Identification of Potential Biomarkers in Glioblastoma through Bioinformatic Analysis and Evaluating Their Prognostic Value.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31119182", "kind": "science-record", "revision": 8, "content_hash": "sha256:f3ed6a00e2ce1a72e8d842dc3f96f51e67f01b1815aad001d67ed036bb2d4290", "created_at": "2026-11-01T15:40:45Z", "updated_at": "2026-11-01T22:43:59Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Potential Biomarkers in Glioblastoma through Bioinformatic Analysis and Evaluating Their Prognostic Value.", "doi": "10.1155/2019/6581576", "pmid": "31119182", "authors": ["Yangmei Zhou", "Li Yang", "Xiaoxi Zhang", "Rui Chen", "Xiuqiong Chen", "Wenhua Tang", "Mengxian Zhang"], "journal": "BioMed research international", "year": 2019, "abstract": "Glioblastoma is a common malignant tumor in the central nervous system with an extremely poor outcome; understanding the mechanisms of glioblastoma at the molecular level is essential for clinical treatment. In the present study, we used bioinformatics analysis to identify potential biomarkers associated with prognosis in glioblastoma and elucidate the underlying mechanisms. The result revealed that 552 common genes were differentially expressed between glioblastoma and normal tissues based on TCGA, GSE4290, and GSE 50161 datasets. Gene Oncology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment and protein-protein interaction (PPI) network were carried out to gain insight into the actions of differentially expressed genes (DEGs). As a result, 20 genes (CALB1, CDC20, CDCA8, CDK1, CEP55, DLGAP5, KIF20A, KIF4A, NDC80, PBK, RRM2, SYN1, SYP, SYT1, TPX2, TTK, VEGFA, BDNF, GNG3, and TOP2A) were found as hub genes via CytoHubba in Cytoscape and functioned mainly by participating in cell cycle and p53 signaling pathway; among them, RRM2 and CEP55 were considered to have relationship with the prognosis of glioblastoma, especially RRM2. High expression of RRM2 was consistent with shorter overall survival time. In conclusion, our study displayed the bioinformatic analysis methods in screening potential oncogenes in glioblastoma and underlying mechanisms. What is more is that we successfully identified RRM2 as a novel biomarker linked with prognosis, which might be expected to be a promising target for the therapy of glioblastoma.", "claims": [{"id": "claim-method", "statement": "Then we utilized the univariate Cox regression analysis and log rank test to draw the survival curves to explore the prognostic related value of the hub genes based on TCGA datasets.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31119182", "locator": "sections[13] \"3.4. Function and Survival Analysis of the Hub Genes\" paragraph 2", "quote": "Then we utilized the univariate Cox regression analysis and log rank test to draw the survival curves to explore the prognostic related value of the hub genes based on TCGA datasets."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data used for analysis in this study are available from the Cancer Genome Atlas and the Gene Expression Omnibus database freely.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31119182", "locator": "sections[19] \"Data Availability\" paragraph 2", "quote": "The data used for analysis in this study are available from the Cancer Genome Atlas and the Gene Expression Omnibus database freely."