{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33558447", "kind": "science-record", "revision": 7, "content_hash": "sha256:74dd728a2790a953db605d2b808c5fdfaff9c93f4de877e5fb3137b6b839866f", "created_at": "2026-11-01T15:41:24Z", "updated_at": "2026-11-01T22:03:04Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Combined identification of ARID1A, CSMD1, and SENP3 as effective prognostic biomarkers for hepatocellular carcinoma.", "doi": "10.18632/aging.202586", "pmid": "33558447", "authors": ["Yuanyuan Zhao", "Bo Yang", "Dong Chen", "Xiaojun Zhou", "Meixi Wang", "Jipin Jiang", "Lai Wei", "Zhishui Chen"], "journal": "Aging", "year": 2021, "abstract": "BACKGROUND: The current study aimed to understand the genetic landscape and investigate the diagnostic and prognostic biomarkers of primary hepatocellular carcinoma (HCC).\nMETHODS: A cohort of 36 Chinese HCC samples with hepatitis B virus (HBV) infection was examined by whole-exome sequencing (WES). Prognosis-related alterations were identified and further verified in the TCGA database and GSE65372 profiles in the GEO database. A Chinese replication cohort of 180 HCC samples with HBV infection was collected to evaluate the candidate genes by immunohistochemical analysis. A receiver operating characteristic (ROC) curve analysis evaluated the prognostic power of candidate genes. Finally, EdU and transwell invasion assay were performed to detect the function of candidate genes.\nRESULTS: A total of 11 novel genes showed a significant association with HCC in the discovery cohort. The data were verified using the GEO and TCGA databases, and the expression of ARID1A, CSMD1, and SENP was evaluated in the replication cohort. Furthermore, ARID1A, CSMD1, and SENP3 are effective prognostic biomarkers for HCC patients in the replication population.\nCONCLUSIONS: Molecular heterogeneity was detected in HCC patients, and ARID1A, CSMD1, and SENP3 were identified as effective HCC prognosis biomarkers. CSMD1 prevents HCC by suppressing cell invasion.", "claims": [{"id": "claim-method", "statement": "Cox regression analysis was used to evaluate the prognostic value adjusted by patient sex, age, and AJCC stage (version VII).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33558447", "locator": "sections[21] \"Statistical analysis\" paragraph 2", "quote": "Cox regression analysis was used to evaluate the prognostic value adjusted by patient sex, age, and AJCC stage (version VII)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data have been deposited with links to BioProject accession number PRJNA607376 in the NCBI BioProject database (https://www.ncbi.nlm.nih.gov/bioproject/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33558447", "locator": "sections[23] \"Availability of data and materials\" paragraph 2", "quote": "The data have been deposited with links to BioProject accession number PRJNA607376 in the NCBI BioProject database (https://www.ncbi.nlm.nih.gov/bioproject/)."}], "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:33558447"], "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:GSE65372"], "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:GSE65372"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33558447", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.18632/aging.202586", "sha256": "sha256:5fc0f14b8ea8db4a41de2f3da97bf2b0fa3db15bae99bcb03dca8d2af7020286", "bytes": 