{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33250051", "kind": "science-record", "revision": 6, "content_hash": "sha256:5fccdb695401497907e7b0ee94b5a2d255f070f984d982ecc76e195b7de99cc6", "created_at": "2026-11-01T15:41:17Z", "updated_at": "2026-11-01T21:24:11Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "KLF7: a new candidate biomarker and therapeutic target for high-grade serous ovarian cancer.", "doi": "10.1186/s13046-020-01775-9", "pmid": "33250051", "authors": ["Marta De Donato", "Gabriele Babini", "Simona Mozzetti", "Marianna Buttarelli", "Alessandra Ciucci", "Gloria Arduini", "Maria Cristina De Rosa", "Giovanni Scambia", "Daniela Gallo"], "journal": "Journal of experimental & clinical cancer research : CR", "year": 2020, "abstract": "BACKGROUND: In spite of great progress in the surgical and clinical management, until now no significant improvement in overall survival of High-Grade Serous Ovarian Cancer (HGSOC) patients has been achieved. Important aspects for disease control remain unresolved, including unclear pathogenesis, high heterogeneity and relapse resistance after chemotherapy. Therefore, further research on molecular mechanisms involved in cancer progression are needed to find new targets for disease management. The Krüppel-like factors (KLFs) are a family of transcriptional regulators controlling several basic cellular processes, including proliferation, differentiation and migration. They have been shown to play a role in various cancer-relevant processes, in a context-dependent way.\nMETHODS: To investigate a possible role of KLF family members as prognostic biomarkers, we carried out a bioinformatic meta-analysis of ovarian transcriptome datasets in different cohorts of late-stage HGSOC patients. In vitro cellular models of HGSOC were used for functional studies exploring the role of KLF7 in disease development and progression. Finally, molecular modelling and virtual screening were performed to identify putative KLF7 inhibitors.\nRESULTS: Bioinformatic analysis highlighted KLF7 as the most significant prognostic gene, among the 17 family members. Univariate and multivariate analyses identified KLF7 as an unfavourable prognostic marker for overall survival in late-stage TCGA-OV and GSE26712 HGSOC cohorts. Functional in vitro studies demonstrated that KLF7 can play a role as oncogene, driving tumour growth and dissemination. Mechanistic targets of KLF7 included genes involved in epithelial to mesenchymal transition, and in maintaining pluripotency and self-renewal characteristics of cancer stem cells. Finally, in silico analysis provided reliable information for drug-target interaction prediction.\nCONCLUSIONS: Results from the present study provide the first evidence for an oncogenic role of KLF7 in HGSOC, suggesting it as a promising prognostic marker and therapeutic target.", "claims": [{"id": "claim-method", "statement": "Univariate and multiple Cox-regression analyses (based on gene, age, stage and residual tumor mass) for Overall Survival (OS) were performed on the eligible datasets", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33250051", "locator": "sections[3] \"KLF family expression data from publicly available databases\" paragraph 2", "quote": "Univariate and multiple Cox-regression analyses (based on gene, age, stage and residual tumor mass) for Overall Survival (OS) were performed on the eligible datasets"}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets analysed during the current study are available in the Array Express repository (https://www.ebi.ac.uk/arrayexpress/experiments/E-MTAB-386/), GEO repository (https://www.ncbi.nlm.nih.gov/geo/) and TCGA repository (https://portal.gdc.cancer.gov/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33250051", "locator": "sections[34] \"Availability of data and materials\" paragraph 2", "quote": "The datasets analysed during the current study are available in the Array Express repository (https://www.ebi.ac.uk/arrayexpress/experiments/E-MTAB-386/), GEO repository (https://www.ncbi.nlm.nih.gov/geo/) and TCGA repository (https://portal.gdc.cancer.gov/)."