}], "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:31119182"], "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:GSE4290"], "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:GSE4290"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31119182", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2019/6581576", "sha256": "sha256:a22bae5429a8d4dcda4eee6c51209f7505af49c3c864c71c9a0ee46de4a53532", "bytes": 37885, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2019/6581576", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6500689", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE4290", "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=GSE4290", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE4290", "version": null, "note": "The data used for analysis in this study are available from the Cancer Genome Atlas and the Gene Expression Omnibus database freely.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used for analysis in this study are available from the Cancer Genome Atlas and the Gene Expression Omnibus database freely.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM97793", "GSM97794", "GSM97795", "GSM97796", "GSM97797", "GSM97798", "GSM97799", "GSM97800", "GSM97801", "GSM97802", "GSM97803", "GSM97804", "GSM97805", "GSM97806", "GSM97807", "GSM97808", "GSM97809", "GSM97810", "GSM97811", "GSM97812", "GSM97813", "GSM97814", "GSM97815", "GSM97816", "GSM97817", "GSM97818", "GSM97819", "GSM97820", "GSM97821", "GSM97822", "GSM97823", "GSM97824", "GSM97825", "GSM97826", "GSM97827", "GSM97828", "GSM97829", "GSM97830", "GSM97831", "GSM97832", "GSM97833", "GSM97834", "GSM97835", "GSM97836", "GSM97837", "GSM97838", "GSM97839", "GSM97840", "GSM97841", "GSM97842", "GSM97843", "GSM97844", "GSM97845", "GSM97846", "GSM97847", "GSM97848", "GSM97849", "GSM97850", "GSM97851", "GSM97852", "GSM97853", "GSM97854", "GSM97855", "GSM97856", "GSM97857", "GSM97858", "GSM97859", "GSM97860", "GSM97861", "GSM97862", "GSM97863", "GSM97864", "GSM97865", "GSM97866", "GSM97867", "GSM97868", "GSM97869", "GSM97870", "GSM97871", "GSM97872", "GSM97873", "GSM97874", "GSM97875", "GSM97876", "GSM97877", "GSM97878", "GSM97879", "GSM97880", "GSM97881", "GSM97882", "GSM97883", "GSM97884", "GSM97885", "GSM97886", "GSM97887", "GSM97888", "GSM97889", "GSM97890", "GSM97891", "GSM97892", "GSM97893", "GSM97894", "GSM97895", "GSM97896", "GSM97897", "GSM97898", "GSM97899", "GSM97900", "GSM97901", "GSM97902", "GSM97903", "GSM97904", "GSM97905", "GSM97906", "GSM97907", "GSM97908", "GSM97909", "GSM97910", "GSM97911", "GSM97912", "GSM97913", "GSM97914", "GSM97915", "GSM97916", "GSM97917", "GSM97918", "GSM97919", "GSM97920", "GSM97921", "GSM97922", "GSM97923", "GSM97924", "GSM97925", "GSM97926", "GSM97927", "GSM97928", "GSM97929", "GSM97930", "GSM97931", "GSM97932", "GSM97933", "GSM97934", "GSM97935", "GSM97936", "GSM97937", "GSM97938", "GSM97939", "GSM97940", "GSM97941", "GSM97942", "GSM97943", "GSM97944", "GSM97945", "GSM97946", "GSM97947", "GSM97948", "GSM97949", "GSM97950", "GSM97951", "GSM97952", "GSM97953", "GSM97954", "GSM97955", "GSM97956", "GSM97957", "GSM97958", "GSM97959", "GSM97960", "GSM97961", "GSM97962", "GSM97963", "GSM97964", "GSM97965", "GSM97966", "GSM97967", "GSM97968", "GSM97969", "GSM97970", "GSM97971", "GSM97972"], "sample_count": 180, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data of glioma samples from Henry Ford Hospital", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE50161", "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=GSE50161", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE50161", "version": null, "note": "The data used for analysis in this study are available from the Cancer Genome Atlas and the Gene Expression Omnibus database freely.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used for analysis in this study are available from the Cancer Genome Atlas and the Gene Expression Omnibus database freely.