A PDCD4-Based Gene Expression Signature Predicts Overall Survival in Renal Cell Carcinoma: A TCGA-Based Discovery and External Validation Study.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41614853", "kind": "science-record", "revision": 2, "content_hash": "sha256:721bfff5e1b1ed0bea59e1b0c2286caf3ff3a8daefab45e3058a24772f739634", "created_at": "2026-11-01T20:31:43Z", "updated_at": "2026-11-01T21:36:33Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A PDCD4-Based Gene Expression Signature Predicts Overall Survival in Renal Cell Carcinoma: A TCGA-Based Discovery and External Validation Study.", "doi": "10.3390/cimb48010022", "pmid": "41614853", "authors": ["Bandar A Suliman"], "journal": "Current issues in molecular biology", "year": 2025, "abstract": "Renal cell carcinoma (RCC) is a heterogeneous disease with variable clinical outcomes. PDCD4 functions as a tumor suppressor, but its role in RCC prognosis remains unclear. We aimed to develop and validate a PDCD4-based gene expression signature for predicting overall survival in RCC. We analyzed RNA-seq data from 541 clear cell RCC patients in The Cancer Genome Atlas (TCGA-KIRC). We identified 100 genes (50 positively and 50 negatively correlated with PDCD4) to create a prognostic signature. Patients were stratified into high- and low-signature groups using median cutoff. Kaplan-Meier analysis and Cox regression models assessed prognostic value. External validation was performed in four independent cohorts: GSE29609, GSE73731, GSE53757, and GSE40435. Low PDCD4 signature scores were associated with significantly worse overall survival (HR = 2.17, 95% CI: 1.58-2.98, p < 0.001) and advanced tumor stage. The median survival difference was approximately 46 months. In multivariate analysis adjusting for age, gender, stage, and grade, the signature remained an independent prognostic factor (HR = 1.57, 95% CI: 1.11-2.22, p = 0.011). The signature demonstrated consistent prognostic patterns across platforms, with high signature scores associated with early-stage disease and low-grade tumors, and with potential clinical utility for risk stratification and treatment planning.", "claims": [{"id": "claim-method", "statement": "Kaplan–Meier analysis and Cox regression models assessed prognostic value.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41614853", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Kaplan–Meier analysis and Cox regression models assessed prognostic value."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data used in this study are publicly available. TCGA-KIRC data can be accessed through the Genomic Data Commons Portal (https://portal.gdc.cancer.gov/, accessed on 11 November 2025, Project ID: TCGA-KIRC). The GSE datasets are available from the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?, accessed on 11 November 2025). All analysis code and processed data files are available from the corresponding author upon reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41614853", "locator": "sections[33] \"Data Availability Statement\" paragraph 2", "quote": "All data used in this study are publicly available. TCGA-KIRC data can be accessed through the Genomic Data Commons Portal (https://portal.gdc.cancer.gov/, accessed on 11 November 2025, Project ID: TCGA-KIRC). The GSE datasets are available from the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?, accessed on 11 November 2025). All analysis code and processed data files are available from the corresponding author upon reasonable request."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Low PDCD4 signature scores were associated with significantly worse overall survival (HR = 2.17, 95% CI: 1.58–2.98, p < 0.001) and advanced tumor stage.", "kind": "quantitative", "target": {"value": 95.0, "unit": "per cent", "tolerance": null, "source": "Low PDCD4 signature scores were associated with significantly worse overall survival (HR = 2.17, 95% CI: 1.58–2.98, p < 0.001) and advanced tumor stage."