}], "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:33250051"], "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:GSE26712"], "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:GSE26712"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33250051", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s13046-020-01775-9", "sha256": "sha256:dc6ae5bf85e097035cb68bbffd655c9fb21ba1ce19e6f7a11665f02f12d1b186", "bytes": 70068, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s13046-020-01775-9", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7702713", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE26712", "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=GSE26712", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE26712", "version": null, "note": "The datasets analysed during the current study are available in the Array Express repository (https://www.ebi.ac.uk/arrayexpress/experiments/E-MTAB-386/), GEO repository (https://www.ncbi.nlm.nih.gov/geo/) and TCGA repository (https://portal.gdc.cancer.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analysed during the current study are available in the Array Express repository (https://www.ebi.ac.uk/arrayexpress/experiments/E-MTAB-386/), GEO repository (https://www.ncbi.nlm.nih.gov/geo/) and TCGA repository (https://portal.gdc.cancer.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM657519", "GSM657520", "GSM657521", "GSM657522", "GSM657523", "GSM657524", "GSM657525", "GSM657526", "GSM657527", "GSM657528", "GSM657529", "GSM657530", "GSM657531", "GSM657532", "GSM657533", "GSM657534", "GSM657535", "GSM657536", "GSM657537", "GSM657538", "GSM657539", "GSM657540", "GSM657541", "GSM657542", "GSM657543", "GSM657544", "GSM657545", "GSM657546", "GSM657547", "GSM657548", "GSM657549", "GSM657550", "GSM657551", "GSM657552", "GSM657553", "GSM657554", "GSM657555", "GSM657556", "GSM657557", "GSM657558", "GSM657559", "GSM657560", "GSM657561", "GSM657562", "GSM657563", "GSM657564", "GSM657565", "GSM657566", "GSM657567", "GSM657568", "GSM657569", "GSM657570", "GSM657571", "GSM657572", "GSM657573", "GSM657574", "GSM657575", "GSM657576", "GSM657577", "GSM657578", "GSM657579", "GSM657580", "GSM657581", "GSM657582", "GSM657583", "GSM657584", "GSM657585", "GSM657586", "GSM657587", "GSM657588", "GSM657589", "GSM657590", "GSM657591", "GSM657592", "GSM657593", "GSM657594", "GSM657595", "GSM657596", "GSM657597", "GSM657598", "GSM657599", "GSM657600", "GSM657601", "GSM657602", "GSM657603", "GSM657604", "GSM657605", "GSM657606", "GSM657607", "GSM657608", "GSM657609", "GSM657610", "GSM657611", "GSM657612", "GSM657613", "GSM657614", "GSM657615", "GSM657616", "GSM657617", "GSM657618", "GSM657619", "GSM657620", "GSM657621", "GSM657622", "GSM657623", "GSM657624", "GSM657625", "GSM657626", "GSM657627", "GSM657628", "GSM657629", "GSM657630", "GSM657631", "GSM657632", "GSM657633", "GSM657634", "GSM657635", "GSM657636", "GSM657637", "GSM657638", "GSM657639", "GSM657640", "GSM657641", "GSM657642", "GSM657643", "GSM657644", "GSM657645", "GSM657646", "GSM657647", "GSM657648", "GSM657649", "GSM657650", "GSM657651", "GSM657652", "GSM657653", "GSM657654", "GSM657655", "GSM657656", "GSM657657", "GSM657658", "GSM657659", "GSM657660", "GSM657661", "GSM657662", "GSM657663", "GSM657664", "GSM657665", "GSM657666", "GSM657667", "GSM657668", "GSM657669", "GSM657670", "GSM657671", "GSM657672", "GSM657673", "GSM657674", "GSM657675", "GSM657676", "GSM657677", "GSM657678", "GSM657679", "GSM657680", "GSM657681", "GSM657682", "GSM657683", "GSM657684", "GSM657685", "GSM657686", "GSM657687", "GSM657688", "GSM657689", "GSM657690", "GSM657691", "GSM657692", "GSM657693", "GSM657694", "GSM657695", "GSM657696", "GSM657697", "GSM657698", "GSM657699", "GSM657700", "GSM657701", "GSM657702", "GSM657703", "GSM657704", "GSM657705", "GSM657706", "GSM657707", "GSM657708", "GSM657709", "GSM657710", "GSM657711", "GSM657712", "GSM657713"], "sample_count": 195, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "A Gene Signature Predicting for Survival in Suboptimally Debulked Patients with Ovarian 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:GSE49997", "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=GSE49997", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE49997", "version": null, "note": "The datasets analysed during the current study are available in the Array Express repository (https://www.ebi.ac.uk/arrayexpress/experiments/E-MTAB-386/), GEO repository (https://www.ncbi.nlm.nih.gov/geo/) and TCGA repository (https://portal.gdc.cancer.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analysed during the current study are available in the Array Express repository (https://www.ebi.ac.uk/arrayexpress/experiments/E-MTAB-386/), GEO repository (https://www.ncbi.nlm.nih.gov/geo/) and TCGA repository (https://portal.gdc.cancer.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1211536", "GSM1211537", "GSM1211538", "GSM1211539", "GSM1211540", "GSM1211541", "GSM1211542", "GSM1211543", "GSM1211544", "GSM1211545", "GSM1211546", "GSM1211547", "GSM1211548", "GSM1211549", "GSM1211550", "GSM1211551", "GSM1211552", "GSM1211553", "GSM1211554", "GSM1211555", "GSM1211556", "GSM1211557", "GSM1211558", "GSM1211559", "GSM1211560", "GSM1211561", "GSM1211562", "GSM1211563", "GSM1211564", "GSM1211565", "GSM1211566", "GSM1211567", "GSM1211568", "GSM1211569", "GSM1211570", "GSM1211571", "GSM1211572", "GSM1211573", "GSM1211574", "GSM1211575", "GSM1211576", "GSM1211577", "GSM1211578", "GSM1211579", "GSM1211580", "GSM1211581", "GSM1211582", "GSM1211583", "GSM1211584", "GSM1211585", "GSM1211586", "GSM1211587", "GSM1211588", "GSM1211589", "GSM1211590", "GSM1211591", "GSM1211592", "GSM1211593", "GSM1211594", "GSM1211595", "GSM1211596", "GSM1211597", "GSM1211598", "GSM1211599", "GSM1211600", "GSM1211601", "GSM1211602", "GSM1211603", "GSM1211604", "GSM1211605", "GSM1211606", "GSM1211607", "GSM1211608", "GSM1211609", "GSM1211610", "GSM1211611", "GSM1211612", "GSM1211613", "GSM1211614", "GSM1211615", "GSM1211616", "GSM1211617", "GSM1211618", "GSM1211619", "GSM1211620", "GSM1211621", "GSM1211622", "GSM1211623", "GSM1211624", "GSM1211625", "GSM1211626", "GSM1211627", "GSM1211628", "GSM1211629", "GSM1211630", "GSM1211631", "GSM1211632", "GSM1211633", "GSM1211634", "GSM1211635", "GSM1211636", "GSM1211637", "GSM1211638", "GSM1211639", "GSM1211640", "GSM1211641", "GSM1211642", "GSM1211643", "GSM1211644", "GSM1211645", "GSM1211646", "GSM1211647", "GSM1211648", "GSM1211649", "GSM1211650", "GSM1211651", "GSM1211652", "GSM1211653", "GSM1211654", "GSM1211655", "GSM1211656", "GSM1211657", "GSM1211658", "GSM1211659", "GSM1211660", "GSM1211661", "GSM1211662", "GSM1211663", "GSM1211664", "GSM1211665", "GSM1211666", "GSM1211667", "GSM1211668", "GSM1211669", "GSM1211670", "GSM1211671", "GSM1211672", "GSM1211673", "GSM1211674", "GSM1211675", "GSM1211676", "GSM1211677", "GSM1211678", "GSM1211679", "GSM1211680", "GSM1211681", "GSM1211682", "GSM1211683", "GSM1211684", "GSM1211685", "GSM1211686", "GSM1211687", "GSM1211688", "GSM1211689", "GSM1211690", "GSM1211691", "GSM1211692", "GSM1211693", "GSM1211694", "GSM1211695", "GSM1211696", "GSM1211697", "GSM1211698", "GSM1211699", "GSM1211700", "GSM1211701", "GSM1211702", "GSM1211703", "GSM1211704", "GSM1211705", "GSM1211706", "GSM1211707", "GSM1211708", "GSM1211709", "GSM1211710", "GSM1211711", "GSM1211712", "GSM1211713", "GSM1211714", "GSM1211715", "GSM1211716", "GSM1211717", "GSM1211718", "GSM1211719", "GSM1211720", "GSM1211721", "GSM1211722", "GSM1211723", "GSM1211724", "GSM1211725", "GSM1211726", "GSM1211727", "GSM1211728", "GSM1211729", "GSM1211730", "GSM1211731", "GSM1211732", "GSM1211733", "GSM1211734", "GSM1211735", "GSM1211736", "GSM1211737", "GSM1211738", "GSM1211739"], "sample_count": 