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1214834", "GSM1214835", "GSM1214836", "GSM1214837", "GSM1214838", "GSM1214839", "GSM1214840", "GSM1214841", "GSM1214842", "GSM1214843", "GSM1214844", "GSM1214845", "GSM1214846", "GSM1214847", "GSM1214848", "GSM1214849", "GSM1214850", "GSM1214851", "GSM1214852", "GSM1214853", "GSM1214854", "GSM1214855", "GSM1214856", "GSM1214857", "GSM1214858", "GSM1214859", "GSM1214860", "GSM1214861", "GSM1214862", "GSM1214863", "GSM1214864", "GSM1214865", "GSM1214866", "GSM1214867", "GSM1214868", "GSM1214869", "GSM1214870", "GSM1214871", "GSM1214872", "GSM1214873", "GSM1214874", "GSM1214875", "GSM1214876", "GSM1214877", "GSM1214878", "GSM1214879", "GSM1214880", "GSM1214881", "GSM1214882", "GSM1214883", "GSM1214884", "GSM1214885", "GSM1214886", "GSM1214887", "GSM1214888", "GSM1214889", "GSM1214890", "GSM1214891", "GSM1214892", "GSM1214893", "GSM1214894", "GSM1214895", "GSM1214896", "GSM1214897", "GSM1214898", "GSM1214899", "GSM1214900", "GSM1214901", "GSM1214902", "GSM1214903", "GSM1214904", "GSM1214905", "GSM1214906", "GSM1214907", "GSM1214908", "GSM1214909", "GSM1214910", "GSM1214911", "GSM1214912", "GSM1214913", "GSM1214914", "GSM1214915", "GSM1214916", "GSM1214917", "GSM1214918", "GSM1214919", "GSM1214920", "GSM1214921", "GSM1214922", "GSM1214923", "GSM1214924", "GSM1214925", "GSM1214926", "GSM1214927", "GSM1214928", "GSM1214929", "GSM1214930", "GSM1214931", "GSM1214932", "GSM1214933", "GSM1214934", "GSM1214935", "GSM1214936", "GSM1214937", "GSM1214938", "GSM1214939", "GSM1214940", "GSM1214941", "GSM1214942", "GSM1214943", "GSM1214944", "GSM1214945", "GSM1214946", "GSM1214947", "GSM1214948", "GSM1214949", "GSM1214950", "GSM1214951", "GSM1214952", "GSM1214953", "GSM1214954", "GSM1214955", "GSM1214956", "GSM1214957", "GSM1214958", "GSM1214959", "GSM1214960", "GSM1214961", "GSM1214962", "GSM1214963"], "sample_count": 130, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from human brain tumors and human normal brain", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE74187", "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=GSE74187", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE74187", "version": null, "note": "The data used for analysis in this study are available from the Cancer Genome Atlas and the Gene Expression Omnibus database freely.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used for analysis in this study are available from the Cancer Genome Atlas and the Gene Expression Omnibus database freely.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1912920", "GSM1912921", "GSM1912922", "GSM1912923", "GSM1912924", "GSM1912925", "GSM1912926", "GSM1912927", "GSM1912928", "GSM1912929", "GSM1912930", "GSM1912931", "GSM1912932", "GSM1912933", "GSM1912934", "GSM1912935", "GSM1912936", "GSM1912937", "GSM1912938", "GSM1912939", "GSM1912940", "GSM1912941", "GSM1912942", "GSM1912943", "GSM1912944", "GSM1912945", "GSM1912946", "GSM1912947", "GSM1912948", "GSM1912949", "GSM1912950", "GSM1912951", "GSM1912952", "GSM1912953", "GSM1912954", "GSM1912955", "GSM1912956", "GSM1912957", "GSM1912958", "GSM1912959", "GSM1912960", "GSM1912961", "GSM1912962", "GSM1912963", "GSM1912964", "GSM1912965", "GSM1912966", "GSM1912967", "GSM1912968", "GSM1912969", "GSM1912970", "GSM1912971", "GSM1912972", "GSM1912973", "GSM1912974", "GSM1912975", "GSM1912976", "GSM1912977", "GSM1912978", "GSM1912979"], "sample_count": 60, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Sixty Glioblastoma Multiforme (GBM) samples obtained from surgical excision with OS and PFS", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:31119182:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8ce71e7dee1da23975c2fd5467e35c7e5b1b16fb560cce3e5711ff5bd00f3c2a", "bytes": 1664, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#tab1", "version": null, "note": "The