Overexpression of BUB1B, CCNA2, CDC20, and CDK1 in tumor tissues predicts poor survival in pancreatic ductal adenocarcinoma.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30765611", "kind": "science-record", "revision": 8, "content_hash": "sha256:d5b50d6afb958d74e49013f106cf35b0b5d136c87fd913c99bc6d06847721ace", "created_at": "2026-11-01T15:40:42Z", "updated_at": "2026-11-01T22:43:49Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Overexpression of BUB1B, CCNA2, CDC20, and CDK1 in tumor tissues predicts poor survival in pancreatic ductal adenocarcinoma.", "doi": "10.1042/BSR20182306", "pmid": "30765611", "authors": ["Shu Dong", "Fei Huang", "Hao Zhang", "Qiwen Chen"], "journal": "Bioscience reports", "year": 2019, "abstract": "Overexpressed genes in tumors usually contributed to aggressiveness in pancreatic ductal adenocarcinoma (PDAC). Using Gene Expression Omnibus (GEO) profiles including GSE46234, GSE71989, and GSE107610, we detected overexpressed genes in tumors with R program, which were enriched by Kyoto Encyclopedia of Genes and Genomes (KEGG), Gene ontology (GO), and Reactome pathway databases. Then, we performed a survival analysis of enriched genes based on TCGA profile. Our results revealed that high BUB1B, CCNA2, CDC20, and CDK1 expression in tumors was significantly associated with worse overall survival (OS) (Log rank P=0.00338, P=0.0447, P=0.00965, and P=0.00479, respectively), which was validated using a Kaplan-Meier plotter with a median cutoff (Log rank P=0.028, P=0.0035, P=0.039, and P=0.0033, respectively). Moreover, overexpression of BUB1B, CCNA2, CDC20, and CDK1 in tumor tissues was significantly associated with disease-free survival (DFS) in PDAC patients (Log rank P=0.00565, P=0.0357, P=0.00104, and P=0.00121, respectively). BUB1B, CCNA2, CDC20, and CDK1 were significantly overexpressed in deceased PDAC patients (all P<0.01) and in patients with recurrence/disease progression (all P<0.05). In addition, PDAC patients with neoplasms of histologic grade G3-4 had significantly higher BUB1B, CCNA2 and CDC20 levels (all P<0.05). In conclusion, the up-regulation of BUB1B, CCNA2, CDC20, CDK1, and WEE1 in tumor tissues are associated with worse OS and DFS in PDAC and is correlated with advanced tumor stage and tumor development.", "claims": [{"id": "claim-method", "statement": "The Limma package [13,14] in Bioconductor was used to identify DEGs (∣log2FC∣ > 1, adjusted P-value <0.05).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30765611", "locator": "sections[4] \"Identification of up-regulated DEGs in PDAC\" paragraph 2", "quote": "The Limma package [13,14] in Bioconductor was used to identify DEGs (∣log2FC∣ > 1, adjusted P-value <0.05)."}], "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:30765611"], "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:30765611", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1042/BSR20182306", "sha256": "sha256:74b1d018f832955860681dd058f0c608b28bd5e68edd7aeb50ea71ded9c49ff1", "bytes": 30611, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1042/BSR20182306", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6390130", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "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": "The Limma package [13,14] in Bioconductor was used to identify DEGs (∣log2FC∣ > 1, adjusted P-value <0.05)."}}, {"id": "method-2", "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": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"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": 0.7, "band": "medium", "quote": "Log rank"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": [], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:30765611"], "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": "2026-10-31T18:41:46Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 28283, "completion_tokens": 1832, "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:30765611", "type": "paper", "label": "pmid:30765611"}, {"id": "source:pmid:30765611", "type": "manuscript", "label": "PMID 30765611 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30765611", "type": "paper", "label": "pmid:30765611"}, {"id": "source:pmid:30765611", "type": "manuscript", "label": "PMID 30765611 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30765611", "type": "extraction", "used": ["source:pmid:30765611"], "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:30765611", "parent_hash": "sha256:bd552a9701a83379f454167e603cdada39125d75587cc9afdd748ecdf05c56b7", "fork_of": null, "generation": 7}, "gaps": ["execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "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": ["The Limma package [13,14] in Bioconductor was used to identify DEGs (∣log2FC∣ > 1, adjusted P-value <0.05)."], "order_basis": "analysis_only", "id": "assay:1"}]}