204, "group_sizes": null, "group_sizes_basis": null, "platform": "2986", "taxon": "Homo sapiens", "title": "Validating the Impact of a Molecular Subtype in Epithelial Ovarian Cancer (EOC) on Progression Free and Overall Survival", "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:GSE9891", "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=GSE9891", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE9891", "version": null, "note": "The datasets analysed during the current study are available in the Array Express repository (https://www.ebi.ac.uk/arrayexpress/experiments/E-MTAB-386/), GEO repository (https://www.ncbi.nlm.nih.gov/geo/) and TCGA repository (https://portal.gdc.cancer.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analysed during the current study are available in the Array Express repository (https://www.ebi.ac.uk/arrayexpress/experiments/E-MTAB-386/), GEO repository (https://www.ncbi.nlm.nih.gov/geo/) and TCGA repository (https://portal.gdc.cancer.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM249714", "GSM249715", "GSM249716", "GSM249717", "GSM249718", "GSM249719", "GSM249720", "GSM249721", "GSM249722", "GSM249723", "GSM249724", "GSM249725", "GSM249726", "GSM249727", "GSM249728", "GSM249729", "GSM249730", "GSM249731", "GSM249732", "GSM249733", "GSM249734", "GSM249735", "GSM249736", "GSM249737", "GSM249738", "GSM249739", "GSM249740", "GSM249741", "GSM249742", "GSM249743", "GSM249744", "GSM249745", "GSM249746", "GSM249747", "GSM249748", "GSM249749", "GSM249750", "GSM249751", "GSM249752", "GSM249753", "GSM249754", "GSM249755", "GSM249756", "GSM249757", "GSM249758", "GSM249759", "GSM249760", "GSM249761", "GSM249762", "GSM249763", "GSM249764", "GSM249765", "GSM249766", "GSM249767", "GSM249768", "GSM249769", "GSM249770", "GSM249771", "GSM249773", "GSM249774", "GSM249775", "GSM249776", "GSM249777", "GSM249778", "GSM249779", "GSM249780", "GSM249781", "GSM249782", "GSM249783", "GSM249784", "GSM249785", "GSM249786", "GSM249788", "GSM249789", "GSM249790", "GSM249791", "GSM249792", "GSM249793", "GSM249794", "GSM249795", "GSM249796", "GSM249797", "GSM249798", "GSM249799", "GSM249800", "GSM249801", "GSM249802", "GSM249803", "GSM249804", "GSM249805", "GSM249806", "GSM249807", "GSM249808", "GSM249809", "GSM249810", "GSM249811", "GSM249812", "GSM249813", "GSM249814", "GSM249815", "GSM249816", "GSM249817", "GSM249818", "GSM249819", "GSM249820", "GSM249821", "GSM249822", "GSM249823", "GSM249824", "GSM249825", "GSM249826", "GSM249827", "GSM249828", "GSM249829", "GSM249830", "GSM249831", "GSM249832", "GSM249833", "GSM249834", "GSM249835", "GSM249836", "GSM249837", "GSM249838", "GSM249839", "GSM249840", "GSM249841", "GSM249842", "GSM249843", "GSM249844", "GSM249845", "GSM249846", "GSM249847", "GSM249848", "GSM249849", "GSM249850", "GSM249851", "GSM249852", "GSM249853", "GSM249854", "GSM249855", "GSM249856", "GSM249857", "GSM249858", "GSM249859", "GSM249860", "GSM249861", "GSM249862", "GSM249863", "GSM249864", "GSM249865", "GSM249866", "GSM249867", "GSM249868", "GSM249869", "GSM249870", "GSM249871", "GSM249872", "GSM249873", "GSM249874", "GSM249875", "GSM249876", "GSM249877", "GSM249878", "GSM249879", "GSM249880", "GSM249881", "GSM249882", "GSM249883", "GSM249884", "GSM249885", "GSM249886", "GSM249887", "GSM249888", "GSM249889", "GSM249890", "GSM249891", "GSM249892", "GSM249893", "GSM249894", "GSM249895", "GSM249896", "GSM249897", "GSM249898", "GSM249899", "GSM249900", "GSM249901", "GSM249902", "GSM249903", "GSM249904", "GSM249905", "GSM249906", "GSM249907", "GSM249908", "GSM249909", "GSM249910", "GSM249911", "GSM249912", "GSM249913", "GSM249914", "GSM249915", "GSM249916", "GSM249917", "GSM249918", "GSM249919", "GSM249920", "GSM249921", "GSM249922", "GSM249923", "GSM249924", "GSM249925", "GSM249926", "GSM249927", "GSM249928", "GSM249929", "GSM249930", "GSM249931", "GSM249932", "GSM249933", "GSM249934", "GSM249935", "GSM249936", "GSM249937", "GSM249938", "GSM249939", "GSM249940", "GSM249941", "GSM249942", "GSM249943", "GSM249944", "GSM249945", "GSM249946", "GSM249947", "GSM249948", "GSM249949", "GSM249950", "GSM249951", "GSM249953", "GSM249954", "GSM249955", "GSM249956", "GSM249957", "GSM249958", "GSM249959", "GSM249960", "GSM249961", "GSM249962", "GSM249963", "GSM249964", "GSM249965", "GSM249966", "GSM249967", "GSM249968", "GSM249969", "GSM249970", "GSM249971", "GSM249972", "GSM249973", "GSM249974", "GSM249975", "GSM249976", "GSM249977", "GSM249978", "GSM249979", "GSM249980", "GSM249981", "GSM249982", "GSM249983", "GSM249984", "GSM249985", "GSM249986", "GSM249987", "GSM249988", "GSM249989", "GSM249990", "GSM249991", "GSM249992", "GSM249993", "GSM249994", "GSM249995", "GSM249996", "GSM249997", "GSM249998", "GSM249999", "GSM250000", "GSM250001"], "sample_count": 285, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression profile of 285 ovarian tumour samples", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33250051:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9147143bc1baaed49439de86ea6d0f1e8fc5d56c57310b3840c6a70d710262ae", "bytes": 666, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab1", "version": null, "note": "Clinicopathological characteristics of GSE26712 and TCGA-OV cohorts", "structure": {"pmcid": "PMC7702713", "section_index": 3, "section_title": "KLF family expression data from publicly available databases", "row_count": 12, "column_count": 3}, "table": {"label": "Table 1", "caption": "Clinicopathological characteristics of GSE26712 and TCGA-OV cohorts", "rows": [["Characteristics", "GSE26712No. of patients (%)", "TCGA-OVNo. of patients (%)"], ["Histological type"], ["HGSOC", "185", "266"], ["Median Age, years (range)", "63 (26–84)a", "59 (31–87)b"], ["FIGO Stage"], ["III", "146 (78.9)", "231 (86.8)"], ["IV", "36 (19.5)", "35 (13.2)"], ["Not available", "3 (1.6)", "–"], ["Residual tumor after primary surgery"], ["≤ 1 cm", "90 (48.6)", "169 (63.5)"], ["> 1 cm", "95 (51.4)", "69 (25.9)"], ["Not available", "–", "28 (10.6)"]], "row_count": 12, "column_count": 3, "numeric_cells": 17, "header_rows": 1, "locator": "section[3]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:33250051:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:71f828062786e61107cb7113526ed6676ded0265b997d4ae2f813374de463e01", "bytes": 719, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#Tab2", "version": null, "note": "Univariate and Multivariate analysis of factors affecting OS in GSE26712 cohort", "structure": {"pmcid": "PMC7702713", "section_index": 17, "section_title": "KLF7 is an independent prognostic factor for OS", "row_count": 14, "column_count": 5}, "table": {"label": "Table 2", "caption": "Univariate and Multivariate analysis of factors affecting OS in GSE26712 cohort", "rows": [["Outcome and variables", "Univariate", "Multivariate"], ["HR (95%CI)", "P", "HR (95%CI)", "P*"], ["Age (yrs)"], ["≤ 63", "", "", "", ""], ["> 63", "1.6 (1.1–2.3)", "0.007", "1.6 (1.1–2.2)", "0.01"], ["FIGO Stage"], ["III", "", "", "", ""], ["IV", "1.4 (0.9–2.3)", "0.1", "–", "–"], ["Residual tumor"], ["≤ 1 cm", "", "", "", ""], ["> 1 cm", "1.7 (1.2–2.4)", "0.003", "1.6 (1.1–2.3)", "0.009"], ["KFL7"], ["Low expression", "", "", "", ""], ["High expression", "2.6 (1.6–4.4)", "0.0003", "2.2 (1.4–3.4)", "< 0.0001"]], "row_count": 14, "column_count": 5, "numeric_cells": 20, "header_rows": 2, "locator": "section[17]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:33250051:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:66cc543027547a3514ea20c2a152d78efc5622d25fe985b1dff291ee4eef1b90", "bytes": 698, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[2]#Tab3", "version": null, "note": "Univariate and Multivariate analysis of factors affecting OS in TCGA-OV cohort", "structure": {"pmcid": "PMC7702713", "section_index": 17, "section_title": "KLF7 is an independent prognostic factor for OS", "row_count": 14, "column_count": 5}, "table": {"label": "Table 3", "caption": "Univariate and Multivariate analysis of factors affecting OS in TCGA-OV cohort", "rows": [["Outcome and variables", "Univariate", "Multivariate"], ["HR (95% CI)", "P", "HR (95% CI)", "P*"], ["Age (yrs)"], ["≤ 59", "", "", "", ""], ["> 59", "1.3 (1.0–1.8)", "0.09", "1.4 (1.0–1.9)", "0.06"], ["FIGO Stage"], ["III", "", "", "", ""], ["IV", "1.1 (0.7–1.8)", "0.7", "–", "–"], ["Residual tumor"], ["≤ 1 cm", "", "", "", ""], ["> 1 cm", "1.1 (0.8–1.6)", "0.5", "–", "–"], ["KFL7"], ["Low expression", "", "", "", ""], ["High expression", "1.6 (1.0–2.4)", "0.037", "1.5 (1.0–2.3)", "0.03"]], "row_count": 14, "column_count": 5, "numeric_cells": 18, "header_rows": 2, "locator": "section[17]/table-wrap[2]#Tab3"}}, {"id": "asset:table:pmid:33250051:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:99d7395c104fca88a1b6a1fbe3f2e6e2023d5618f568c39862b8748cb958fb7c", "bytes": 737, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[24]/table-wrap[1]#Tab4", "version": null, "note": "Druggable sites identified by SiteMap", "structure": {"pmcid": "PMC7702713", "section_index": 24, "section_title": "Structural analysis of the modelled protein and identification of binding sites", "row_count": 4, "column_count": 3}, "table": {"label": "Table 4", "caption": "Druggable sites identified by SiteMap", "rows": [["", "SiteScore", "Residues"], ["Site1", "0.866", "Gly225, Cys226, Arg227, Lys228, Val229, Tyr230, Hys235, Ala238, Hys239, Thr242, Hys243, Pro248, Tyr249, Lys250, Cys251, Ser252, Trp253, Glu254, Gly255, Cys256, Glu257, Trp258, Arg259, Ser263, Asp264, Leu266, Thr267, Tyr270, Arg271, Thr274, Ala276."], ["Site2", "0.838", "Trp258, Phe260, Ala261, Glu265, Arg268, Hys269, Arg271, Lys272, Gly275, Ala276, Lys277, Phe288, Ser289, Arg290, Hys293."], ["Site3", "0.812", "His219, Arg220, Cys221, Gln222, Phe223, Ser233, Leu236, Lys237, Gln240, Arg241, His243, Thr244"]], "row_count": 4, "column_count": 3, "numeric_cells": 6, "header_rows": 1, "locator": "section[24]/table-wrap[1]#Tab4"}}, {"id": "asset:table:pmid:33250051:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:46f2c42082d0155e9eac20d912cf748616bb78fcd49a4ff4c304308ab794ee3a", "bytes": 561, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[25]/table-wrap[1]#Tab5", "version": null, "note": "Docking score and estimated binding free energy of the selected hit compounds", "structure": {"pmcid": "PMC7702713", "section_index": 25, "section_title": "Computational virtual screening against KLF7", "row_count": 11, "column_count": 3}, "table": {"label": "Table 5", "caption": "Docking score and estimated binding free energy of the selected hit compounds", "rows": [["", "Docking score", "MM-GBSA (kcal/mol)"], ["#1", "−10.737", "−49.30"], ["#2", "−8.459", "−23.19"], ["#3", "−8.066", "−42.47"], ["#4", "−8.044", "−32.42"], ["#5", "−7.932", "−16.37"], ["#6", "−7.580", "−36.22"], ["#7", "−7.499", "−24.72"], ["#8", "−7.475", "−5.06"], ["#9", "−7.461", "−38.42"], ["#10", "−7.368", "−31.69"]], "row_count": 11, "column_count": 3, "numeric_cells": 30, "header_rows": 1, "locator": "section[25]/table-wrap[1]#Tab5"}}], "gaps": ["asset:data:geo:GSE26712 not downloaded", "asset:data:geo:GSE26712 licence not read", "asset:data:geo:GSE49997 not downloaded", "asset:data:geo:GSE49997 licence not read", "asset:data:geo:GSE9891 not downloaded", "asset:data:geo:GSE9891 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Univariate and multiple Cox-regression analyses (based on gene, age, stage and residual tumor