{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34260294", "kind": "science-record", "revision": 7, "content_hash": "sha256:aa2f33c280754e3bb30c77cc1b3e3f8317c1ce5fcf7ee305ace35420f91affd4", "created_at": "2026-11-01T15:41:43Z", "updated_at": "2026-11-01T22:04:13Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "HMGCS2 in metabolic pathways was associated with overall survival in hepatocellular carcinoma: A LASSO-derived study.", "doi": "10.1177/00368504211031749", "pmid": "34260294", "authors": ["Rongrong Ding", "Tianyou Chen", "Yuan Zhang", "Xiaorong Chen", "Liping Zhuang", "Zongguo Yang"], "journal": "Science progress", "year": 2021, "abstract": "This integrated bioinformatic study aimed to investigate potential prognostic candidates in hepatocellular carcinoma (HCC). In the GSE14520, GSE101685, and The Cancer Genome Atlas (TCGA) datasets, differentially expressed genes (DEGs) were identified and functional pathways of common DEGs were enriched. The least absolute shrinkage and selection operator (LASSO) model was used to screen the potential parameters associated with overall survival (OS) in HCC patients. Metabolic pathways were the most significantly enriched functional pathways of common DEGs in these three datasets. After LASSO model analysis, HMGCS2, UGP2, BCLC staging and TNM staging were screened as potential prognostic candidates for OS in HCC patients in GSE14520. HMGCS2 in the metabolic pathway was significantly downregulated in tumor tissues and peripheral blood mononuclear cells in HCC patients (all p < 0.05). Cox regression model indicated that HMGCS2 might be associate with OS in HCC patients in GSE14520 and in the TCGA (p = 0.029 and p = 0.05, respectively). Kaplan-Meier analysis demonstrated that HMGCS2 downregulation in tumors contributed to an unfavorable OS in HCC patients, both in GSE14520 and in the TCGA (p = 0.0001 and p = 0.0002, respectively). Additionally, HMGCS2 was significantly downregulated in HCC patients with high alpha-fetoprotein (AFP), main tumor size >5 cm, multinodular, advanced tumor staging including BCLC, TNM and CLIP (all p < 0.05). HMGCS2 was involved in metabolic pathways, and downregulated HMGCS2 in tumors was associated with unfavorable OS in HCC patients.", "claims": [{"id": "claim-method", "statement": "The Kaplan-Meier method was used to compare OS between different groups, and the log-rank test was used to estimate the significances in survival between groups.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34260294", "locator": "sections[9] \"Statistical analysis\" paragraph 2", "quote": "The Kaplan-Meier method was used to compare OS between different groups, and the log-rank test was used to estimate the significances in survival between groups."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34260294", "locator": "sections[18] \"Footnotes\" paragraph 2", "quote": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request."}], "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:34260294"], "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:GSE101685"], "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:GSE101685"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34260294", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1177/00368504211031749", "sha256": "sha256:90518c862d4baf7bb51e7a98ea3601fb463caa969ef6b8e8ea3e17d78f7b202e", "bytes": 