}, "evidence": [{"asset": "source:pmid:41614853", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Low PDCD4 signature scores were associated with significantly worse overall survival (HR = 2.17, 95% CI: 1.58–2.98, p < 0.001) and advanced tumor stage."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Low PDCD4 signature scores were associated with significantly worse overall survival (HR = 2.17, 95% CI: 1.58–2.98, p < 0.001) and advanced tumor stage.", "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:41614853"], "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:GSE29609"], "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:GSE29609"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41614853", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/cimb48010022", "sha256": "sha256:77ec0ee6344c4f3a8a6067b1eecf26f0c413eb65c233c53bff158d716e65b309", "bytes": 54176, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/cimb48010022", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12840172", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE29609", "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=GSE29609", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE29609", "version": null, "note": "All data used in this study are publicly available. TCGA-KIRC data can be accessed through the Genomic Data Commons Portal (https://portal.gdc.cancer.gov/, accessed on 11 November 2025, Project ID: TCGA-KIRC). The GSE datasets are available from the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?, accessed on 11 November 2025). All analysis code and processed data files are available from the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data used in this study are publicly available. TCGA-KIRC data can be accessed through the Genomic Data Commons Portal (https://portal.gdc.cancer.gov/, accessed on 11 November 2025, Project ID: TCGA-KIRC). The GSE datasets are available from the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?, accessed on 11 November 2025). All analysis code and processed data files are available from the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM733579", "GSM733580", "GSM733581", "GSM733582", "GSM733583", "GSM733584", "GSM733585", "GSM733586", "GSM733587", "GSM733588", "GSM733589", "GSM733590", "GSM733591", "GSM733592", "GSM733593", "GSM733594", "GSM733595", "GSM733596", "GSM733597", "GSM733598", "GSM733599", "GSM733600", "GSM733601", "GSM733602", "GSM733603", "GSM733604", "GSM733605", "GSM733606", "GSM733607", "GSM733608", "GSM733609", "GSM733610", "GSM733611", "GSM733612", "GSM733613", "GSM733614", "GSM733615", "GSM733616", "GSM733617"], "sample_count": 39, "group_sizes": null, "group_sizes_basis": null, "platform": "1708", "taxon": "Homo sapiens", "title": "Clear-cell renal cell carcinomas tumors", "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:GSE40435", "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=GSE40435", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE40435", "version": null, "note": "All data used in this study are publicly available. TCGA-KIRC data can be accessed through the Genomic Data Commons Portal (https://portal.gdc.cancer.gov/, accessed on 11 November 2025, Project ID: TCGA-KIRC). The GSE datasets are available from the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?, accessed on 11 November 2025). All analysis code and processed data files are available from the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data used in this study are publicly available. TCGA-KIRC data can be accessed through the Genomic Data Commons Portal (https://portal.gdc.cancer.gov/, accessed