Screening and Identification of Key Biomarkers for Bladder Cancer: A Study Based on TCGA and GEO Data.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32047816", "kind": "science-record", "revision": 4, "content_hash": "sha256:b677f973092cceb60c2a892a332cf547b07050208c3b29bdc3da64ab29ee4185", "created_at": "2026-11-01T15:40:56Z", "updated_at": "2026-11-01T22:01:17Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Screening and Identification of Key Biomarkers for Bladder Cancer: A Study Based on TCGA and GEO Data.", "doi": "10.1155/2020/8283401", "pmid": "32047816", "authors": ["Yingkun Xu", "Guangzhen Wu", "Jianyi Li", "Jiatong Li", "Ningke Ruan", "Liye Ma", "Xiaoyang Han", "Yanjun Wei", "Liang Li", "Hongge Zhang", "Yougen Chen", "Qinghua Xia"], "journal": "BioMed research international", "year": 2020, "abstract": "Bladder cancer (BLCA) is a common malignant cancer, and it is the most common genitourinary cancer in the world. The recurrence rate is the highest of all cancers, and the treatment of BLCA has only slightly improved over the past 30 years. Genetic and environmental factors play an important role in the development and progression of BLCA. However, the mechanism of cancer development remains to be proven. Therefore, the identification of potential oncogenes is urgent for developing new therapeutic directions and designing novel biomarkers for the diagnosis and prognosis of BLCA. Based on this need, we screened overlapping differentially expressed genes (DEG) from the GSE7476, GSE13507, and TCGA BLCA datasets. To identify the central genes from these DEGs, we performed a protein-protein interaction network analysis. To investigate the role of DEGs and the underlying mechanisms in BLCA, we performed Gene Ontology (GO) and Kyoto Gene and Genomic Encyclopedia (KEGG) analysis; we identified the hub genes via different evaluation methods in cytoHubba and then selected the target genes by performing survival analysis. Finally, the relationship between these target genes and tumour immunity was analysed to explore the roles of these genes. In summary, our current studies indicate that both cell division cycle 20 (CDC20) and abnormal spindle microtubule assembly (ASPM) genes are potential prognostic biomarkers for BLCA. It may also be a potential immunotherapeutic target with future clinical significance.", "claims": [{"id": "claim-method", "statement": "Statistical significance of differences between and among groups was assessed using the t-test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32047816", "locator": "sections[13] \"2.11. Statistical Analysis\" paragraph 2", "quote": "Statistical significance of differences between and among groups was assessed using the t-test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data used to support the findings of this study are available from the corresponding author upon request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32047816", "locator": "sections[27] \"Data Availability\" paragraph 2", "quote": "The data used to support the findings of this study are available from the corresponding author upon request."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:32047816"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32047816", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2020/8283401", "sha256": "sha256:e54d95735f0f34a0162f92b01a478f47cf16dd0cd16f8b5946995916b0e60f92", "bytes": 30247, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2020/8283401", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7003274", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "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": "t-test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Statistical significance of differences between and among groups was assessed using the t-test."}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["The data used to support the findings of this study are available from the corresponding author upon request."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:32047816"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:56:46Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 24149, "completion_tokens": 1959, "cached_tokens": 776}}, "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:32047816", "type": "paper", "label": "pmid:32047816"}, {"id": "source:pmid:32047816", "type": "manuscript", "label": "PMID 32047816 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32047816", "type": "paper", "label": "pmid:32047816"}, {"id": "source:pmid:32047816", "type": "manuscript", "label": "PMID 32047816 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32047816", "type": "extraction", "used": ["source:pmid:32047816"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:32047816", "parent_hash": "sha256:e4c7e5af8bff351e3ce23fbc67e67182d95960058f7df9e3e542ec220d6caba5", "fork_of": null, "generation": 3}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "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"}]}