Identification of Potential Key Genes and Pathways in Enzalutamide-Resistant Prostate Cancer Cell Lines: A Bioinformatics Analysis with Data from the Gene Expression Omnibus (GEO) Database.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32724813", "kind": "science-record", "revision": 8, "content_hash": "sha256:bb96ed372bf7bf96d9971c6babf0ab11396bdc09d0c8921289e2d89f42181424", "created_at": "2026-11-01T15:41:06Z", "updated_at": "2026-11-01T22:45:08Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Potential Key Genes and Pathways in Enzalutamide-Resistant Prostate Cancer Cell Lines: A Bioinformatics Analysis with Data from the Gene Expression Omnibus (GEO) Database.", "doi": "10.1155/2020/8341097", "pmid": "32724813", "authors": ["Long Zheng", "Xiaojie Dou", "Xiaodong Ma", "Wei Qu", "Xiaoshuang Tang"], "journal": "BioMed research international", "year": 2020, "abstract": "Enzalutamide (ENZ) has been approved for the treatment of advanced prostate cancer (PCa), but some patients develop ENZ resistance initially or after long-term administration. Although a few key genes have been discovered by previous efforts, the complete mechanisms of ENZ resistance remain unsolved. To further identify more potential key genes and pathways in the development of ENZ resistance, we employed the GSE104935 dataset, including 5 ENZ-resistant (ENZ-R) and 5 ENZ-sensitive (ENZ-S) PCa cell lines, from the Gene Expression Omnibus (GEO) database. Integrated bioinformatics analyses were conducted, such as analysis of differentially expressed genes (DEGs), Gene Ontology (GO) enrichment analysis, Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis, protein-protein interaction (PPI) analysis, gene set enrichment analysis (GSEA), and survival analysis. From these, we identified 201 DEGs (93 upregulated and 108 downregulated) and 12 hub genes (AR, ACKR3, GPER1, CCR7, NMU, NDRG1, FKBP5, NKX3-1, GAL, LPAR3, F2RL1, and PTGFR) that are potentially associated with ENZ resistance. One upregulated pathway (hedgehog pathway) and seven downregulated pathways (pathways related to androgen response, p53, estrogen response, TNF-α, TGF-β, complement, and pancreas β cells) were identified as potential key pathways involved in the occurrence of ENZ resistance. Our findings may contribute to further understanding the molecular mechanisms of ENZ resistance and provide some clues for the prevention and treatment of ENZ resistance.", "claims": [{"id": "claim-method", "statement": "Normalization of expression matrix data was executed by the R command normalizeBetweenArrays, while the DEG analysis was performed by the limma R package.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32724813", "locator": "sections[4] \"2.2. Genomic Analysis of Differentially Expressed Genes (DEGs)\" paragraph 2", "quote": "Normalization of expression matrix data was executed by the R command normalizeBetweenArrays, while the DEG analysis was performed by the limma R package."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data of GSE104935 used in our study are available via GEO (https://www.ncbi.nlm.nih.gov/geo/) or by appropriate request to the authors.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32724813", "locator": "sections[18] \"Data Availability\" paragraph 2", "quote": "The data of GSE104935 used in our study are available via GEO (https://www.ncbi.nlm.nih.gov/geo/) or by appropriate request to the authors."}], "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:32724813"], "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:GSE104935"], "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:GSE104935"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32724813", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2020/8341097", "sha256": "sha256:ea4bda2a2cea6f8f5e8228045f712410ae9be4bc79b020679f13b8d39a3ba810", "bytes": 21428, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2020/8341097", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7382728", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE104935", "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=GSE104935", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE104935", "version": null, "note": "The data of GSE104935 used in our study are available via GEO (https://www.ncbi.nlm.nih.gov/geo/) or by appropriate request to the authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data of GSE104935 used in our study are available via GEO (https://www.ncbi.nlm.nih.gov/geo/) or by appropriate request to the authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2810313", "GSM2810314", "GSM2810315", "GSM2810316", "GSM2810317", "GSM2810318", "GSM2810319", "GSM2810320", "GSM2810321", "GSM2810322"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Ligand-independent CXCR7 Activation of MAPK Signaling leads to Prostate Cancer Enzalutamide Resistance", "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:GSE104935 not downloaded", "asset:data:geo:GSE104935 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "Normalization of expression matrix data was executed by the R command normalizeBetweenArrays, while the DEG analysis was performed by the limma R package."}}, {"id": "method-2", "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-3", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "pathway enrichment"}}], "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE104935"], "resolved_accessions": ["GSE104935"], "statements": ["The data of GSE104935 used in our study are available via GEO (https://www.ncbi.nlm.nih.gov/geo/) or by appropriate request to the authors."], "basis": "The paper names GSE104935 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:32724813", "data:geo:GSE104935"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE104935"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:21:27Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 16894, "completion_tokens": 1591, "cached_tokens": 528}}, "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:32724813", "type": "paper", "label": "pmid:32724813"}, {"id": "source:pmid:32724813", "type": "manuscript", "label": "PMID 32724813 full text"}, {"id": "data:geo:GSE104935", "type": "dataset", "label": "GEO GSE104935"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32724813", "type": "paper", "label": "pmid:32724813"}, {"id": "source:pmid:32724813", "type": "manuscript", "label": "PMID 32724813 full text"}, {"id": "data:geo:GSE104935", "type": "dataset", "label": "GEO GSE104935"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32724813", "type": "extraction", "used": ["source:pmid:32724813"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE104935", "type": "accession_resolution", "used": ["data:geo:GSE104935"], "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:32724813", "parent_hash": "sha256:1c7a956586c30a787fbd0157f59b1526b86ee9f1b411a26b74cfe7374a0e23cd", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE104935 licence not read", "asset:data:geo:GSE104935 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Normalization of expression matrix data was executed by the R command normalizeBetweenArrays, while the DEG analysis was performed by the limma R package."], "order_basis": "analysis_only", "id": "assay:1"}]}