Ten hub genes associated with progression and prognosis of pancreatic carcinoma identified by co-expression analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29483831", "kind": "science-record", "revision": 5, "content_hash": "sha256:9d5e6bb233dd8dcf1e7e1bbefe3281977ffc10e7f4760490a4bc06de2870e038", "created_at": "2026-11-01T15:40:32Z", "updated_at": "2026-11-01T21:59:43Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Ten hub genes associated with progression and prognosis of pancreatic carcinoma identified by co-expression analysis.", "doi": "10.7150/ijbs.22619", "pmid": "29483831", "authors": ["Zhou Zhou", "Yian Cheng", "Yinan Jiang", "Shi Liu", "Meng Zhang", "Jing Liu", "Qiu Zhao"], "journal": "International journal of biological sciences", "year": 2018, "abstract": "Since the five-year survival rate is less than 5%, pancreatic ductal adenocarcinoma (PDAC) remains the 4th cause of cancer-related death. Although PDAC has been repeatedly researched in recent years, it is still predicted to be the second leading cause of cancer death by year 2030. In our study, the differentially expressed genes in dataset GSE62452 were used to construct a co-expression network by WGCNA. The yellow module related to grade of PDAC was screened. Combined with co-expression network and PPI network, 36 candidates were screened. After survival and regression analysis by using GSE62452 and TCGA dataset, we identified 10 real hub genes (CCNA2, CCNB1, CENPF, DLGAP5, KIF14, KIF23, NEK2, RACGAP1, TPX2 and UBE2C) tightly related to progression of PDAC. According to Oncomine database and The Human Protein Atlas (HPA), we found that all real hub genes were overexpressed in pancreatic carcinoma compared with normal tissues on transcriptional and translational level. ROC curve was plotted and AUC was calculated to distinguish recurrent and non-recurrent PDAC and every AUC of the real hub gene was greater than 0.5. Finally, functional enrichment analysis and gene set enrichment (GSEA) was performed and both of them showed the cell cycle played a vital role in PDAC.", "claims": [{"id": "claim-method", "statement": "The dataset GSE62452 containing 69 pancreatic tumors and mRNASeq data followed information of 146 PDAC patients in TCGA were separately subjected to survival analysis and regression analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29483831", "locator": "sections[16] \"Survival analysis and regression analysis for common hub genes\" paragraph 2", "quote": "The dataset GSE62452 containing 69 pancreatic tumors and mRNASeq data followed information of 146 PDAC patients in TCGA were separately subjected to survival analysis and regression analysis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Dataset GSE62452 performed on Affymetrix Human Gene 1.0 ST Array (Affymetrix, Santa Clara, CA, USA), including 69 pancreatic tumors and 61 adjacent non-tumor tissues from patients with pancreatic ductal adenocarcinoma (PDAC), was used as the training set to construct co-expression networks and identify hub genes in our study 18.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29483831", "locator": "sections[3] \"Data collection and preprocessing\" paragraph 2", "quote": "Dataset GSE62452 performed on Affymetrix Human Gene 1.0 ST Array (Affymetrix, Santa Clara, CA, USA), including 69 pancreatic tumors and 61 adjacent non-tumor tissues from patients with pancreatic ductal adenocarcinoma (PDAC), was used as the training set to construct co-expression networks and identify hub genes in our study 18."}], "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:29483831"], "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:GSE62165"], "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:GSE62165"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29483831", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7150/ijbs.22619", "sha256": "sha256:7cee531cff21f9d8fbce3d25045636506b1b52bc6783fc3bff1805c08a68da40", "bytes": 39886, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7150/ijbs.22619", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5821034", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE62165", "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=GSE62165", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE62165", "version": null, "note": "Dataset GSE62452 performed on Affymetrix Human Gene 1.0 ST Array (Affymetrix, Santa Clara, CA, USA), including 69 pancreatic tumors and 61 adjacent non-tumor tissues from patients with pancreatic ductal adenocarcinoma (PDAC), was used as the training set to construct co-expression networks and identify hub genes in our study 18.