{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31528121", "kind": "science-record", "revision": 7, "content_hash": "sha256:00b2232f76e4ba5cd62574f43dbc3d7d5e23aae2aa2722dd0b2a977bc7f272c2", "created_at": "2026-11-01T15:40:49Z", "updated_at": "2026-11-01T22:00:50Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Prognostic significance of TOP2A in non-small cell lung cancer revealed by bioinformatic analysis.", "doi": "10.1186/s12935-019-0956-1", "pmid": "31528121", "authors": ["Wenxia Ma", "Bin Wang", "Yaping Zhang", "Ziyue Wang", "Dan Niu", "Siyu Chen", "Zhirong Zhang", "Ningning Shen", "Weixia Han", "Xiaoqin Zhang", "Rong Wei", "Chen Wang"], "journal": "Cancer cell international", "year": 2019, "abstract": "BACKGROUND: Lung cancer has been a common malignant tumor with a leading cause of morbidity and mortality, current molecular targets are woefully lacking comparing to the highly progressive cancer. The study is designed to identify new prognostic predictors and potential gene targets based on bioinformatic analysis of Gene Expression Omnibus (GEO) database.\nMETHODS: Four cDNA expression profiles GSE19188, GSE101929, GSE18842 and GSE33532 were chosen from GEO database to analyze the differently expressed genes (DEGs) between non-small cell lung cancer (NSCLC) and normal lung tissues. After the DEGs functions were analyzed, the protein-protein interaction network (PPI) of DEGs were constructed, and the core gene in the network which has high connectivity degree with other genes was identified. We analyzed the association of the gene with the development of NSCLC as well as its prognosis. Lastly we explored the conceivable signaling mechanism of the gene regulation during the development of NSCLC.\nRESULTS: A total of 92 up regulated and 214 down regulated DEGs were shared in four cDNA expression profiles. Based on their PPI network, TOP2A was connected with most of other genes and was selected for further analysis. Kaplan-Meier overall survival analysis (OS) revealed that TOP2A was associated with worse NSCLC patients survival. And both GEPIA analysis and immunohistochemistry experiment (IHC) confirmed that TOP2A was aberrant gain of expression in cancer comparing to normal tissues. The clinical significance of TOP2A and probable signaling pathways it involved in were further explored, and a positive correlation between TOP2A and TPX2 expression was found in lung cancer tissues.\nCONCLUSION: Using bioinformatic analysis, we revealed that TOP2A could be adopted as a prognostic indicator of NSCLC and it potentially regulate cancer development through co-work with TPX2. However, more detailed experiments are needed to clarify its drug target role in clinical medical use.", "claims": [{"id": "claim-method", "statement": "In the study, we used Kaplan–Meier plotter to analyze the correlation between TOP2A gene and NSCLC patients OS, followed by drawing the survival curve.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31528121", "locator": "sections[6] \"Kaplan–Meier survival analysis\" paragraph 2", "quote": "In the study, we used Kaplan–Meier plotter to analyze the correlation between TOP2A gene and NSCLC patients OS, followed by drawing the survival curve."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data generated or analyzed during this study are included in this published article.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31528121", "locator": "sections[29] \"notes\" paragraph 1", "quote": "All data generated or analyzed during this study are included in this published article."