on 11 November 2025, Project ID: TCGA-KIRC). The GSE datasets are available from the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?, accessed on 11 November 2025). All analysis code and processed data files are available from the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM993983", "GSM993984", "GSM993985", "GSM993986", "GSM993987", "GSM993988", "GSM993989", "GSM993990", "GSM993991", "GSM993992", "GSM993993", "GSM993994", "GSM993995", "GSM993996", "GSM993997", "GSM993998", "GSM993999", "GSM994000", "GSM994001", "GSM994002", "GSM994003", "GSM994004", "GSM994005", "GSM994006", "GSM994007", "GSM994008", "GSM994009", "GSM994010", "GSM994011", "GSM994012", "GSM994013", "GSM994014", "GSM994015", "GSM994016", "GSM994017", "GSM994018", "GSM994019", "GSM994020", "GSM994021", "GSM994022", "GSM994023", "GSM994024", "GSM994025", "GSM994026", "GSM994027", "GSM994028", "GSM994029", "GSM994030", "GSM994031", "GSM994032", "GSM994033", "GSM994034", "GSM994035", "GSM994036", "GSM994037", "GSM994038", "GSM994039", "GSM994040", "GSM994041", "GSM994042", "GSM994043", "GSM994044", "GSM994045", "GSM994046", "GSM994047", "GSM994048", "GSM994049", "GSM994050", "GSM994051", "GSM994052", "GSM994053", "GSM994054", "GSM994055", "GSM994056", "GSM994057", "GSM994058", "GSM994059", "GSM994060", "GSM994061", "GSM994062", "GSM994063", "GSM994064", "GSM994065", "GSM994066", "GSM994067", "GSM994068", "GSM994069", "GSM994070", "GSM994071", "GSM994072", "GSM994073", "GSM994074", "GSM994075", "GSM994076", "GSM994077", "GSM994078", "GSM994079", "GSM994080", "GSM994081", "GSM994082", "GSM994083", "GSM994084", "GSM994085", "GSM994086", "GSM994087", "GSM994088", "GSM994089", "GSM994090", "GSM994091", "GSM994092", "GSM994093", "GSM994094", "GSM994095", "GSM994096", "GSM994097", "GSM994098", "GSM994099", "GSM994100", "GSM994101", "GSM994102", "GSM994103", "GSM994104", "GSM994105", "GSM994106", "GSM994107", "GSM994108", "GSM994109", "GSM994110", "GSM994111", "GSM994112", "GSM994113", "GSM994114", "GSM994115", "GSM994116", "GSM994117", "GSM994118", "GSM994119", "GSM994120", "GSM994121", "GSM994122", "GSM994123", "GSM994124", "GSM994125", "GSM994126", "GSM994127", "GSM994128", "GSM994129", "GSM994130", "GSM994131", "GSM994132", "GSM994133", "GSM994134", "GSM994135", "GSM994136", "GSM994137", "GSM994138", "GSM994139", "GSM994140", "GSM994141", "GSM994142", "GSM994143", "GSM994144", "GSM994145", "GSM994146", "GSM994147", "GSM994148", "GSM994149", "GSM994150", "GSM994151", "GSM994152", "GSM994153", "GSM994154", "GSM994155", "GSM994156", "GSM994157", "GSM994158", "GSM994159", "GSM994160", "GSM994161", "GSM994162", "GSM994163", "GSM994164", "GSM994165", "GSM994166", "GSM994167", "GSM994168", "GSM994169", "GSM994170", "GSM994171", "GSM994172", "GSM994173", "GSM994174", "GSM994175", "GSM994176", "GSM994177", "GSM994178", "GSM994179", "GSM994180", "GSM994181", "GSM994182", "GSM994183", "GSM994184"], "sample_count": 202, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Integrative genome-wide gene expression profiling of clear cell renal cell carcinoma in Czech Republic", "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:GSE53757", "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=GSE53757", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53757", "version": null, "note": "All data used in this study are publicly available. TCGA-KIRC data can be accessed through the Genomic Data Commons Portal (https://portal.gdc.cancer.gov/, accessed on 11 November 2025, Project ID: TCGA-KIRC). The GSE datasets are available from the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?, accessed on 11 November 2025). All analysis code and processed data files are available from the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data used in this study are publicly available. TCGA-KIRC data