Identification of hub genes and pathways in bladder cancer using bioinformatics analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35291419", "kind": "science-record", "revision": 4, "content_hash": "sha256:a4c619a2b00558685bf94c70870361ff6f3eb80f6ec31aadbe6dc776cf51dd75", "created_at": "2026-11-01T18:14:04Z", "updated_at": "2026-11-01T22:06:07Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "partial", "title": "Identification of hub genes and pathways in bladder cancer using bioinformatics analysis.", "doi": null, "pmid": "35291419", "authors": ["Danhui Li", "Fan Zhen", "Jianwei Le", "Guodong Chen", "Jianhua Zhu"], "journal": "American journal of clinical and experimental urology", "year": 2022, "abstract": "Bladder cancer (BC) is the most common malignant tumor of urinary tract system. The aim of this study was to investigate the genetic signatures of bladder cancer (BC) and identify its potential molecular mechanisms. The gene expression profiles of GSE3167 (50 samples, including 41BC and 9 non-cancerous urothelial cells) was downloaded from the GEO database. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes pathway (KEGG) were performed to identify enriched pathways, and a protein-protein interaction (PPI) network was used to identify hub genes and for module analysis. Moreover, we conducted expression and survival analyses to screen and validate hub genes. In total, 1528 DEGs were identified in bladder cancer (BC), including 1212 up-regulated genes and 316 down-regulated genes. Up-regulated differentially expressed genes (DEGs) were significantly enriched in negative regulation of macromolecule metabolic process, macromolecule catabolic process, proteolysis and regulation of cell death, while the down-regulated differentially expressed genes (DEGs) were mainly involved in cell surface receptor linked signal transduction, ion transport, cell-cell signaling and defense response. The top 10 hub genes with the highest degrees were selected from the PPI network. These genes included HSP90AA1, MYH11, MYL9, CNN1, ACTC1, RAN, ENO1, HNRNPC, ACTG2 and YWHAZ. From sub-networks, we found these genes were involved in the proteasome, pathways in cancer and cell cycle. Hence, the identified DEGs and hub genes may be beneficial to elucidate the mechanisms underlying BC.", "claims": [{"id": "claim-method", "statement": "Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes pathway (KEGG) were performed to identify enriched pathways, and a protein-protein interaction (PPI) network was used to identify hub genes and for module analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35291419", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes pathway (KEGG) were performed to identify enriched pathways, and a protein-protein interaction (PPI) network was used to identify hub genes and for module analysis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The gene expression profiles of GSE3167 (50 samples, including 41BC and 9 non-cancerous urothelial cells) was downloaded from the GEO database.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35291419", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The gene expression profiles of GSE3167 (50 samples, including 41BC and 9 non-cancerous urothelial cells) was downloaded from the GEO database."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study identified 1,528 differentially expressed genes in bladder cancer, comprising 1,212 up-regulated and 316 down-regulated genes.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:35291419", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "In total, 1528 DEGs were identified in bladder cancer (BC), including 1212 up-regulated genes and 316 down-regulated genes."}], "state": "complete"}], "gaps": ["doi"]}, "experiment": {"state": "complete", "objective": "The study identified 1,528 differentially expressed genes in bladder cancer, comprising 1,212 up-regulated and 316 down-regulated genes.", "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:35291419"], "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:GSE3167"], "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:GSE3167"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35291419", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": null, "sha256": "sha256:ed8366cd61286219bd973de402c6e8d1fcde966d8fb0c36a803cc978ea0f6170", "bytes": 1606, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "35291419", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8918393", "source": "ncbi_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE3167", "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=GSE3167", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE3167", "version": null, "note": "The gene expression profiles of GSE3167 (50 samples, including 41BC and 9 non-cancerous urothelial cells) was downloaded from the GEO database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The gene expression profiles of GSE3167 (50 samples, including 41BC and 9 non-cancerous urothelial cells) was downloaded from the GEO database.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM71019", "GSM71020", "GSM71021", "GSM71022", "GSM71023", "GSM71024", "GSM71025", "GSM71026", "GSM71027", "GSM71028", "GSM71029", "GSM71030", "GSM71031", "GSM71032", "GSM71033", "GSM71034", "GSM71035", "GSM71036", "GSM71037", "GSM71038", "GSM71039", "GSM71040", "GSM71041", "GSM71042", "GSM71043", "GSM71044", "GSM71045", "GSM71046", "GSM71047", "GSM71048", "GSM71049", "GSM71050", "GSM71051", "GSM71052", "GSM71053", "GSM71054", "GSM71055", "GSM71056", "GSM71057", "GSM71058", "GSM71059", "GSM71060", "GSM71061", "GSM71062", "GSM71063", "GSM71064", "GSM71065", "GSM71066", "GSM71067", "GSM71068", "GSM71069", "GSM71070", "GSM71071", "GSM71072", "GSM71073", "GSM71074", "GSM71075", "GSM71076", "GSM71077", "GSM71078"], "sample_count": 60, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Classification of carcinoma in situ lesions in human bladder cancer", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE3167 not downloaded", "asset:data:geo:GSE3167 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-2", "family": null, "specific": null, "label": "Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes pathway (KEGG) enrichment analyses", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes pathway (KEGG) were performed to identify enriched pathways, and a protein-protein interaction (PPI) network was used to identify hub genes and for module analysis."}}], "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": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "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": ["GSE3167"], "resolved_accessions": ["GSE3167"], "statements": ["The gene expression profiles of GSE3167 (50 samples, including 41BC and 9 non-cancerous urothelial cells) was downloaded from the GEO database."], "basis": "The paper names GSE3167 in GEO database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:35291419", "data:geo:GSE3167"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE3167"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:38:02Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 5, "usage": {"prompt_tokens": 1976, "completion_tokens": 765, "cached_tokens": 0}}, "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:35291419", "type": "paper", "label": "pmid:35291419"}, {"id": "source:pmid:35291419", "type": "manuscript", "label": "PMID 35291419 full text"}, {"id": "data:geo:GSE3167", "type": "dataset", "label": "GEO GSE3167"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35291419", "type": "paper", "label": "pmid:35291419"}, {"id": "source:pmid:35291419", "type": "manuscript", "label": "PMID 35291419 full text"}, {"id": "data:geo:GSE3167", "type": "dataset", "label": "GEO GSE3167"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35291419", "type": "extraction", "used": ["source:pmid:35291419"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE3167", "type": "accession_resolution", "used": ["data:geo:GSE3167"], "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:35291419", "parent_hash": "sha256:466cca6befe3254f75388c6f763ee98d4b50e6a86f6a0735db9edfb860e65540", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE3167 licence not read", "asset:data:geo:GSE3167 not downloaded", "doi", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "analysis_only", "id": "assay:1"}]}