Identification of epithelial-related artificial neural network prognostic models for the prediction of bladder cancer prognosis through comprehensive analysis of single-cell and bulk RNA sequencing.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39157397", "kind": "science-record", "revision": 3, "content_hash": "sha256:209d264a34c8751b68a076a662c03a7756aa33fa0fe304e7ccf814905970d078", "created_at": "2026-11-01T20:29:17Z", "updated_at": "2026-11-01T22:12:30Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of epithelial-related artificial neural network prognostic models for the prediction of bladder cancer prognosis through comprehensive analysis of single-cell and bulk RNA sequencing.", "doi": "10.1016/j.heliyon.2024.e34632", "pmid": "39157397", "authors": ["Fan Zhao", "Kun Zhang", "Limin Ma", "Yeqing Huang"], "journal": "Heliyon", "year": 2024, "abstract": "Background: Bladder cancer (BLCA) presents as a heterogeneous epithelial malignancy. Progress in the early detection and effective treatment of BLCA relies heavily on the identification of novel biomarkers. Therefore, the primary goal of this study is to pinpoint potential biomarkers for BLCA through the fusion of single-cell RNA sequencing and RNA sequencing assessments. Furthermore, the aim is to establish practical clinical prognostic models that can facilitate accurate categorization and individualized therapy for patients.\nMethods: In this research, training sets were acquired from the TCGA database, whereas validation sets (GSE32894) and single-cell datasets (GSE135337) were extracted from the GEO database. Single-cell analysis was utilized to obtain characteristic subpopulations along with their associated marker genes. Subsequently, a novel BLCA subtype was identified within TCGA-BLCA. Furthermore, an artificial neural network prognostic model was constructed within the TCGA-BLCA cohort and subsequently verified utilizing a validation set. Two machine learning algorithms were employed to screen hub genes. QRT-qPCR was performed to detect the gene expression levels utilized in the construction of prognostic models across various cell lines. Additionally, the cMAP database and molecular docking were utilized for searching small molecule drugs.\nResults: The results of single-cell analysis revealed the presence of epithelial cells in multiple subpopulations, with 1579 marker genes selected for subsequent investigations. Subsequently, four epithelial cell subtypes were identified within the TCGA-BLCA cohort. Notably, cluster A exhibited a significant survival advantage. Concurrently, an artificial neural network prognostic model comprising 17 feature genes was constructed, accurately stratifying patient risk. Patients categorized in the low-risk group demonstrated a considerable survival advantage. The ROC analysis suggested that the model has strong prognostic ability. Furthermore, the findings of the validation group align consistently with those from the training group. Two types of machine learning algorithms screened NFIC as hub genes. Forskolin, a small molecule drug that binds to NFIC, was identified by employing a cMAP database and molecular docking.\nConclusion: The analysis results supplement the research on the role of epithelial cells in BLCA. An artificial neural network prognostic model containing 17 characteristic genes demonstrates the capability to accurately stratify patient risk, thereby potentially improving clinical decision-making and optimizing personalized therapeutic approaches.", "claims": [{"id": "claim-method", "statement": "Then, an artificial neural network prognostic model based on 17 genes was developed and evaluated.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39157397", "locator": "sections[23] \"Construction and validation of an artificial neural network prognostic model\" paragraph 2", "quote": "Then, an artificial neural network prognostic model based on 17 genes was developed and evaluated."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data comes from TCGA database (https://portal.gdc.cancer.gov) and GEO database (https://www.ncbi.nlm.nih.gov/geo/). Readers can download and use it for free.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39157397", "locator": "sections[33] \"Data Availability Statement\" paragraph 2", "quote": "All data comes from TCGA database (https://portal.gdc.cancer.gov) and GEO database (https://www.ncbi.nlm.nih.gov/geo/). Readers can download and use it for free."}], "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:39157397"], "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:GSE135337"], "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:GSE135337"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39157397", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.heliyon.2024.e34632", "sha256": "sha256:71fc03c8e07505de28704ad9d16e8605cdad8e4e427a0e088348883935f8c694", "bytes": 52457, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.heliyon.2024.e34632", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11328080", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE135337", "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=GSE135337", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE135337", "version": null, "note": "All data comes from TCGA database (https://portal.gdc.cancer.gov) and GEO database (https://www.ncbi.nlm.nih.gov/geo/). Readers can download and use it for free.