Novel Potential Biomarkers Associated With Epithelial to Mesenchymal Transition and Bladder Cancer Prognosis Identified by Integrated Bioinformatic Analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32695668", "kind": "science-record", "revision": 6, "content_hash": "sha256:55e5e14eed120cfe765c1a720686baf04ed9211f52ec1014fbe77de8d0d78398", "created_at": "2026-11-01T15:41:06Z", "updated_at": "2026-11-01T21:23:32Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Novel Potential Biomarkers Associated With Epithelial to Mesenchymal Transition and Bladder Cancer Prognosis Identified by Integrated Bioinformatic Analysis.", "doi": "10.3389/fonc.2020.00931", "pmid": "32695668", "authors": ["Chengyuan Wang", "Yujing Yang", "Lei Yin", "Ningde Wei", "Ting Hong", "Zuyu Sun", "Jiaxi Yao", "Zhi Li", "Tao Liu"], "journal": "Frontiers in oncology", "year": 2020, "abstract": "Bladder cancer (BC) is one of the most common malignancies in terms of incidence and recurrence worldwide. The aim of this study was to identify novel prognostic biomarkers related to BC progression utilizing weighted gene co-expression network analysis (WGCNA) and further bioinformatic analysis. First, we constructed a co-expression network by using WGCNA among 274 TCGA-BLCA patients and preliminarily screened out four genes (CORO1C, TMPRSS4, PIK3C2B, and ZNF692) associated with advanced clinical traits. In support, GSE19915 and specimens from 124 patients were used to validate the genes selected by WGCNA; then, CORO1C and TMPRSS4 were confirmed as hub genes with strong prognostic values in BC. Moreover, the result of gene set enrichment analysis (GSEA) and gene set variation analysis (GSVA) indicated that CORO1C and TMPRSS4 might be involved in the process of epithelial to mesenchymal transition (EMT) reversely. In addition, high expression of CORO1C was found to be significantly correlated with tumor-infiltrating neutrophils (TINs), a negative regulatory component that facilitates tumor distant progression and induces poor clinical outcome. In conclusion, our study first identified CORO1C and TMPRSS4 as vital regulators in the process of tumor progression through influencing EMT and could be developed to effective prognostic and therapeutic targets in future BC treatment.", "claims": [{"id": "claim-method", "statement": "Tumor samples within the above data sets were divided based on the candidate hub gene's median expressive value, and the survival analysis was estimated by the Kaplan–Meier (K-M) survival curves of each patient with overall survival (OS) as the end point.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32695668", "locator": "sections[13] \"Survival Analysis of the Candidate Hub Genes\" paragraph 2", "quote": "Tumor samples within the above data sets were divided based on the candidate hub gene's median expressive value, and the survival analysis was estimated by the Kaplan–Meier (K-M) survival curves of each patient with overall survival (OS) as the end point."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study, these can be found in The Cancer Genome Atlas (https://cancergenome.nih.gov/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32695668", "locator": "sections[21] \"Data Availability Statement\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study, these can be found in The Cancer Genome Atlas (https://cancergenome.nih.gov/)."}], "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:32695668"], "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:GSE19915"], "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:GSE19915"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32695668", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fonc.2020.00931", "sha256": "sha256:5785fbbad3912f1c544660459e0cf37ee3e1d0c2541ab53bd96ca997f2f17c7e", "bytes": 40618, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fonc.2020.00931", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7338771", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE19915", "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=GSE19915", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19915", "version": null, "note": "Publicly available datasets were analyzed in this study, these can be found in The Cancer Genome Atlas (https://cancergenome.nih.