36735, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1177/00368504211031749", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10358623", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE101685", "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=GSE101685", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE101685", "version": null, "note": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2711996", "GSM2711997", "GSM2711998", "GSM2711999", "GSM2712000", "GSM2712001", "GSM2712002", "GSM2712003", "GSM2712004", "GSM2712005", "GSM2712006", "GSM2712007", "GSM2712008", "GSM2712009", "GSM2712010", "GSM2712011", "GSM2712012", "GSM2712013", "GSM2712014", "GSM2712015", "GSM2712016", "GSM2712017", "GSM2712018", "GSM2712019", "GSM2712020", "GSM2712021", "GSM2712022", "GSM2712023", "GSM2712024", "GSM2712025", "GSM2712026", "GSM2712027"], "sample_count": 32, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profile of hepatocellular carcinoma patients in Taiwan", "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": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "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:GSE33006", "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=GSE33006", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33006", "version": null, "note": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM818276", "GSM818277", "GSM818278", "GSM818279", "GSM818280", "GSM818281"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profiles from the hepatocellular carcinoma (HCC) tissues", "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": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "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:GSE49515", "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=GSE49515", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE49515", "version": null, "note": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1200291", "GSM1200292", "GSM1200293", "GSM1200294", "GSM1200295", "GSM1200296", "GSM1200297", "GSM1200298", "GSM1200299", "GSM1200300", "GSM1200301", "GSM1200302", "GSM1200303", "GSM1200304", "GSM1200305", "GSM1200306", "GSM1200307", "GSM1200308", "GSM1200309", "GSM1200310", "GSM1200311", "GSM1200312", "GSM1200313", "GSM1200314", "GSM1200315", "GSM1200316"], "sample_count": 26, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression profiling of PBMC from patients with 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:GSE55092", "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=GSE55092", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE55092", "version": null, "note": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1329321", "GSM1329322", "GSM1329323", "GSM1329324", "GSM1329325", "GSM1329326", "GSM1329327", "GSM1329328", "GSM1329329", "GSM1329330", "GSM1329331", "GSM1329332", "GSM1329333", "GSM1329334", "GSM1329335", "GSM1329336", "GSM1329337", "GSM1329338", "GSM1329339", "GSM1329340", "GSM1329341", "GSM1329342", "GSM1329343", "GSM1329344", "GSM1329345", "GSM1329346", "GSM1329347", "GSM1329348", "GSM1329349", "GSM1329350", "GSM1329351", "GSM1329352", "GSM1329353", "GSM1329354", "GSM1329355", "GSM1329356", "GSM1329357", "GSM1329358", "GSM1329359", "GSM1329360", "GSM1329361", "GSM1329362", "GSM1329363", "GSM1329364", "GSM1329365", "GSM1329366", "GSM1329367", "GSM1329368", "GSM1329369", "GSM1329370", "GSM1329371", "GSM1329372", "GSM1329373", "GSM1329374", "GSM1329375", "GSM1329376", "GSM1329377", "GSM1329378", "GSM1329379", "GSM1329380", "GSM1329381", "GSM1329382", "GSM1329383", "GSM1329384", "GSM1329385", "GSM1329386", "GSM1329387", "GSM1329388", "GSM1329389", "GSM1329390", "GSM1329391", "GSM1329392", "GSM1329393", "GSM1329394", "GSM1329395", "GSM1329396", "GSM1329397", "GSM1329398", "GSM1329399", "GSM1329400", "GSM1329401", "GSM1329402", "GSM1329403", "GSM1329404", "GSM1329405", "GSM1329406", "GSM1329407", "GSM1329408", "GSM1329409", "GSM1329410", "GSM1329411", "GSM1329412", "GSM1329413", "GSM1329414", "GSM1329415", "GSM1329416", "