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data comes from TCGA database (https://portal.gdc.cancer.gov) and GEO database (https://www.ncbi.nlm.nih.gov/geo/). Readers can download and use it for free.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4006644", "GSM4006645", "GSM4006646", "GSM4006647", "GSM4006648", "GSM4751267", "GSM4751268", "GSM5329919"], "sample_count": 8, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "Transcriptomic Characterization of Local Invasion in Human Bladder Cancer by Single Cell RNA Sequencing", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE32894", "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=GSE32894", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32894", "version": null, "note": "All data comes from TCGA database (https://portal.gdc.cancer.gov) and GEO database (https://www.ncbi.nlm.nih.gov/geo/). Readers can download and use it for free.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data comes from TCGA database (https://portal.gdc.cancer.gov) and GEO database (https://www.ncbi.nlm.nih.gov/geo/). Readers can download and use it for free.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM814052", "GSM814053", "GSM814054", "GSM814055", "GSM814056", "GSM814057", "GSM814058", "GSM814059", "GSM814060", "GSM814061", "GSM814062", "GSM814063", "GSM814064", "GSM814065", "GSM814066", "GSM814067", "GSM814068", "GSM814069", "GSM814070", "GSM814071", "GSM814072", "GSM814073", "GSM814074", "GSM814075", "GSM814076", "GSM814077", "GSM814078", "GSM814079", "GSM814080", "GSM814081", "GSM814082", "GSM814083", "GSM814084", "GSM814085", "GSM814086", "GSM814087", "GSM814088", "GSM814089", "GSM814090", "GSM814091", "GSM814092", "GSM814093", "GSM814094", "GSM814095", "GSM814096", "GSM814097", "GSM814098", "GSM814099", "GSM814100", "GSM814101", "GSM814102", "GSM814103", "GSM814104", "GSM814105", "GSM814106", "GSM814107", "GSM814108", "GSM814109", "GSM814110", "GSM814111", "GSM814112", "GSM814113", "GSM814114", "GSM814115", "GSM814116", "GSM814117", "GSM814118", "GSM814119", "GSM814120", "GSM814121", "GSM814122", "GSM814123", "GSM814124", "GSM814125", "GSM814126", "GSM814127", "GSM814128", "GSM814129", "GSM814130", "GSM814131", "GSM814132", "GSM814133", "GSM814134", "GSM814135", "GSM814136", "GSM814137", "GSM814138", "GSM814139", "GSM814140", "GSM814141", "GSM814142", "GSM814143", "GSM814144", "GSM814145", "GSM814146", "GSM814147", "GSM814148", "GSM814149", "GSM814150", "GSM814151", "GSM814152", "GSM814153", "GSM814154", "GSM814155", "GSM814156", "GSM814157", "GSM814158", "GSM814159", "GSM814160", "GSM814161", "GSM814162", "GSM814163", "GSM814164", "GSM814165", "GSM814166", "GSM814167", "GSM814168", "GSM814169", "GSM814170", "GSM814171", "GSM814172", "GSM814173", "GSM814174", "GSM814175", "GSM814176", "GSM814177", "GSM814178", "GSM814179", "GSM814180", "GSM814181", "GSM814182", "GSM814183", "GSM814184", "GSM814185", "GSM814186", "GSM814187", "GSM814188", "GSM814189", "GSM814190", "GSM814191", "GSM814192", "GSM814193", "GSM814194", "GSM814195", "GSM814196", "GSM814197", "GSM814198", "GSM814199", "GSM814200", "GSM814201", "GSM814202", "GSM814203", "GSM814204", "GSM814205", "GSM814206", "GSM814207", "GSM814208", "GSM814209", "GSM814210", "GSM814211", "GSM814212", "GSM814213", "GSM814214", "GSM814215", "GSM814216", "GSM814217", "GSM814218", "GSM814219", "GSM814220", "GSM814221", "GSM814222", "GSM814223", "GSM814224", "GSM814225", "GSM814226", "GSM814227", "GSM814228", "GSM814229", "GSM814230", "GSM814231", "GSM814232", "GSM814233", "GSM814234", "GSM814235", "GSM814236", "GSM814237", "GSM814238", "GSM814239", "GSM814240", "GSM814241", "GSM814242", "GSM814243", "GSM814244", "GSM814245", "GSM814246", "GSM814247", "GSM814248", "GSM814249", "GSM814250", "GSM814251", "GSM814252", "GSM814253", "GSM814254", "GSM814255", "GSM814256", "GSM814257", "GSM814258", "GSM814259", "GSM814260", "GSM814261", "GSM814262", "GSM814263", "GSM814264", "GSM814265", "GSM814266", "GSM814267", "GSM814268", "GSM814269", "GSM814270", "GSM814271", "GSM814272", "GSM814273", "GSM814274", "GSM814275", "GSM814276", "GSM814277", "GSM814278", "GSM814279", "GSM814280", "GSM814281", "GSM814282", "GSM814283", "GSM814284", "GSM814285", "GSM814286", "GSM814287", "GSM814288", "GSM814289", "GSM814290", "GSM814291", "GSM814292", "GSM814293", "GSM814294", "GSM814295", "GSM814296", "GSM814297", "GSM814298", "GSM814299", "GSM814300", "GSM814301", "GSM814302", "GSM814303", "GSM814304", "GSM814305", "GSM814306", "GSM814307", "GSM814308", "GSM814309", "GSM814310", "GSM814311", "GSM814312", "GSM814313", "GSM814314", "GSM814315", "GSM814316", "GSM814317", "GSM814318", "GSM814319", "GSM814320", "GSM814321", "GSM814322", "GSM814323", "GSM814324", "GSM814325", "GSM814326", "GSM814327", "GSM814328", "GSM814329", "GSM814330", "GSM814331", "GSM814332", "GSM814333", "GSM814334", "GSM814335", "GSM814336", "GSM814337", "GSM814338", "GSM814339", "GSM814340", "GSM814341", "GSM814342", "GSM814343", "GSM814344", "GSM814345", "GSM814346", "GSM814347", "GSM814348", "GSM814349", "GSM814350", "GSM814351", "GSM814352", "GSM814353", "GSM814354", "GSM814355", "GSM814356", "GSM814357", "GSM814358", "GSM814359"], "sample_count": 