mass) for Overall Survival (OS) were performed on the eligible datasets"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE26712", "GSE49997", "GSE9891"], "resolved_accessions": ["GSE26712", "GSE49997", "GSE9891"], "statements": ["The datasets analysed during the current study are available in the Array Express repository (https://www.ebi.ac.uk/arrayexpress/experiments/E-MTAB-386/), GEO repository (https://www.ncbi.nlm.nih.gov/geo/) and TCGA repository (https://portal.gdc.cancer.gov/)."], "basis": "The paper names GSE26712, GSE49997, GSE9891 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:33250051", "data:geo:GSE26712", "asset:table:pmid:33250051:1", "asset:table:pmid:33250051:2", "asset:table:pmid:33250051:3", "asset:table:pmid:33250051:4", "asset:table:pmid:33250051:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE26712"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:24:44Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 56085, "completion_tokens": 2765, "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:33250051", "type": "paper", "label": "pmid:33250051"}, {"id": "source:pmid:33250051", "type": "manuscript", "label": "PMID 33250051 full text"}, {"id": "data:geo:GSE26712", "type": "dataset", "label": "GEO GSE26712"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33250051", "type": "paper", "label": "pmid:33250051"}, {"id": "source:pmid:33250051", "type": "manuscript", "label": "PMID 33250051 full text"}, {"id": "data:geo:GSE26712", "type": "dataset", "label": "GEO GSE26712"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33250051", "type": "extraction", "used": ["source:pmid:33250051"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE26712", "type": "accession_resolution", "used": ["data:geo:GSE26712"], "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:33250051", "parent_hash": "sha256:f23e6646f79f7748d08f2a6219d1e1bb44257c9358fa168a45377b33f8d9e7d3", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE26712 licence not read", "asset:data:geo:GSE26712 not downloaded", "asset:data:geo:GSE49997 licence not read", "asset:data:geo:GSE49997 not downloaded", "asset:data:geo:GSE9891 licence not read", "asset:data:geo:GSE9891 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.69, "evidence": ["out a bioinformatic meta-analysis of ovarian transcriptome datasets in different cohorts of late-stage"], "order_basis": "paper_text_order:969", "id": "assay:1"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["e ovary [29]. PEO1, NIH:OVCAR-3 and HEY were cultured in RPMI 1640 (Roswell Park Memorial Institute M", "drich, St. Louis, MO, USA). OV-90 cells were cultured in 1:1 mixture of MCDB 105 medium (containing a"], "order_basis": "paper_text_order:3286", "id": "assay:2"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["e S1A. Sequences information related to KLF7 siRNA pool. Table S1B. KLF7 transcript variants re"], "order_basis": "paper_text_order:8613", "id": "assay:3"}, {"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["KLF7 transcript variants recognized by KLF7 RT-qPCR oligos. Table S2. Primer sequences used for", "oligos. Table S2. Primer sequences used for RT-qPCR. Additional file 2. Bioinformatic meta-analy", "F7 transcript variants recognized by KLF7 RT-qPCR oligos. Table S2. Primer sequences used for", "igos. Table S2. Primer sequences used for RT-qPCR. Additional file 2. Bioinformatic meta-analy"], "order_basis": "paper_text_order:8681", "id": "assay:4"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Univariate and multiple Cox-regression analyses (based on gene, age, stage and residual tumor mass) for Overall Survival (OS) were performed on the eligible datasets"], "order_basis": "consumes_earlier_output", "id": "assay:5"}]},"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":"2026-11-04T00:35:20+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}}}