A zinc finger protein gene signature enables bladder cancer treatment stratification.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33962398", "kind": "science-record", "revision": 9, "content_hash": "sha256:2ce037aa28fb8c03bc38012ebd63ac718529c2f1e15a1cd220995124e8622f0a", "created_at": "2026-11-01T15:41:34Z", "updated_at": "2026-11-01T22:46:39Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A zinc finger protein gene signature enables bladder cancer treatment stratification.", "doi": "10.18632/aging.202984", "pmid": "33962398", "authors": ["Jiandong Zhang", "Chen Zhang", "Peng Cao", "Xiang Zheng", "Baozhong Yu", "Haoyuan Cao", "Zihao Gao", "Feilong Zhang", "Jiyuan Wu", "Huawei Cao", "Changzhen Hao", "Zejia Sun", "Wei Wang"], "journal": "Aging", "year": 2021, "abstract": "Bladder cancer (BC) is a commonly occurring malignant tumor affecting the urinary tract. Zinc finger proteins (ZNFs) constitute the largest transcription factor family in the human genome and are therefore attractive biomarker candidates for BC prognosis. In this study, we profiled the expression of ZNFs in The Cancer Genome Atlas (TCGA) BC cohort and developed a novel prognostic signature based on 7 ZNF-coding genes. After external validation of the model in the GSE48276 dataset, we integrated the 7-ZNF-gene signature with patient clinicopathological data to construct a nomogram that forecasted 1-, 2-, and 3-year OS with good predictive accuracy. We then accessed The Genomics of Drug Sensitivity in Cancer database to predict the therapeutic drug responses of signature-defined high- and low-risk BC patients in the TCGA cohort. Greater sensitivity to chemotherapy was revealed in the low-risk group. Finally, we conducted gene set enrichment analysis of the signature genes and established, by applying the ESTIMATE algorithm, distinct correlations between the two risk groups and the presence of stromal and immune cell types in the tumor microenvironment. By allowing effective risk stratification of BC patients, our novel ZNF gene signature may enable tailoring more intensive treatment for high-risk patients.", "claims": [{"id": "claim-method", "statement": "Differentially expressed genes (DEGs) between tumor and matched normal tissues were identified in the TCGA cohort by the “limma” R package using a false discovery rate (FDR) < 0.05.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33962398", "locator": "sections[14] \"Construction and validation of a prognostic model\" paragraph 2", "quote": "Differentially expressed genes (DEGs) between tumor and matched normal tissues were identified in the TCGA cohort by the “limma” R package using a false discovery rate (FDR) < 0.05."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The transcriptional data and corresponding clinical information of 403 chemotherapy-naïve BC patients and 19 normal bladder control samples were downloaded from the TCGA website (https://www.cancer.gov/tcga.) [38].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33962398", "locator": "sections[13] \"Sample information and data collection\" paragraph 2", "quote": "The transcriptional data and corresponding clinical information of 403 chemotherapy-naïve BC patients and 19 normal bladder control samples were downloaded from the TCGA website (https://www.cancer.gov/tcga.) [38]."}], "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:33962398"], "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:GSE48276"], "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": {"fdr_threshold": "limma” R package with a false discovery rate (FDR) < 0"}, "inputs": ["data:geo:GSE48276"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33962398", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.18632/aging.202984", "sha256": "sha256:5e551f80d50f0d7219a40c274d8474ec7d71a0119f957a22b6e60c222c5b1989", "bytes": 40749, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.18632/aging.202984", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8148496", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE48276", "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=GSE48276", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE48276", "version": null, "note": "The transcriptional data and corresponding clinical information of 403 chemotherapy-naïve BC patients and 19 normal bladder control samples were downloaded from the TCGA website (https://www.cancer.gov/tcga.) [38].