GO and KEGG terms enriched by upregulated DEGs.", "structure": {"pmcid": "PMC6500689", "section_index": 11, "section_title": "3.2. GO and KEGG Pathway Analysis for Overlapped DEGs", "row_count": 21, "column_count": 4}, "table": {"label": "Table 1", "caption": "The GO and KEGG terms enriched by upregulated DEGs.", "rows": [["Category", "Term", "Count", "P-Value"], ["GOTERM_BP_FAT", "GO:0030198~extracellular matrix organization", "14", "3.88E-12"], ["GOTERM_BP_FAT", "GO:0043062~extracellular structure organization", "16", "7.24E-12"], ["GOTERM_BP_FAT", "GO:0007049~cell cycle", "28", "2.27E-10"], ["GOTERM_BP_FAT", "GO:0000279~M phase", "19", "3.12E-10"], ["GOTERM_BP_FAT", "GO:0007067~mitosis", "16", "5.21E-10"], ["GOTERM_CC_FAT", "GO:0031012~extracellular matrix", "21", "6.61E-13"], ["GOTERM_CC_FAT", "GO:0005578~proteinaceous extracellular matrix", "19", "1.80E-11"], ["GOTERM_CC_FAT", "GO:0005576~extracellular region", "42", "1.61E-10"], ["GOTERM_CC_FAT", "GO:0044421~extracellular region part", "28", "8.32E-10"], ["GOTERM_CC_FAT", "GO:0044420~extracellular matrix part", "12", "9.61E-10"], ["GOTERM_MF_FAT", "GO:0005201~extracellular matrix structural constituent", "9", "2.58E-07"], ["GOTERM_MF_FAT", "GO:0048407~platelet-derived growth factor binding", "4", "6.59E-05"], ["GOTERM_MF_FAT", "GO:0004857~enzyme inhibitor activity", "9", "9.87E-04"], ["GOTERM_MF_FAT", "GO:0050840~extracellular matrix binding", "4", "0.001069556"], ["GOTERM_MF_FAT", "GO:0001871~pattern binding", "7", "0.001084076"], ["KEGG_PATHWAY", "hsa04512: ECM-receptor interaction", "10", "2.22E-09"], ["KEGG_PATHWAY", "hsa04510: Focal adhesion", "10", "4.37E-06"], ["KEGG_PATHWAY", "hsa04610: Complement and coagulation cascades", "6", "8.15E-05"], ["KEGG_PATHWAY", "hsa04110: Cell cycle", "5", "0.009122958"], ["KEGG_PATHWAY", "hsa04115: p53 signaling pathway", "4", "0.010179414"]], "row_count": 21, "column_count": 4, "numeric_cells": 60, "header_rows": 1, "locator": "section[11]/table-wrap[1]#tab1"}}, {"id": "asset:table:pmid:31119182:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:fac24e8d35e404678460616eb5c52579bffb5e10c99729a2e164e7fed2b3724d", "bytes": 1641, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#tab2", "version": null, "note": "The GO and KEGG terms enriched by downregulated DEGs.", "structure": {"pmcid": "PMC6500689", "section_index": 11, "section_title": "3.2. GO and KEGG Pathway Analysis for Overlapped DEGs", "row_count": 21, "column_count": 4}, "table": {"label": "Table 2", "caption": "The GO and KEGG terms enriched by downregulated DEGs.", "rows": [["Category", "Term", "Count", "P-Value"], ["GOTERM_BP_FAT", "GO:0007268~synaptic transmission", "52", "1.62E-31"], ["GOTERM_BP_FAT", "GO:0019226~transmission of nerve impulse", "54", "5.18E-30"], ["GOTERM_BP_FAT", "GO:0007267~cell-cell signaling", "57", "4.96E-21"], ["GOTERM_BP_FAT", "GO:0006836~neurotransmitter transport", "23", "2.20E-18"], ["GOTERM_BP_FAT", "GO:0050877~neurological system process", "72", "3.01E-15"], ["GOTERM_CC_FAT", "GO:0045202~synapse", "63", "1.62E-35"], ["GOTERM_CC_FAT", "GO:0044456~synapse part", "51", "7.00E-32"], ["GOTERM_CC_FAT", "GO:0043005~neuron projection", "50", "4.79E-24"], ["GOTERM_CC_FAT", "GO:0008021~synaptic vesicle", "25", "1.28E-20"], ["GOTERM_CC_FAT", "GO:0030054~cell junction", "49", "1.50E-15"], ["GOTERM_MF_FAT", "GO:0022836~gated channel activity", "36", "6.73E-16"], ["GOTERM_MF_FAT", "GO:0005216~ion channel activity", "39", "3.23E-15"], ["GOTERM_MF_FAT", "GO:0015267~channel activity", "40", "4.98E-15"], ["GOTERM_MF_FAT", "GO:0022803~passive transmembrane transporter activity", "40", "5.43E-15"], ["GOTERM_MF_FAT", "GO:0022838~substrate specific