{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37373065", "kind": "science-record", "revision": 3, "content_hash": "sha256:e34510ce4ff1c96367bc829a12dceaaca9274caa057af392f1191642ec29e91a", "created_at": "2026-11-01T19:02:07Z", "updated_at": "2026-11-01T22:52:12Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "In Silico Identification of a BRCA1:miR-29:DNMT3 Axis Involved in the Control of Hormone Receptors in BRCA1-Associated Breast Cancers.", "doi": "10.3390/ijms24129916", "pmid": "37373065", "authors": ["Manuela Santarosa", "Davide Baldazzi", "Michela Armellin", "Roberta Maestro"], "journal": "International journal of molecular sciences", "year": 2023, "abstract": "Germline inactivating mutations in the BRCA1 gene lead to an increased lifetime risk of ovarian and breast cancer (BC). Most BRCA1-associated BC are triple-negative tumors (TNBC), aggressive forms of BC characterized by a lack of expression of estrogen and progesterone hormone receptors (HR) and HER2. How BRCA1 inactivation may favor the development of such a specific BC phenotype remains to be elucidated. To address this question, we focused on the role of miRNAs and their networks in mediating BRCA1 functions. miRNA, mRNA, and methylation data were retrieved from the BRCA cohort of the TCGA project. The cohort was divided into a discovery set (Hi-TCGA) and a validation set (GA-TCGA) based on the platform used for miRNA analyses. The METABRIC, GSE81002, and GSE59248 studies were used as additional validation data sets. BCs were differentiated into BRCA1-like and non-BRCA1-like based on an established signature of BRCA1 pathway inactivation. Differential expression of miRNAs, gene enrichment analysis, functional annotation, and methylation correlation analyses were performed. The miRNAs downregulated in BRCA1-associated BC were identified by comparing the miRNome of BRCA1-like with non-BRCA1-like tumors from the Hi-TCGA discovery cohort. miRNAs:gene-target anticorrelation analyses were then performed. The target genes of miRNAs downregulated in the Hi-TCGA series were enriched in the BRCA1-like tumors from the GA-TCGA and METABRIC validation data sets. Functional annotation of these genes revealed an over-representation of several biological processes ascribable to BRCA1 activity. The enrichment of genes related to DNA methylation was particularly intriguing, as this is an aspect of BRCA1 functions that has been poorly explored. We then focused on the miR-29:DNA methyltransferase network and showed that the miR-29 family, which was downregulated in BRCA1-like tumors, was associated with poor prognosis in these BCs and inversely correlated with the expression of the DNA methyltransferases DNMT3A and DNMT3B. This, in turn, correlated with the methylation extent of the promoter of HR genes. These results suggest that BRCA1 may control the expression of HR via a miR-29:DNMT3:HR axis and that disruption of this network may contribute to the receptor negative phenotype of tumors with dysfunctional BRCA1.", "claims": [{"id": "claim-method", "statement": "Spearman rank order correlation coefficients were computed between the normalized miRNA expression levels from the Hi-TCGA data set and the corresponding log2 RSEM-normalized counts of the putative targets. Statistical differences between groups were evaluated using the Welch t-test or a Mann–Whitney rank sum test, depending on the normal distribution of the variables considered. Survival was estimated using the Kaplan–Meier method, and differences between groups were evaluated with the log-rank test using the Survival and Survminer R packages [78,79].