37222, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.18632/aging.202586", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7906131", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE65372", "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=GSE65372", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE65372", "version": null, "note": "The data have been deposited with links to BioProject accession number PRJNA607376 in the NCBI BioProject database (https://www.ncbi.nlm.nih.gov/bioproject/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data have been deposited with links to BioProject accession number PRJNA607376 in the NCBI BioProject database (https://www.ncbi.nlm.nih.gov/bioproject/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1594003", "GSM1594004", "GSM1594005", "GSM1594006", "GSM1594007", "GSM1594008", "GSM1594009", "GSM1594010", "GSM1594011", "GSM1594012", "GSM1594013", "GSM1594014", "GSM1594015", "GSM1594016", "GSM1594017", "GSM1594018", "GSM1594019", "GSM1594020", "GSM1594021", "GSM1594022", "GSM1594023", "GSM1594024", "GSM1594025", "GSM1594026", "GSM1594027", "GSM1594028", "GSM1594029", "GSM1594030", "GSM1594031", "GSM1594032", "GSM1594033", "GSM1594034", "GSM1594035", "GSM1594036", "GSM1594037", "GSM1594038", "GSM1594039", "GSM1594040", "GSM1594041", "GSM1594042", "GSM1594043", "GSM1594044", "GSM1594045", "GSM1594046", "GSM1594047", "GSM1594048", "GSM1594049", "GSM1594050", "GSM1594051", "GSM1594052", "GSM1594053", "GSM1594054", "GSM1594055", "GSM1594056"], "sample_count": 54, "group_sizes": null, "group_sizes_basis": null, "platform": "14951", "taxon": "Homo sapiens", "title": "Molecular heterogeneity of multinodular hepatocellular carcinoma [gene expression]", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PRJNA607376", "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=PRJNA607376", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PRJNA607376", "version": null, "note": "The data have been deposited with links to BioProject accession number PRJNA607376 in the NCBI BioProject database (https://www.ncbi.nlm.nih.gov/bioproject/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data have been deposited with links to BioProject accession number PRJNA607376 in the NCBI BioProject database (https://www.ncbi.nlm.nih.gov/bioproject/).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:35:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33558447:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7462062f79c6b25a7d39996cf30e6eaac245d8f7facc3f4dbea09f6dc05efe5f", "bytes": 2589, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#t1", "version": null, "note": "Clinical characteristics of HCC patients in the discovery population.", "structure": {"pmcid": "PMC7906131", "section_index": 3, "section_title": "Genetic mutation landscape of HCC in the discovery population", "row_count": 37, "column_count": 8}, "table": {"label": "Table 1", "caption": "Clinical characteristics of HCC patients in the discovery population.", "rows": [["Sample ID", "Age at diagnosis (years)", "Sex", "Type of LPC#", "Group*", "Total SNVs", "Total InDels", "Total CNVs"], ["LAAAP2T1", "50", "male", "HCC, HBV-infected", "B", "65", "2", "0"], ["LAAAP3T1", "49", "male", "HCC, HBV-infected", "B", "100", "6", "0"], ["LAAAP5T1", "56", "male", "HCC, HBV-infected", "B", "381", "20", "0"], ["LAAARTT1", "51", "male", "HCC, HBV-infected", "B", "3", "0", "0"], ["LAAATYT1", "54", "male", "HCC, HBV-infected", "C", "23", "1", "0"], ["LAAAXZT2", "53", "male", "HCC, HBV-infected", "B", "21", "1", "0"], ["LAAB4BT1", "57", "male", "HCC, HBV-infected", "A", "30", "1", "0"], ["LAABBRT1", "43", "male", "HCC, HBV-infected", "NA", "144", "6", "4"], ["LAABXST1", "39", "male", "HCC, HBV-infected", "C", "78", "5", "1"], ["LAACBFT1", "59", "male", "HCC, HBV-infected", "C", "95", "6", "1"], ["LAACERT1", "47", "male", "HCC, HBV-infected", "A", "65", "8", "0"], ["LAACLYT1", "56", "male", "HCC, HBV-infected", "C", "133", "1", "1"], ["LAACQQT1", "60", "male", "HCC, HBV-infected", "NA", "462", "12", "0"], ["LAACZ6T1", "27", "male", "HCC, HBV-infected", "A", "71", "1", "0"], ["LAADHST1", "45", "male", "HCC, HBV-infected", "B", "91", "5", "0"], ["LAADHTT2", "60", "male", "HCC, HBV-infected", "B", "1", "0", "0"], ["LAADWRT1", "36", "male", "HCC, HBV-infected", "A", "69", "6", "0"], ["LAADX9T1", "34", "male", "HCC, HBV-infected", "C", "37", "4", "0"], ["LAAEBQT1", "49", "male", "HCC, HBV-infected", "B", "84", "0", "0"], ["LAAEPST1", "25", "male", "HCC, HBV-infected", "B", "31", "2", "0"], ["LAAERTT1", "36", "male", "HCC, HBV-infected", "B", "23", "2", "0"], ["LAAFWBT1", "49", "male", "HCC, HBV-infected", "B", "57", "1", "0"], ["LAL1904T", "67", "male", "HCC, HBV-infected", "NA", "148", "9", "0"], ["LBC7309T", "62", "male", "HCC, HBV-infected", "NA", "168", "15", "0"], ["LBD8969T", "49", "male", "HCC, HBV-infected", "NA", "139", "6", "0"], ["LBD9689T", "56", "male", "HCC, HBV-infected", "NA", "410", "13", "0"], ["LBE0743T", "42", "male", "HCC, HBV-infected", "A", "53", "4", "0"], ["LBE1024T", "34", "male", "HCC, HBV-infected", "NA", "21", "3", "1"], ["LBE1400T", "49", "male", "HCC, HBV-infected", "A", "56", "1", "0"], ["LBF2989T", "53", "male", "HCC, HBV-infected", "NA", "118", "15", "0"], ["LBF3617T", "54", "male", "HCC, HBV-infected", "NA", "46", "2", "1"], ["LBF4416T", "50", "male", "HCC, HBV-infected", "NA", "98", "2", "0"], ["LBG5412T", "55", "male", "HCC, HBV-infected", "NA", "49", "3", "0"], ["LBG5819T", "51", "male", "HCC, HBV-infected", "A", "695", "15", "3"], ["LBG6756T", "43", "male", "HCC, HBV-infected", "A", "49", "8", "0"], ["LBI0230T", "40", "male", "HCC, HBV-infected", "A", "117", "6", "0"]], "row_count": 37, "column_count": 8, "numeric_cells": 158, "header_rows": 0, "locator": "section[3]/table-wrap[1]#t1"}}, {"id": "asset:table:pmid:33558447:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:874d3c4afa40c1ebfd2e90cbf64dd1c2ed000e545b01d00260744da0c34f10f3", "bytes": 550, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#t2", "version": null, "note": "Comparison of genes associated with HCC prognosis in groups A and B#.", "structure": {"pmcid": "PMC7906131", "section_index": 4, "section_title": "Prognosis-related alterations in the discovery population", "row_count": 6, "column_count": 5}, "table": {"label": "Table 2", "caption": "Comparison of genes associated with HCC prognosis in groups A and B#.", "rows": [["Gene", "Frequency in group A", "Frequency in group B", "Likelihood ratio P-value in the discovery population", "Adjusted P-value in GEO database"], ["TP53", "0.6", "0.40", ">0.05", ">0.05"], ["CTNNB1", "0.4", "0.20", "0.018*", ">0.05"], ["KMT2C", "0.3", "0", "0.03*", "0.046*"], ["ARID1A", "0.3", "0", "0.03*", "0.039*"], ["PCLO", "0.3", "0", "0.03*", ">0.05"]], "row_count": 6, "column_count": 5, "numeric_cells": 21, "header_rows": 0, "locator": "section[4]/table-wrap[1]#t2"}}, {"id": "asset:table:pmid:33558447:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7356d51ef8c1d1dcc7dcdf3959a49bf787e55c5f18f3fc5e3dde84cdc260bdd6", "bytes": 553, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#t3", "version": null, "note": "New driver genes associated with early-recurrence and late-recurrence of HCC.", "structure": {"pmcid": "PMC7906131", "section_index": 