{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28808310", "kind": "science-record", "revision": 8, "content_hash": "sha256:7e0d170457d3cb21157b16c20196469a2e15493e68871939d9493d4465fa5ea5", "created_at": "2026-11-01T15:40:27Z", "updated_at": "2026-11-01T21:59:28Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Genome-scale analysis identifies NEK2, DLGAP5 and ECT2 as promising diagnostic and prognostic biomarkers in human lung cancer.", "doi": "10.1038/s41598-017-08615-5", "pmid": "28808310", "authors": ["Yuan-Xiang Shi", "Ji-Ye Yin", "Yao Shen", "Wei Zhang", "Hong-Hao Zhou", "Zhao-Qian Liu"], "journal": "Scientific reports", "year": 2017, "abstract": "This study aims to identify promising biomarkers for the early detection of lung cancer and evaluate the prognosis of lung cancer patients. Genome-wide mRNA expression data obtained from the Gene Expression Omnibus (GSE19188, GSE18842 and GSE40791), including 231 primary tumor samples and 210 normal samples, were used to discover differentially expressed genes (DEGs). NEK2, DLGAP5 and ECT2 were found to be highly expressed in tumor samples. These results were experimentally confirmed by quantitative reverse transcription-polymerase chain reaction (qRT-PCR). The elevated expression of the three candidate genes was also validated using the Cancer Genome Atlas (TCGA) datasets, which consist of 349 tumor and 58 normal tissues. Furthermore, we performed receiver operating characteristics (ROC) analysis to assess the diagnostic value of these lung cancer biomarkers, and the results suggested that NEK2, DLGAP5 and ECT2 expression levels could robustly distinguish lung cancer patients from normal subjects. Finally, Kaplan-Meier analysis revealed that elevated NEK2, DLGAP5 and ECT2 expression was negatively correlated with both overall survival (OS) and relapse-free survival (RFS). Taken together, these findings indicate that these three genes might be used as promising biomarkers for the early detection of lung cancer, as well as predicting the prognosis of lung cancer patients.", "claims": [{"id": "claim-method", "statement": "Survival analysis was carried out according to Kaplan–Meier analysis and the Log-rank test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28808310", "locator": "sections[14] \"Statistical analysis\" paragraph 2", "quote": "Survival analysis was carried out according to Kaplan–Meier analysis and the Log-rank test."}], "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:28808310"], "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:GSE18842"], "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:GSE18842"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28808310", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-017-08615-5", "sha256": "sha256:accad122c25c2ea3da6aaa75e76c05cc4b5f32b3982e1dd51362791bcc5d295c", "bytes": 32697, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-017-08615-5", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5556079", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE18842", "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=GSE18842", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE18842", "version": null, "note": "Three lung cancer datasets (GSE19188, GSE18842, GSE40791) generated from the Affymetrix platform and corresponding clinical information of lung cancer patients were retrieved from the Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo). GSE19188, including 91 tumors and 65 adjacent normal lung tissues, GSE18842, which includes 46 tumors and 45 controls, and GSE40791 containing 94 tumors and 100 non-tumor tissues.Validation datasets were acquired from the Cancer Genome Atlas (TCGA) data portal (http://tcga-data.nci. nih.gov).