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37373065", "locator": "sections[14] \"4.4. Disease-Free Survival and Statistical Analysis\" paragraph 2", "quote": "Spearman rank order correlation coefficients were computed between the normalized miRNA expression levels from the Hi-TCGA data set and the corresponding log2 RSEM-normalized counts of the putative targets."}, {"asset": "source:pmid:37373065", "locator": "sections[14] \"4.4. Disease-Free Survival and Statistical Analysis\" paragraph 2", "quote": "Statistical differences between groups were evaluated using the Welch t-test or a Mann–Whitney rank sum test, depending on the normal distribution of the variables considered."}, {"asset": "source:pmid:37373065", "locator": "sections[14] \"4.4. Disease-Free Survival and Statistical Analysis\" paragraph 2", "quote": "Survival was estimated using the Kaplan–Meier method, and differences between groups were evaluated with the log-rank test using the Survival and Survminer R packages [78,79]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data sets analyzed in the current study are publicly available from TCGA Research Network: TCGA-BRCA project, https://www.cancer.gov/tcga; from the METABRIC project (information at https://ega-archive.org/studies/EGAS00000000098); and from Gene Expression Omnibus database (GEO; https://www.ncbi.nlm.nih.gov/gds) for the GSE81002 and GSE59248 series.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37373065", "locator": "sections[20] \"notes\" paragraph 1", "quote": "The data sets analyzed in the current study are publicly available from TCGA Research Network: TCGA-BRCA project, https://www.cancer.gov/tcga; from the METABRIC project (information at https://ega-archive.org/studies/EGAS00000000098); and from Gene Expression Omnibus database (GEO; https://www.ncbi.nlm.nih.gov/gds) for the GSE81002 and GSE59248 series."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "", "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:37373065"], "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:GSE59248"], "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:GSE59248"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37373065", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/ijms24129916", "sha256": "sha256:4cffc95aa837dacdd81e39ae9deed4b9165ac935f8c8d8bd5e8a779a49b11d3c", "bytes": 31082, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/ijms24129916", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10298721", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE59248", "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=GSE59248", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE59248", "version": null, "note": "The data sets analyzed in the current study are publicly available from TCGA Research Network: TCGA-BRCA project, https://www.cancer.gov/tcga; from the METABRIC project (information at https://ega-archive.org/studies/EGAS00000000098); and from Gene Expression Omnibus database (GEO; https://www.ncbi.nlm.nih.gov/gds) for the GSE81002 and GSE59248 series.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data sets analyzed in the current study are publicly available from TCGA Research Network: TCGA-BRCA project, https://www.cancer.gov/tcga; from the METABRIC project (information at https://ega-archive.org/studies/EGAS00000000098); and from Gene Expression Omnibus database (GEO; https://www.ncbi.nlm.nih.gov/gds) for the GSE81002 and GSE59248 series.