5, "section_title": "New HCC driver genes identified in the discovery population", "row_count": 8, "column_count": 5}, "table": {"label": "Table 3", "caption": "New driver genes associated with early-recurrence and late-recurrence of HCC.", "rows": [["Group#", "Gene", "CHASM Score", "P-value", "FDR"], ["A", "MAP4K4", "0.738", "1.20E-03*", "0.05"], ["A", "COX5B", "0.728", "1.80E-03*", "0.1"], ["A", "ACTN3", "0.712", "2.20E-03*", "0.1"], ["A", "CFTR", "0.698", "3.80E-03*", "0.1"], ["A", "LRRC7", "0.696", "4.00E-03*", "0.1"], ["C", "PRKCG", "0.68", "1.72E-04*", "0.05"], ["C", "SENP3", "0.744", "8.00E-04*", "0.1"]], "row_count": 8, "column_count": 5, "numeric_cells": 21, "header_rows": 0, "locator": "section[5]/table-wrap[1]#t3"}}, {"id": "asset:table:pmid:33558447:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8732b33afd3abb70cdeaf13b101d8a0f25591d805e700ebd4fb09d3ef92e412f", "bytes": 1086, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#t4", "version": null, "note": "Clinical characteristics of the discovery population.", "structure": {"pmcid": "PMC7906131", "section_index": 7, "section_title": "ARID1A, CSMD1, and SENP3 are effective prognostic biomarkers for HBV-infected HCC patients in the replication population", "row_count": 21, "column_count": 2}, "table": {"label": "Table 4", "caption": "Clinical characteristics of the discovery population.", "rows": [["Parameters", "Validation samples for HCC (n = 175)"], ["Sex (Number of males, %)", "149, 85.14%"], ["Age (years mean ± SD)", "52.65 ± 11.26"], ["Number of tumors (mean ± SD)", "1.18 ± 0.48"], ["Size of the tumor (cm, mean ± SD)", "5.20 ± 3.25"], ["Total bilirubin (μmol/L, mean ± SD)", "14.37 ± 6.10"], ["ALT (U/L, mean ± SD)", "57.70 ± 84.01"], ["ALB (g/dL, mean ± SD)", "4.36 ± 0.52"], ["AFP (μg/L, mean ± SD)", "4846.82 ± 14002.93"], ["GGT (U/L, mean ± SD)", "82.37 ± 77.46"], ["Liver cirrhosis (number, %)", "154, 88.00%"], ["AJCC staging (Version VII)", ""], ["Stage 1 (number, %)", "116, 66.29%"], ["Stage 2 (number, %)", "57, 32.57%"], ["Stage 3 (number, %)", "2, 1.14%"], ["Pathology grade", ""], ["Grade I (number, %)", "1, 0.57%"], ["Grade I-II (number, %)", "5, 2.86%"], ["Grade II (number, %)", "94, 53.71%"], ["Grade II-III (number, %)", "28, 16.00%"], ["Grade III (number, %)", "47, 26.86%"]], "row_count": 21, "column_count": 2, "numeric_cells": 22, "header_rows": 0, "locator": "section[7]/table-wrap[1]#t4"}}, {"id": "asset:table:pmid:33558447:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:870e19a193d921e20c901d9f4f467ebdc77d8a7386cbc9f7100e28d5a8b5d65e", "bytes": 504, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[2]#t5", "version": null, "note": "ROC curve analysis of ARID1A, CSMD1, and SENP3 expression in HCC survival prediction.", "structure": {"pmcid": "PMC7906131", "section_index": 7, "section_title": "ARID1A, CSMD1, and SENP3 are effective prognostic biomarkers for HBV-infected HCC patients in the replication population", "row_count": 4, "column_count": 7}, "table": {"label": "Table 5", "caption": "ROC curve analysis of ARID1A, CSMD1, and SENP3 expression in HCC survival prediction.", "rows": [["Parameters", "Value range", "Cutoff value", "AUC", "SE", "P-value", "95% CI"], ["ARID1A", "0–2.5", "1.5", "0.489", "0.045", "0.803", "0.402–0.576"], ["CSMD1", "0–3", "1.5", "0.573", "0.043", "0.099", "0.488–0.658"], ["SENP3", "0–2.5", "1.2", "0.609", "0.042", "0.013*", "0.526–0.692"]], "row_count": 4, "column_count": 7, "numeric_cells": 19, "header_rows": 