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Three lung cancer datasets (GSE19188, GSE18842, GSE40791) generated from the Affymetrix platform and corresponding clinical information of lung cancer patients were retrieved from the Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo). GSE19188, including 91 tumors and 65 adjacent normal lung tissues, GSE18842, which includes 46 tumors and 45 controls, and GSE40791 containing 94 tumors and 100 non-tumor tissues.Validation datasets were acquired from the Cancer Genome Atlas (TCGA) data portal (http://tcga-data.nci. nih.gov).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM466947", "GSM466948", "GSM466949", "GSM466950", "GSM466951", "GSM466952", "GSM466953", "GSM466954", "GSM466955", "GSM466956", "GSM466957", "GSM466958", "GSM466959", "GSM466960", "GSM466961", "GSM466962", "GSM466963", "GSM466964", "GSM466965", "GSM466966", "GSM466967", "GSM466968", "GSM466969", "GSM466970", "GSM466971", "GSM466972", "GSM466973", "GSM466974", "GSM466975", "GSM466976", "GSM466977", "GSM466978", "GSM466979", "GSM466980", "GSM466981", "GSM466982", "GSM466983", "GSM466984", "GSM466985", "GSM466986", "GSM466987", "GSM466988", "GSM466989", "GSM466990", "GSM466991", "GSM466992", "GSM466993", "GSM466994", "GSM466995", "GSM466996", "GSM466997", "GSM466998", "GSM466999", "GSM467000", "GSM467001", "GSM467002", "GSM467003", "GSM467004", "GSM467005", "GSM467006", "GSM467007", "GSM467008", "GSM467009", "GSM467010", "GSM467011", "GSM467012", "GSM467013", "GSM467014", "GSM467015", "GSM467016", "GSM467017", "GSM467018", "GSM467019", "GSM467020", "GSM467021", "GSM467022", "GSM467023", "GSM467024", "GSM467025", "GSM467026", "GSM467027", "GSM467028", "GSM467029", "GSM467030", "GSM467031", "GSM467032", "GSM467033", "GSM467034", "GSM467035", "GSM467036", "GSM467037"], "sample_count": 91, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression analysis of human lung cancer and control samples", "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:GSE19188", "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=GSE19188", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19188", "version": null, "note": "Three lung cancer datasets (GSE19188, GSE18842, GSE40791) generated from the Affymetrix platform and corresponding clinical information of lung cancer patients were retrieved from the Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo). GSE19188, including 91 tumors and 65 adjacent normal lung tissues, GSE18842, which includes 46 tumors and 45 controls, and GSE40791 containing 94 tumors and 100 non-tumor tissues.Validation datasets were acquired from the Cancer Genome Atlas (TCGA) data portal (http://tcga-data.nci. nih.gov).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Three lung cancer datasets (GSE19188, GSE18842, GSE40791) generated from the Affymetrix platform and corresponding clinical information of lung cancer patients were retrieved from the Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo). GSE19188, including 91 tumors and 65 adjacent normal lung tissues, GSE18842, which includes 46 tumors and 45 controls, and GSE40791 containing 94 tumors and 100 non-tumor tissues.Validation datasets were acquired from the Cancer Genome Atlas (TCGA) data portal (http://tcga-data.nci. nih.gov).