308, "group_sizes": null, "group_sizes_basis": null, "platform": "6947", "taxon": "Homo sapiens", "title": "A Molecular Taxonomy 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}}], "gaps": ["asset:data:geo:GSE135337 not downloaded", "asset:data:geo:GSE135337 licence not read", "asset:data:geo:GSE32894 not downloaded", "asset:data:geo:GSE32894 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": 0.7, "band": "medium", "quote": "ROC analysis"}}, {"id": "method-2", "family": null, "specific": null, "label": "Artificial neural network prognostic model", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Then, an artificial neural network prognostic model based on 17 genes was developed and evaluated."}}], "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": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: roc."}, "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": ["GSE32894", "GSE135337"], "resolved_accessions": ["GSE32894", "GSE135337"], "statements": ["All data comes from TCGA database (https://portal.gdc.cancer.gov) and GEO database (https://www.ncbi.nlm.nih.gov/geo/). Readers can download and use it for free."], "basis": "The paper names GSE32894, GSE135337 in GEO database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "assets": ["source:pmid:39157397", "data:geo:GSE135337"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE135337"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:29:03Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 14305, "completion_tokens": 1250, "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:39157397", "type": "paper", "label": "pmid:39157397"}, {"id": "source:pmid:39157397", "type": "manuscript", "label": "PMID 39157397 full text"}, {"id": "data:geo:GSE135337", "type": "dataset", "label": "GEO GSE135337"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39157397", "type": "paper", "label": "pmid:39157397"}, {"id": "source:pmid:39157397", "type": "manuscript", "label": "PMID 39157397 full text"}, {"id": "data:geo:GSE135337", "type": "dataset", "label": "GEO GSE135337"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39157397", "type": "extraction", "used": ["source:pmid:39157397"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE135337", "type": "accession_resolution", "used": ["data:geo:GSE135337"], "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:39157397", "parent_hash": "sha256:5aea1991cb0b82c91705311bf441050c420111b7a94519e1e41fdbdf8c740abb", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE135337 licence not read", "asset:data:geo:GSE135337 not downloaded", "asset:data:geo:GSE32894 licence not read", "asset:data:geo:GSE32894 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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": 0.99, "evidence": ["mprehensive analysis of single-cell and bulk RNA sequencing.", "s for BLCA through the fusion of single-cell RNA sequencing and RNA sequencing assessments. Furthermore,", "the fusion of single-cell RNA sequencing and RNA sequencing assessments. Furthermore, the aim is to esta", "and methods Datasets and patient samples The RNA-seq data, clinical information, and mutation dat"], "order_basis": "paper_text_order:138", "id": "assay:1"}, {"role": "data_generation", "definition_id": "scrna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "unsupported", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["al biomarkers for BLCA through the fusion of single-cell RNA sequencing and RNA sequencing assessments. Furthermore,", "dataset consisted of 224 tumor samples. The scRNA-seq dataset GSE135337 for BLCA was obtained from"], "order_basis": "paper_text_order:470", "id": "assay:2"}, {"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["ithms were employed to screen hub genes. QRT-qPCR was performed to detect the gene expression"], "order_basis": "paper_text_order:1289", "id": "assay:3"}, {"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": ["en BLCA patients. Cell culture and transient transfection SV-HUC-1, EJ-1 and BT-B cells were purchased", "C) and siRNA for KRTCAP2 (Sagon, China) were transfected into the cells utilizing Lipofectamine 2000", "E F-12 medium. The negative control (NC) and siRNA for KRTCAP2 (Sagon, China) were transfected"], "order_basis": "paper_text_order:3438", "id": "assay:4"}, {"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": ["otechnology Co. (Beijing, China). Cells were cultured in DEME F-12 medium. The negative control (NC)"], "order_basis": "paper_text_order:3561", "id": "assay:5"}, {"role": "analysis", "definition_id": "diagnostic_evaluation", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["ROC analysis"], "order_basis": "consumes_earlier_output", "id": "assay:6"}]}