}], "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:31528121"], "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:GSE101929"], "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:GSE101929"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31528121", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12935-019-0956-1", "sha256": "sha256:a0831813c5ffa83125859a023edc52ba9d8fdf035116aa44c67b13f8bc19d7b4", "bytes": 40489, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12935-019-0956-1", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6737627", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE101929", "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=GSE101929", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE101929", "version": null, "note": "All data generated or analyzed during this study are included in this published article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2718949", "GSM2718950", "GSM2718951", "GSM2718952", "GSM2718953", "GSM2718954", "GSM2718955", "GSM2718956", "GSM2718957", "GSM2718958", "GSM2718959", "GSM2718960", "GSM2718961", "GSM2718962", "GSM2718963", "GSM2718964", "GSM2718965", "GSM2718966", "GSM2718967", "GSM2718968", "GSM2718969", "GSM2718970", "GSM2718971", "GSM2718972", "GSM2718973", "GSM2718974", "GSM2718975", "GSM2718976", "GSM2718977", "GSM2718978", "GSM2718979", "GSM2718980", "GSM2718981", "GSM2718982", "GSM2718983", "GSM2718984", "GSM2718985", "GSM2718986", "GSM2718987", "GSM2718988", "GSM2718989", "GSM2718990", "GSM2718991", "GSM2718992", "GSM2718993", "GSM2718994", "GSM2718995", "GSM2718996", "GSM2718997", "GSM2718998", "GSM2718999", "GSM2719000", "GSM2719001", "GSM2719002", "GSM2719003", "GSM2719004", "GSM2719005", "GSM2719006", "GSM2719007", "GSM2719008", "GSM2719009", "GSM2719010", "GSM2719011", "GSM2719012", "GSM2719013", "GSM2719014"], "sample_count": 66, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression data from African Americans and European Americans with non-small cell lung cancer", "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: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": "All data generated or analyzed during this study are included in this published article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article.", "access_statement_kind": "data_availability_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": "All data generated or analyzed during this study are included in this published article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article.", "access_statement_kind": "data_availability_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:GSE33532", "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=GSE33532", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33532", "version": null, "note": "All data generated or analyzed during this study are included in this published article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM835268", "GSM835269", "GSM835270", "GSM835271", "GSM835272", "GSM835273", "GSM835274", "GSM835275", "GSM835276", "GSM835277", "GSM835278", "GSM835279", "GSM835280", "GSM835281", "GSM835282", "GSM835283", "GSM835284", "GSM835285", "GSM835286", "GSM835287", "GSM835288", "GSM835289", "GSM835290", "GSM835291", "GSM835292", "GSM835293", "GSM835294", "GSM835295", "GSM835296", "GSM835297", "GSM835298", "GSM835299", "GSM835300", "GSM835301", "GSM835302", "GSM835303", "GSM835304", "GSM835305", "GSM835306", "GSM835307", "GSM835308", "GSM835309", "GSM835310", "GSM835311", "GSM835312", "GSM835313", "GSM835314", "GSM835315", "GSM835316", "GSM835317", "GSM835318", "GSM835319", "GSM835320", "GSM835321", "GSM835322", "GSM835323", "GSM835324", "GSM835325", "GSM835326", "GSM835327", "GSM835328", "GSM835329", "GSM835330", "GSM835331", "GSM835332", "GSM835333", "GSM835334", "GSM835335", "GSM835336", "GSM835337", "GSM835338", "GSM835339", "GSM835340", "GSM835341", "GSM835342", "GSM835343", "GSM835344", "GSM835345", "GSM835346", "GSM835347", "GSM835348", "GSM835349", "GSM835350", "GSM835351", "GSM835352", "GSM835353", "GSM835354", "GSM835355", "GSM835356", "GSM835357", "GSM835358", "GSM835359", "GSM835360", "GSM835361", "GSM835362", "GSM835363", "GSM835364", "GSM835365", "GSM835366", "GSM835367"], "sample_count": 100, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Intratumor heterogeneity of gene expression profiles in early stage non-small cell lung cancer (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": "asset:table:pmid:31528121:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5f51eb5e1533e57fc9000e323d0f12df0c835bbcd31ab39c87428a48ed6d865c", "bytes": 1069, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#Tab1", "version": null, "note": "The significant changes of TOP2A expression in transcription level between different types of lung cancer and normal tissues (ONCOMINE database)", "structure": {"pmcid": "PMC6737627", "section_index": 17, "section_title": "Aberrant TOP2A up regulation in human NSCLC cancer", "row_count": 11, "column_count": 6}, "table": {"label": "Table 1", "caption": "The significant changes of TOP2A expression in transcription level between different types of lung cancer and normal tissues (ONCOMINE database)", "rows": [["Subtype of lung cancer", "P-value", "Fold change", "Rank (%)", "Sample", "References"], ["Lung adenocarcinoma", "1.65E−5", "4.578", "1", "9", "Yamagata"], ["Squamous cell lung carcinoma", "2.84E−6", "4.284", "1", "12", "Yamagata"], ["Lung adenocarcinoma", "1.13E−19", "11.812", "1", "110", "Hou"], ["squamous cell lung carcinoma", "2.34E−38", "23.698", "1", "92", "Hou"], ["Large cell lung carcinoma", "6.08E−9", "24.158", "1", "84", "Hou"], ["Squamous cell lung carcinoma", "7.26E−9", "35.709", "1", "38", "Bhattacharjee"], ["Small cell lung carcinoma", "8.63e−8", "12.935", "1", "23", "Bhattacharjee"], ["Lung adenocarcinoma", "2.17E−5", "3.222", "2", "46", "Garber"], ["Squamous cell lung carcinoma", "1.53E−6", "4.478", "1", "19", "Garber"], ["Large cell lung carcinoma", "3.82E−5", "4.043", "1", "10", "Garber"]], "row_count": 11, "column_count": 6, "numeric_cells": 40, "header_rows": 1, "locator": "section[17]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:31528121:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1ecbba0ff11a56b06027d037a3e5028c144c70ba1be3bea76160b4df2ee096f2", "bytes": 1567, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#Tab2", "version": null, "note": "The relationship between TOP2A and NSCLC clinical pathological parameters", "structure": {"pmcid": "PMC6737627", "section_index": 18, "section_title": "IHC experiment validation of TOP2A gain of expression", "row_count": 39, "column_count": 4}, "table": {"label": "Table 2", "caption": "The relationship between TOP2A and NSCLC clinical pathological parameters", "rows": [["Group", "TOP2A", "P value"], ["−", "+"], ["Histological subtype"], ["Adenocarcinoma", "48 (78.7%)", "13 (21.3%)", "P = 0.000"], ["Squamous carcinoma", "20 (43.5%)", "26 (56.5%)"], ["Gender"], ["Male", "35 (51.5%)", "33 (48.5%)", "P = 0.001"], ["Female", "33 (84.6%)", "6 (15.4%)"], ["Age"], ["< 55", "15 (75.0%)", "5 (25.0%)", "P = 0.238"], ["≥ 55", "53 (60.9%)", "34 (39.1%)"], ["Smoke"], ["No", "34 (79.1%)", "9 (20.9%)", "P = 0.006"], ["Yes", "34 (53.1%)", "30 (46.9%)"], ["Location"], ["Upper lobe", "31 (58.5%)", "22 (41.5%)", "P = 0.521"], ["Middle lobe", "7 (63.6%)", "4 (36.4%)"], ["Lower lobe", "30 (69.8%)", "13 (30.2%)"], ["Tumor size"], ["< 2 cm", "13 (76.5%)", "4 (23.5%)", "P = 0.228"], ["≥ 2 cm", "55 (61.6%)", "35 (38.9%)"], ["Differentiation poorly"], ["Differentiated", "13 (54.2%)", "11 (45.8%)", "P = 0.182"], ["Moderately differentiated", "47 (63.5%)", "27 (36.5%)"], ["Well differentiated", "8 (88.9%)", "1 (11.1%)"], ["p-Stage"], ["I", "22 (64.7%)", "12 (35.3%)", "P = 0.907"], ["II", "19 (67.9%)", "9 (32.1%)"], ["III", "11 (57.9%)", "8 (42.1%)"], ["IV", "16 (61.5%)", "10 (38.5%)"], ["Invasion of capsule"], ["No", "42 (68.9%)", "19 (31.1%)", "P = 0.190"], ["Yes", "26 (56.5%)", "20 (43.5%)"], ["Invasion of bronchial stump"], ["No", "63 (65.6%)", "33 (34.4%)", "P = 0.188"], ["Yes", "5 (45.5%)", "6 (54.5%)"], ["LN metastasis"], ["−", "46 (62.2%)", "28 (37.8%)", "P = 0.656"], ["+", "22 (66.7%)", "11 (33.3%)"]], "row_count": 39, "column_count": 4, "numeric_cells": 67, "header_rows": 2, "locator": "section[18]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:31528121:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4fe32492dd5ddaf5c024cfa2e36f1e16716b8b3a5aee298138240dbbd3952c5f", "bytes": 723, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[1]#Tab3", "version": null, "note": "Cox proportional hazards regression on NSCLC overall survival", "structure": {"pmcid": "PMC6737627", "section_index": 19, "section_title": "TCGA data explored independent prognostic indicator value of TOP2A in adenocarcinoma", "row_count": 10, "column_count": 7}, "table": {"label": "Table 3", "caption": "Cox proportional hazards regression on NSCLC overall survival", "rows": [["Variables", "Lung adenocarcinoma", "Lung squamous cell carcinoma"], ["Hazard ratio", "95% CI", "P value", "Hazard ratio", "95% CI", "P value"], ["T"], ["T1 vs T2 vs T3 vs T4", "1.356", "1.104–1.665", "0.004", "1.275", "0.998–1.630", "0.052"], ["N"], ["N0 vs N1–3", "1.839", "1.198–2.822", "0.005", "1.097", "0.726–1.657", "0.66"], ["M"], ["M0 vs M1", "1.031", "0.865–1.229", "0.735", "1.235", "1.017–1.500", "0.033"], ["TOP2A expression"], ["< median vs > median", "0.663", "0.500–0.879", "0.004", "1.246", "0.914–1.699", "0.064"]], "row_count": 10, "column_count": 7, "numeric_cells": 27, "header_rows": 2, "locator": "section[19]/table-wrap[1]#Tab3"}}, {"id": "asset:table:pmid:31528121:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d4cb7cbcf01f876c42ba0b4c5fadeefaf07d2b209a06a5ac9a02b4fb85b3cd8d", "bytes": 800, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#Tab4", "version": null, "note": "Biological process events centered on TOP2A", "structure": {"pmcid": "PMC6737627", "section_index": 20, "section_title": "TOP2A centered signaling pathways", "row_count": 6, "column_count": 5}, "table": {"label": "Table 4", "caption": "Biological process events centered on TOP2A", "rows": [["Description", "Counts", "Background gene counts", "FDR", "Matching proteins in the network"], ["Mitotic cell cycle", "10", "628", "9.19E−12", "BUB1, CCNB2, CDC20, CDK1, DLGAP5, NCAPG, PBK, TOP2A, TPX2, UBE2C"], ["Cell division", "9", "483", "6.67E−11", "BUB1, CCNB2, CDC20, CDK1, NCAPG, TOP1, TOP2A, TPX2, UBE2C"], ["Mitotic cell cycle process", "9", "564", "1.76E−10", "BUB1, CCNB2, CDC20, CDK1, DLGAP5, NCAPG, TOP2A, TPX2, UBE2C"], ["Nuclear division", "7", "268", "4.29E−09", "BUB1, CDC20, DLGAP5, NCAPG, TOP2A, TPX2, UBE2C"], ["Chromosome segregation", "6", "253", "1.89E−07", "BUB1, CDC20, DLGAP5, NCAPG, TOP1, TOP2A"]], "row_count": 6, "column_count": 5, "numeric_cells": 20, "header_rows": 1, "locator": "section[20]/table-wrap[1]#Tab4"}}, {"id": "asset:table:pmid:31528121:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b942dbdb59423a3020954188622fbbbb00c8fb1ef3793963fd43ff70fc17c9fa", "bytes": 804, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[2]#Tab5", "version": null, "note": "KEGG signaling pathways centered on TOP2A", "structure": {"pmcid": "PMC6737627", "section_index": 20, "section_title": "TOP2A centered signaling pathways", "row_count": 9, "column_count": 5}, "table": {"label": "Table 5", "caption": "KEGG signaling pathways centered on TOP2A", "rows": [["Term description", "Counts", "Background gene counts", "FDR", "Matching proteins in the network"], ["Cell cycle", "4", "123", "5.57E−06", "BUB1, CCNB2, CDC20, CDK1"], ["Oocyte meiosis", "4", "116", "5.57E−06", "BUB1, CCNB2, CDC20, CDK1"], ["Progesterone-mediated oocyte maturation", "3", "94", "8.19E−05", "BUB1, CCNB2, CDK1"], ["p53 signaling