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM475656", "GSM475657", "GSM475658", "GSM475659", "GSM475660", "GSM475661", "GSM475662", "GSM475663", "GSM475664", "GSM475665", "GSM475666", "GSM475667", "GSM475668", "GSM475669", "GSM475670", "GSM475671", "GSM475672", "GSM475673", "GSM475674", "GSM475675", "GSM475676", "GSM475677", "GSM475678", "GSM475679", "GSM475680", "GSM475681", "GSM475682", "GSM475683", "GSM475684", "GSM475685", "GSM475686", "GSM475687", "GSM475688", "GSM475689", "GSM475690", "GSM475691", "GSM475692", "GSM475693", "GSM475694", "GSM475695", "GSM475696", "GSM475697", "GSM475698", "GSM475699", "GSM475700", "GSM475701", "GSM475702", "GSM475703", "GSM475704", "GSM475705", "GSM475706", "GSM475707", "GSM475708", "GSM475709", "GSM475710", "GSM475711", "GSM475712", "GSM475713", "GSM475714", "GSM475715", "GSM475716", "GSM475717", "GSM475718", "GSM475719", "GSM475720", "GSM475721", "GSM475722", "GSM475723", "GSM475724", "GSM475725", "GSM475726", "GSM475727", "GSM475728", "GSM475729", "GSM475730", "GSM475731", "GSM475732", "GSM475733", "GSM475734", "GSM475735", "GSM475736", "GSM475737", "GSM475738", "GSM475739", "GSM475740", "GSM475741", "GSM475742", "GSM475743", "GSM475744", "GSM475745", "GSM475746", "GSM475747", "GSM475748", "GSM475749", "GSM475750", "GSM475751", "GSM475752", "GSM475753", "GSM475754", "GSM475755", "GSM475756", "GSM475757", "GSM475758", "GSM475759", "GSM475760", "GSM475761", "GSM475762", "GSM475763", "GSM475764", "GSM475765", "GSM475766", "GSM475767", "GSM475768", "GSM475769", "GSM475770", "GSM475771", "GSM475772", "GSM475773", "GSM475774", "GSM475775", "GSM475776", "GSM475777", "GSM475778", "GSM475779", "GSM475780", "GSM475781", "GSM475782", "GSM475783", "GSM475784", "GSM475785", "GSM475786", "GSM475787", "GSM475788", "GSM475789", "GSM475790", "GSM475791", "GSM475792", "GSM475793", "GSM475794", "GSM475795", "GSM475796", "GSM475797", "GSM475798", "GSM475799", "GSM475800", "GSM475801", "GSM475802", "GSM475803", "GSM475804", "GSM475805", "GSM475806", "GSM475807", "GSM475808", "GSM475809", "GSM475810", "GSM475811"], "sample_count": 156, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data for early stage NSCLC", "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:GSE40791", "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=GSE40791", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE40791", "version": null, "note": "Three lung cancer datasets (GSE19188, GSE18842, GSE40791) generated from the Affymetrix platform and corresponding clinical information of lung cancer patients were retrieved from the Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo). GSE19188, including 91 tumors and 65 adjacent normal lung tissues, GSE18842, which includes 46 tumors and 45 controls, and GSE40791 containing 94 tumors and 100 non-tumor tissues.Validation datasets were acquired from the Cancer Genome Atlas (TCGA) data portal (http://tcga-data.nci. nih.gov).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Three lung cancer datasets (GSE19188, GSE18842, GSE40791) generated from the Affymetrix platform and corresponding clinical information of lung cancer patients were retrieved from the Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo). GSE19188, including 91 tumors and 65 adjacent normal lung tissues, GSE18842, which includes 46 tumors and 45 controls, and GSE40791 containing 94 tumors and 100 non-tumor tissues.Validation datasets were acquired from the Cancer Genome Atlas (TCGA) data portal (http://tcga-data.nci. nih.gov).