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The transcriptional data and corresponding clinical information of 403 chemotherapy-naïve BC patients and 19 normal bladder control samples were downloaded from the TCGA website (https://www.cancer.gov/tcga.) [38].", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1173901", "GSM1173902", "GSM1173903", "GSM1173904", "GSM1173905", "GSM1173906", "GSM1173907", "GSM1173908", "GSM1173909", "GSM1173910", "GSM1173911", "GSM1173912", "GSM1173913", "GSM1173914", "GSM1173915", "GSM1173916", "GSM1173917", "GSM1173918", "GSM1173919", "GSM1173920", "GSM1173921", "GSM1173922", "GSM1173923", "GSM1173924", "GSM1173925", "GSM1173926", "GSM1173927", "GSM1173928", "GSM1173929", "GSM1173930", "GSM1173931", "GSM1173932", "GSM1173933", "GSM1173934", "GSM1173935", "GSM1173936", "GSM1173937", "GSM1173938", "GSM1173939", "GSM1173940", "GSM1173941", "GSM1173942", "GSM1173943", "GSM1173944", "GSM1173945", "GSM1173946", "GSM1173947", "GSM1173948", "GSM1173949", "GSM1173950", "GSM1173951", "GSM1173952", "GSM1173953", "GSM1173954", "GSM1173955", "GSM1173956", "GSM1173957", "GSM1173968", "GSM1173969", "GSM1173970", "GSM1173971", "GSM1173972", "GSM1173973", "GSM1173974", "GSM1173975", "GSM1173976", "GSM1173977", "GSM1173978", "GSM1173979", "GSM1173980", "GSM1173981", "GSM1173982", "GSM1173983", "GSM1173986", "GSM1173987", "GSM1173988", "GSM1173989", "GSM1173990", "GSM1173991", "GSM1173992", "GSM1173993", "GSM1173994", "GSM1173995", "GSM1173996", "GSM1173997", "GSM1173998", "GSM1173999", "GSM1174000", "GSM1174001", "GSM1174002", "GSM1174003", "GSM1174004", "GSM1174005", "GSM1174006", "GSM1174007", "GSM1174008", "GSM1174009", "GSM1174010", "GSM1174011", "GSM1174012", "GSM1174013", "GSM1174014", "GSM1174015", "GSM1174016", "GSM1174017", "GSM1174018", "GSM1174019", "GSM1174020", "GSM1174021", "GSM1174022", "GSM1174023", "GSM1174024", "GSM1174025", "GSM1174026", "GSM1174027", "GSM1174028"], "sample_count": 116, "group_sizes": null, "group_sizes_basis": null, "platform": "14951", "taxon": "Homo sapiens", "title": "Gene expression profiling of urothelial 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": "asset:table:pmid:33962398:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2766e46f6f03b41f648d6d392dee9bd065f2aef0abc9c067b6f9faba54966f62", "bytes": 694, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#t1", "version": null, "note": "The coefficient of selected genes.", "structure": {"pmcid": "PMC8148496", "section_index": 4, "section_title": "Development of a ZNF gene-based prognostic signature for BC", "row_count": 8, "column_count": 6}, "table": {"label": "Table 1", "caption": "The coefficient of selected genes.", "rows": [["Gene", "coefficient", "HR", "HR.95Low", "HR.95High", "P value"], ["ZHX3", "0.148896", "1.160553", "0.989119", "1.361699", "0.067879"], ["ZNF350", "-0.0615", "0.940356", "0.877571", "1.007633", "0.08111"], ["ZNRD1", "-0.06775", "0.934497", "0.877895", "0.994749", "0.033577"], ["ZNF195", "-0.11088", "0.895049", "0.823812", "0.972446", "0.008786"], ["SUZ12", "0.064369", "1.066486", "1.035628", "1.098264", "1.73E-05"], ["APEX2", "-0.03312", "0.967418", "0.943455", "0.99199", "0.009642"], ["EBF4", "-0.04355", "0.957387", "0.912023", "1.005007", "0.078698"]], "row_count": 8, "column_count": 6, "numeric_cells": 40, "header_rows": 0, "locator": "section[4]/table-wrap[1]#t1"}}], "gaps": ["asset:data:geo:GSE48276 not downloaded", "asset:data:geo:GSE48276 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {"fdr_threshold": "limma” R package with a false discovery rate (FDR) < 0"}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Differentially expressed genes (DEGs) between tumor and matched normal tissues were identified in the TCGA cohort by the “limma” R package using a false discovery rate (FDR) < 0.05."}}, {"id": "method-2", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Wilcoxon"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE48276"], "resolved_accessions": ["GSE48276"], "statements": ["The transcriptional data and corresponding clinical information of 403 chemotherapy-naïve BC patients and 19 normal bladder control samples were downloaded from the TCGA website (https://www.cancer.gov/tcga.) [38]."], "basis": "The paper names GSE48276 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:33962398", "data:geo:GSE48276", "asset:table:pmid:33962398:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE48276"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:29:59Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 32242, "completion_tokens": 1894, "cached_tokens": 776}}, "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:33962398", "type": "paper", "label": "pmid:33962398"}, {"id": "source:pmid:33962398", "type": "manuscript", "label": "PMID 33962398 full text"}, {"id": "data:geo:GSE48276", "type": "dataset", "label": "GEO GSE48276"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33962398", "type": "paper", "label": "pmid:33962398"}, {"id": "source:pmid:33962398", "type": "manuscript", "label": "PMID 33962398 full text"}, {"id": "data:geo:GSE48276", "type": "dataset", "label": "GEO GSE48276"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33962398", "type": "extraction", "used": ["source:pmid:33962398"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE48276", "type": "accession_resolution", "used": ["data:geo:GSE48276"], "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:33962398", "parent_hash": "sha256:5469726a1e8c6a7c15e5d52f68f71388010af23090950e5f05b0f827e5dd488d", "fork_of": null, "generation": 8}, "gaps": ["asset:data:geo:GSE48276 licence not read", "asset:data:geo:GSE48276 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Differentially expressed genes (DEGs) between tumor and matched normal tissues were identified in the TCGA cohort by the “limma” R package using a false discovery rate (FDR) < 0.05."], "order_basis": "analysis_only", "id": "assay:1"}]}