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1431259", "GSM1431260", "GSM1431261", "GSM1431262", "GSM1431263", "GSM1431264", "GSM1431265", "GSM1431266", "GSM1431267", "GSM1431268", "GSM1431269", "GSM1431270", "GSM1431271", "GSM1431272", "GSM1431273", "GSM1431274", "GSM1431275", "GSM1431276", "GSM1431277", "GSM1431278", "GSM1431279", "GSM1431280", "GSM1431281", "GSM1431282", "GSM1431283", "GSM1431284", "GSM1431285", "GSM1431286", "GSM1431287", "GSM1431288", "GSM1431289", "GSM1431290", "GSM1431291", "GSM1431292", "GSM1431293", "GSM1431294", "GSM1431295", "GSM1431296", "GSM1431297", "GSM1431298", "GSM1431299", "GSM1431300", "GSM1431301", "GSM1431302", "GSM1431303", "GSM1431304", "GSM1431305", "GSM1431306", "GSM1431307", "GSM1431308", "GSM1431309", "GSM1431310", "GSM1431311", "GSM1431312", "GSM1431313", "GSM1431314", "GSM1431315", "GSM1431316", "GSM1431317", "GSM1431318", "GSM1431319", "GSM1431320", "GSM1431321", "GSM1431322", "GSM1431323", "GSM1431324", "GSM1431325", "GSM1431326", "GSM1431327", "GSM1431328", "GSM1431329", "GSM1431330", "GSM1431331", "GSM1431332", "GSM1431333", "GSM1431334", "GSM1431335", "GSM1431336", "GSM1431337", "GSM1431338", "GSM1431339", "GSM1431340", "GSM1431341", "GSM1431342", "GSM1431343", "GSM1431344", "GSM1431345", "GSM1431346", "GSM1431347", "GSM1431348", "GSM1431349", "GSM1431350", "GSM1431351", "GSM1431352", "GSM1431353", "GSM1431354", "GSM1431355", "GSM1431356", "GSM1431357", "GSM1431358", "GSM1431359", "GSM1431360", "GSM1431361", "GSM1431362", "GSM1431363", "GSM1431364", "GSM1431365", "GSM1431366", "GSM1431367", "GSM1431368", "GSM1431369", "GSM1431370", "GSM1431371", "GSM1431372", "GSM1431373", "GSM1431374", "GSM1431375", "GSM1431376", "GSM1431377", "GSM1431378", "GSM1431379", "GSM1431380", "GSM1431381", "GSM1431382", "GSM1431383", "GSM1431384", "GSM1431385", "GSM1431386", "GSM1431387", "GSM1431388", "GSM1431389", "GSM1431390", "GSM1431391", "GSM1431392", "GSM1431393", "GSM1431394", "GSM1431395", "GSM1431396", "GSM1431397", "GSM1431398", "GSM1431399", "GSM1431400", "GSM1431401", "GSM1431402", "GSM1431403", "GSM1431404", "GSM1431405", "GSM1431406", "GSM1431407", "GSM1431408", "GSM1431409", "GSM1431410", "GSM1431411"], "sample_count": 153, "group_sizes": null, "group_sizes_basis": null, "platform": "13607;15019", "taxon": "Homo sapiens", "title": "Molecular features of subtype-specific progression from ductal carcinoma in situ to invasive breast cancer", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE81002", "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=GSE81002", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE81002", "version": null, "note": "The data sets analyzed in the current study are publicly available from TCGA Research Network: TCGA-BRCA project, https://www.cancer.gov/tcga; from the METABRIC project (information at https://ega-archive.org/studies/EGAS00000000098); and from Gene Expression Omnibus database (GEO; https://www.ncbi.nlm.nih.gov/gds) for the GSE81002 and GSE59248 series.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data sets analyzed in the current study are publicly available from TCGA Research Network: TCGA-BRCA project, https://www.cancer.gov/tcga; from the METABRIC project (information at https://ega-archive.org/studies/EGAS00000000098); and from Gene Expression Omnibus database (GEO; https://www.ncbi.nlm.nih.gov/gds) for the GSE81002 and GSE59248 series.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1403342", "GSM1403343", "GSM1403344", "GSM1403345", "GSM1403346", "GSM1403347", "GSM1403348", "GSM1403349", "GSM1403350", "GSM1403351", "GSM1403352", "GSM1403353", "GSM1403354", "GSM1403355", "GSM1403356", "GSM1403357", "GSM1403358", "GSM1403359", "GSM1403360", "GSM1403361", "GSM1403362", "GSM1403363", "GSM1403364", "GSM1403365", "GSM1403366", "GSM1403367", "GSM1403368", "GSM1403369", "GSM1403370", "GSM1403371", "GSM1403372", "GSM1403373", "GSM1403374", "GSM1403375", "GSM1403376", "GSM1403377", "GSM1403378", "GSM1403379", "GSM1403380", "GSM1403381", "GSM1403382", "GSM1403383", "GSM1403384", "GSM1403385", "GSM1403386", "GSM1403387", "GSM1403388", "GSM1403389", "GSM1403390", "GSM1403391", "GSM1403392", "GSM1403393", "GSM1403394", "GSM1403395", "GSM1403396", "GSM1403397", "GSM1403398", "GSM1403399", "GSM1403400", "GSM1403401", "GSM1403402", "GSM1403403", "GSM1403404", "GSM1403405", "GSM1403406", "GSM1403407", "GSM1403408", "GSM1403409", "GSM1403410", "GSM1403411", "GSM1403412", "GSM1403413", "GSM1403414", "GSM1403415", "GSM1403416", "GSM1403417", "GSM1403418", "GSM1403419", "GSM1403420", "GSM1403421", "GSM1403422", "GSM1403423", "GSM1403424", "GSM1403425", "GSM1403426", "GSM1403427", "GSM1403428", "GSM1403429", "GSM1403430", "GSM1403431", "GSM1403432", "GSM1403433", "GSM1403434", "GSM1403435", "GSM1403436", "GSM1403437", "GSM1403438", "GSM1403439", "GSM1403440", "GSM1403441", "GSM1403442", "GSM1403443", "GSM1403444", "GSM1403445", "GSM1403446", "GSM1403447", "GSM1403448", "GSM1403449", "GSM1403450", "GSM1403451", "GSM1403452", "GSM1403453", "GSM1403454", "GSM1403455", "GSM1403456", "GSM1403457", "GSM1403458", "GSM1403459", "GSM1403460", "GSM1403461", "GSM1403462", "GSM1403463", "GSM1403464", "GSM1403465", "GSM1403466", "GSM1403467", "GSM1403468", "GSM1403469", "GSM1403470", "GSM1403471", "GSM1403472", "GSM1403473", "GSM1403474", "GSM1403475", "GSM1403476", "GSM1403477", "GSM1403478", "GSM1403479", "GSM1403480", "GSM1403481", "GSM1403482", "GSM1403483", "GSM1403484", "GSM1403485", "GSM1403486", "GSM1403487", "GSM1403488", "GSM1403489", "GSM1403490", "GSM1403491", "GSM1403492", "GSM1403493", "GSM1403494", "GSM1403495", "GSM1403496", "GSM1403497", "GSM1403498", "GSM1403499", "GSM1403500", "GSM1403501", "GSM1403502", "GSM1403503", "GSM1403504", "GSM1403505", "GSM1403506", "GSM1403507", "GSM1403508", "GSM1403509", "GSM1403510", "GSM1403511", "GSM1403512", "GSM1403513", "GSM1403514", "GSM1403515", "GSM1403516", "GSM1403517", "GSM1403518", "GSM1403519", "GSM1403520", "GSM1403521", "GSM1403522", "GSM1403523", "GSM1403524", "GSM1403525", "GSM1403526", "GSM1403527", "GSM1403528", "GSM1403529", "GSM1403530", "GSM1403531", "GSM1403532", "GSM1403533", "GSM1403534", "GSM1403535", "GSM1403536", "GSM1403537", "GSM1403538", "GSM1403539", "GSM1403540", "GSM1403541", "GSM1403542", "GSM1403543", "GSM1403544", "GSM1403545", "GSM1403546", "GSM1403547", "GSM1403548", "GSM1403549", "GSM1403550", "GSM1403551", "GSM1403552", "GSM1403553", "GSM1403554", "GSM1403555", "GSM1403556", "GSM1403557", "GSM1403558", "GSM1403559", "GSM1403560", "GSM1403561", "GSM1403562", "GSM1403563", "GSM1403564", "GSM1403565", "GSM1403566", "GSM1403567", "GSM1403568", "GSM1403569", "GSM1403570", "GSM1403571", "GSM1403572", "GSM1403573", "GSM1403574", "GSM1403575", "GSM1403576", "GSM1403577", "GSM1403578", "GSM1403579", "GSM1403580", "GSM1403581", "GSM1403582", "GSM1403583", "GSM1403584", "GSM1403585", "GSM1403586", "GSM1403587", "GSM1403588", "GSM1403589", "GSM1403590", "GSM1403591", "GSM1403592", "GSM1403593", "GSM1403594", "GSM1403595", "GSM1403596", "GSM1403597", "GSM1403598", "GSM1403599", "GSM1403600", "GSM1403601", "GSM1403602", "GSM1403603", "GSM1403604", "GSM1403605", "GSM1403606", "GSM1403607", "GSM1403608", "GSM1403609", "GSM1403610", "GSM1403611", "GSM1403612", "GSM1403613", "GSM1403614", "GSM1403615", "GSM1403616", "GSM1403617", "GSM1403618", "GSM1403619", "GSM1403620", "GSM1403621", "GSM1403622", "GSM1403623", "GSM1403624", "GSM1403625", "GSM1403626", "GSM1403627", "GSM1403628", "GSM1403629", "GSM1403630", "GSM1403631", "GSM1403632", "GSM1403633", "GSM1403634", "GSM1403635", "GSM1403636", "GSM1403637", "GSM1403638", "GSM1403639", "GSM1403640", "GSM1403641", "GSM1403642", "GSM1403643", "GSM1403644", "GSM1403645", "GSM1403646", "GSM1403647", "GSM1403648", "GSM1403649", "GSM1403650", "GSM1403651", "GSM1403652", "GSM1403