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1001510", "GSM1001511", "GSM1001512", "GSM1001513", "GSM1001514", "GSM1001515", "GSM1001516", "GSM1001517", "GSM1001518", "GSM1001519", "GSM1001520", "GSM1001521", "GSM1001522", "GSM1001523", "GSM1001524", "GSM1001525", "GSM1001526", "GSM1001527", "GSM1001528", "GSM1001529", "GSM1001530", "GSM1001531", "GSM1001532", "GSM1001533", "GSM1001534", "GSM1001535", "GSM1001536", "GSM1001537", "GSM1001538", "GSM1001539", "GSM1001540", "GSM1001541", "GSM1001542", "GSM1001543", "GSM1001544", "GSM1001545", "GSM1001546", "GSM1001547", "GSM1001548", "GSM1001549", "GSM1001550", "GSM1001551", "GSM1001552", "GSM1001553", "GSM1001554", "GSM1001555", "GSM1001556", "GSM1001557", "GSM1001558", "GSM1001559", "GSM1001560", "GSM1001561", "GSM1001562", "GSM1001563", "GSM1001564", "GSM1001565", "GSM1001566", "GSM1001567", "GSM1001568", "GSM1001569", "GSM1001570", "GSM1001571", "GSM1001572", "GSM1001573", "GSM1001574", "GSM1001575", "GSM1001576", "GSM1001577", "GSM1001578", "GSM1001579", "GSM1001580", "GSM1001581", "GSM1001582", "GSM1001583", "GSM1001584", "GSM1001585", "GSM1001586", "GSM1001587", "GSM1001588", "GSM1001589", "GSM1001590", "GSM1001591", "GSM1001592", "GSM1001593", "GSM1001594", "GSM1001595", "GSM1001596", "GSM1001597", "GSM1001598", "GSM1001599", "GSM1001600", "GSM1001601", "GSM1001602", "GSM1001603", "GSM1001604", "GSM1001605", "GSM1001606", "GSM1001607", "GSM1001608", "GSM1001609", "GSM1001610", "GSM1001611", "GSM1001612", "GSM1001613", "GSM1001614", "GSM1001615", "GSM1001616", "GSM1001617", "GSM1001618", "GSM1001619", "GSM1001620", "GSM1001621", "GSM1001622", "GSM1001623", "GSM1001624", "GSM1001625", "GSM1001626", "GSM1001627", "GSM1001628", "GSM1001629", "GSM1001630", "GSM1001631", "GSM1001632", "GSM1001633", "GSM1001634", "GSM1001635", "GSM1001636", "GSM1001637", "GSM1001638", "GSM1001639", "GSM1001640", "GSM1001641", "GSM1001642", "GSM1001643", "GSM1001644", "GSM1001645", "GSM1001646", "GSM1001647", "GSM1001648", "GSM1001649", "GSM1001650", "GSM1001651", "GSM1001652", "GSM1001653", "GSM1001654", "GSM1001655", "GSM1001656", "GSM1001657", "GSM1001658", "GSM1001659", "GSM1001660", "GSM1001661", "GSM1001662", "GSM1001663", "GSM1001664", "GSM1001665", "GSM1001666", "GSM1001667", "GSM1001668", "GSM1001669", "GSM1001670", "GSM1001671", "GSM1001672", "GSM1001673", "GSM1001674", "GSM1001675", "GSM1001676", "GSM1001677", "GSM1001678", "GSM1001679", "GSM1001680", "GSM1001681", "GSM1001682", "GSM1001683", "GSM1001684", "GSM1001685", "GSM1001686", "GSM1001687", "GSM1001688", "GSM1001689", "GSM1001690", "GSM1001691", "GSM1001692", "GSM1001693", "GSM1001694", "GSM1001695", "GSM1001696", "GSM1001697", "GSM1001698", "GSM1001699", "GSM1001700", "GSM1001701", "GSM1001702", "GSM1001703"], "sample_count": 194, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Usp44 binds centrin to regulate centrosome positioning and suppress tumorigenesis", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:28808310:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:114e65e760be95e55646e08b97127f85851bd7d772b0759dbf7aeaa533f71044", "bytes": 612, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#Tab1", "version": null, "note": "Clinicopathological characteristics of patients for clinical validation cohorts.", "structure": {"pmcid": "PMC5556079", "section_index": 4, "section_title": "Independent validation", "row_count": 20, "column_count": 2}, "table": {"label": "Table 1", "caption": "Clinicopathological characteristics of patients for clinical validation cohorts.", "rows": [["Clinical and pathological variables", "Clinical validation cohorts (N = 56)"], ["Age (years)"], ["<60", "29"], ["≥60", "27"], ["Gender"], ["Male", "54"], ["Female", "2"], ["Smoking