{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31010415", "kind": "science-record", "revision": 7, "content_hash": "sha256:cfaf1fad89e92b0e4fb80dba68772effba17174d0ca257fc8a5552c307c362b4", "created_at": "2026-11-01T15:40:44Z", "updated_at": "2026-11-01T22:00:30Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of significant genes with poor prognosis in ovarian cancer via bioinformatical analysis.", "doi": "10.1186/s13048-019-0508-2", "pmid": "31010415", "authors": ["Hao Feng", "Zhong-Yi Gu", "Qin Li", "Qiong-Hua Liu", "Xiao-Yu Yang", "Jun-Jie Zhang"], "journal": "Journal of ovarian research", "year": 2019, "abstract": "Ovarian cancer (OC) is the highest frequent malignant gynecologic tumor with very complicated pathogenesis. The purpose of the present academic work was to identify significant genes with poor outcome and their underlying mechanisms. Gene expression profiles of GSE36668, GSE14407 and GSE18520 were available from GEO database. There are 69 OC tissues and 26 normal tissues in the three profile datasets. Differentially expressed genes (DEGs) between OC tissues and normal ovarian (OV) tissues were picked out by GEO2R tool and Venn diagram software. Next, we made use of the Database for Annotation, Visualization and Integrated Discovery (DAVID) to analyze Kyoto Encyclopedia of Gene and Genome (KEGG) pathway and gene ontology (GO). Then protein-protein interaction (PPI) of these DEGs was visualized by Cytoscape with Search Tool for the Retrieval of Interacting Genes (STRING). There were total of 216 consistently expressed genes in the three datasets, including 110 up-regulated genes enriched in cell division, sister chromatid cohesion, mitotic nuclear division, regulation of cell cycle, protein localization to kinetochore, cell proliferation and Cell cycle, progesterone-mediated oocyte maturation and p53 signaling pathway, while 106 down-regulated genes enriched in palate development, blood coagulation, positive regulation of transcription from RNA polymerase II promoter, axonogenesis, receptor internalization, negative regulation of transcription from RNA polymerase II promoter and no significant signaling pathways. Of PPI network analyzed by Molecular Complex Detection (MCODE) plug-in, all 33 up-regulated genes were selected. Furthermore, for the analysis of overall survival among those genes, Kaplan-Meier analysis was implemented and 20 of 33 genes had a significantly worse prognosis. For validation in Gene Expression Profiling Interactive Analysis (GEPIA), 15 of 20 genes were discovered highly expressed in OC tissues compared to normal OV tissues. Furthermore, four genes (BUB1B, BUB1, TTK and CCNB1) were found to significantly enrich in the cell cycle pathway via re-analysis of DAVID. In conclusion, we have identified four significant up-regulated DEGs with poor prognosis in OC on the basis of integrated bioinformatical methods, which could be potential therapeutic targets for OC patients.", "claims": [{"id": "claim-method", "statement": "The log rank P value and hazard ratio (HR) with 95% confidence intervals were computed and showed on the plot.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31010415", "locator": "sections[7] \"Survival analysis and RNA sequencing expression of core genes\" paragraph 2", "quote": "The log rank P value and hazard ratio (HR) with 95% confidence intervals were computed and showed on the plot."