSE54236 not downloaded", "asset:data:geo:GSE54236 licence not read", "asset:data:geo:GSE57957 not downloaded", "asset:data:geo:GSE57957 licence not read", "asset:data:geo:GSE60502 not downloaded", "asset:data:geo:GSE60502 licence not read", "asset:data:geo:GSE62232 not downloaded", "asset:data:geo:GSE62232 licence not read", "asset:data:geo:GSE64041 not downloaded", "asset:data:geo:GSE64041 licence not read", "asset:data:geo:GSE76297 not downloaded", "asset:data:geo:GSE76297 licence not read", "asset:data:geo:GSE76427 not downloaded", "asset:data:geo:GSE76427 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "The overall survival (OS), relapse-free survival (RFS), and progress-free survival (PFS) of HCC patients were calculated with Kaplan–Meier curves and log-rank tests."}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-3", "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": 0.8, "band": "high", "quote": "PPI"}}, {"id": "method-4", "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": 0.8, "band": "high", "quote": "chi-square"}}], "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": ["logrank_test"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: log_rank_test."}, "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": ["GSE39791", "GSE14520", "GSE45436", "GSE54236", "GSE57957", "GSE60502", "GSE62232", "GSE64041", "GSE76297", "GSE76427", "GSE102083"], "resolved_accessions": ["GSE39791", "GSE14520", "GSE45436", "GSE54236", "GSE57957", "GSE60502", "GSE62232", "GSE64041", "GSE76297", "GSE76427", "GSE102083"], "statements": ["The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material."], "basis": "The paper names GSE39791, GSE14520, GSE45436, GSE54236, GSE57957, GSE60502, GSE62232, GSE64041, GSE76297, GSE76427, GSE102083 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": ["logrank_test"], "assets": ["source:pmid:34350180", "data:geo:GSE102083", "asset:table:pmid:34350180:1", "asset:table:pmid:34350180:2", "asset:table:pmid:34350180:3", "asset:table:pmid:34350180:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE102083"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:33:26Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 43676, "completion_tokens": 3905, "cached_tokens": 784}}, "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:34350180", "type": "paper", "label": "pmid:34350180"}, {"id": "source:pmid:34350180", "type": "manuscript", "label": "PMID 34350180 full text"}, {"id": "data:geo:GSE102083", "type": "dataset", "label": "GEO GSE102083"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34350180", "type": "paper", "label": "pmid:34350180"}, {"id": "source:pmid:34350180", "type": "manuscript", "label": "PMID 34350180 full text"}, {"id": "data:geo:GSE102083", "type": "dataset", "label": "GEO GSE102083"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34350180", "type": "extraction", "used": ["source:pmid:34350180"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE102083", "type": "accession_resolution", "used": ["data:geo:GSE102083"], "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:34350180", "parent_hash": "sha256:096aa494166bf8183319168f445c1c5fc87e8ed6bcde412f034d5a8ef47abbd8", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE102083 licence not read", "asset:data:geo:GSE102083 not downloaded", "asset:data:geo:GSE14520 licence not read", "asset:data:geo:GSE14520 not downloaded", "asset:data:geo:GSE39791 licence not read", "asset:data:geo:GSE39791 not downloaded", "asset:data:geo:GSE45436 licence not read", "asset:data:geo:GSE45436 not downloaded", "asset:data:geo:GSE54236 licence not read", "asset:data:geo:GSE54236 not downloaded", "asset:data:geo:GSE57957 licence not read", "asset:data:geo:GSE57957 not downloaded", "asset:data:geo:GSE60502 licence not read", "asset:data:geo:GSE60502 not downloaded", "asset:data:geo:GSE62232 licence not read", "asset:data:geo:GSE62232 not downloaded", "asset:data:geo:GSE64041 licence not read", "asset:data:geo:GSE64041 not downloaded", "asset:data:geo:GSE76297 licence not read", "asset:data:geo:GSE76297 not downloaded", "asset:data:geo:GSE76427 licence not read", "asset:data:geo:GSE76427 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": ["ssion Omnibus (GEO) database. Then, a tissue microarray comprising 90 HCC specimens and 90 adjacent", "erials and Methods Tissue Samples The tissue microarray (TMA) from Asians containing 90 normal liver"], "order_basis": "paper_text_order:669", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["logrank_test"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The overall survival (OS), relapse-free survival (RFS), and progress-free survival (PFS) of HCC patients were calculated with Kaplan–Meier curves and log-rank tests."], "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":"2026-11-04T01:29:37+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}}}