{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30930932", "kind": "science-record", "revision": 7, "content_hash": "sha256:87108a239bf0d334ef06e2ce296eddbf1492a6944e46fe2f4a0775b906010300", "created_at": "2026-11-01T15:40:43Z", "updated_at": "2026-11-01T22:00:28Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Triple-Negative Breast Cancer Genes and a Novel High-Risk Breast Cancer Prediction Model Development Based on PPI Data and Support Vector Machines.", "doi": "10.3389/fgene.2019.00180", "pmid": "30930932", "authors": ["Ming Li", "Yu Guo", "Yuan-Ming Feng", "Ning Zhang"], "journal": "Frontiers in genetics", "year": 2019, "abstract": "Triple-negative breast cancer (TNBC) is a special subtype of breast cancer that is difficult to treat. It is crucial to identify breast cancer-related genes that could provide new biomarkers for breast cancer diagnosis and potential treatment goals. In the development of our new high-risk breast cancer prediction model, seven raw gene expression datasets from the NCBI gene expression omnibus (GEO) database (GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852) were used. Using the maximum relevance minimum redundancy (mRMR) method, we selected significant genes. Then, we mapped transcripts of the genes on the protein-protein interaction (PPI) network from the Search Tool for the Retrieval of Interacting Genes (STRING) database, as well as traced the shortest path between each pair of proteins. Genes with higher betweenness values were selected from the shortest path proteins. In order to ensure validity and precision, a permutation test was performed. We randomly selected 248 proteins from the PPI network for shortest path tracing and repeated the procedure 100 times. We also removed genes that appeared more frequently in randomized results. As a result, 54 genes were selected as potential TNBC-related genes. Using 14 out the 54 genes, which are potential TNBC associated genes, as input features into a support vector machine (SVM), a novel model was trained to predict high-risk breast cancer. The prediction accuracy of normal tissues and TNBC tissues reached 95.394%, and the predictions of Stage II and Stage III TNBC reached 86.598%, indicating that such genes play important roles in distinguishing breast cancers, and that the method could be promising in practical use. According to reports, some of the 54 genes we identified from the PPI network are associated with breast cancer in the literature. Several other genes have not yet been reported but have functional resemblance with known cancer genes. These may be novel breast cancer-related genes and need further experimental validation. Gene ontology (GO) enrichment and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were performed to appraise the 54 genes. It was indicated that cellular response to organic cyclic compounds has an influence in breast cancer, and most genes may be related with viral carcinogenesis.", "claims": [{"id": "claim-method", "statement": "We employed the mRMR method (Peng et al., 2005; Li et al., 2012a,b; Zhang et al., 2012; Zou et al., 2016b; Su et al., 2018) to rank the importance of all 12,437 genes examined.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30930932", "locator": "sections[4] \"The mRMR Method\" paragraph 2", "quote": "We employed the mRMR method (Peng et al., 2005; Li et al., 2012a,b; Zhang et al., 2012; Zou et al., 2016b; Su et al., 2018) to rank the importance of all 12,437 genes examined."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets generated for this study can be found in NCBI GEO, GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30930932", "locator": "sections[21] \"Data Availability\" paragraph 2", "quote": "The datasets generated for this study can be found in NCBI GEO, GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852."