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets used and/or analyzed in the present study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31010415", "locator": "sections[18] \"Availability of data and materials\" paragraph 2", "quote": "The datasets used and/or analyzed in the present study are available from the corresponding author on reasonable request."}], "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:31010415"], "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:GSE14407"], "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:GSE14407"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31010415", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s13048-019-0508-2", "sha256": "sha256:0b42f033726faddd350b81d84d83855ca772f06236d6f012d3fdef06645d22cf", "bytes": 31652, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s13048-019-0508-2", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6477749", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE14407", "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=GSE14407", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE14407", "version": null, "note": "The datasets used and/or analyzed in the present study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed in the present study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM359972", "GSM359973", "GSM359974", "GSM359975", "GSM359976", "GSM359977", "GSM359978", "GSM359979", "GSM359980", "GSM359981", "GSM359982", "GSM359983", "GSM359984", "GSM360039", "GSM360040", "GSM360041", "GSM360042", "GSM360043", "GSM360044", "GSM360045", "GSM360046", "GSM360047", "GSM360048", "GSM360049"], "sample_count": 24, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Ovarian Cancer gene expression profiling identifies the surface of the ovary as a stem cell niche", "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:GSE18520", "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=GSE18520", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE18520", "version": null, "note": "The datasets used and/or analyzed in the present study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed in the present study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM461348", "GSM461349", "GSM461350", "GSM461351", "GSM461352", "GSM461353", "GSM461354", "GSM461355", "GSM461356", "GSM461357", "GSM461358", "GSM461359", "GSM461360", "GSM461361", "GSM461362", "GSM461363", "GSM461364", "GSM461365", "GSM461366", "GSM461367", "GSM461368", "GSM461369", "GSM461370", "GSM461371", "GSM461372", "GSM461373", "GSM461374", "GSM461375", "GSM461376", "GSM461377", "GSM461378", "GSM461379", "GSM461380", "GSM461381", "GSM461382", "GSM461383", "GSM461384", "GSM461385", "GSM461386", "GSM461387", "GSM461388", "GSM461389", "GSM461390", "GSM461391", "GSM461392", "GSM461393", "GSM461394", "GSM461395", "GSM461396", "GSM461397", "GSM461398", "GSM461399", "GSM461400", "GSM462643", "GSM462644", "GSM462645", "GSM462646", "GSM462647", "GSM462648", "GSM462649", "GSM462650", "GSM462651", "GSM462652"], "sample_count": 63, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Whole-genome oligonucleotide expression analysis of papillary serous ovarian adenocarcinomas", "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:GSE36668", "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=GSE36668", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE36668", "version": null, "note": "The datasets used and/or analyzed in the present study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed in the present study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM898297", "GSM898298", "GSM898299", "GSM898300", "GSM898301", "GSM898302", "GSM898303", "GSM898304", "GSM898305", "GSM898306", "GSM898307", "GSM898308"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from