GSM1329417", "GSM1329418", "GSM1329419", "GSM1329420", "GSM1329421", "GSM1329422", "GSM1329423", "GSM1329424", "GSM1329425", "GSM1329426", "GSM1329427", "GSM1329428", "GSM1329429", "GSM1329430", "GSM1329431", "GSM1329432", "GSM1329433", "GSM1329434", "GSM1329435", "GSM1329436", "GSM1329437", "GSM1329438", "GSM1329439", "GSM1329440", "GSM1329441", "GSM1329442", "GSM1329443", "GSM1329444", "GSM1329445", "GSM1329446", "GSM1329447", "GSM1329448", "GSM1329449", "GSM1329450", "GSM1329451", "GSM1329452", "GSM1329453", "GSM1329454", "GSM1329455", "GSM1329456", "GSM1329457", "GSM1329458", "GSM1329459", "GSM1329460"], "sample_count": 140, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Viral Expression and Molecular Profiling in Liver Tissue versus Microdissected Hepatocytes in Hepatitis B Virus - Associated 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:GSE58208", "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=GSE58208", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE58208", "version": null, "note": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1403309", "GSM1403310", "GSM1403311", "GSM1403312", "GSM1403313", "GSM1403314", "GSM1403315", "GSM1403316", "GSM1403317", "GSM1403318", "GSM1403319", "GSM1403320", "GSM1403321", "GSM1403322", "GSM1403323", "GSM1403324", "GSM1403325", "GSM1403326", "GSM1403327", "GSM1403328", "GSM1403329", "GSM1403330", "GSM1403331", "GSM1403332", "GSM1403333", "GSM1403334", "GSM1403335"], "sample_count": 27, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profiling of PBMC from normal individuals, chronic hepatitis B carriers and hepatocellular carcinoma patients", "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": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "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:GSE84402", "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=GSE84402", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE84402", "version": null, "note": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2233086", "GSM2233087", "GSM2233088", "GSM2233089", "GSM2233090", "GSM2233091", "GSM2233092", "GSM2233093", "GSM2233094", "GSM2233095", "GSM2233096", "GSM2233097", "GSM2233098", "GSM2233099", "GSM2233100", "GSM2233101", "GSM2233102", "GSM2233103", "GSM2233104", "GSM2233105", "GSM2233106", "GSM2233107", "GSM2233108", "GSM2233109", "GSM2233110", "GSM2233111", "GSM2233112", "GSM2233113"], "sample_count": 28, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from human hepatocellular carcinoma tissues and the correponding non-cancerous tissues", "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:34260294:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3ac5dbee8964a6c444452873c5056a3a37d6467b3701de6468bcaaf36447fa03", "bytes": 1225, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#table1-00368504211031749", "version": null, "note": "Details of GEO and TCGA datasets included in this study.", "structure": {"pmcid": "PMC10358623", "section_index": 4, "section_title": "Data source", "row_count": 11, "column_count": 6}, "table": {"label": "Table 1.", "caption": "Details of GEO and TCGA datasets included in this study.", "rows": [["Datasets", "Contributor(s)", "Sample", "HCC", "Non-HCC", "Platform"], ["GSE14520", "Wang et al.(2009)", "Tissue", "247", "239", "Affymetrix Human Genome U133A 2.0 Array/Affymetrix HT Human Genome U133A Array"], ["GSE33006", "Huang et al.(2011)", "Tissue", "3", "3", "Affymetrix Human Genome U133 Plus 2.0 Array"], ["GSE45436", "Hsieh(2013)", "Tissue", "97", "37", "Affymetrix Human Genome U133 Plus 2.0 Array"], ["GSE55092", "Melis et al.