{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36685860", "kind": "science-record", "revision": 4, "content_hash": "sha256:0909c614a4e5c1a433ceec7cf8601cfb65ed5ade8438b09438d6024fcd310d90", "created_at": "2026-11-01T19:01:14Z", "updated_at": "2026-11-01T22:51:05Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of oncogenes and tumor-suppressor genes with hepatocellular carcinoma: A comprehensive analysis based on TCGA and GEO datasets.", "doi": "10.3389/fgene.2022.934883", "pmid": "36685860", "authors": ["Yue Zhu", "Yanfei Wang", "Mengyao Hu", "Xiaoting Lu", "Guoping Sun"], "journal": "Frontiers in genetics", "year": 2022, "abstract": "Aim: Existing targeted therapies for hepatocellular carcinoma (HCC) are resistant and have limitations. It is crucial to find new HCC-related target genes. Methods: RNA-sequencing data of HCC were gathered from The Cancer Genome Atlas and Gene Expression Omnibus datasets. Initially, differentially expressed genes between normal and tumor tissues were identified from four Gene Expression Omnibus datasets, GSE36376, GSE102079, GSE54236, and GSE45267. GO terms and KEGG pathway enrichment analyses were performed to explore the potential biological functions of differentially expressed genes. A PPI network was constructed by using the STRING database, and up-regulated and down-regulated hub genes were defined through 12 topological approaches. Subsequently, the correlation bounded by up-regulated genes and down-regulated genes in the diagnosis, prognosis, and clinicopathological features of HCC was analyzed. Beyond a shadow of doubt, the key oncogene PBK and tumor suppressor gene F9 were screened out, and the specific mechanism was investigated through GSEA enrichment analysis and immune correlation analysis. The role of PBK in HCC was further verified by western blot, CCK8, transwell, and tube formation experiments. Results: CDCA5, CDC20, PBK, PRC1, TOP2A, and NCAPG are good indicators of HCC diagnosis and prognosis. The low expressions of F9, AFM, and C8B indicate malignant progression and poor prognosis of HCC. PBK was found to be closely related to VEGF, VEGFR, and PDGFR pathways. Experiments showed that PBK promotes HCC cell proliferation, migration, invasion, and tube formation in HUVEC cells. F9 was negatively correlated with the degree of immune infiltration, and low expression of F9 suggested a poor response to immunotherapy. Conclusion: The role of HCC-related oncogenes and tumor-suppressor genes in diagnosis and prognosis was identified. In addition, we have found that PBK may promote tumor proliferation through angiogenesis and F9 may be a predictor of tumor immunotherapy response.", "claims": [{"id": "claim-method", "statement": "The limma package of R software was used to identify the DEGs in four datasets.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36685860", "locator": "sections[10] \"Identification of differentially expressed genes\" paragraph 2", "quote": "The limma package of R software was used to identify the DEGs in four datasets."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding author.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36685860", "locator": "sections[28] \"Data availability statement\" paragraph 2", "quote": "The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding author."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The analysis identified 104 differentially expressed genes, including 23 up-regulated genes and 81 down-regulated genes, in HCC tissue samples.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36685860", "locator": "sections[20] \"Identification of DEGs\" paragraph 2", "quote": "As presented in Figures 1E, F, we made an attempt to identify 104 DEGs, including 23 up-regulated genes and 81 down-regulated genes in the HCC tissue samples."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The analysis identified 104 differentially expressed genes, including 23 up-regulated genes and 81 down-regulated genes, in HCC tissue samples.", "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:36685860"], "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:GSE102079"], "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:GSE102079"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36685860", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2022.934883", "sha256": "sha256:d5a65d430c1597d5e5152f159e93de47956362965449305c5c4302ee7bad284c", "bytes": 47623, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2022.934883", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9845404", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE102079", "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=GSE102079", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE102079", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding author.", "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"], "sample_count": 257, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "FABP4 overexpressed in intratumoral hepatic stellate cells within hepatocellular carcinoma with metabolic risk factors (part 