serous ovarian carcinomas, serous ovarian borderline tumors and surface epithelium scrapings from normal ovaries", "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:31010415:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:faa85a2946daaae04abf667343bd9fd61cc5af1cbd6241d79393e7ed9aa305f6", "bytes": 1978, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#Tab1", "version": null, "note": "All 216 commonly differentially expressed genes (DEGs) were detected from three profile datasets, including 106 down-regulated genes and 110 up-regulated genes in the OC tissues compared to normal OV tissues", "structure": {"pmcid": "PMC6477749", "section_index": 9, "section_title": "Identifcation of DEGs in ovarian cancers", "row_count": 3, "column_count": 2}, "table": {"label": "Table 1", "caption": "All 216 commonly differentially expressed genes (DEGs) were detected from three profile datasets, including 106 down-regulated genes and 110 up-regulated genes in the OC tissues compared to normal OV tissues", "rows": [["DEGs", "Genes Name"], ["Up-regulated", "C1orf106 MPZL2 EHF KLK6 MMP7 KLHL14 IGF2BP3 CCNB1 FOXQ1 PROM2 SUSD2 CLDN4 DEFB1 MEOX1 SMIM22 KLK8 FOXM1 CDK1 SORT1 MUC1 KIF11 ELF3 E2F1 FOLR1 MAL SULT1C2 CENPU STON2 GRHL2 KIF14 KCCAT333 AURKB MTHFD2 LOC101929219///LOC100505650///C1orf186 KIAA1217 KIF4A MCM10 CBS SOX17 EPHX4 CDH6 MELK CDC20 CXXC5 AIF1L DCDC2 INHBB BUB1 PRR11 TRIP13 CDCA5 SLC2A1 DUXAP10 EPCAM HMGA2 RGS1 ECT2 DEPDC1 MTFR2 LPAR3 UBE2C CCNB2 LOC100288637///ARHGAP11B CRABP2 CD24 LINC00673///LINC00511 PRSS2 LOC613266 TTC39A PRC1 PSAT1 LRP8 PTH2R RRM2 SLC35F6///CENPA TOP2A WDR72 S100A2 PAX8 KIF15 WFDC2 TFAP2A BUB1B TIMELESS NR2F6 MECOM RAD51AP1 ESCO2 LYNX1 ESRP1 DTL FAM83D HMMR C12orf56 GPM6B LOC101928554 CENPK LCN2 PRAME KIAA0101 HMGA1 TTK NCAPG CP SLC52A2 LINC01296///DUXAP10 NEK2 CENPF NUSAP1 ST6GALNAC1"], ["Down-regulated", "MUM1L1 NAP1L2 CYP2U1 VGLL3 GHR NEFH TMEM255A PPM1K TSPAN8 BAMBI MICU3 OC101930363///LOC101928349///LOC100507387///FAM153C///FAM153A///FAM153B LOC100507387///FAM153A///FAM153B BDH2 DPYD ANTXR2 HLF PRSS35 THBD PRRX1 LY75-CD302///CD302///LY75 ABCA8 WDR17 ZFPM2 OMD TCF21 PDGFD KLF2 SNCAIP NEGR1 NT5E RUNX1T1 TRPC1 SNCA PLEKHH2 GAS1RR MTUS1 GPM6A CPED1 MGARP LSAMP EFEMP1 B3GALT2 CHGB DIRAS3 PRKAR2B FAM13C KCNT2 TMEM150C ECM2 GIPC2 OGN SNX29P2 ARX TCEAL2 NAP1L3 SDPR TCEAL7 NBEA CXorf57 CSGALNACT1 CYS1 CNTN1 AKAP12 MEOX2 COL14A1 CALCRL ALDH1A1 SMPD3 TBX3 WNT2B ANKRD29 NR2F1-AS1 MCC CBLN4 CELF2 ITM2A GNG11 PGR OGFOD1 TFPI GPRASP1 PEG3 PCDH9 HAND2-AS1 RBMS3 FGF13 PRDM5 MAF PDE8B SIGLEC11 TLE4 DCN PEX5L BNC2 GATM RNF128 LHX9 AOX1 AKT3 OLFML1 RNASE4 GATA4 NXPH2 NDN LOC100506718///FLRT2"]], "row_count": 3, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[9]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:31010415:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9e019f79efdda720ae65348059b9707ccd5e1f1e14f498c46957883234b9a0c4", "bytes": 3481, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#Tab2", "version": null, "note": "Gene ontology analysis of differentially expressed genes in ovarian cancer", "structure": {"pmcid": "PMC6477749", "section_index": 10, "section_title": "DEGs gene ontology and KEGG pathway analysis in ovarian cancers", "row_count": 33, "column_count": 7}, "table": {"label": "Table 2", "caption": "Gene ontology analysis of differentially expressed genes in ovarian cancer", "rows": [["Expression", "Category", "Term", "Count", "%", "p-Value", "FDR"], ["Up-regulated", "GOTERM_BP_DIRECT", "GO:0051301~cell