(2014)", "Tissue", "49", "91", "Affymetrix Human Genome U133 Plus 2.0 Array"], ["GSE60502", "Kao(2014)", "Tissue", "18", "18", "Affymetrix Human Genome U133A Array"], ["GSE84402", "Qin et al.(2016)", "Tissue", "14", "14", "Affymetrix Human Genome U133 Plus 2.0 Array"], ["GSE101685", "Sen-Yung(2017)", "Tissue", "24", "8", "Affymetrix Human Genome U133 Plus 2.0 Array"], ["GSE58208", "Hui(2014)", "PBMCs", "10", "17", "Affymetrix Human Genome U133 Plus 2.0 Array"], ["GSE49515", "Hui (2013)", "PBMCs", "10", "10", "Affymetrix Human Genome U133 Plus 2.0 Array"], ["TCGA-LIHC", "TCGA", "Tissue", "374", "50", "RNAseq Htseq"]], "row_count": 11, "column_count": 6, "numeric_cells": 47, "header_rows": 1, "locator": "section[4]/table-wrap[1]#table1-00368504211031749"}}, {"id": "asset:table:pmid:34260294:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3ceed7ad53d65801391d4ba2b0f501dac66fb388d33c7a28b7b0d747c87c2960", "bytes": 2841, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#table2-00368504211031749", "version": null, "note": "Significant genes enriched in the top 20 functional pathways.", "structure": {"pmcid": "PMC10358623", "section_index": 11, "section_title": "Common genes identification and enrichment", "row_count": 21, "column_count": 5}, "table": {"label": "Table 2.", "caption": "Significant genes enriched in the top 20 functional pathways.", "rows": [["ID", "Description", "p value", "Adj. p value", "Enriched genes"], ["hsa00280", "Valine, leucine andisoleucine degradation", "0.078", "0.235", "ABAT; EHHADH; ACAT1; ACAA1; AOX1; ECHS1; ALDH6A1; HMGCS2; ALDH2"], ["hsa00380", "Tryptophan metabolism", "0.065", "0.213", "ACAT1; CYP1A2; AOX1; ECHS1; CAT; ALDH8A1; TDO2; ALDH2"], ["hsa05322", "Systemic lupus erythematosus", "0.157", "0.377", "C8A; C8B; C9; C1R; C1S; C6"], ["hsa05150", "Staphylococcus aureus infection", "0.045", "0.196", "CFI; C1R; PLG; C1S"], ["hsa00830", "Retinol metabolism", "0.019", "0.196", "CYP4A11; RDH16; AOX1; CYP2A6; CYP3A4; ADH1C; ADH1A; CYP2C9; CYP2C8; ADH1B"], ["hsa03320", "PPAR signaling pathway", "0.047", "0.196", "ACAA1; CYP4A11; PCK2; ACSL1; HMGCS2; PCK1"], ["hsa05133", "Pertussis", "0.124", "0.33", "CD14; SERPING1; C1R; C1S"], ["hsa04080", "Neuroactiveligand-receptor interaction", "0.269", "0.517", "AGTR1; VIPR1; GHR; PLG"], ["hsa00980", "Metabolism of xenobioticsby cytochrome P450", "0.05", "0.196", "CYP2A6; CYP3A4; ADH1C; ADH1A; CYP2C9; ADH1B; CYP2E1"], ["hsa01100", "Metabolic pathways", "0.001", "0.048", "AGL; CA2; KMO; CYP2C18; GSTZ1; CYP2B6; PEMT; GLUD1; GNE; GBA3; ACSM5; CYP2J2; CYP4F2; EPHX2; ACADSB; GLYAT; GCH1; GLS2; NAT2; BDH2; RGN; ABAT; GNMT; ADH6; GYS2; UGP2; FTCD; EHHADH; HAO1; ALAS1; HAO2; ACAT1; DPYS; CYP1A2; ACAA1; CYP4A11; PCK2; GRHPR; RDH16; AOX1; CYP2A6; ECHS1; CAT; ALDH6A1; ACSL1; FBP1; ALDH8A1; HMGCS2; MAT1A; AKR1D1; NNMT; BHMT; TAT; CYP3A4; TDO2; ALDH2; ADH1C; ADH1A; CYP2C9; ALDOB; ASS1; CYP2C8; PCK1; ADH1B; CYP2E1"], ["hsa05167", "Kaposi sarcoma-associated herpesvirus infection", "0.254", "0.516", "GABARAPL1; RCAN1; FOS; CXCL2"], ["hsa00010", "Glycolysis/gluconeogenesis", "0.053", "0.196", "FBP1; ALDH2; ADH1C; ADH1A; ALDOB; PCK1; ADH1B"], ["hsa04068", "FoxO signaling pathway", "0.117", "0.33", "IGF1; PCK2; CAT; PCK1"], ["hsa00071", "Fatty acid degradation", "0.047", "0.196", "ADH6; EHHADH; ACAT1; ACAA1; CYP4A11; ECHS1; ACSL1; ALDH2; ADH1C; ADH1A; ADH1B"], ["hsa00982", "Drug metabolism—cytochrome P450", "0.025", "0.196", "FMO3; CYP1A2; AOX1; CYP2A6; CYP3A4; ADH1C; ADH1A; CYP2C9; CYP2C8; ADH1B; CYP2E1"], ["hsa03030", "DNA replication", "0.067", "0.213", "PCNA; MCM6; RFC4; MCM3; MCM2; MCM7; RNASEH2A; MCM5; PRIM1; POLE2"], ["hsa04610", "Complement and coagulation cascades", "0.003", "0.079", "C7; KLKB1; CFI; CPB2; C8A; C8B; C9; SERPING1; C1R; PLG; C1S; C6; FGA; F9"], ["hsa05204", "Chemical