1)", "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:GSE36376", "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=GSE36376", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE36376", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM890128", "GSM890129", "GSM890130", "GSM890131", "GSM890132", "GSM890133", "GSM890134", "GSM890135", "GSM890136", "GSM890137", "GSM890138", "GSM890139", "GSM890140", "GSM890141", "GSM890142", "GSM890143", "GSM890144", "GSM890145", "GSM890146", "GSM890147", "GSM890148", "GSM890149", "GSM890150", "GSM890151", "GSM890152", "GSM890153", "GSM890154", "GSM890155", "GSM890156", "GSM890157", "GSM890158", "GSM890159", "GSM890160", "GSM890161", "GSM890162", "GSM890163", "GSM890164", "GSM890165", "GSM890166", "GSM890167", "GSM890168", "GSM890169", "GSM890170", "GSM890171", "GSM890172", "GSM890173", "GSM890174", "GSM890175", "GSM890176", "GSM890177", "GSM890178", "GSM890179", "GSM890180", "GSM890181", "GSM890182", "GSM890183", "GSM890184", "GSM890185", "GSM890186", "GSM890187", "GSM890188", "GSM890189", "GSM890190", "GSM890191", "GSM890192", "GSM890193", "GSM890194", "GSM890195", "GSM890196", "GSM890197", "GSM890198", "GSM890199", "GSM890200", "GSM890201", "GSM890202", "GSM890203", "GSM890204", "GSM890205", "GSM890206", "GSM890207", "GSM890208", "GSM890209", "GSM890210", "GSM890211", "GSM890212", "GSM890213", "GSM890214", "GSM890215", "GSM890216", "GSM890217", "GSM890218", "GSM890219", "GSM890220", "GSM890221", "GSM890222", "GSM890223", "GSM890224", "GSM890225", "GSM890226", "GSM890227", "GSM890228", "GSM890229", "GSM890230", "GSM890231", "GSM890232", "GSM890233", "GSM890234", "GSM890235", "GSM890236", "GSM890237", "GSM890238", "GSM890239", "GSM890240", "GSM890241", "GSM890242", "GSM890243", "GSM890244", "GSM890245", "GSM890246", "GSM890247", "GSM890248", "GSM890249", "GSM890250", "GSM890251", "GSM890252", "GSM890253", "GSM890254", "GSM890255", "GSM890256", "GSM890257", "GSM890258", "GSM890259", "GSM890260", "GSM890261", "GSM890262", "GSM890263", "GSM890264", "GSM890265", "GSM890266", "GSM890267", "GSM890268", "GSM890269", "GSM890270", "GSM890271", "GSM890272", "GSM890273", "GSM890274", "GSM890275", "GSM890276", "GSM890277", "GSM890278", "GSM890279", "GSM890280", "GSM890281", "GSM890282", "GSM890283", "GSM890284", "GSM890285", "GSM890286", "GSM890287", "GSM890288", "GSM890289", "GSM890290", "GSM890291", "GSM890292", "GSM890293", "GSM890294", "GSM890295", "GSM890296", "GSM890297", "GSM890298", "GSM890299", "GSM890300", "GSM890301", "GSM890302", "GSM890303", "GSM890304", "GSM890305", "GSM890306", "GSM890307", "GSM890308", "GSM890309", "GSM890310", "GSM890311", "GSM890312", "GSM890313", "GSM890314", "GSM890315", "GSM890316", "GSM890317", "GSM890318", "GSM890319", "GSM890320", "GSM890321", "GSM890322", "GSM890323", "GSM890324", "GSM890325", "GSM890326", "GSM890327", "GSM890328", "GSM890329", "GSM890330", "GSM890331", "GSM890332", "GSM890333", "GSM890334", "GSM890335", "GSM890336", "GSM890337", "GSM890338", "GSM890339", "GSM890340", "GSM890341", "GSM890342", "GSM890343", "GSM890344", "GSM890345", "GSM890346", "GSM890347", "GSM890348", "GSM890349", "GSM890350", "GSM890351", "GSM890352", "GSM890353", "GSM890354", "GSM890355", "GSM890356", "GSM890357", "GSM890358", "GSM890359", "GSM890360", "GSM890361", "GSM890362", "GSM890363", "GSM890364", "GSM890365", "GSM890366", "GSM890367", "GSM890368", "GSM890369", "GSM890370", "GSM890371", "GSM890372", "GSM890373", "GSM890374", "GSM890375", "GSM890376", "GSM890377", "GSM890378", "GSM890379", "GSM890380", "GSM890381", "GSM890382", "GSM890383", "GSM890384", "GSM890385", "GSM890386", "GSM890387", "GSM890388", "GSM890389", "GSM890390", "GSM890391", "GSM890392", "GSM890393", "GSM890394", "GSM890395", "GSM890396", "GSM890397", "GSM890398", "GSM890399", "GSM890400", "GSM890401", "GSM890402", "GSM890403", "GSM890404", "GSM890405", "GSM890406", "GSM890407", "GSM890408", "GSM890409", "GSM890410", "GSM890411", "GSM890412", "GSM890413", "GSM890414", "GSM890415", "GSM890416", "GSM890417", "GSM890418", "GSM890419", "GSM890420", "GSM890421", "GSM890422", "GSM890423", "GSM890424", "GSM890425", "GSM890426", "GSM890427", "GSM890428", "GSM890429", "GSM890430", "GSM890431", "GSM890432", "GSM890433", "GSM890434", "GSM890435", "GSM890436", "GSM890437", "GSM890438", "GSM890439", "GSM890440", "GSM890441", "GSM890442", "GSM890443", "GSM890444", "GSM890445", "GSM890446", "GSM890447", "GSM890448", "GSM890449", "GSM890450", "GSM890451", "GSM890452", "GSM890453", "GSM890454", "GSM890455", "GSM890456", "GSM890457", "GSM890458", "GSM890459", "GSM890460", "GSM890461", "GSM890462", "GSM890463", "GSM890464", "GSM890465", "GSM890466", "GSM890467", "GSM890468", "GSM890469", "GSM890470", "GSM890471", "GSM890472", "GSM890473", "GSM890474", "GSM890475", "GSM890476", "GSM890477", "GSM890478", "GSM890479", "GSM890480", "GSM890481", "GSM890482", "GSM890483", "GSM890484", "GSM890485", "GSM890486", "GSM890487", "GSM890488", "GSM890489", "GSM890490", "GSM890491", "GSM890492", "GSM890493", "GSM890494", "GSM890495", "GSM890496", "GSM890497", "GSM890498", "GSM890499", "GSM890500", "GSM890501", "GSM890502", "GSM890503", "GSM890504", "GSM890505", "GSM890506", "GSM890507", "GSM890508", "GSM890509", "GSM890510", "GSM890511", "GSM890512", "GSM890513", "GSM890514", "GSM890515", "GSM890516", "GSM890517", "GSM890518", "GSM890519", "GSM890520", "GSM890521", "GSM890522", "GSM890523", "GSM890524", "GSM890525", "GSM890526", "GSM890527", "GSM890528", "GSM890529", "GSM890530", "GSM890531", "GSM890532", "GSM890533", "GSM890534", "GSM890535", "GSM890536", "GSM890537", "GSM890538", "GSM890539", "GSM890540", "GSM890541", "GSM890542", "GSM890543", "GSM890544", "GSM890545", "GSM890546", "GSM890547", "GSM890548", "GSM890549", "GSM890550", "GSM890551", "GSM890552", "GSM890553", "GSM890554", "GSM890555", "GSM890556", "GSM890557", "GSM890558", "GSM890559", "GSM890560"], "sample_count": 433, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Gene Expression Profiles of both tumor and adjacent non-tumor liver Identify Hepatocellular Carcinoma Patients at High Risk of Recurrence after Curative Hepatectomy", "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:GSE45267", "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=GSE45267", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE45267", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding author.", "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"], "sample_count": 87, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profiles of human hepatocellular carcinoma (training set 1)", "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 original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding author.", "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}}], "gaps": ["asset:data:geo:GSE102079 not downloaded", "asset:data:geo:GSE102079 licence not read", "asset:data:geo:GSE36376 not downloaded", "asset:data:geo:GSE36376 licence not read", "asset:data:geo:GSE45267 not downloaded", "asset:data:geo:GSE45267 licence not read", "asset:data:geo:GSE54236 not downloaded", "asset:data:geo:GSE54236 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The limma package of R software was used to identify the DEGs in four datasets."}}, {"id": "method-2", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Wilcoxon"}}, {"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": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Spearman correlation"}}, {"id": "method-5", "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": "PPI"}}, {"id": "method-6", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "pathway enrichment"}}, {"id": "method-7", "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": ["method.reader_differs_from_extractor"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE36376", "GSE102079", "GSE54236", "GSE45267"], "resolved_accessions": ["GSE36376", "GSE102079", "GSE54236", "GSE45267"], "statements": ["The original contributions presented in the study are included in the article/Supplementary Material; further inquiries can be directed to the corresponding author."], "basis": "The paper names GSE36376, GSE102079, GSE54236, GSE45267 in Gene Expression Omnibus and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:36685860", "data:geo:GSE102079"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE102079"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:24:18Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 14295, "completion_tokens": 1973, "cached_tokens": 264}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:36685860", "type": "paper", "label": "pmid:36685860"}, {"id": "source:pmid:36685860", "type": "manuscript", "label": "PMID 36685860 full text"}, {"id": "data:geo:GSE102079", "type": "dataset", "label": "GEO GSE102079"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36685860", "type": "paper", "label": "pmid:36685860"}, {"id": "source:pmid:36685860", "type": "manuscript", "label": "PMID 36685860 full text"}, {"id": "data:geo:GSE102079", "type": "dataset", "label": "GEO GSE102079"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36685860", "type": "extraction", "used": ["source:pmid:36685860"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE102079", "type": "accession_resolution", "used": ["data:geo:GSE102079"], "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:36685860", "parent_hash": "sha256:04bee02bf338f1f59c2331873baec68e52ffb97481f6133b25d99e3b3177a779", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE102079 licence not read", "asset:data:geo:GSE102079 not downloaded", "asset:data:geo:GSE36376 licence not read", "asset:data:geo:GSE36376 not downloaded", "asset:data:geo:GSE45267 licence not read", "asset:data:geo:GSE45267 not downloaded", "asset:data:geo:GSE54236 licence not read", "asset:data:geo:GSE54236 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["find new HCC-related target genes. Methods: RNA-sequencing data of HCC were gathered from The Cancer Ge", ". Correlation analysis of genes and pathways RNA-sequencing expression profiles and the corresponding cl"], "order_basis": "paper_text_order:264", "id": "assay:1"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["e role of PBK in HCC was further verified by western blot, CCK8, transwell, and tube formation experim"], "order_basis": "paper_text_order:1267", "id": "assay:2"}, {"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["in HCC was further verified by western blot, CCK8, transwell, and tube formation experiments."], "order_basis": "paper_text_order:1281", "id": "assay:3"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The limma package of R software was used to identify the DEGs in four datasets."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"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":"2026-11-04T03:38:23+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}}}