channel activity", "39", "8.74E-15"], ["KEGG_PATHWAY", "hsa04080: Neuroactive ligand-receptor interaction", "25", "3.52E-10"], ["KEGG_PATHWAY", "hsa04020: Calcium signaling pathway", "21", "4.34E-10"], ["KEGG_PATHWAY", "hsa04720: Long-term potentiation", "9", "8.19E-05"], ["KEGG_PATHWAY", "hsa04012: ErbB signaling pathway", "8", "0.00232"], ["KEGG_PATHWAY", "hsa04010: MAPK signaling pathway", "13", "0.010508"]], "row_count": 21, "column_count": 4, "numeric_cells": 60, "header_rows": 1, "locator": "section[11]/table-wrap[2]#tab2"}}, {"id": "asset:table:pmid:31119182:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:db7eb51c115fa77fbea4ee0fe8ad0f215965a5fe7a96a5d99a72469be250c167", "bytes": 1039, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#tab3", "version": null, "note": "The statistical results of the connectivity of the network.", "structure": {"pmcid": "PMC6500689", "section_index": 12, "section_title": "3.3. PPI Network and Hub Genes", "row_count": 21, "column_count": 5}, "table": {"label": "Table 3", "caption": "The statistical results of the connectivity of the network.", "rows": [["Gene", "MCC", "DMNC", "MNC", "Degree"], ["TOP2A", "9.22E+13", "0.87325", "40", "56"], ["CDK1", "9.22E+13", "0.68829", "47", "47"], ["VEGFA", "5763", "0.18902", "40", "43"], ["SYT1", "4.37E+07", "0.37425", "40", "42"], ["CDC20", "9.22E+13", "1.01161", "34", "37"], ["KIF4A", "9.22E+13", "0.98669", "34", "36"], ["CALB1", "4586", "0.27262", "33", "35"], ["BDNF", "7597", "0.33146", "32", "35"], ["SYP", "3760934", "0.39583", "33", "35"], ["DLGAP5", "9.22E+13", "1.1534", "33", "35"], ["KIF20A", "9.22E+13", "1.05547", "35", "35"], ["TTK", "9.22E+13", "1.10629", "34", "35"], ["NDC80", "9.22E+13", "1.13243", "33", "35"], ["GNG3", "7267294", "0.41708", "32", "34"], ["CEP55", "9.22E+13", "1.07639", "34", "34"], ["SYN1", "3799485", "0.41397", "31", "34"], ["PBK", "9.22E+13", "1.09881", "34", "34"], ["CDCA8", "9.22E+13", "1.1038", "34", "34"], ["TPX2", "9.22E+13", "1.11408", "33", "34"], ["RRM2", "9.22E+13", "1.03281", "33", "34"]], "row_count": 21, "column_count": 5, "numeric_cells": 84, "header_rows": 1, "locator": "section[12]/table-wrap[1]#tab3"}}, {"id": "asset:table:pmid:31119182:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7610dfa8aea15ca5a311f1252d771c000134cccf50ea1e6272ce11e47ef34dc5", "bytes": 1595, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#tab4", "version": null, "note": "The GO and KEGG terms enriched by 20 hub genes.", "structure": {"pmcid": "PMC6500689", "section_index": 13, "section_title": "3.4. Function and Survival Analysis of the Hub Genes", "row_count": 13, "column_count": 5}, "table": {"label": "Table 4", "caption": "The GO and KEGG terms enriched by 20 hub genes.", "rows": [["Category", "Term", "count", "P-Value", "Genes"], ["GOTERM_BP_FAT", "GO:0000279~M phase", "9", "6.73E-09", "CDK1, CDCA8, DLGAP5, TPX2, TTK, CDC20, NDC80, CEP55, PBK"], ["GOTERM_BP_FAT", "GO:0000280~nuclear division", "8", "1.17E-08", "CDK1, CDCA8, DLGAP5, TPX2, CDC20, NDC80, CEP55, PBK"], ["GOTERM_BP_FAT", "GO:0007067~mitosis", "8", "1.17E-08", "CDK1, CDCA8, DLGAP5, TPX2, CDC20, NDC80, CEP55, PBK"], ["GOTERM_BP_FAT", "GO:0000087~M phase of mitotic cell cycle", "8", "1.32E-08", "CDK1, CDCA8, DLGAP5, TPX2, CDC20, NDC80, CEP55, PBK"], ["GOTERM_BP_FAT", "GO:0048285~organelle fission", "8", "1.54E-08", "CDK1, CDCA8, DLGAP5, TPX2, CDC20, NDC80, CEP55, PBK"], ["GOTERM_CC_FAT", "GO:0015630~microtubule cytoskeleton", "10", "1.60E-08", "CDK1, CDCA8, KIF4A, DLGAP5, TPX2, TTK, CDC20, CEP55, TOP2A, KIF20A"], ["GOTERM_BP_FAT", "GO:0000278~mitotic cell cycle", "9", "1.69E-08", "CDK1, CDCA8, DLGAP5, TPX2, TTK, CDC20, NDC80, CEP55, PBK"], ["GOTERM_CC_FAT", "GO:0005819~spindle", "7", "3.46E-08", "CDK1, CDCA8, KIF4A, DLGAP5, TPX2, TTK, CDC20"], ["GOTERM_BP_FAT", "GO:0022403~cell