Gene Expression Analysis Reveals Key Genes and Signalings Associated with the Prognosis of Prostate Cancer.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34497666", "kind": "science-record", "revision": 7, "content_hash": "sha256:a6225963fcf938b03aa931dfc7af4bba6cb99e9edb7cd1d19e91bedba40c0235", "created_at": "2026-11-01T15:41:51Z", "updated_at": "2026-11-01T22:04:40Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Gene Expression Analysis Reveals Key Genes and Signalings Associated with the Prognosis of Prostate Cancer.", "doi": "10.1155/2021/9946015", "pmid": "34497666", "authors": ["Hao Shen", "Yong-Lian Guo", "Guo-Hao Li", "Wei Zhao", "Ling Zhang"], "journal": "Computational and mathematical methods in medicine", "year": 2021, "abstract": "It is urgent to identify novel biomarkers for prostate cancer (PCa) prognosis and to understand the mechanisms regulating the tumorigenesis for PCa treatment. In this study, GSE17951 and TCGA were used to identify the differentially expressed genes (DEGs). Our study demonstrated that 1533 genes with increased expression and 2301 genes with decreased expression in PCa. Bioinformatics analysis data indicated that these up-regulated genes had an association with the modulation of mitotic nuclear division, sister chromatid cohesion, cell division, and cell cycle. Additionally, our results revealed downregulated genes took part in modulating extracellular matrix organization, angiogenesis, signal transduction, and Ras signaling pathway. Hub upregulated and downregulated PPI networks were identified by protein-protein interaction (PPI) network analysis and MCODE analysis. Of note, 12 cell cycle regulators, comprising CCNB1, CCNB2, PLK1, TTK, AURKA, CDC20, BUB1, PTTG1, CDC45, CDC25C, CCNA2, and BUB1B, were demonstrated to function crucially in PCa development. By detecting their expression in PCa cell lines, we confirmed that these cell cycle regulator expressions were heightened in PCa cells. GEPIA databases analysis showed that higher expression of these cell cycle regulators was correlated to shorter disease-free survival (DFS) time in PCa samples. Our findings collectively suggested targeting cell cycle pathways may offer novel prognosis and treatment biomarkers for PCa.", "claims": [{"id": "claim-method", "statement": "Comparisons between groups were analyzed by students' T-test or Mann–Whitney U-test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34497666", "locator": "sections[6] \"2.4. Statistical Analysis\" paragraph 2", "quote": "Comparisons between groups were analyzed by students' T-test or Mann–Whitney U-test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Previously reported lncRNAs data were used to support this study and are available at [doi:10.1158/0008-5472.CAN-10-2585]. These datasets are cited at relevant places within the text as references.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34497666", "locator": "sections[16] \"Data Availability\" paragraph 2", "quote": "Previously reported lncRNAs data were used to support this study and are available at [doi:10.1158/0008-5472.CAN-10-2585]. These datasets are cited at relevant places within the text as references."}], "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:34497666"], "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:GSE17951"], "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:GSE17951"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34497666", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2021/9946015", "sha256": "sha256:911d7c686584877841b9182eeb77e17005ffd9c0c6493ae3d1065ccfa4fb6cb1", "bytes": 26317, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2021/9946015", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8419495", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE17951", "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=GSE17951", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE17951", "version": null, "note": "Previously reported lncRNAs data were used to support this study and are available at [doi:10.1158/0008-5472.CAN-10-2585]. These datasets are cited at relevant places within the text as references.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Previously reported lncRNAs data were used to support this study and are available at [doi:10.1158/0008-5472.CAN-10-2585]. These datasets are cited at relevant places within the text as references.