carcinogenesis", "0.031", "0.196", "ADH6; CYP1A2; CYP2A6; CYP3A4; ADH1C; ADH1A; CYP2C9; CYP2C8; ADH1B; CYP2E1"], ["hsa00650", "Butanoate metabolism", "0.212", "0.463", "BDH2; ABAT; EHHADH; ACAT1; ECHS1; HMGCS2"], ["hsa05146", "Amoebiasis", "0.051", "0.196", "C8A; C8B; C9; CXCL2"]], "row_count": 21, "column_count": 5, "numeric_cells": 67, "header_rows": 1, "locator": "section[11]/table-wrap[1]#table2-00368504211031749"}}, {"id": "asset:table:pmid:34260294:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9447956760cf3d3e28b3dcdfbc7df8d8d06b1f5583fb39bdebc629ff0301c541", "bytes": 1629, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#table3-00368504211031749", "version": null, "note": "Cox regression models for identification of parameters associated with OS in HCC patients in GSE14520 and in the TCGA.", "structure": {"pmcid": "PMC10358623", "section_index": 12, "section_title": "Identification of potential candidates for OS in HCC", "row_count": 25, "column_count": 5}, "table": {"label": "Table 3.", "caption": "Cox regression models for identification of parameters associated with OS in HCC patients in GSE14520 and in the TCGA.", "rows": [["Variables #", "Univariate", "Multivariate"], ["", "HR (95% CI)", "p value", "HR (95% CI)", "p value"], ["GSE14520 dataset"], ["HMGCS2, high versus low", "0.43 (0.27–0.667)", "<0.001", "0.57 (0.34–0.94)", "0.029"], ["UGP2, high versus low", "0.57 (0.37–0.89)", "0.013", "0.95 (0.58–1.56)", "0.844"], ["BCLC staging"], ["0–A", "Reference", "1.0", "Reference", "1.0"], ["B", "2.40 (1.28–4.53)", "0.007", "1.31 (0.61–2.80)", "0.493"], ["C", "4.60 (2.72–7.76)", "<0.001", "2.51 (1.12–5.62)", "0.025"], ["TNM staging"], ["I", "Reference", "1.0", "Reference", "1.0"], ["II", "2.08 (1.21–3.59)", "0.008", "1.87 (1.07–3.27)", "0.027"], ["III", "4.93 (2.82–8.60)", "<0.001", "2.37 (1.04–5.41)", "0.041"], ["TCGA-LIHC dataset*"], ["HMGCS2, high versus low", "0.49 (0.35–0.71)", "<0.001", "0.63 (0.39–1.0)", "0.05"], ["UGP2, high versus low", "0.62 (0.44–0.88)", "0.007", "0.77 (0.49–1.23)", "0.279"], ["AJCC staging"], ["I", "Reference", "1.0", "Reference", "1.0"], ["II", "1.49 (0.91–2.44)", "0.111", "1.27 (0.68–2.36)", "0.454"], ["III", "2.82 (1.85–4.28)", "<0.001", "2.12 (1.25–3.59)", "0.005"], ["IV", "2.64 (1.38–5.04)", "0.003", "2.65 (1.25–5.62)", "0.011"], ["Vascular invasion"], ["None", "Reference", "1.0", "Reference", "1.0"], ["Microvascular", "1.25 (0.80–1.97)", "0.327", "0.96 (0.57–1.60)", "0.873"], ["Macrovascular", "2.24 (1.06–4.72)", "0.034", "1.45 (0.66–3.19)", "0.361"]], "row_count": 25, "column_count": 5, "numeric_cells": 64, "header_rows": 2, "locator": "section[12]/table-wrap[1]#table3-00368504211031749"}}], "gaps": ["asset:data:geo:GSE101685 not downloaded", "asset:data:geo:GSE101685 licence not read", "asset:data:geo:GSE14520 not downloaded", "asset:data:geo:GSE14520 licence not read", "asset:data:geo:GSE33006 not downloaded", "asset:data:geo:GSE33006 licence not read", "asset:data:geo:GSE45436 not downloaded", "asset:data:geo:GSE45436 licence not read", "asset:data:geo:GSE49515 not downloaded", "asset:data:geo:GSE49515 licence not read", "asset:data:geo:GSE55092 not downloaded", "asset:data:geo:GSE55092 licence not read", "asset:data:geo:GSE58208 not downloaded", "asset:data:geo:GSE58208 licence not read", "asset:data:geo:GSE60502 not downloaded", "asset:data:geo:GSE60502 licence not read", "asset:data:geo:GSE84402 not downloaded", "asset:data:geo:GSE84402 licence not read"]}, "analysis": {"state": "partial", "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 Kaplan-Meier method was used to compare OS between different groups, and the log-rank test was used to estimate the significances in survival between groups."