653", "GSM1403654", "GSM1403655", "GSM1403656", "GSM1403657", "GSM1403658", "GSM1403659", "GSM1403660", "GSM1403661", "GSM1403662", "GSM1403663", "GSM1403664", "GSM1403665", "GSM1403666", "GSM1403667", "GSM1403668", "GSM1403669", "GSM1403670", "GSM1403671", "GSM1403672", "GSM1403673", "GSM1403674", "GSM1403675", "GSM1403676", "GSM1403677", "GSM1403678", "GSM1403679", "GSM1403680", "GSM1403681", "GSM1403682", "GSM1403683", "GSM1403684", "GSM1403685", "GSM1403686", "GSM1403687", "GSM1403688", "GSM1403689", "GSM1403690", "GSM1403691", "GSM1403692", "GSM1403693", "GSM1403694", "GSM1403695", "GSM1403696", "GSM1403697", "GSM1403698", "GSM1403699", "GSM1403700", "GSM1403701", "GSM1403702", "GSM1403703", "GSM1403704", "GSM1403705", "GSM1403706", "GSM1403707", "GSM1403708", "GSM1403709", "GSM1403710", "GSM1403711", "GSM1403712", "GSM1403713", "GSM1403714", "GSM1403715", "GSM1403716", "GSM1403717", "GSM1403718", "GSM1403719", "GSM1403720", "GSM1403721", "GSM1403722", "GSM1403723", "GSM1403724", "GSM1403725", "GSM1403726", "GSM1403727", "GSM1403728", "GSM1403729", "GSM1403730", "GSM1403731", "GSM1403732", "GSM1403733", "GSM1403734", "GSM1403735", "GSM1403736", "GSM1403737", "GSM1403738", "GSM1403739", "GSM1403740", "GSM1403741", "GSM1403742", "GSM1403743", "GSM1403744", "GSM1403745", "GSM1403746", "GSM1403747", "GSM1403748", "GSM1403749", "GSM1403750", "GSM1403751", "GSM1403752", "GSM1403753", "GSM1403754", "GSM1403755", "GSM1403756", "GSM1403757", "GSM1403758", "GSM1403759", "GSM1403760", "GSM1403761", "GSM1403762", "GSM1403763", "GSM1403764", "GSM1403765", "GSM1403766", "GSM1403767", "GSM1403768", "GSM1403769", "GSM1403770", "GSM1403771", "GSM1403772", "GSM1403773", "GSM1403774", "GSM1403775", "GSM1403776", "GSM1403777", "GSM1403778", "GSM1403779", "GSM1403780", "GSM1403781", "GSM1403782", "GSM1403783", "GSM1403784", "GSM1403785", "GSM1403786", "GSM1403787", "GSM1403788", "GSM1403789", "GSM1403790", "GSM1403791", "GSM1403792", "GSM1403793", "GSM1403794", "GSM1403795", "GSM1403796", "GSM1403797", "GSM1403798", "GSM1403799", "GSM1403800", "GSM1403801", "GSM1403802", "GSM1403803", "GSM1403804", "GSM1403805", "GSM1403806", "GSM1403807", "GSM1403808", "GSM1403809", "GSM1403810", "GSM1403811", "GSM1403812", "GSM1403813", "GSM1403814", "GSM1403815", "GSM1403816", "GSM1403817", "GSM1403818", "GSM1403819", "GSM1403820", "GSM1403821", "GSM1403822", "GSM1403823", "GSM1403824", "GSM1403825", "GSM1403826", "GSM1403827", "GSM1403828", "GSM1403829", "GSM1403830", "GSM1403831", "GSM1403832", "GSM1403833", "GSM1403834", "GSM1403835", "GSM1403836", "GSM1403837", "GSM1403838", "GSM1403839", "GSM1403840", "GSM1403841", "GSM1403842", "GSM1403843", "GSM1403844", "GSM1403845", "GSM1403846", "GSM1403847", "GSM1403848", "GSM1403849", "GSM1403850", "GSM1403851", "GSM1403852", "GSM1403853", "GSM1403854", "GSM1403855", "GSM1403856", "GSM1403857", "GSM1403858", "GSM1403859", "GSM1403860", "GSM1403861", "GSM1403862", "GSM1403863", "GSM1403864", "GSM1403865", "GSM1403866", "GSM1403867", "GSM1403868", "GSM1403869", "GSM1403870", "GSM1403871", "GSM1403872", "GSM1403873", "GSM1403874", "GSM1403875", "GSM1403876", "GSM1403877", "GSM1403878", "GSM1403879", "GSM1403880", "GSM1403881", "GSM1403882", "GSM1403883", "GSM1403884", "GSM1403885", "GSM1403886", "GSM1403887", "GSM1403888", "GSM1403889", "GSM1403890", "GSM1403891", "GSM1403892", "GSM1403893", "GSM1403894", "GSM1403895", "GSM1403896", "GSM1403897", "GSM1403898", "GSM1403899", "GSM1403900", "GSM1403901", "GSM1403902", "GSM1403903", "GSM1403904", "GSM1403905", "GSM1403906", "GSM1403907", "GSM2140316", "GSM2140317", "GSM2140318", "GSM2140319", "GSM2140320", "GSM2140321", "GSM2140322", "GSM2140323", "GSM2140324", "GSM2140325", "GSM2140326", "GSM2140327", "GSM2140328", "GSM2140329", "GSM2140330", "GSM2140331", "GSM2140332", "GSM2140333", "GSM2140334", "GSM2140335", "GSM2140336", "GSM2140337", "GSM2140338", "GSM2140339", "GSM2140340", "GSM2140341", "GSM2140342", "GSM2140343", "GSM2140344", "GSM2140345", "GSM2140346", "GSM2140347", "GSM2140348", "GSM2140349", "GSM2140350", "GSM2140351", "GSM2140352", "GSM2140353", "GSM2140354", "GSM2140355", "GSM2140356", "GSM2140357", "GSM2140358", "GSM2140359", "GSM2140360", "GSM2140361", "GSM2140362", "GSM2140363", "GSM2140364", "GSM2140365", "GSM2140366", "GSM2140367", "GSM2140368", "GSM2140369", "GSM2140370", "GSM2140371", "GSM2140372", "GSM2140373", "GSM2140374", "GSM2140375", "GSM2140376", "GSM2140377", "GSM2140378", "GSM2140379", "GSM2140380", "GSM2140381", "GSM2140382", "GSM2140383", "GSM2140384", "GSM2140385", "GSM2140386", "GSM2140387", "GSM2140388", "GSM2140389", "GSM2140390", "GSM2140391", "GSM2140392", "GSM2140393", "GSM2140394", "GSM2140395", "GSM2140396", "GSM2140397", "GSM2140398", "GSM2140399", "GSM2140400", "GSM2140401", "GSM2140402", "GSM2140403", "GSM2140404", "GSM2140405", "GSM2140406", "GSM2140407", "GSM2140408", "GSM2140409", "GSM2140410", "GSM2140411", "GSM2140412", "GSM2140413", "GSM2140414", "GSM2140415", "GSM2140416", "GSM2140417", "GSM2140418", "GSM2140419", "GSM2140420", "GSM2140421", "GSM2140422", "GSM2140423", "GSM2140424", "GSM2140425", "GSM2140426", "GSM2140427", "GSM2140428", "GSM2140429", "GSM2140430", "GSM2140431", "GSM2140432", "GSM2140433", "GSM2140434", "GSM2140435", "GSM2140436", "GSM2140437", "GSM2140438", "GSM2140439", "GSM2140440", "GSM2140441", "GSM2140442", "GSM2140443", "GSM2140444", "GSM2140445", "GSM2140446", "GSM2140447", "GSM2140448", "GSM2140449", "GSM2140450", "GSM2140451", "GSM2140452", "GSM2140453", "GSM2140454", "GSM2140455", "GSM2140456", "GSM2140457", "GSM2140458", "GSM2140459", "GSM2140460", "GSM2140461", "GSM2140462", "GSM2140463", "GSM2140464", "GSM2140465", "GSM2140466", "GSM2140467", "GSM2140468", "GSM2140469", "GSM2140470", "GSM2140471", "GSM2140472", "GSM2140473", "GSM2140474", "GSM2140475", "GSM2140476", "GSM2140477", "GSM2140478", "GSM2140479", "GSM2140480", "GSM2140481", "GSM2140482", "GSM2140483", "GSM2140484", "GSM2140485", "GSM2140486", "GSM2140487", "GSM2140488", "GSM2140489", "GSM2140490", "GSM2140491", "GSM2140492", "GSM2140493", "GSM2140494", "GSM2140495", "GSM2140496", "GSM2140497", "GSM2140498", "GSM2140499", "GSM2140500", "GSM2140501", "GSM2140502", "GSM2140503", "GSM2140504", "GSM2140505", "GSM2140506", "GSM2140507", "GSM2140508", "GSM2140509", "GSM2140510", "GSM2140511", "GSM2140512", "GSM2140513", "GSM2140514", "GSM2140515", "GSM2140516", "GSM2140517", "GSM2140518", "GSM2140519", "GSM2140520", "GSM2140521", "GSM2140522", "GSM2140523", "GSM2140524", "GSM2140525", "GSM2140526", "GSM2140527", "GSM2140528", "GSM2140529", "GSM2140530", "GSM2140531", "GSM2140532", "GSM2140533", "GSM2140534", "GSM2140535", "GSM2140536", "GSM2140537", "GSM2140538", "GSM2140539", "GSM2140540", "GSM2140541", "GSM2140542", "GSM2140543", "GSM2140544", "GSM2140545", "GSM2140546", "GSM2140547", "GSM2140548", "GSM2140549", "GSM2140550", "GSM2140551", "GSM2140552", "GSM2140553", "GSM2140554", "GSM2140555"], "sample_count": 806, "group_sizes": null, "group_sizes_basis": null, "platform": "10656;14550", "taxon": "Homo sapiens", "title": "Integrative clustering reveals a novel split in the luminal A subtype of breast cancer with impact on outcome", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE59248 not downloaded", "asset:data:geo:GSE59248 licence not read", "asset:data:geo:GSE81002 not downloaded", "asset:data:geo:GSE81002 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "welch_t_test", "label": "Group