can be accessed through the Genomic Data Commons Portal (https://portal.gdc.cancer.gov/, accessed on 11 November 2025, Project ID: TCGA-KIRC). The GSE datasets are available from the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?, accessed on 11 November 2025). All analysis code and processed data files are available from the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1300062", "GSM1300063", "GSM1300064", "GSM1300065", "GSM1300066", "GSM1300067", "GSM1300068", "GSM1300069", "GSM1300070", "GSM1300071", "GSM1300072", "GSM1300073", "GSM1300074", "GSM1300075", "GSM1300076", "GSM1300077", "GSM1300078", "GSM1300079", "GSM1300080", "GSM1300081", "GSM1300082", "GSM1300083", "GSM1300084", "GSM1300085", "GSM1300086", "GSM1300087", "GSM1300088", "GSM1300089", "GSM1300090", "GSM1300091", "GSM1300092", "GSM1300093", "GSM1300094", "GSM1300095", "GSM1300096", "GSM1300097", "GSM1300098", "GSM1300099", "GSM1300100", "GSM1300101", "GSM1300102", "GSM1300103", "GSM1300104", "GSM1300105", "GSM1300106", "GSM1300107", "GSM1300108", "GSM1300109", "GSM1300110", "GSM1300111", "GSM1300112", "GSM1300113", "GSM1300114", "GSM1300115", "GSM1300116", "GSM1300117", "GSM1300118", "GSM1300119", "GSM1300120", "GSM1300121", "GSM1300122", "GSM1300123", "GSM1300124", "GSM1300125", "GSM1300126", "GSM1300127", "GSM1300128", "GSM1300129", "GSM1300130", "GSM1300131", "GSM1300132", "GSM1300133", "GSM1300134", "GSM1300135", "GSM1300136", "GSM1300137", "GSM1300138", "GSM1300139", "GSM1300140", "GSM1300141", "GSM1300142", "GSM1300143", "GSM1300144", "GSM1300145", "GSM1300146", "GSM1300147", "GSM1300148", "GSM1300149", "GSM1300150", "GSM1300151", "GSM1300152", "GSM1300153", "GSM1300154", "GSM1300155", "GSM1300156", "GSM1300157", "GSM1300158", "GSM1300159", "GSM1300160", "GSM1300161", "GSM1300162", "GSM1300163", "GSM1300164", "GSM1300165", "GSM1300166", "GSM1300167", "GSM1300168", "GSM1300169", "GSM1300170", "GSM1300171", "GSM1300172", "GSM1300173", "GSM1300174", "GSM1300175", "GSM1300176", "GSM1300177", "GSM1300178", "GSM1300179", "GSM1300180", "GSM1300181", "GSM1300182", "GSM1300183", "GSM1300184", "GSM1300185", "GSM1300186", "GSM1300187", "GSM1300188", "GSM1300189", "GSM1300190", "GSM1300191", "GSM1300192", "GSM1300193", "GSM1300194", "GSM1300195", "GSM1300196", "GSM1300197", "GSM1300198", "GSM1300199", "GSM1300200", "GSM1300201", "GSM1300202", "GSM1300203", "GSM1300204", "GSM1300205"], "sample_count": 144, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene array analysis of clear cell renal cell carcinoma tissue versus matched normal kidney tissue", "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:GSE73731", "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=GSE73731", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE73731", "version": null, "note": "All data used in this study are publicly available. TCGA-KIRC data can be accessed through the Genomic Data Commons Portal (https://portal.gdc.cancer.gov/, accessed on 11 November 2025, Project ID: TCGA-KIRC). The GSE datasets are available from the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?, accessed on 11 November 2025). All analysis code and processed data files are available from the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data used in this study are publicly available. TCGA-KIRC data can be accessed through the Genomic Data Commons Portal (https://portal.gdc.cancer.gov/, accessed on 11 November 2025, Project ID: TCGA-KIRC). The GSE datasets are available from the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?, accessed on 11 November 2025). All analysis code and processed data files are available from the corresponding author upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1930996", "GSM1930997", "GSM1930998", "GSM1930999", "GSM1931000", "GSM1931001", "GSM1931002", "GSM1931003", "GSM1931004", "GSM1931005", "GSM1931006", "GSM1931007", "GSM1931008", "GSM1931009", "GSM1931010", "GSM1931011", "GSM1931012", "GSM1931013", "GSM1931014", "GSM1931015", "GSM1931016", "GSM1931017", "GSM1931018", "GSM1931019", "GSM1931020", "GSM1931021", "GSM1931022", "GSM1931023", "GSM1931024", "GSM1931025", "GSM1931026", "GSM1931027", "GSM1931028", "GSM1931029", "GSM1931030", "GSM1931031", "GSM1931032", "GSM1931033", "GSM1931034", "GSM1931035", "GSM1931036", "GSM1931037", "GSM1931038", "GSM1931039", "GSM1931040", "GSM1931041", "GSM1931042", "GSM1931043", "GSM1931044", "GSM1931045", "GSM1931046", "GSM1931047", "GSM1931048", "GSM1931049", "GSM1931050", "GSM1931051", "GSM1931052", "GSM1931053", "GSM1931054", "GSM1931055", "GSM1931056", "GSM1931057", "GSM1931058", "GSM1931059", "GSM1931060", "GSM1931061", "GSM1931062", "GSM1931063", "GSM1931064", "GSM1931065", "GSM1931066", "GSM1931067", "GSM1931068", "GSM1931069", "GSM1931070", "GSM1931071", "GSM1931072", "GSM1931073", "GSM1931074", "GSM1931075", "GSM1931076", "GSM1931077", "GSM1931078", "GSM1931079", "GSM1931080", "GSM1931081", "GSM1931082", "GSM1931083", "GSM1931084", "GSM1931085", "GSM1931086", "GSM1931087", "GSM1931088", "GSM1931089", "GSM1931090", "GSM1931091", "GSM1931092", "GSM1931093", "GSM1931094", "GSM1931095", "GSM1931096", "GSM1931097", "GSM1931098", "GSM1931099", "GSM1931100", "GSM1931101", "GSM1931102", "GSM1931103", "GSM1931104", "GSM1931105", "GSM1931106", "GSM1931107", "GSM1931108", "GSM1931109", "GSM1931110", "GSM1931111", "GSM1931112", "GSM1931113", "GSM1931114", "GSM1931115", "GSM1931116", "GSM1931117", "GSM1931118", "GSM1931119", "GSM1931120", "GSM1931121", "GSM1931122", "GSM1931123", "GSM1931124", "GSM1931125", "GSM1931126", "GSM1931127", "GSM1931128", "GSM1931129", "GSM1931130", "GSM1931131", "GSM1931132", "GSM1931133", "GSM1931134", "GSM1931135", "GSM1931136", "GSM1931137", "GSM1931138", "GSM1931139", "GSM1931140", "GSM1931141", "GSM1931142", "GSM1931143", "GSM1931144", "GSM1931145", "GSM1931146", "GSM1931147", "GSM1931148", "GSM1931149", "GSM1931150", "GSM1931151", "GSM1931152", "GSM1931153", "GSM1931154", "GSM1931155", "GSM1931156", "GSM1931157", "GSM1931158", "GSM1931159", "GSM1931160", "GSM1931161", "GSM1931162", "GSM1931163", "GSM1931164", "GSM1931165", "GSM1931166", "GSM1931167", "GSM1931168", "GSM1931169", "GSM1931170", "GSM1931171", "GSM1931172", "GSM1931173", "GSM1931174", "GSM1931175", "GSM1931176", "GSM1931177", "GSM1931178", "GSM1931179", "GSM1931180", "GSM1931181", "GSM1931182", "GSM1931183", "GSM1931184", "GSM1931185", "GSM1931186", "GSM1931187", "GSM1931188", "GSM1931189", "GSM1931190", "GSM1931191", "GSM1931192", "GSM1931193", "GSM1931194", "GSM1931195", "GSM1931196", "GSM1931197", "GSM1931198", "GSM1931199", "GSM1931200", "GSM1931201", "GSM1931202", "GSM1931203", "GSM1931204", "GSM1931205", "GSM1931206", "GSM1931207", "GSM1931208", "GSM1931209", "GSM1931210", "GSM1931211", "GSM1931212", "GSM1931213", "GSM1931214", "GSM1931215", "GSM1931216", "GSM1931217", "GSM1931218", "GSM1931219", "GSM1931220", "GSM1931221", "GSM1931222", "GSM1931223", "GSM1931224", "GSM1931225", "GSM1931226", "GSM1931227", "GSM1931228", "GSM1931229", "GSM1931230", "GSM1931231", "GSM1931232", "GSM1931233", "GSM1931234", "GSM1931235", "GSM1931236", "GSM1931237", "GSM1931238", "GSM1931239", "GSM1931240", "GSM1931241", "GSM1931242", "GSM1931243", "GSM1931244", "GSM1931245", "GSM1931246", "GSM1931247", "GSM1931248", "GSM1931249", "GSM1931250", "GSM1931251", "GSM1931252", "GSM1931253", "GSM1931254", "GSM1931255", "GSM1931256", "GSM1931257", "GSM1931258", "GSM1931259", "GSM1931260"], "sample_count": 265, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Clear cell renal cell carcinoma (ccRCC) samples", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE29609 not downloaded", "asset:data:geo:GSE29609 licence not read", "asset:data:geo:GSE40435 not downloaded", "asset:data:geo:GSE40435 licence not read", "asset:data:geo:GSE53757 not downloaded", "asset:data:geo:GSE53757 licence not read", "asset:data:geo:GSE73731 not downloaded", "asset:data:geo:GSE73731 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": "Kaplan–Meier analysis and Cox regression models assessed prognostic value."