0, "locator": "section[7]/table-wrap[2]#t5"}}, {"id": "asset:table:pmid:33558447:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e13e6e67188d305cb04a4d953f210e321b2dd4522b383a3e09d62ff5f4106639", "bytes": 1059, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[3]#t6", "version": null, "note": "Prognostic value of ARID1A, CSMD1, and SENP3 expression in HCC using the Cox regression model.", "structure": {"pmcid": "PMC7906131", "section_index": 7, "section_title": "ARID1A, CSMD1, and SENP3 are effective prognostic biomarkers for HBV-infected HCC patients in the replication population", "row_count": 8, "column_count": 5}, "table": {"label": "Table 6", "caption": "Prognostic value of ARID1A, CSMD1, and SENP3 expression in HCC using the Cox regression model.", "rows": [["Parameters", "Group 1 value", "Group 2 value", "Padj value", "HR (95% CI)"], ["ARID1A", "≤1.5", ">1.5", "0.191", "0.702 (0.413–1.194)"], ["CSMD1", "<1.5", "≥1.5", "0.125", "1.425 (0.906–2.241)"], ["SENP3", "≤1.2", ">1.2", "0.032*", "1.858 (1.054–3.272)"], ["ARID1A and CSMD1", "≤1.5 for ARID1A and ≥1.5 for CSMD1", ">1.5 for ARID1A or <1.5 for CSMD1", "0.218", "0.685 (0.375–1.251)"], ["ARID1A and SENP3", "≤1.5 for ARID1A and >1.2 for SENP3", ">1.5 for ARID1A or ≤1.2 for SENP3", "0.038*", "0.554 (0.317–0.969)"], ["CSMD1 and SENP3", "≥1.5 for CSMD1 and >1.2 for SENP3", "<1.5 for CSMD1 or ≤1.2 for SENP3", "0.006*", "0.535 (0.342–0.837)"], ["ARID1A and CSMD1 and SENP3", "≤1.5 for ARID1A and ≥1.5 for CSMD1 or >1.2 for SENP3", ">1.5 for ARID1A or <1.5 for CSMD1 or ≤1.2 for SENP3", "0.046*", "0.528 (0.282–0.989)"]], "row_count": 8, "column_count": 5, "numeric_cells": 31, "header_rows": 0, "locator": "section[7]/table-wrap[3]#t6"}}, {"id": "asset:table:pmid:33558447:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e949e14a912ba3824a706bca7896524957a8fe9d0ae8ce170817c3b56a9a43f2", "bytes": 567, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#t7", "version": null, "note": "siRNA sequences for ARID1A, SENP3, and CSMD1.", "structure": {"pmcid": "PMC7906131", "section_index": 12, "section_title": "RNAi, cell culture, and transfection", "row_count": 10, "column_count": 2}, "table": {"label": "Table 7", "caption": "siRNA sequences for ARID1A, SENP3, and CSMD1.", "rows": [["Name", "Sequence"], ["st-h-ARID1A-1", "CACCTCTCCTAGCAAGTCT"], ["st-h-ARID1A-2", "GATCCTTATGGCAGCATGA"], ["st-h-ARID1A-3", "CAGGCAGCCAAACTATAAT"], ["st-h-SENP3-1", "GGAGGAGGATGAAGATGAA"], ["st-h-SENP3-2", "CCAGCATCCTCATCAGCAA"], ["st-h-SENP3-3", "GCAGGACATGCCCAAACTT"], ["st-h-CSMD1-1", "GGACAAGCATCGTTTGAAA"], ["st-h-CSMD1-2", "GGATGATGATTTCGAAATA"], ["st-h-CSMD1-3", "GAACCAAACTACAACATTA"]], "row_count": 10, "column_count": 2, "numeric_cells": 9, "header_rows": 0, "locator": "section[12]/table-wrap[1]#t7"}}], "gaps": ["asset:data:geo:GSE65372 not downloaded", "asset:data:geo:GSE65372 licence not read", "asset:data:geo:PRJNA607376 not downloaded", "asset:data:geo:PRJNA607376 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "Cox regression analysis was used to evaluate the prognostic value adjusted by patient sex, age, and AJCC stage (version VII)."