A 44-gene set constructed for predicting the prognosis of clear cell renal cell carcinoma.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30272265", "kind": "science-record", "revision": 7, "content_hash": "sha256:0b60c488850a5deee0a8b7b01e1ae371914e202a19a74b907da79367bbd1f38f", "created_at": "2026-11-01T15:40:37Z", "updated_at": "2026-11-01T22:00:04Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A 44-gene set constructed for predicting the prognosis of clear cell renal cell carcinoma.", "doi": "10.3892/ijmm.2018.3899", "pmid": "30272265", "authors": ["Yonggang Wang", "Yao Wang", "Feng Liu"], "journal": "International journal of molecular medicine", "year": 2018, "abstract": "Clear cell renal cell carcinoma (ccRCC) is the most frequent type of renal cell carcinoma (RCC). The present study aimed to examine prognostic markers and construct a prognostic prediction system for ccRCC. The mRNA sequencing data of ccRCC was downloaded from The Cancer Genome Atlas (TCGA) database, and the GSE40435 dataset was obtained from the Gene Expression Omnibus database. Using the Limma package, the differentially expressed genes (DEGs) in the TCGA dataset and GSE40435 dataset were obtained, respectively, and the overlapped DEGs were selected. Subsequently, Cox regression analysis was applied for screening prognosis‑associated genes. Following visualization of the co‑expression network using Cytoscape software, the network modules were examined using the GraphWeb tool. Functional annotation for genes in the network was performed using the clusterProfiler package. Finally, a prognostic prediction system was constructed through Bayes discriminant analysis and confirmed with the GSE29609 validation dataset. The results revealed a total of 263 overlapped DEGs and 161 prognosis‑associated genes. Following construction of the co‑expression network, 16 functional terms and three pathways were obtained for genes in the network. In addition, red, yellow (involving chemokine ligand 10 (CXCL10), CD27 molecule (CD27) and runt‑related transcription factor 3 (RUNX3)], green (involving angiopoietin‑like 4 (ANGPTL4), stanniocalcin 2 (STC2), and sperm associated antigen 4 (SPAG4)], and cyan modules were extracted from the co‑expression network. Additionally, the prognostic prediction system involving 44 signature genes, including ANGPTL4, STC2, CXCL10, SPAG4, CD27, matrix metalloproteinase (MMP9) and RUNX3, was identified and confirmed. In conclusion, the 44‑gene prognostic prediction system involving ANGPTL4, STC2, CXCL10, SPAG4, CD27, MMP9 and RUNX3 may be utilized for predicting the prognosis of patients with ccRCC.", "claims": [{"id": "claim-data-access", "statement": "The datasets used during the current study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30272265", "locator": "sections[16] \"Availability of data and materials\" paragraph 2", "quote": "The datasets used during the current study are available from the corresponding author on 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:30272265"], "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:30272265", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3892/ijmm.2018.3899", "sha256": "sha256:e50b911f7b23ac587920bc861d6423d7e995754f00ca69c37802ba6431cdc8e1", "bytes": 38881, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3892/ijmm.2018.3899", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6202093", "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": "The datasets used during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used during the current study are available from the corresponding author on 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": "The datasets used during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used during the current study are available from the corresponding author on 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": "asset:table:pmid:30272265:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:76f427fab8e353af91de00ee4e110d59b18dce37521c24eddd6cf9a6ed73c312", "bytes": 2591, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#tI-ijmm-42-06-3105", "version": null, "note": "Information of the 44 signature genes in The Cancer Genome Atlas dataset.", "structure": {"pmcid": "PMC6202093", "section_index": 13, "section_title": "Construction and validation of prognostic prediction system", "row_count": 