division", "16", "15.24", "9.45E-10", "1.43E-06"], ["GOTERM_BP_DIRECT", "GO:0007067~mitotic nuclear division", "14", "13.33", "1.21E-09", "1.84E-06"], ["GOTERM_BP_DIRECT", "GO:0007062~sister chromatid cohesion", "8", "7.62", "1.76E-06", "0.002667"], ["GOTERM_BP_DIRECT", "GO:0051726~regulation of cell cycle", "8", "7.62", "6.07E-06", "0.009214"], ["GOTERM_BP_DIRECT", "GO:0034501~protein localization to kinetochore", "4", "3.81", "1.98E-05", "0.030061"], ["GOTERM_BP_DIRECT", "GO:0008283~cell proliferation", "11", "10.48", "3.81E-05", "0.057753"], ["GOTERM_CC_DIRECT", "GO:0005654~nucleoplasm", "37", "35.24", "8.26E-08", "9.94E-05"], ["GOTERM_CC_DIRECT", "GO:0030496~midbody", "9", "8.57", "3.99E-07", "4.80E-04"], ["GOTERM_CC_DIRECT", "GO:0005876~spindle microtubule", "6", "5.71", "3.37E-06", "0.004057"], ["GOTERM_CC_DIRECT", "GO:0005819~spindle", "8", "7.62", "3.49E-06", "0.004203"], ["GOTERM_CC_DIRECT", "GO:0005829~cytosol", "35", "33.33", "4.42E-05", "0.053183"], ["GOTERM_CC_DIRECT", "GO:0005634~nucleus", "48", "45.71", "5.52E-05", "0.066432"], ["GOTERM_MF_DIRECT", "GO:0005515~protein binding", "72", "68.57", "5.60E-07", "7.08E-04"], ["GOTERM_MF_DIRECT", "GO:0043565~sequence-specific DNA binding", "11", "10.48", "5.14E-04", "0.647343"], ["GOTERM_MF_DIRECT", "GO:0008017~microtubule binding", "7", "6.67", "9.63E-04", "1.210835"], ["GOTERM_MF_DIRECT", "GO:0008574~ATP-dependent microt-ubule motor activity, plus-end-directed", "3", "2.86", "0.003788", "4.685832"], ["GOTERM_MF_DIRECT", "GO:0019901~protein kinase binding", "8", "7.62", "0.0044544", "5.488301"], ["Down-regulated", "GOTERM_BP_DIRECT", "GO:0060021~palate development", "5", "4.91", "4.95E-04", "0.721802"], ["GOTERM_BP_DIRECT", "GO:0007596~blood coagulation", "6", "5.89", "0.001956", "2.823695"], ["GOTERM_BP_DIRECT", "GO:0045944~positive regulation of transcription from RNA polymerase II promoter", "12", "11.76", "0.00728", "10.1353"], ["GOTERM_BP_DIRECT", "GO:0000122~negative regulation of transcription from RNA polymerase II promoter", "10", "9.80", "0.00773", "10.72979"], ["GOTERM_BP_DIRECT", "GO:0007409~axonogenesis", "4", "3.92", "0.011841", "15.98884"], ["GOTERM_BP_DIRECT", "GO:0031623~receptor internalization", "3", "2.94", "0.018262", "23.62882"], ["GOTERM_CC_DIRECT", "GO:0031225~anchored component of membrane", "5", "4.90", "0.002893", "3.225113"], ["GOTERM_CC_DIRECT", "GO:0005576~extracellular region", "17", "16.67", "0.008777", "9.4952"], ["GOTERM_CC_DIRECT", "GO:0005578~proteinaceous extracellular matrix", "6", "5.88", "0.013131", "13.89424"], ["GOTERM_CC_DIRECT", "GO:0005615~extracellular space", "14", "13.72", "0.022365", "22.58432"], ["GOTERM_MF_DIRECT", "GO:0043565~sequence-specific DNA binding", "10", "9.80", "0.00117", "1.454993"], ["GOTERM_MF_DIRECT", "GO:0001078~transcriptional repressor activity, RNA polymerase II core promoter proximal region sequence-specific binding", "4", "3.92", "0.018506", "20.85873"], ["GOTERM_MF_DIRECT", "GO:0001085~RNA polymerase II transcription factor binding", "3", "2.94", "0.023394", "25.65558"], ["GOTERM_MF_DIRECT", "GO:0001077~transcriptional activator activity, RNA polymerase II core promoter proximal region sequence-specific binding", "5", "4.90", "0.031296", "32.84726"], ["GOTERM_MF_DIRECT", "GO:0008083~growth factor activity", "4", "3.92", "0.048426", "46.29421"]], "row_count": 33, "column_count": 7, "numeric_cells": 160, "header_rows": 1, "locator": "section[10]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:31010415:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d45fd9b81a414587c3844c7b254e3928338cf0ec24bef0ba97bc64ed00a1ad12", "bytes": 565, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[2]#Tab3", "version": null, "note": "KEGG pathway analysis of differentially expressed genes in ovarian cancer", "structure": {"pmcid": "PMC6477749", "section_index": 10, "section_title": "DEGs gene ontology and KEGG pathway analysis in ovarian cancers", "row_count": 4, "column_count": 6}, "table": {"label": "Table 3", "caption": "KEGG pathway analysis of differentially expressed genes in ovarian cancer", "rows": [["Pathway ID", "Name", "Count", "%", "p-Value", "Genes"], ["hsa04110", "Cell cycle", "8", "7.62", "7.31E-07", "CCNB1, E2F1, CDK1, CCNB2, BUB1, TTK, BUB1B, CDC20"], ["hsa04115", "p53 signaling pathway", "4", "3.81", "0.002934", "CCNB1, CDK1, CCNB2, RRM2"], ["hsa04914", "Progesterone-mediated oocyte maturation", "4", "3.81", "0.006123", "CCNB1, CDK1, CCNB2, BUB1"]], "row_count": 4, "column_count": 6, "numeric_cells": 14, "header_rows": 1, "locator": "section[10]/table-wrap[2]#Tab3"}}, {"id": "asset:table:pmid:31010415:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2aca246bb7a4d0850826f860ef58e00b31b270835231d55acc065fb312983249", "bytes": 542, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#Tab4", "version": null, "note": "The prognostic information of the 33 key candidate genes", "structure": {"pmcid": "PMC6477749", "section_index": 12, "section_title": "Analysis of core genes by the Kaplan Meier plotter and GEPIA", "row_count": 3, "column_count": 2}, "table": {"label": "Table 4", "caption": "The prognostic information of the 33 key candidate genes", "rows": [["Category", "Genes"], ["Genes with significantly worse survival (P < 0.05)", "BUB1 BUB1B CCNB1 CDCA5 CENPF CENPK DEPDC1 ECT2 FAM83D FOXM1 HMMR KIF11 KIF14 KIF15 MCM10 NCAPG RAD51AP1 TIMELESS TTK UBE2C"], ["Genes without significantly worse survival (P > 0.05)", "AURKB CCNB2 CDC20 DTL E2F1 KIAA0101 KIF4A MELK NEK2 NUSAP1 PRC1 RRM2 TRIP13"]], "row_count": 3, "column_count": 2, "numeric_cells": 4, "header_rows": 1, "locator": "section[12]/table-wrap[1]#Tab4"}}, {"id": "asset:table:pmid:31010415:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:99b2bc0c0e5f4f0ad1cb55e97bb5eed40eefc4167aeb628182b06cec4750c50f", "bytes": 426, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#Tab5", "version": null, "note": "Vadidation of 20 genes via GEPIA", "structure": {"pmcid": "PMC6477749", "section_index": 12, "section_title": "Analysis of core genes by the Kaplan Meier plotter and GEPIA", "row_count": 3, "column_count": 2}, "table": {"label": "Table 5", "caption": "Vadidation of 20 genes via GEPIA", "rows": [["Category", "Genes"], ["Genes with high expressed in OC (P < 0.05)", "BUB1 BUB1B CCNB1 CDCA5 CENPF DEPDC1 ECT2 FAM83D FOXM1 HMMR KIF11 NCAPG RAD51AP1 TTK UBE2C"], ["Genes without high expressed in OC (P > 0.05)", "CENPK KIF14 KIF15 MCM10 TIMELESS"]], "row_count": 3, "column_count": 2, "numeric_cells": 4, "header_rows": 1, "locator": "section[12]/table-wrap[2]#Tab5"}}, {"id": "asset:table:pmid:31010415:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e10906ff5c84e5a98109bcb892becd6d8426eabd270988f7ffcf8b9b47702076", "bytes": 420, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#Tab6", "version": null, "note": "Re-analysis of 15 selected genes via KEGG pathway enrichment", "structure": {"pmcid": "PMC6477749", "section_index": 13, "section_title": "Re-analysis of 15 selected genes via KEGG pathway enrichment", "row_count": 3, "column_count": 6}, "table": {"label": "Table 6", "caption": "Re-analysis of 15 selected genes via KEGG pathway enrichment", "rows": [["Pathway