}], "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:30930932"], "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:GSE15852"], "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:GSE15852"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30930932", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2019.00180", "sha256": "sha256:5cd98148cdd93be8bd2bdf9bf3d8ed82a90d69c653843ab929cf19c008917399", "bytes": 30003, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2019.00180", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6428707", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE15852", "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=GSE15852", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15852", "version": null, "note": "The datasets generated for this study can be found in NCBI GEO, GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated for this study can be found in NCBI GEO, GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM398074", "GSM398075", "GSM398076", "GSM398077", "GSM398078", "GSM398079", "GSM398080", "GSM398081", "GSM398082", "GSM398083", "GSM398084", "GSM398085", "GSM398086", "GSM398087", "GSM398088", "GSM398089", "GSM398090", "GSM398091", "GSM398092", "GSM398093", "GSM398094", "GSM398095", "GSM398096", "GSM398097", "GSM398098", "GSM398099", "GSM398100", "GSM398101", "GSM398102", "GSM398103", "GSM398104", "GSM398105", "GSM398106", "GSM398107", "GSM398108", "GSM398109", "GSM398110", "GSM398111", "GSM398112", "GSM398113", "GSM398114", "GSM398115", "GSM398116", "GSM398117", "GSM398118", "GSM398119", "GSM398120", "GSM398121", "GSM398122", "GSM398123", "GSM398124", "GSM398125", "GSM398126", "GSM398127", "GSM398128", "GSM398129", "GSM398130", "GSM398131", "GSM398132", "GSM398133", "GSM398134", "GSM398135", "GSM398136", "GSM398137", "GSM398138", "GSM398139", "GSM398140", "GSM398141", "GSM398142", "GSM398143", "GSM398144", "GSM398145", "GSM398146", "GSM398147", "GSM398148", "GSM398149", "GSM398150", "GSM398151", "GSM398152", "GSM398153", "GSM398154", "GSM398155", "GSM398156", "GSM398157", "GSM398158", "GSM398159"], "sample_count": 86, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Expression data from human breast tumors and their paired normal tissues", "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:GSE20194", "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=GSE20194", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE20194", "version": null, "note": "The datasets generated for this study can be found in NCBI GEO, GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated for this study can be found in NCBI GEO, GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM505327", "GSM505328", "GSM505329", "GSM505330", "GSM505331", "GSM505333", "GSM505334", "GSM505335", "GSM505336", "GSM505337", "GSM505338", "GSM505339", "GSM505340", "GSM505341", "GSM505342", "GSM505343", "GSM505344", "GSM505345", "GSM505346", "GSM505347", "GSM505348", "GSM505349", "GSM505350", "GSM505351", "GSM505352", "GSM505353", "GSM505354", "GSM505355", "GSM505356", "GSM505357", "GSM505358", "GSM505359", "GSM505360", "GSM505361", "GSM505362", "GSM505363", "GSM505364", "GSM505365", "GSM505366", "GSM505367", "GSM505368", "GSM505369", "GSM505370", "GSM505371", "GSM505372", "GSM505373", "GSM505374", "GSM505375", "GSM505376", "GSM505377", "GSM505378", "GSM505379", "GSM505380", "GSM505381", "GSM505382", "GSM505383", "GSM505384", "GSM505385", "GSM505386", "GSM505387", "GSM505388", "GSM505389", "GSM505390", "GSM505391", "GSM505392", "GSM505393", "GSM505394", "GSM505395", "GSM505396", "GSM505397", "GSM505398", "GSM505399", "GSM505400", "GSM505401", "GSM505402", "GSM505403", "GSM505404", "GSM505405", "GSM505406", "GSM505407", "GSM505408", "GSM505409", "GSM505410", "GSM505411", "GSM505412", "GSM505413", "GSM505414", "GSM505415", "GSM505416", "GSM505417", "GSM505418", "GSM505419", "GSM505420", "GSM505421", "GSM505422", "GSM505423", "GSM505424", "GSM505425", "GSM505426", "GSM505427", "GSM505428", "GSM505429", "GSM505430", "GSM505431", "GSM505432", "GSM505433", "GSM505434", "GSM505435", "GSM505436", "GSM505437", "GSM505438", "GSM505439", "GSM505440", "GSM505441", "GSM505442", "GSM505443", "GSM505444", "GSM505445", "GSM505446", "GSM505447", "GSM505448", "GSM505449", "GSM505450", "GSM505451", "GSM505452", "GSM505453", "GSM505454", "GSM505455", "GSM505456", "GSM505457", "GSM505458", "GSM505459", "GSM505460", "GSM505461", "GSM505462", "GSM505463", "GSM505464", "GSM505465", "GSM505466", "GSM505467", "GSM505468", "GSM505469", "GSM505470", "GSM505471", "GSM505472", "GSM505473", "GSM505474", "GSM505475", "GSM505476", "GSM505477", "GSM505478", "GSM505479", "GSM505480", "GSM505481", "GSM505482", "GSM505483", "GSM505484", "GSM505485", "GSM505486", "GSM505487", "GSM505488", "GSM505489", "GSM505490", "GSM505491", "GSM505492", "GSM505493", "GSM505494", "GSM505495", "GSM505496", "GSM505497", "GSM505498", "GSM505499", "GSM505500", "GSM505501", "GSM505502", "GSM505503", "GSM505504", "GSM505505", "GSM505506", "GSM505507", "GSM505508", "GSM505509", "GSM505510", "GSM505511", "GSM505512", "GSM505513", "GSM505514", "GSM505515", "GSM505516", "GSM505517", "GSM505518", "GSM505519", "GSM505520", "GSM505521", "GSM505522", "GSM505523", "GSM505524", "GSM505525", "GSM505526", "GSM505527", "GSM505528", "GSM505529", "GSM505530", "GSM505531", "GSM505532", "GSM505533", "GSM505534", "GSM505535", "GSM505536", "GSM505537", "GSM505538", "GSM505539", "GSM505540", "GSM505541", "GSM505542", "GSM505543", "GSM505544", "GSM505545", "GSM505546", "GSM505547", "GSM505548", "GSM505549", "GSM505550", "GSM505551", "GSM505552", "GSM505553", "GSM505554", "GSM505555", "GSM505556", "GSM505557", "GSM505558", "GSM505559", "GSM505560", "GSM505561", "GSM505562", "GSM505563", "GSM505564", "GSM505565", "GSM505566", "GSM505567", "GSM505568", "GSM505569", "GSM505570", "GSM505571", "GSM505572", "GSM505573", "GSM505574", "GSM505575", "GSM505576", "GSM505577", "GSM505578", "GSM505579", "GSM505580", "GSM505581", "GSM505582", "GSM505583", "GSM505584", "GSM505585", "GSM505586", "GSM505587", "GSM505588", "GSM505589", "GSM505590", "GSM505591", "GSM505592", "GSM505593", "GSM505594", "GSM505595", "GSM505596", "GSM505597", "GSM505598", "GSM505599", "GSM505600", "GSM505601", "GSM505602", "GSM505603", "GSM505604", "GSM505605"], "sample_count": 278, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "MAQC-II Project: human breast cancer (BR) data set", "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:GSE20271", "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=GSE20271", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE20271", "version": null, "note": "The datasets generated for this study can be found in NCBI GEO, GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated for this study can be found in NCBI GEO, GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM508012", "GSM508013", "GSM508014", "GSM508015", "GSM508016", "GSM508017", "GSM508018", "GSM508019", "GSM508020", "GSM508021", "GSM508022", "GSM508023", "GSM508024", "GSM508025", "GSM508026", "GSM508027", "GSM508028", "GSM508029", "GSM508030", "GSM508031", "GSM508032", "GSM508033", "GSM508034", "GSM508035", "GSM508036", "GSM508037", "GSM508038", "GSM508039", "GSM508040", "GSM508041", "GSM508042", "GSM508043", "GSM508044", "GSM508045", "GSM508046", "GSM508047", "GSM508048", "GSM508049", "GSM508050", "GSM508051", "GSM508052", "GSM508053", "GSM508054", "GSM508055", "GSM508056", "GSM508057", "GSM508058", "GSM508059", "GSM508060", "GSM508061", "GSM508062", "GSM508063", "GSM508064", "GSM508065", "GSM508066", "GSM508067", "GSM508068", "GSM508069", "GSM508070", "GSM508071", "GSM508072", "GSM508073", "GSM508074", "GSM508075", "GSM508076", "GSM508077", "GSM508078", "GSM508079", "GSM508080", "GSM508081", "GSM508082", "GSM508083", "GSM508084", "GSM508085", "GSM508086", "GSM508087", "GSM508088", "GSM508089", "GSM508090", "GSM508091", "GSM508092", "GSM508093", "GSM508094", "GSM508095", "GSM508096", "GSM508097", "GSM508098", "GSM508099", "GSM508100", "GSM508101", "GSM508102", "GSM508103", "GSM508104", "GSM508105", "GSM508106", "GSM508107", "GSM508108", "GSM508109", "GSM508110", "GSM508111", "GSM508112", "GSM508113", "GSM508114", "GSM508115", "GSM508116", "GSM508117", "GSM508118", "GSM508119", "GSM508120", "GSM508121", "GSM508122", "GSM508123", "GSM508124", "GSM508125", "GSM508126", "GSM508127", "GSM508128", "GSM508129", "GSM508130", "GSM508131", "GSM508132", "GSM508133", "GSM508134", "GSM508135", "GSM508136", "GSM508137", "GSM508138", "GSM508139", "GSM508140", "GSM508141", "GSM508142", "GSM508143", "GSM508144", "GSM508145", "GSM508146", "GSM508147", "GSM508148", "GSM508149", "GSM508150", "GSM508151", "GSM508152", "GSM508153", "GSM508154", "GSM508155", "GSM508156", "GSM508157", "GSM508158", "GSM508159", "GSM508160", "GSM508161", "GSM508162", "GSM508163", "GSM508164", "GSM508165", "GSM508166", "GSM508167", "GSM508168", "GSM508169", "GSM508170", "GSM508171", "GSM508172", "GSM508173", "GSM508174", "GSM508175", "GSM508176", "GSM508177", "GSM508178", "GSM508179", "GSM508180", "GSM508181", "GSM508182", "GSM508183", "GSM508184", "GSM508185", "GSM508186", "GSM508187", "GSM508188", "GSM508189"], "sample_count": 178, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Expression data from breast cancer FNA biopsies from patients", "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:GSE31519", "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=GSE31519", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31519", "version": null, "note": "The datasets generated for this study can be found in NCBI GEO, GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated for this study can be found in NCBI GEO, GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM782523", "GSM782524", "GSM782525", "GSM782526", "GSM782527", "GSM782528", "GSM782529", "GSM782530", "GSM782531", "GSM782532", "GSM782533", "GSM782534", "GSM782535", "GSM782536", "GSM782537", "GSM782538", "GSM782539", "GSM782540", "GSM782541", "GSM782542", "GSM782543", "GSM782544", "GSM782545", "GSM782546", "GSM782547", "GSM782548", "GSM782549", "GSM782550", "GSM782551", "GSM782552", "GSM782553", "GSM782554", "GSM782555", "GSM782556", "GSM782557", "GSM782558", "GSM782559", "GSM782560", "GSM782561", "GSM782562", "GSM782563", "GSM782564", "GSM782565", "GSM782566", "GSM782567", "GSM782568", "GSM782569", "GSM782570", "GSM782571", "GSM782572", "GSM782573", "GSM782574", "GSM782575", "GSM782576", "GSM782577", "GSM782578", "GSM782579", "GSM782580", "GSM782581", "GSM782582", "GSM782583", "GSM782584", "GSM782585", "GSM782586", "GSM782587", "GSM782588", "GSM782589"], "sample_count": 67, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "A Clinically Relevant Gene Signature in Triple-Negative and Basal-Like Breast 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:GSE32646", "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=GSE32646", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32646", "version": null, "note": "The datasets generated for this study can be found in NCBI GEO, GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated for this study can be found in NCBI GEO, GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM809184", "GSM809185", "GSM809186", "GSM809187", "GSM809188", "GSM809189", "GSM809190", "GSM809191", "GSM809192", "GSM809193", "GSM809194", "GSM809195", "GSM809196", "GSM809197", "GSM809198", "GSM809199", "GSM809200", "GSM809201", "GSM809202", "GSM809203", "GSM809204", "GSM809205", "GSM809206", "GSM809207", "GSM809208", "GSM809209", "GSM809210", "GSM809211", "GSM809212", "GSM809213", "GSM809214", "GSM809215", "GSM809216", "GSM809217", "GSM809218", "GSM809219", "GSM809220", "GSM809221", "GSM809222", "GSM809223", "GSM809224", "GSM809225", "GSM809226", "GSM809227", "GSM809228", "GSM809229", "GSM809230", "GSM809231", "GSM809232", "GSM809233", "GSM809234", "GSM809235", "GSM809236", "GSM809237", "GSM809238", "GSM809239", "GSM809240", "GSM809241", "GSM809242", "GSM809243", "GSM809244", "GSM809