}}, {"id": "method-2", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "ANOVA"}}, {"id": "method-3", "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": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-4", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Cox regression"}}, {"id": "method-5", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "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": ["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": ["GSE14520", "GSE101685", "GSE33006", "GSE45436", "GSE55092", "GSE60502", "GSE84402", "GSE58208", "GSE49515"], "resolved_accessions": ["GSE14520", "GSE101685", "GSE33006", "GSE45436", "GSE55092", "GSE60502", "GSE84402", "GSE58208", "GSE49515"], "statements": ["Data availability: Datasets of the current study are available from The Cancer Genome Atlas (https://portal.gdc.cancer.gov/) and the NCBI Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/). The combined datasets were available from corresponding authors with reasonable request."], "basis": "The paper names GSE14520, GSE101685, GSE33006, GSE45436, GSE55092, GSE60502, GSE84402, GSE58208, GSE49515 in NCBI 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:34260294", "data:geo:GSE101685", "asset:table:pmid:34260294:1", "asset:table:pmid:34260294:2", "asset:table:pmid:34260294:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE101685"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:32:32Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 28583, "completion_tokens": 4025, "cached_tokens": 792}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:34260294", "type": "paper", "label": "pmid:34260294"}, {"id": "source:pmid:34260294", "type": "manuscript", "label": "PMID 34260294 full text"}, {"id": "data:geo:GSE101685", "type": "dataset", "label": "GEO GSE101685"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34260294", "type": "paper", "label": "pmid:34260294"}, {"id": "source:pmid:34260294", "type": "manuscript", "label": "PMID 34260294 full text"}, {"id": "data:geo:GSE101685", "type": "dataset", "label": "GEO GSE101685"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34260294", "type": "extraction", "used": ["source:pmid:34260294"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE101685", "type": "accession_resolution", "used": ["data:geo:GSE101685"], "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:34260294", "parent_hash": "sha256:487673345c5c2ea3cafd3870b1c0700d858f687d9de0f4e23f4d6bb38fd59070", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE101685 licence not read", "asset:data:geo:GSE101685 not downloaded", "asset:data:geo:GSE14520 licence not read", "asset:data:geo:GSE14520 not downloaded", "asset:data:geo:GSE33006 licence not read", "asset:data:geo:GSE33006 not downloaded", "asset:data:geo:GSE45436 licence not read", "asset:data:geo:GSE45436 not downloaded", "asset:data:geo:GSE49515 licence not read", "asset:data:geo:GSE49515 not downloaded", "asset:data:geo:GSE55092 licence not read", "asset:data:geo:GSE55092 not downloaded", "asset:data:geo:GSE58208 licence not read", "asset:data:geo:GSE58208 not downloaded", "asset:data:geo:GSE60502 licence not read", "asset:data:geo:GSE60502 not downloaded", "asset:data:geo:GSE84402 licence not read", "asset:data:geo:GSE84402 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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 Kaplan-Meier method was used to compare OS between different groups, and the log-rank test was used to estimate the significances in survival between groups."], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:15:47+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}}}