}}, {"id": "method-2", "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-3", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC curve"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE65372", "PRJNA607376"], "resolved_accessions": ["GSE65372"], "statements": ["The data have been deposited with links to BioProject accession number PRJNA607376 in the NCBI BioProject database (https://www.ncbi.nlm.nih.gov/bioproject/)."], "basis": "The paper names GSE65372 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:33558447", "data:geo:GSE65372", "asset:table:pmid:33558447:1", "asset:table:pmid:33558447:2", "asset:table:pmid:33558447:3", "asset:table:pmid:33558447:4", "asset:table:pmid:33558447:5", "asset:table:pmid:33558447:6", "asset:table:pmid:33558447:7"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE65372"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:26:49Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 31540, "completion_tokens": 1486, "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:33558447", "type": "paper", "label": "pmid:33558447"}, {"id": "source:pmid:33558447", "type": "manuscript", "label": "PMID 33558447 full text"}, {"id": "data:geo:GSE65372", "type": "dataset", "label": "GEO GSE65372"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33558447", "type": "paper", "label": "pmid:33558447"}, {"id": "source:pmid:33558447", "type": "manuscript", "label": "PMID 33558447 full text"}, {"id": "data:geo:GSE65372", "type": "dataset", "label": "GEO GSE65372"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33558447", "type": "extraction", "used": ["source:pmid:33558447"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE65372", "type": "accession_resolution", "used": ["data:geo:GSE65372"], "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:33558447", "parent_hash": "sha256:c16d09872323ce343156d3b6f59dbca8f099e24a07e207946e8bc41077e238fa", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE65372 licence not read", "asset:data:geo:GSE65372 not downloaded", "asset:data:geo:PRJNA607376 licence not read", "asset:data:geo:PRJNA607376 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["collected to evaluate the candidate genes by immunohistochemical analysis. A receiver operating characteristi", "Co. Ltd, Shanghai, China) was performed for immunohistochemical (IHC) analysis. HCC samples were diagnosed b", "nd SENP3 in tumor and paracarcinoma tissues. Immunofluorescence staining, ×200. A paired-samples t-test was", "these patients are presented in Table 4. The IHC analysis of ARID1A, CSMD1, and SENP3 protein"], "order_basis": "paper_text_order:620", "id": "assay:1"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ed on ARID1A, CSMD1, and SENP3 during tissue microarray analysis of 180 HCC samples paired with tumo", "5, 26]. For the replication cohort, a tissue microarray of 180 HCC samples with HBV infection paired"], "order_basis": "paper_text_order:1608", "id": "assay:2"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["stological analysis. RNAi, cell culture, and transfection Hep3B cell line was purchased from ATCC (Ame", "target sequences are listed in Table 7. For transfection, the cells were seeded at a density of 1×105", "05 cells/well for 24 h. Then, the cells were transfected with siRNA fragments and negative control si", "24 h. Then, the cells were transfected with siRNA fragments and negative control siRNAs. siRNA"], "order_basis": "paper_text_order:6476", "id": "assay:3"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["Culture Collection, Rockville, MD, USA) and cultured in RPMI-1640 medium supplemented with 10% fetal"], "order_basis": "paper_text_order:6589", "id": "assay:4"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Cox regression analysis was used to evaluate the prognostic value adjusted by patient sex, age, and AJCC stage (version VII)."], "order_basis": "consumes_earlier_output", "id": "assay:5"}]},"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":"2026-11-04T03:03:31+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}}}