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study, these can be found in The Cancer Genome Atlas (https://cancergenome.nih.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM497679", "GSM497680", "GSM497681", "GSM497682", "GSM497683", "GSM497684", "GSM497685", "GSM497686", "GSM497687", "GSM497688", "GSM497689", "GSM497690", "GSM497691", "GSM497692", "GSM497693", "GSM497694", "GSM497695", "GSM497696", "GSM497697", "GSM497698", "GSM497699", "GSM497700", "GSM497701", "GSM497702", "GSM497703", "GSM497704", "GSM497705", "GSM497706", "GSM497707", "GSM497708", "GSM497709", "GSM497710", "GSM497711", "GSM497712", "GSM497713", "GSM497714", "GSM497715", "GSM497716", "GSM497717", "GSM497718", "GSM497719", "GSM497720", "GSM497721", "GSM497722", "GSM497723", "GSM497724", "GSM497725", "GSM497726", "GSM497727", "GSM497728", "GSM497729", "GSM497730", "GSM497731", "GSM497732", "GSM497733", "GSM497734", "GSM497735", "GSM497736", "GSM497737", "GSM497738", "GSM497739", "GSM497740", "GSM497741", "GSM497742", "GSM497743", "GSM497744", "GSM497745", "GSM497746", "GSM497747", "GSM497748", "GSM497749", "GSM497750", "GSM497751", "GSM497752", "GSM497753", "GSM497754", "GSM497755", "GSM497756", "GSM497757", "GSM497758", "GSM497759", "GSM497760", "GSM497761", "GSM497762", "GSM497775", "GSM497776", "GSM497777", "GSM497778", "GSM497779", "GSM497780", "GSM497781", "GSM497782", "GSM497783", "GSM497784", "GSM497785", "GSM497786", "GSM497787", "GSM497788", "GSM497789", "GSM497790", "GSM497791", "GSM497792", "GSM497793", "GSM497794", "GSM497795", "GSM497796", "GSM497797", "GSM497798", "GSM497799", "GSM497800", "GSM497801", "GSM497802", "GSM497803", "GSM497804", "GSM497805", "GSM497806", "GSM497807", "GSM497808", "GSM497809", "GSM497810", "GSM497811", "GSM497812", "GSM497813", "GSM497814", "GSM497815", "GSM497816", "GSM497817", "GSM497818", "GSM497819", "GSM497820", "GSM497821", "GSM497822", "GSM497823", "GSM497824", "GSM497825", "GSM497826", "GSM497827", "GSM497828", "GSM497829", "GSM497830", "GSM497831", "GSM497832", "GSM497833", "GSM497834", "GSM497835", "GSM497836", "GSM497837", "GSM497838", "GSM497839", "GSM497840", "GSM497841", "GSM497842", "GSM497843", "GSM497844", "GSM497845", "GSM497846", "GSM497847", "GSM497848", "GSM497849", "GSM497850", "GSM497851", "GSM497852", "GSM497853", "GSM497854", "GSM497855", "GSM497856", "GSM497857", "GSM497858", "GSM497859", "GSM497860", "GSM497861", "GSM497862", "GSM497863", "GSM497864", "GSM497865", "GSM497866", "GSM497867", "GSM497868", "GSM497869", "GSM497870", "GSM497871", "GSM497872", "GSM497873", "GSM497874", "GSM497875", "GSM497876", "GSM497877", "GSM497878", "GSM497879", "GSM497880", "GSM497881", "GSM497882", "GSM497883", "GSM497884", "GSM497885", "GSM497886", "GSM497887", "GSM497888", "GSM497889", "GSM497890", "GSM497891", "GSM497892", "GSM497893", "GSM497894", "GSM497895", "GSM497896", "GSM497897", "GSM497898", "GSM497899", "GSM497900", "GSM497901", "GSM497902", "GSM497903", "GSM497904", "GSM497905", "GSM497906", "GSM497907", "GSM497908", "GSM497909", "GSM497910", "GSM497911", "GSM497912", "GSM497913", "GSM497914", "GSM497915", "GSM497916", "GSM497917", "GSM497918", "GSM497919", "GSM497920", "GSM497921", "GSM497922", "GSM497923", "GSM497924", "GSM497925", "GSM497926", "GSM497927", "GSM497928", "GSM497929", "GSM497930", "GSM497931", "GSM497932", "GSM497933", "GSM497934", "GSM497935", "GSM497936", "GSM497937", "GSM497938", "GSM497939", "GSM497940", "GSM497941", "GSM497942", "GSM497943", "GSM497944", "GSM497945", "GSM497946", "GSM497947", "GSM497948", "GSM497949", "GSM497950", "GSM497951", "GSM497952", "GSM497953", "GSM497954", "GSM497955", "GSM497956", "GSM497957", "GSM497958", "GSM497959", "GSM497960", "GSM497961", "GSM497962", "GSM497963", "GSM497964", "GSM497965", "GSM497966", "GSM497967", "GSM497968", "GSM497969", "GSM497970", "GSM497971", "GSM497972", "GSM497973", "GSM497974", "GSM497975"], "sample_count": 