ID", "Name", "Count", "%", "p-Value", "Genes"], ["hsa04110", "Cell cycle", "4", "26.7", "1.1E-04", "CCNB1 BUB1 TTK BUB1B"], ["hsa04914", "Progesterone-mediated oocyte maturation", "2", "13.3", "7.3E-02", "CCNB1 BUB1"]], "row_count": 3, "column_count": 6, "numeric_cells": 8, "header_rows": 1, "locator": "section[13]/table-wrap[1]#Tab6"}}], "gaps": ["asset:data:geo:GSE14407 not downloaded", "asset:data:geo:GSE14407 licence not read", "asset:data:geo:GSE18520 not downloaded", "asset:data:geo:GSE18520 licence not read", "asset:data:geo:GSE36668 not downloaded", "asset:data:geo:GSE36668 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "The log rank P value and hazard ratio (HR) with 95% confidence intervals were computed and showed on the plot."}}, {"id": "method-2", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-3", "family": "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-4", "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": 0.8, "band": "high", "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": ["logrank_test"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: log_rank_test."}, "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": ["GSE36668", "GSE18520", "GSE14407"], "resolved_accessions": ["GSE36668", "GSE18520", "GSE14407"], "statements": ["The datasets used and/or analyzed in the present study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE36668, GSE18520, GSE14407 in NCBI-GEO (Gene Expression Omnibus) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["logrank_test"], "assets": ["source:pmid:31010415", "data:geo:GSE14407", "asset:table:pmid:31010415:1", "asset:table:pmid:31010415:2", "asset:table:pmid:31010415:3", "asset:table:pmid:31010415:4", "asset:table:pmid:31010415:5", "asset:table:pmid:31010415:6"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE14407"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:14:41Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 26736, "completion_tokens": 2713, "cached_tokens": 528}}, "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:31010415", "type": "paper", "label": "pmid:31010415"}, {"id": "source:pmid:31010415", "type": "manuscript", "label": "PMID 31010415 full text"}, {"id": "data:geo:GSE14407", "type": "dataset", "label": "GEO GSE14407"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31010415", "type": "paper", "label": "pmid:31010415"}, {"id": "source:pmid:31010415", "type": "manuscript", "label": "PMID 31010415 full text"}, {"id": "data:geo:GSE14407", "type": "dataset", "label": "GEO GSE14407"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31010415", "type": "extraction", "used": ["source:pmid:31010415"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE14407", "type": "accession_resolution", "used": ["data:geo:GSE14407"], "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:31010415", "parent_hash": "sha256:d711fb8fa713e776205423e0d7e73a4dc9e6757b6b73999b19c3bc93f341e4bf", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE14407 licence not read", "asset:data:geo:GSE14407 not downloaded", "asset:data:geo:GSE18520 licence not read", "asset:data:geo:GSE18520 not downloaded", "asset:data:geo:GSE36668 licence not read", "asset:data:geo:GSE36668 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": ["logrank_test"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The log rank P value and hazard ratio (HR) with 95% confidence intervals were computed and showed on the plot."], "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":"2026-11-04T02:45:47+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}}}