}}, {"id": "method-2", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "cox_ph", "expected_value": 95.0, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}, {"id": "target-published-estimate-hazard-ratio", "claim_id": "claim-target-result", "operation": "cox_ph", "expected_value": 2.17, "unit": "hazard ratio", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}, {"id": "target-published-estimate-p-value", "claim_id": "claim-target-result", "operation": "cox_ph", "expected_value": 0.001, "unit": "p-value", "tolerance": null, "state": "complete", "note": "The threshold the paper applied to its own result, as the paper states it. A run that reproduces the effect is judged against this threshold."}], "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": ["GSE29609", "GSE73731", "GSE53757", "GSE40435"], "resolved_accessions": ["GSE29609", "GSE73731", "GSE53757", "GSE40435"], "statements": ["All data used in this study are publicly available. TCGA-KIRC data can be accessed through the Genomic Data Commons Portal (https://portal.gdc.cancer.gov/, accessed on 11 November 2025, Project ID: TCGA-KIRC). The GSE datasets are available from the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?, accessed on 11 November 2025). All analysis code and processed data files are available from the corresponding author upon reasonable request."], "basis": "The paper names GSE29609, GSE73731, GSE53757, GSE40435 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:41614853", "data:geo:GSE29609"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE29609"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:11:58Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 16412, "completion_tokens": 2204, "cached_tokens": 264}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:41614853", "type": "paper", "label": "pmid:41614853"}, {"id": "source:pmid:41614853", "type": "manuscript", "label": "PMID 41614853 full text"}, {"id": "data:geo:GSE29609", "type": "dataset", "label": "GEO GSE29609"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41614853", "type": "paper", "label": "pmid:41614853"}, {"id": "source:pmid:41614853", "type": "manuscript", "label": "PMID 41614853 full text"}, {"id": "data:geo:GSE29609", "type": "dataset", "label": "GEO GSE29609"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41614853", "type": "extraction", "used": ["source:pmid:41614853"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE29609", "type": "accession_resolution", "used": ["data:geo:GSE29609"], "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:41614853", "parent_hash": "sha256:f403441e14f0d5072e1c5a5d50f18427eea2d3ba7403b7ffdb5e365d1c7f33b7", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:GSE29609 licence not read", "asset:data:geo:GSE29609 not downloaded", "asset:data:geo:GSE40435 licence not read", "asset:data:geo:GSE40435 not downloaded", "asset:data:geo:GSE53757 licence not read", "asset:data:geo:GSE53757 not downloaded", "asset:data:geo:GSE73731 licence not read", "asset:data:geo:GSE73731 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["dicting overall survival in RCC. We analyzed RNA-seq data from 541 clear cell RCC patients in The"], "order_basis": "paper_text_order:398", "id": "assay:1"}, {"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": ["Kaplan–Meier analysis and Cox regression models assessed prognostic value."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}