status"], ["Smoker", "48"], ["Non-smoker", "8"], ["Clinical stage"], ["I-II", "28"], ["III-IV", "28"], ["Differentiation"], ["Well", "8"], ["Moderate", "27"], ["Poor", "21"], ["Lymph node metastasis"], ["Yes", "21"], ["No", "35"]], "row_count": 20, "column_count": 2, "numeric_cells": 16, "header_rows": 1, "locator": "section[4]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:28808310:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d89442df2f3bb1d5a1d2b3d07404d05e6d0d8a72fd534824c8e69628c721d64f", "bytes": 1406, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#Tab2", "version": null, "note": "Correlation between NEK2/ DLGAP5/ECT2 expression and clinical characteristics in 349 lung cancer patients.", "structure": {"pmcid": "PMC5556079", "section_index": 5, "section_title": "Correlation between the three biomarkers and clinicopathologic variables", "row_count": 21, "column_count": 11}, "table": {"label": "Table 2", "caption": "Correlation between NEK2/ DLGAP5/ECT2 expression and clinical characteristics in 349 lung cancer patients.", "rows": [["Characteristic", "n = 349", "NEK2 expression levels", "DLGAP5 expression levels", "ECT2 expression levels"], ["low (n = 174)", "high (n = 175)", "P", "low (n = 174)", "high (n = 175)", "P", "low (n = 174)", "high (n = 175)", "P"], ["Age (years)"], ["<65", "159", "69", "90", "0.027", "69", "90", "0.027", "74", "85", "0.257"], ["≥65", "190", "105", "85", "", "105", "85", "", "100", "90", ""], ["Gender"], ["Female", "190", "113", "77", "<0.001", "114", "76", "<0.001", "109", "81", "0.002"], ["Male", "159", "61", "98", "", "60", "99", "", "65", "94", ""], ["Clinical stage"], ["I & II", "281", "148", "133", "0.033", "149", "132", "0.016", "144", "137", "0.292"], ["III & IV", "68", "26", "42", "", "25", "43", "", "30", "38", ""], ["New tumor event"], ["YES", "99", "40", "59", "0.26", "39", "60", "0.014", "40", "59", "0.026"], ["NO", "250", "134", "116", "", "135", "115", "", "134", "116", ""], ["Pathologic T stage"], ["T1", "127", "82", "45", "<0.001", "79", "48", "0.001", "79", "48", "0.002"], ["T2", "180", "76", "104", "", "74", "106", "", "77", "103", ""], ["T3 + T4", "40", "16", "24", "", "21", "21", "", "18", "24", ""], ["Therapy outcome"], ["CR + PR", "145", "81", "64", "0.004", "81", "64", "0.01", "82", "63", "0.012"], ["SD + PD", "86", "31", "55", "", "33", "53", "", "34", "52", ""]], "row_count": 21, "column_count": 11, "numeric_cells": 118, "header_rows": 2, "locator": "section[5]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:28808310:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d80f4b16c9fb5b851707ba94be8c53b1a5541ce725fbf062f1b2e6227b11130c", "bytes": 1261, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#Tab3", "version": null, "note": "ROC curve analyses using NEK2/DLGAP5/ECT2 for distinguishing patients with lung cancer from normal control subjects.", "structure": {"pmcid": "PMC5556079", "section_index": 6, "section_title": "Diagnostic value of NEK2, DLGAP5 and ECT2 in lung cancer", "row_count": 13, "column_count": 7}, "table": {"label": "Table 3", "caption": "ROC curve analyses using NEK2/DLGAP5/ECT2 for distinguishing patients with lung cancer from normal control subjects.", "rows": [["", "Lung cancer datasets", "AUC value", "P value", "95% CI", "Cut off value", "Specificity, sensitivity"], ["NEK2", "GSE19188", "0.9272", "<0.0001", "0.8826–0.9719", "−0.718", "0.890, 0.923"], ["GSE18842", "1", "<0.0001", "1.0000–1.0000", "4.384", "1.000, 1.000"], ["GSE40791", "0.9665", "<0.0001", "0.9415–0.9915", "3.991", "0.926, 