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Dataset GSE62452 performed on Affymetrix Human Gene 1.0 ST Array (Affymetrix, Santa Clara, CA, USA), including 69 pancreatic tumors and 61 adjacent non-tumor tissues from patients with pancreatic ductal adenocarcinoma (PDAC), was used as the training set to construct co-expression networks and identify hub genes in our study 18.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1520738", "GSM1520739", "GSM1520740", "GSM1520741", "GSM1520742", "GSM1520743", "GSM1520744", "GSM1520745", "GSM1520746", "GSM1520747", "GSM1520748", "GSM1520749", "GSM1520750", "GSM1520751", "GSM1520752", "GSM1520753", "GSM1520754", "GSM1520755", "GSM1520756", "GSM1520757", "GSM1520758", "GSM1520759", "GSM1520760", "GSM1520761", "GSM1520762", "GSM1520763", "GSM1520764", "GSM1520765", "GSM1520766", "GSM1520767", "GSM1520768", "GSM1520769", "GSM1520770", "GSM1520771", "GSM1520772", "GSM1520773", "GSM1520774", "GSM1520775", "GSM1520776", "GSM1520777", "GSM1520778", "GSM1520779", "GSM1520780", "GSM1520781", "GSM1520782", "GSM1520783", "GSM1520784", "GSM1520785", "GSM1520786", "GSM1520787", "GSM1520788", "GSM1520789", "GSM1520790", "GSM1520791", "GSM1520792", "GSM1520793", "GSM1520794", "GSM1520795", "GSM1520796", "GSM1520797", "GSM1520798", "GSM1520799", "GSM1520800", "GSM1520801", "GSM1520802", "GSM1520803", "GSM1520804", "GSM1520805", "GSM1520806", "GSM1520807", "GSM1520808", "GSM1520809", "GSM1520810", "GSM1520811", "GSM1520812", "GSM1520813", "GSM1520814", "GSM1520815", "GSM1520816", "GSM1520817", "GSM1520818", "GSM1520819", "GSM1520820", "GSM1520821", "GSM1520822", "GSM1520823", "GSM1520824", "GSM1520825", "GSM1520826", "GSM1520827", "GSM1520828", "GSM1520829", "GSM1520830", "GSM1520831", "GSM1520832", "GSM1520833", "GSM1520834", "GSM1520835", "GSM1520836", "GSM1520837", "GSM1520838", "GSM1520839", "GSM1520840", "GSM1520841", "GSM1520842", "GSM1520843", "GSM1520844", "GSM1520845", "GSM1520846", "GSM1520847", "GSM1520848", "GSM1520849", "GSM1520850", "GSM1520851", "GSM1520852", "GSM1520853", "GSM1520854", "GSM1520855", "GSM1520856", "GSM1520857", "GSM1520858", "GSM1520859", "GSM1520860", "GSM1520861", "GSM1520862", "GSM1520863", "GSM1520864", "GSM1520865", "GSM1520866", "GSM1520867", "GSM1520868"], "sample_count": 131, "group_sizes": null, "group_sizes_basis": null, "platform": "13667", "taxon": "Homo sapiens", "title": "Prognostic relevance of molecular subtypes and master regulators in pancreatic ductal adenocarcinoma", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE62452", "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=GSE62452", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE62452", "version": null, "note": "Dataset GSE62452 performed on Affymetrix Human Gene 1.0 ST Array (Affymetrix, Santa Clara, CA, USA), including 69 pancreatic tumors and 61 adjacent non-tumor tissues from patients with pancreatic ductal adenocarcinoma (PDAC), was used as the training set to construct co-expression networks and identify hub genes in our study 18.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Dataset GSE62452 performed on Affymetrix Human Gene 1.0 ST Array (Affymetrix, Santa Clara, CA, USA), including 69 pancreatic tumors and 61 adjacent non-tumor tissues from patients with pancreatic ductal adenocarcinoma (PDAC), was used as the training set to construct co-expression networks and identify hub genes in our study 18.