45, "column_count": 4}, "table": {"label": "Table I", "caption": "Information of the 44 signature genes in The Cancer Genome Atlas dataset.", "rows": [["Gene", "logFC", "P-value", "FDR"], ["C10orf99", "−2.344", "6.88×10−64", "3.23×10−61"], ["ADAMDEC1", "−1.896", "1.81×10−55", "6.03×10−53"], ["HS3ST2", "−1.641", "2.44×10−48", "5.72×10−46"], ["IL20RB", "−1.514", "3.55×10−47", "7.49×10−45"], ["SLC17A2", "−1.182", "7.10×10−28", "5.23×10−26"], ["LAG3", "−0.863", "6.59×10−22", "3.17×10−20"], ["SPAG4", "−0.856", "1.76×10−29", "1.43×10−27"], ["CD27", "−0.820", "2.44×10−22", "1.24×10−20"], ["SH2D1A", "−0.804", "1.55×10−18", "5.34×10−17"], ["STC2", "−0.802", "7.73×10−32", "7.47×10−30"], ["MMP9", "−0.797", "5.24×10−22", "2.54×10−20"], ["ANGPTL4", "−0.786", "5.94×10−37", "7.60×10−35"], ["OSCAR", "−0.753", "2.63×10−17", "7.89×10−16"], ["HHLA2", "−0.742", "1.70×10−24", "9.79×10−23"], ["RASD2", "−0.734", "6.34×10−20", "2.43×10−18"], ["NKG7", "−0.728", "2.15×10−21", "9.80×10−20"], ["INHBB", "−0.723", "1.73×10−24", "9.92×10−23"], ["CD96", "−0.718", "1.58×10−18", "5.42×10−17"], ["NOD2", "−0.687", "2.47×10−14", "5.39×10−13"], ["P2RX7", "−0.674", "1.82×10−16", "5.02×10−15"], ["PGF", "−0.655", "7.44×10−22", "3.54×10−20"], ["RASAL3", "−0.627", "5.19×10−16", "1.36×10−14"], ["ST8SIA4", "−0.627", "2.64×10−19", "9.66×10−18"], ["CDCA7", "−0.624", "1.16×10−11", "1.96×10−10"], ["CHSY3", "−0.624", "3.61×10−13", "7.12×10−12"], ["CXCL10", "−0.622", "4.34×10−17", "1.27×10−15"], ["CD6", "−0.622", "1.38×10−14", "3.09×10−13"], ["RUNX3", "−0.615", "1.35×10−16", "3.79×10−15"], ["SLC1A3", "−0.609", "6.02×10−16", "1.56×10−14"], ["CXCL9", "−0.609", "2.13×10−18", "7.18×10−17"], ["TRIM9", "−0.605", "5.80×10−15", "1.36×10−13"], ["SEMA5B", "−0.599", "3.69×10−20", "1.47×10−18"], ["PDGFRA", "0.605", "9.58×10−21", "4.11×10−19"], ["ADH1B", "0.667", "8.24×10−26", "5.35×10−24"], ["G6PC", "0.693", "3.07×10−21", "1.37×10−19"], ["KRT7", "0.718", "3.93×10−29", "3.09×10−27"], ["TMEM30B", "0.754", "1.11×10−29", "9.13×10−28"], ["FAM167A", "0.911", "8.99×10−37", "1.13×10−34"], ["TFAP2A", "0.948", "4.13×10−36", "5.13×10−34"], ["SLC13A3", "1.009", "9.21×10−49", "2.29×10−46"], ["TMEM45B", "1.036", "1.43×10−47", "3.12×10−45"], ["C1orf116", "1.062", "5.48×10−47", "1.14×10−44"], ["SCNN1B", "1.404", "2.16×10−85", "2.74×10−82"], ["ATP6V1B1", "1.456", "1.36×10−92", "1.91×10−89"]], "row_count": 45, "column_count": 4, "numeric_cells": 143, "header_rows": 1, "locator": "section[13]/table-wrap[1]#tI-ijmm-42-06-3105"}}], "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"]}, "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": 0.7, "band": "medium", "quote": "Cox regression"}}, {"id": "method-2", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.7, "band": "medium", "quote": "Limma"}}], "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": ["GSE40435", "GSE29609"], "resolved_accessions": ["GSE40435", "GSE29609"], "statements": ["The datasets used during the current study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE40435, GSE29609 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:30272265", "data:geo:GSE29609", "asset:table:pmid:30272265:1"], "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": "2026-10-31T18:36:50Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 32362, "completion_tokens": 1883, "cached_tokens": 10888}}, "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:30272265", "type": "paper", "label": "pmid:30272265"}, {"id": "source:pmid:30272265", "type": "manuscript", "label": "PMID 30272265 full text"}, {"id": "data:geo:GSE29609", "type": "dataset", "label": "GEO GSE29609"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30272265", "type": "paper", "label": "pmid:30272265"}, {"id": "source:pmid:30272265", "type": "manuscript", "label": "PMID 30272265 full text"}, {"id": "data:geo:GSE29609", "type": "dataset", "label": "GEO GSE29609"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30272265", "type": "extraction", "used": ["source:pmid:30272265"], "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:30272265", "parent_hash": "sha256:31be9a2d25c40f6f56ba32db374bd7cbffb5d08b01a98601f51b4b6d1808c5bc", "fork_of": null, "generation": 6}, "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", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": 0.7, "evidence": ["Cox regression"], "order_basis": "analysis_only", "id": "assay:1"}]}