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM449147", "GSM449148", "GSM449149", "GSM449150", "GSM449151", "GSM449152", "GSM449153", "GSM449154", "GSM449155", "GSM449156", "GSM449157", "GSM449158", "GSM449159", "GSM449160", "GSM449161", "GSM449162", "GSM449163", "GSM449164", "GSM449165", "GSM449166", "GSM449167", "GSM449168", "GSM449169", "GSM449170", "GSM449171", "GSM449172", "GSM449173", "GSM449174", "GSM449175", "GSM449176", "GSM449177", "GSM449178", "GSM449179", "GSM449180", "GSM449181", "GSM449182", "GSM449183", "GSM449184", "GSM449185", "GSM449186", "GSM449187", "GSM449188", "GSM449189", "GSM449190", "GSM449191", "GSM449192", "GSM449193", "GSM449194", "GSM449195", "GSM449196", "GSM449197", "GSM449198", "GSM449199", "GSM449200", "GSM449201", "GSM449202", "GSM449203", "GSM449204", "GSM449205", "GSM449206", "GSM449207", "GSM449208", "GSM449209", "GSM449210", "GSM449211", "GSM449212", "GSM449213", "GSM449214", "GSM449215", "GSM449216", "GSM449217", "GSM449218", "GSM449219", "GSM449220", "GSM449221", "GSM449222", "GSM449223", "GSM449224", "GSM449225", "GSM449226", "GSM449227", "GSM449228", "GSM449229", "GSM449230", "GSM449231", "GSM449232", "GSM449233", "GSM449234", "GSM449235", "GSM449236", "GSM449237", "GSM449238", "GSM449239", "GSM449240", "GSM449241", "GSM449242", "GSM449243", "GSM449244", "GSM449245", "GSM449246", "GSM449247", "GSM449248", "GSM449249", "GSM449250", "GSM449251", "GSM449252", "GSM449253", "GSM449254", "GSM449255", "GSM449256", "GSM449257", "GSM449258", "GSM449259", "GSM449260", "GSM449261", "GSM449262", "GSM449263", "GSM449264", "GSM449265", "GSM449266", "GSM449267", "GSM449268", "GSM449269", "GSM449270", "GSM449271", "GSM449272", "GSM449273", "GSM449274", "GSM449275", "GSM449276", "GSM449277", "GSM449278", "GSM449279", "GSM449280", "GSM449281", "GSM449282", "GSM449283", "GSM449284", "GSM449285", "GSM449286", "GSM449287", "GSM449288", "GSM449289", "GSM449290", "GSM449291", "GSM449292", "GSM449293", "GSM449294", "GSM449295", "GSM449296", "GSM449297", "GSM449298", "GSM449299", "GSM449300"], "sample_count": 154, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression analysis of prostate cancer samples using Affymetrix U133Plus2 array", "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:GSE17951 not downloaded", "asset:data:geo:GSE17951 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-2", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Cox proportional hazards"}}, {"id": "method-3", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Log-rank"}}, {"id": "method-4", "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": "PPI"}}, {"id": "method-5", "family": null, "specific": null, "label": "Students' T-test or Mann–Whitney U-test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Comparisons between groups were analyzed by students' T-test or Mann–Whitney U-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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE17951"], "resolved_accessions": ["GSE17951"], "statements": ["Previously reported lncRNAs data were used to support this study and are available at [doi:10.1158/0008-5472.CAN-10-2585]. These datasets are cited at relevant places within the text as references."], "basis": "The paper names GSE17951 in GEO database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:34497666", "data:geo:GSE17951"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE17951"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:34:36Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 23727, "completion_tokens": 2428, "cached_tokens": 793}}, "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:34497666", "type": "paper", "label": "pmid:34497666"}, {"id": "source:pmid:34497666", "type": "manuscript", "label": "PMID 34497666 full text"}, {"id": "data:geo:GSE17951", "type": "dataset", "label": "GEO GSE17951"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34497666", "type": "paper", "label": "pmid:34497666"}, {"id": "source:pmid:34497666", "type": "manuscript", "label": "PMID 34497666 full text"}, {"id": "data:geo:GSE17951", "type": "dataset", "label": "GEO GSE17951"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34497666", "type": "extraction", "used": ["source:pmid:34497666"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE17951", "type": "accession_resolution", "used": ["data:geo:GSE17951"], "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:34497666", "parent_hash": "sha256:7b5b2e7097b00a8e519d3be2e0bb1d86aba7a319798e3a999c1b2673dcff2f46", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE17951 licence not read", "asset:data:geo:GSE17951 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Kaplan-Meier"], "order_basis": "analysis_only", "id": "assay:1"}]}