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1527105", "GSM1527106", "GSM1527107", "GSM1527108", "GSM1527109", "GSM1527110", "GSM1527111", "GSM1527112", "GSM1527113", "GSM1527114", "GSM1527115", "GSM1527116", "GSM1527117", "GSM1527118", "GSM1527119", "GSM1527120", "GSM1527121", "GSM1527122", "GSM1527123", "GSM1527124", "GSM1527125", "GSM1527126", "GSM1527127", "GSM1527128", "GSM1527129", "GSM1527130", "GSM1527131", "GSM1527132", "GSM1527133", "GSM1527134", "GSM1527135", "GSM1527136", "GSM1527137", "GSM1527138", "GSM1527139", "GSM1527140", "GSM1527141", "GSM1527142", "GSM1527143", "GSM1527144", "GSM1527145", "GSM1527146", "GSM1527147", "GSM1527148", "GSM1527149", "GSM1527150", "GSM1527151", "GSM1527152", "GSM1527153", "GSM1527154", "GSM1527155", "GSM1527156", "GSM1527157", "GSM1527158", "GSM1527159", "GSM1527160", "GSM1527161", "GSM1527162", "GSM1527163", "GSM1527164", "GSM1527165", "GSM1527166", "GSM1527167", "GSM1527168", "GSM1527169", "GSM1527170", "GSM1527171", "GSM1527172", "GSM1527173", "GSM1527174", "GSM1527175", "GSM1527176", "GSM1527177", "GSM1527178", "GSM1527179", "GSM1527180", "GSM1527181", "GSM1527182", "GSM1527183", "GSM1527184", "GSM1527185", "GSM1527186", "GSM1527187", "GSM1527188", "GSM1527189", "GSM1527190", "GSM1527191", "GSM1527192", "GSM1527193", "GSM1527194", "GSM1527195", "GSM1527196", "GSM1527197", "GSM1527198", "GSM1527199", "GSM1527200", "GSM1527201", "GSM1527202", "GSM1527203", "GSM1527204", "GSM1527205", "GSM1527206", "GSM1527207", "GSM1527208", "GSM1527209", "GSM1527210", "GSM1527211", "GSM1527212", "GSM1527213", "GSM1527214", "GSM1527215", "GSM1527216", "GSM1527217", "GSM1527218", "GSM1527219", "GSM1527220", "GSM1527221", "GSM1527222", "GSM1527223", "GSM1527224", "GSM1527225", "GSM1527226", "GSM1527227", "GSM1527228", "GSM1527229", "GSM1527230", "GSM1527231", "GSM1527232", "GSM1527233", "GSM1527234"], "sample_count": 130, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Microarray gene-expression profiles of 69 pancreatic tumors and 61 adjacent non-tumor tissue from patients with pancreatic ductal adenocarcinoma", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE62165 not downloaded", "asset:data:geo:GSE62165 licence not read", "asset:data:geo:GSE62452 not downloaded", "asset:data:geo:GSE62452 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": "PPI"}}, {"id": "method-2", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.7, "band": "medium", "quote": "ROC curve"}}, {"id": "method-3", "family": null, "specific": null, "label": "Survival analysis and regression analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The dataset GSE62452 containing 69 pancreatic tumors and mRNASeq data followed information of 146 PDAC patients in TCGA were separately subjected to survival analysis and regression 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": ["GSE62452", "GSE62165"], "resolved_accessions": ["GSE62452", "GSE62165"], "statements": ["Dataset GSE62452 performed on Affymetrix Human Gene 1.0 ST Array (Affymetrix, Santa Clara, CA, USA), including 69 pancreatic tumors and 61 adjacent non-tumor tissues from patients with pancreatic ductal adenocarcinoma (PDAC), was used as the training set to construct co-expression networks and identify hub genes in our study 18."], "basis": "The paper names GSE62452, GSE62165 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": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:29483831", "data:geo:GSE62165"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE62165"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:11:03Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 32706, "completion_tokens": 1723, "cached_tokens": 656}}, "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:29483831", "type": "paper", "label": "pmid:29483831"}, {"id": "source:pmid:29483831", "type": "manuscript", "label": "PMID 29483831 full text"}, {"id": "data:geo:GSE62165", "type": "dataset", "label": "GEO GSE62165"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29483831", "type": "paper", "label": "pmid:29483831"}, {"id": "source:pmid:29483831", "type": "manuscript", "label": "PMID 29483831 full text"}, {"id": "data:geo:GSE62165", "type": "dataset", "label": "GEO GSE62165"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29483831", "type": "extraction", "used": ["source:pmid:29483831"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE62165", "type": "accession_resolution", "used": ["data:geo:GSE62165"], "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:29483831", "parent_hash": "sha256:94b70a1c3d1627bbaad2de349bb2468f16c3d5414b2e2e4fce89025a2e23522c", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE62165 licence not read", "asset:data:geo:GSE62165 not downloaded", "asset:data:geo:GSE62452 licence not read", "asset:data:geo:GSE62452 not downloaded", "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": ["PPI"], "order_basis": "analysis_only", "id": "assay:1"}]}