285, "group_sizes": null, "group_sizes_basis": null, "platform": "4723;3883;5186", "taxon": "Homo sapiens", "title": "Subtype classification, grading, and outcome prediction of urothelial carcinomas by combined mRNA profiling and aCGH", "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:32695668:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:699e9e40b01280580c560b6ad629fe955fe85d99e5224f5b092df493d2c139e1", "bytes": 735, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "The candidate hub gene and gene numbers of all 17 modules determined by WGCNA.", "structure": {"pmcid": "PMC7338771", "section_index": 3, "section_title": "Co-expression Network Construction and Module Identification", "row_count": 18, "column_count": 3}, "table": {"label": "Table 1", "caption": "The candidate hub gene and gene numbers of all 17 modules determined by WGCNA.", "rows": [["Module colors", "Gene frequency", "Candidate hub gene"], ["Black", "283", "NUDC"], ["Turquoise", "935", "NDUF83"], ["Lightyellow", "39", "PIM2"], ["Grey60", "59", "C1QBP"], ["Pink", "270", "SELPLG"], ["Purple", "395", "CORO1C"], ["Blue", "793", "ECT2"], ["Salmon", "144", "PPM1G"], ["Brown", "671", "CNOT1"], ["Cyan", "422", "PIK3C2B"], ["Light green", "45", "TMPRSS4"], ["Green yellow", "170", "EMILIN1"], ["Royal blue", "31", "ITGAV"], ["Magenta", "254", "ILF2"], ["Midnight blue", "115", "UBE2L6"], ["Green", "291", "ZNF692"], ["Light cyan", "83", "NELFB"]], "row_count": 18, "column_count": 3, "numeric_cells": 20, "header_rows": 1, "locator": "section[3]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:32695668:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f3a66a0f629d9cdf915b26b81edfc0385fa75732ff0afaeb28c939720f651fd1", "bytes": 1062, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#T2", "version": null, "note": "The correlations between the CORO1C and clinicopathological features based on TCGA-BLCA data.", "structure": {"pmcid": "PMC7338771", "section_index": 5, "section_title": "Validation of the Candidate Hub Genes by Immunohistochemistry and GSE19915", "row_count": 22, "column_count": 4}, "table": {"label": "Table 2A", "caption": "The correlations between the CORO1C and clinicopathological features based on TCGA-BLCA data.", "rows": [["Clinicopathological parameters", "n", "Mean ±SD", "p-value"], ["Age (years)", "", "", "0.1138"], ["<60", "70", "16.7603 ± 12.4954", ""], ["≥60", "204", "17.9346 ± 10.4981", ""], ["Gender", "", "", "0.4653"], ["Male", "202", "17.3079 ± 10.8785", ""], ["Female", "72", "18.5508 ± 11.4752", ""], ["Stage", "", "", "0.9494"], ["Stage II–III", "180", "17.8167 ± 11.2904", ""], ["Stage IV", "94", "17.2857 ± 10.5661", ""], ["T category", "", "", "0.0042*"], ["T2", "95", "15.1989 ± 9.8401", ""], ["T3–T4", "179", "18.9772 ± 11.4297", ""], ["N catagory", "", "", "0.9832"], ["No", "183", "17.7768 ± 11.2386", ""], ["Yes", "91", "17.3486 ± 10.6557", ""], ["M catagory", "", "", "0.0002*"], ["No", "129", "15.3059 ± 10.3289", ""], ["Yes", "145", "19.7062 ± 11.2547", ""], ["Grade", "", "", "0.0002*"], ["High grade", "257", "18.1919 ± 11.0845", ""], ["Low grade", "17", "9.2089 ± 5.4622", ""]], "row_count": 22, "column_count": 4, "numeric_cells": 37, "header_rows": 1, "locator": "section[5]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:32695668:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c381ef5f852de9253a24262f3bac8a6afa6e0d27a2291964880eb9c38e179d7a", "bytes": 1067, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[2]#T3", "version": null, "note": "The correlations between the TMPRSS4 and clinicopathological features based on TCGA-BLCA data.", "structure": {"pmcid": "PMC7338771", "section_index": 5, "section_title": "Validation of the Candidate Hub Genes by