comparison", "dsl_operations": ["welch_t"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "reordered", "quote": "Spearman rank order correlation coefficients were computed between the normalized miRNA expression levels from the Hi-TCGA data set and the corresponding log2 RSEM-normalized counts of the putative targets. Statistical differences between groups were evaluated using the Welch t-test or a Mann–Whitney rank sum test, depending on the normal distribution of the variables considered. Survival was estimated using the Kaplan–Meier method, and differences between groups were evaluated with the log-rank test using the Survival and Survminer R packages [78,79]."}}, {"id": "method-2", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}], "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": ["welch_t"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: welch_t_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": ["GSE81002", "GSE59248"], "resolved_accessions": ["GSE81002", "GSE59248"], "statements": ["The data sets analyzed in the current study are publicly available from TCGA Research Network: TCGA-BRCA project, https://www.cancer.gov/tcga; from the METABRIC project (information at https://ega-archive.org/studies/EGAS00000000098); and from Gene Expression Omnibus database (GEO; https://www.ncbi.nlm.nih.gov/gds) for the GSE81002 and GSE59248 series."], "basis": "The paper names GSE81002, GSE59248 in Gene Expression Omnibus database (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["welch_t"], "assets": ["source:pmid:37373065", "data:geo:GSE59248"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE59248"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:45:07Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9685, "completion_tokens": 2680, "cached_tokens": 264}}, "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:37373065", "type": "paper", "label": "pmid:37373065"}, {"id": "source:pmid:37373065", "type": "manuscript", "label": "PMID 37373065 full text"}, {"id": "data:geo:GSE59248", "type": "dataset", "label": "GEO GSE59248"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37373065", "type": "paper", "label": "pmid:37373065"}, {"id": "source:pmid:37373065", "type": "manuscript", "label": "PMID 37373065 full text"}, {"id": "data:geo:GSE59248", "type": "dataset", "label": "GEO GSE59248"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37373065", "type": "extraction", "used": ["source:pmid:37373065"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE59248", "type": "accession_resolution", "used": ["data:geo:GSE59248"], "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:37373065", "parent_hash": "sha256:55e8cfc491c45577b1e198ecbe7f7f0434e38067ac1518cfff4c266864f6ef0f", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE59248 licence not read", "asset:data:geo:GSE59248 not downloaded", "asset:data:geo:GSE81002 licence not read", "asset:data:geo:GSE81002 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["welch_t"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Spearman rank order correlation coefficients were computed between the normalized miRNA expression levels from the Hi-TCGA data set and the corresponding log2 RSEM-normalized counts of the putative targets. Statistical differences between groups were evaluated using the Welch t-test or a Mann–Whitney rank sum test, depending on the normal distribution of the variables considered. Survival was estimated using the Kaplan–Meier method, and differences between groups were evaluated with the log-rank test using the Survival and Survminer R packages [78,79]."], "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":"2026-11-04T02:53:14+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}}}