0.910"], ["TCGA", "0.9733", "<0.0001", "0.9647–0.9883", "−0.871", "0.868, 0.983"], ["DLGAP5", "GSE19188", "0.9158", "<0.0001", "0.8703–0.9614", "−0.401", "0.846, 0.892"], ["GSE18842", "1", "<0.0001", "1.0000–1.0000", "4.505", "1.000, 1.000"], ["GSE40791", "0.9572", "<0.0001", "0.9297–0.9847", "4.043", "0.883, 0.940"], ["TCGA", "0.973", "<0.0001", "0.9578–0.9881", "−1.338", "0.905, 0.983"], ["ECT2", "GSE19188", "0.9013", "<0.0001", "0.8495–0.9530", "−0.008", "0.802, 0.969"], ["GSE18842", "0.9986", "<0.0001", "0.9950–1.002", "6.439", "0.978, 1.000"], ["GSE40791", "0.9728", "<0.0001", "0.9488–0.9967", "8.008", "0.926, 0.950"], ["TCGA", "0.9601", "<0.0001", "0.9421–0.9782", "−0.628", "0.888, 0.948"]], "row_count": 13, "column_count": 7, "numeric_cells": 70, "header_rows": 1, "locator": "section[6]/table-wrap[1]#Tab3"}}, {"id": "asset:table:pmid:28808310:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b0b7b4260797b916add6a6cee7c9a3579b7903ccfe682f9c55cd2c7fec461e84", "bytes": 2398, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#Tab4", "version": null, "note": "Univariate and multivariate Cox regression analyses for overall survival and recurrence-free survival.", "structure": {"pmcid": "PMC5556079", "section_index": 7, "section_title": "Prognostic value of NEK2, DLGAP5 and ECT2 in lung cancer", "row_count": 26, "column_count": 5}, "table": {"label": "Table 4", "caption": "Univariate and multivariate Cox regression analyses for overall survival and recurrence-free survival.", "rows": [["Variable", "OS", "RFS"], ["HR (95% CI)", "P-value", "HR (95% CI)", "P-value"], ["Univariate analysis"], ["Age (<65 vs. ≥65)", "1.262(0.826–1.929)", "0.281", "1.415(0.943–2.123)", "0.094"], ["Gender (Female vs. Male)", "1.172(0.774–1.775)", "0.454", "0.992(0.666–1.477)", "0.968"], ["Clinical stage (I–II vs. III–IV)", "2.439(1.579–3.768)", "<0.001", "1.453(0.911–2.318)", "0.117"], ["Smoking history (yes vs. no)", "0.815(0.516–1.286)", "0.378", "0.847(0.551–1.301)", "0.448"], ["NEK2 (low vs. high)", "1.749(1.140–2.681)", "0.010", "1.738(1.161–2.601)", "0.007"], ["DLGAP5 (low vs. high)", "1.986(1.285–3.070)", "0.002", "1.798(1.201–2.692)", "0.004"], ["ECT2 (low vs. high)", "1.779(1.162–2.722)", "0.008", "1.752(1.172–2.619)", "0.006"], ["Multivariate analysis"], ["Age (<65 vs. ≥65)", "1.719(1.050–2.815)", "0.031", "1.919(1.210–3.043)", "0.006"], ["Gender (Female vs. Male)", "1.218(0.780–1.903)", "0.386", "0.991(0.650–1.513)", "0.968"], ["Clinical stage (I–II vs. III–IV)", "2.372(1.484–3.790)", "<0.001", "1.400(0.845–2.318)", "0.191"], ["Smoking history (yes vs. no)", "0.826(0.495–1.378)", "0.464", "0.779(0.489–1.241)", "0.294"], ["NEK2 (low vs. high)", "1.718(1.073–2.751)", "0.024", "1.771(1.142–2.745)", "0.011"], ["Age (<65 vs. ≥65)", "1.880(1.131–3.123)", "0.015", "1.978(1.240–3.153)", "0.004"], ["Gender (Female vs. Male)", "1.155(0.736–1.811)", "0.531", "0.935(0.610–1.432)", "0.756"], ["Clinical stage (I–II vs. III–IV)", "2.388(1.493–3.821)", "<0.001", "1.400(0.846–2.319)", "0.191"], ["Smoking history (yes vs. no)", "0.826(0.492–1.386)", "0.469", "0.769(0.482–1.226)", "0.270"], ["DLGAP5 (low vs. high)", "2.101(1.294–3.412)", "0.003", "1.895(1.218–2.949)", "0.005"], ["Age (<65 vs. ≥65)", "1.586(0.971–2.590)", "0.066", "1.742(1.101–2756)", "0.018"], ["Gender (Female vs. Male)", "1.242(0.793–1.945)", "0.344", "1.005(0.659–1.533)", "0.982"], ["Clinical stage (I–II vs. III–IV)", "2.501(1.565–3.996)", "<0.001", "1.465(0.886–2.421)", "0.137"], ["Smoking history (yes vs. no)", "0.820(0.491–1.372)", "0.450", "0.770(0483–1.227)", "0.272"], ["ECT2 (low vs. high)", "1.805(1.142–2.853)", "0.012", "1.699(1.105–2.612)", "0.016"]], "row_count": 26, "column_count": 5, "numeric_cells": 94, "header_rows": 2, "locator": "section[7]/table-wrap[1]#Tab4"}}], "gaps": ["asset:data:geo:GSE18842 not downloaded", "asset:data:geo:GSE18842 licence not read", "asset:data:geo:GSE19188 not downloaded", "asset:data:geo:GSE19188 licence not read", "asset:data:geo:GSE40791 not downloaded", "asset:data:geo:GSE40791 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": 0.7, "band": "medium", "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": "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": 0.8, "band": "high", "quote": "ROC curve"}}, {"id": "method-5", "family": null, "specific": null, "label": "Kaplan–Meier analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Survival analysis was carried out according to Kaplan–Meier analysis and the Log-rank 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": ["GSE19188", "GSE18842", "GSE40791"], "resolved_accessions": ["GSE19188", "GSE18842", "GSE40791"], "statements": ["Three lung cancer datasets (GSE19188, GSE18842, GSE40791) generated from the Affymetrix platform and corresponding clinical information of lung cancer patients were retrieved from the Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo). GSE19188, including 91 tumors and 65 adjacent normal lung tissues, GSE18842, which includes 46 tumors and 45 controls, and GSE40791 containing 94 tumors and 100 non-tumor tissues.Validation datasets were acquired from the Cancer Genome Atlas (TCGA) data portal (http://tcga-data.nci. nih.gov)."], "basis": "The paper names GSE19188, GSE18842, GSE40791 in Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA) 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:28808310", "data:geo:GSE18842", "asset:table:pmid:28808310:1", "asset:table:pmid:28808310:2", "asset:table:pmid:28808310:3", "asset:table:pmid:28808310:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE18842"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": null, "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 0, "usage": {}}, "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:28808310", "type": "paper", "label": "pmid:28808310"}, {"id": "source:pmid:28808310", "type": "manuscript", "label": "PMID 28808310 full text"}, {"id": "data:geo:GSE18842", "type": "dataset", "label": "GEO GSE18842"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28808310", "type": "paper", "label": "pmid:28808310"}, {"id": "source:pmid:28808310", "type": "manuscript", "label": "PMID 28808310 full text"}, {"id": "data:geo:GSE18842", "type": "dataset", "label": "GEO GSE18842"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28808310", "type": "extraction", "used": ["source:pmid:28808310"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE18842", "type": "accession_resolution", "used": ["data:geo:GSE18842"], "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:28808310", "parent_hash": "sha256:46991503ff44f96eb228c007786f821a64069cd6422778ff3377dc8474a919f1", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE18842 licence not read", "asset:data:geo:GSE18842 not downloaded", "asset:data:geo:GSE19188 licence not read", "asset:data:geo:GSE19188 not downloaded", "asset:data:geo:GSE40791 licence not read", "asset:data:geo:GSE40791 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": 0.7, "evidence": ["Kaplan-Meier"], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:36:34+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}