Immunohistochemistry and GSE19915", "row_count": 22, "column_count": 4}, "table": {"label": "Table 2B", "caption": "The correlations between the TMPRSS4 and clinicopathological features based on TCGA-BLCA data.", "rows": [["Clinicopathological parameters", "n", "Mean ±SD", "p-value"], ["Age (years)", "", "", "0.0026*"], ["<60", "70", "30.1060 ± 29.5519", ""], ["≥60", "204", "19.7486 ± 28.5467", ""], ["Gender", "", "", "0.9064"], ["Male", "202", "23.6351 ± 31.065", ""], ["Female", "72", "18.9148 ± 22.5550", ""], ["Stage", "", "", "0.0039*"], ["Stage II–III", "180", "25.3212 ± 30.0975", ""], ["Stage IV", "94", "16.7907 ± 26.3627", ""], ["T category", "", "", "0.0001*"], ["T2", "95", "28.7322 ± 31.8749", ""], ["T3-T4", "179", "19.0312 ± 20.0176", ""], ["N catagory", "", "", "0.0033*"], ["No", "183", "25.5201 ± 30.5025", ""], ["Yes", "91", "16.1095 ± 25.0689", ""], ["M catagory", "", "", "0.0002*"], ["No", "129", "28.4354 ± 32.4548", ""], ["Yes", "145", "17.0205 ± 24.6583", ""], ["Grade", "", "", "<0.0001*"], ["High grade", "257", "20.1151 ± 27.2240", ""], ["Low grade", "17", "56.8559 ± 35.3721", ""]], "row_count": 22, "column_count": 4, "numeric_cells": 37, "header_rows": 1, "locator": "section[5]/table-wrap[2]#T3"}}], "gaps": ["asset:data:geo:GSE19915 not downloaded", "asset:data:geo:GSE19915 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Spearman correlation"}}, {"id": "method-2", "family": null, "specific": null, "label": "Kaplan–Meier (K-M) survival analysis using the GSE19915 source data from the Gene Expression Omnibus database", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Tumor samples within the above data sets were divided based on the candidate hub gene's median expressive value, and the survival analysis was estimated by the Kaplan–Meier (K-M) survival curves of each patient with overall survival (OS) as the end point."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": ["spearman_rho"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: spearman."}, "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": ["GSE19915"], "resolved_accessions": ["GSE19915"], "statements": ["Publicly available datasets were analyzed in this study, these can be found in The Cancer Genome Atlas (https://cancergenome.nih.gov/)."], "basis": "The paper names GSE19915 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": ["spearman_rho"], "assets": ["source:pmid:32695668", "data:geo:GSE19915", "asset:table:pmid:32695668:1", "asset:table:pmid:32695668:2", "asset:table:pmid:32695668:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE19915"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:21:15Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 28851, "completion_tokens": 1909, "cached_tokens": 9736}}, "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:32695668", "type": "paper", "label": "pmid:32695668"}, {"id": "source:pmid:32695668", "type": "manuscript", "label": "PMID 32695668 full text"}, {"id": "data:geo:GSE19915", "type": "dataset", "label": "GEO GSE19915"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32695668", "type": "paper", "label": "pmid:32695668"}, {"id": "source:pmid:32695668", "type": "manuscript", "label": "PMID 32695668 full text"}, {"id": "data:geo:GSE19915", "type": "dataset", "label": "GEO GSE19915"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32695668", "type": "extraction", "used": ["source:pmid:32695668"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE19915", "type": "accession_resolution", "used": ["data:geo:GSE19915"], "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:32695668", "parent_hash": "sha256:48ef88da8954a502e41838cc88ec01938dc7076ab6cb5d956195f333fd898019", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE19915 licence not read", "asset:data:geo:GSE19915 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["spearman_rho"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Spearman correlation"], "order_basis": "analysis_only", "id": "assay:1"}]}