cycle phase", "9", "4.04E-08", "CDK1, CDCA8, DLGAP5, TPX2, TTK, CDC20, NDC80, CEP55, PBK"], ["GOTERM_BP_FAT", "GO:0022402~cell cycle process", "9", "4.43E-07", "CDK1, CDCA8, DLGAP5, TPX2, TTK, CDC20, NDC80, CEP55, PBK"], ["KEGG_PATHWAY", "hsa04110: Cell cycle", "3", "0.008429", "CDK1, TTK, CDC20"], ["KEGG_PATHWAY", "hsa04115: p53 signaling pathway", "2", "0.077638", "CDK1, RRM2"]], "row_count": 13, "column_count": 5, "numeric_cells": 47, "header_rows": 1, "locator": "section[13]/table-wrap[1]#tab4"}}], "gaps": ["asset:data:geo:GSE4290 not downloaded", "asset:data:geo:GSE4290 licence not read", "asset:data:geo:GSE50161 not downloaded", "asset:data:geo:GSE50161 licence not read", "asset:data:geo:GSE74187 not downloaded", "asset:data:geo:GSE74187 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "Then we utilized the univariate Cox regression analysis and log rank test to draw the survival curves to explore the prognostic related value of the hub genes based on TCGA datasets."}}, {"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": 0.8, "band": "high", "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": 0.8, "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": "protein-protein interaction"}}, {"id": "method-5", "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": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE4290", "GSE50161", "GSE74187"], "resolved_accessions": ["GSE4290", "GSE50161", "GSE74187"], "statements": ["The data used for analysis in this study are available from the Cancer Genome Atlas and the Gene Expression Omnibus database freely."], "basis": "The paper names GSE4290, GSE50161, GSE74187 in Gene Expression Omnibus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:31119182", "data:geo:GSE4290", "asset:table:pmid:31119182:1", "asset:table:pmid:31119182:2", "asset:table:pmid:31119182:3", "asset:table:pmid:31119182:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE4290"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:15:05Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 31367, "completion_tokens": 1726, "cached_tokens": 10504}}, "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:31119182", "type": "paper", "label": "pmid:31119182"}, {"id": "source:pmid:31119182", "type": "manuscript", "label": "PMID 31119182 full text"}, {"id": "data:geo:GSE4290", "type": "dataset", "label": "GEO GSE4290"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31119182", "type": "paper", "label": "pmid:31119182"}, {"id": "source:pmid:31119182", "type": "manuscript", "label": "PMID 31119182 full text"}, {"id": "data:geo:GSE4290", "type": "dataset", "label": "GEO GSE4290"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31119182", "type": "extraction", "used": ["source:pmid:31119182"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE4290", "type": "accession_resolution", "used": ["data:geo:GSE4290"], "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:31119182", "parent_hash": "sha256:6bd6030a431a91950e40d6b5edea7e0f7c117b3555c22524c240f6f35e28b1da", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE4290 licence not read", "asset:data:geo:GSE4290 not downloaded", "asset:data:geo:GSE50161 licence not read", "asset:data:geo:GSE50161 not downloaded", "asset:data:geo:GSE74187 licence not read", "asset:data:geo:GSE74187 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Then we utilized the univariate Cox regression analysis and log rank test to draw the survival curves to explore the prognostic related value of the hub genes based on TCGA datasets."], "order_basis": "analysis_only", "id": "assay:1"}]}