pathway", "2", "68", "0.0022", "CCNB2, CDK1"], ["Ubiquitin mediated proteolysis", "2", "134", "0.0066", "CDC20, UBE2C"], ["Cellular senescence", "2", "156", "0.0074", "CCNB2, CDK1"], ["Viral carcinogenesis", "2", "183", "0.0086", "CDC20, CDK1"], ["HTLV-I infection", "2", "250", "0.0137", "CCNB2, CDC20"]], "row_count": 9, "column_count": 5, "numeric_cells": 30, "header_rows": 1, "locator": "section[20]/table-wrap[2]#Tab5"}}], "gaps": ["asset:data:geo:GSE101929 not downloaded", "asset:data:geo:GSE101929 licence not read", "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:GSE33532 not downloaded", "asset:data:geo:GSE33532 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": "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-3", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "Chi-square"}}, {"id": "method-4", "family": null, "specific": null, "label": "Kaplan–Meier survival analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "In the study, we used Kaplan–Meier plotter to analyze the correlation between TOP2A gene and NSCLC patients OS, followed by drawing the survival curve."}}], "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", "GSE101929", "GSE18842", "GSE33532"], "resolved_accessions": ["GSE19188", "GSE101929", "GSE18842", "GSE33532"], "statements": ["All data generated or analyzed during this study are included in this published article."], "basis": "The paper names GSE19188, GSE101929, GSE18842, GSE33532 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": ["survival_km"], "assets": ["source:pmid:31528121", "data:geo:GSE101929", "asset:table:pmid:31528121:1", "asset:table:pmid:31528121:2", "asset:table:pmid:31528121:3", "asset:table:pmid:31528121:4", "asset:table:pmid:31528121:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE101929"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:16:29Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 30971, "completion_tokens": 4121, "cached_tokens": 784}}, "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:31528121", "type": "paper", "label": "pmid:31528121"}, {"id": "source:pmid:31528121", "type": "manuscript", "label": "PMID 31528121 full text"}, {"id": "data:geo:GSE101929", "type": "dataset", "label": "GEO GSE101929"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31528121", "type": "paper", "label": "pmid:31528121"}, {"id": "source:pmid:31528121", "type": "manuscript", "label": "PMID 31528121 full text"}, {"id": "data:geo:GSE101929", "type": "dataset", "label": "GEO GSE101929"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31528121", "type": "extraction", "used": ["source:pmid:31528121"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE101929", "type": "accession_resolution", "used": ["data:geo:GSE101929"], "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:31528121", "parent_hash": "sha256:4be595a08afba6fa74b8569d0d9713963d4a423e2e78fe32ab531a30082019df", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE101929 licence not read", "asset:data:geo:GSE101929 not downloaded", "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:GSE33532 licence not read", "asset:data:geo:GSE33532 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["tients survival. And both GEPIA analysis and immunohistochemistry experiment (IHC) confirmed that TOP2A was ab", "nalysis and immunohistochemistry experiment (IHC) confirmed that TOP2A was aberrant gain of e", "TOP2A between NSCLC and normal lung samples. Immunohistochemistry (IHC) experiment regents and tissue samples", "in were from the hospital supply department. Immunohistochemistry (IHC) experiment protocol IHC experiment was"], "order_basis": "paper_text_order:1429", "id": "assay:1"}, {"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": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T00:40:44+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}}}