245", "GSM809246", "GSM809247", "GSM809248", "GSM809249", "GSM809250", "GSM809251", "GSM809252", "GSM809253", "GSM809254", "GSM809255", "GSM809256", "GSM809257", "GSM809258", "GSM809259", "GSM809260", "GSM809261", "GSM809262", "GSM809263", "GSM809264", "GSM809265", "GSM809266", "GSM809267", "GSM809268", "GSM809269", "GSM809270", "GSM809271", "GSM809272", "GSM809273", "GSM809274", "GSM809275", "GSM809276", "GSM809277", "GSM809278", "GSM809279", "GSM809280", "GSM809281", "GSM809282", "GSM809283", "GSM809284", "GSM809285", "GSM809286", "GSM809287", "GSM809288", "GSM809289", "GSM809290", "GSM809291", "GSM809292", "GSM809293", "GSM809294", "GSM809295", "GSM809296", "GSM809297", "GSM809298"], "sample_count": 115, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "GSTP1 expression predicts poor pathological complete response to neoadjuvant chemotherapy in ER-negative breast 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:GSE45255", "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=GSE45255", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE45255", "version": null, "note": "The datasets generated for this study can be found in NCBI GEO, GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated for this study can be found in NCBI GEO, GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1100037", "GSM1100038", "GSM1100039", "GSM1100040", "GSM1100041", "GSM1100042", "GSM1100043", "GSM1100044", "GSM1100045", "GSM1100046", "GSM1100047", "GSM1100048", "GSM1100049", "GSM1100050", "GSM1100051", "GSM1100052", "GSM1100053", "GSM1100054", "GSM1100055", "GSM1100056", "GSM1100057", "GSM1100058", "GSM1100059", "GSM1100060", "GSM1100061", "GSM1100062", "GSM1100063", "GSM1100064", "GSM1100065", "GSM1100066", "GSM1100067", "GSM1100068", "GSM1100069", "GSM1100070", "GSM1100071", "GSM1100072", "GSM1100073", "GSM1100074", "GSM1100075", "GSM1100076", "GSM1100077", "GSM1100078", "GSM1100079", "GSM1100080", "GSM1100081", "GSM1100082", "GSM1100083", "GSM1100084", "GSM1100085", "GSM1100086", "GSM1100087", "GSM1100088", "GSM1100089", "GSM1100090", "GSM1100091", "GSM1100092", "GSM1100093", "GSM1100094", "GSM1100095", "GSM1100096", "GSM1100097", "GSM1100098", "GSM1100099", "GSM1100100", "GSM1100101", "GSM1100102", "GSM1100103", "GSM1100104", "GSM1100105", "GSM1100106", "GSM1100107", "GSM1100108", "GSM1100109", "GSM1100110", "GSM1100111", "GSM1100112", "GSM1100113", "GSM1100114", "GSM1100115", "GSM1100116", "GSM1100117", "GSM1100118", "GSM1100119", "GSM1100120", "GSM1100121", "GSM1100122", "GSM1100123", "GSM1100124", "GSM1100125", "GSM1100126", "GSM1100127", "GSM1100128", "GSM1100129", "GSM1100130", "GSM1100131", "GSM1100132", "GSM1100133", "GSM1100134", "GSM1100135", "GSM1100136", "GSM1100137", "GSM1100138", "GSM1100139", "GSM1100140", "GSM1100141", "GSM1100142", "GSM1100143", "GSM1100144", "GSM1100145", "GSM1100146", "GSM1100147", "GSM1100148", "GSM1100149", "GSM1100150", "GSM1100151", "GSM1100152", "GSM1100153", "GSM1100154", "GSM1100155", "GSM1100156", "GSM1100157", "GSM1100158", "GSM1100159", "GSM1100160", "GSM1100161", "GSM1100162", "GSM1100163", "GSM1100164", "GSM1100165", "GSM1100166", "GSM1100167", "GSM1100168", "GSM1100169", "GSM1100170", "GSM1100171", "GSM1100172", "GSM1100173", "GSM1100174", "GSM1100175"], "sample_count": 139, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Expression Profiles of Breast Tumors from Singapore and Europe", "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:GSE9574", "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=GSE9574", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE9574", "version": null, "note": "The datasets generated for this study can be found in NCBI GEO, GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated for this study can be found in NCBI GEO, GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM241999", "GSM242000", "GSM242001", "GSM242002", "GSM242003", "GSM242004", "GSM242005", "GSM242006", "GSM242007", "GSM242008", "GSM242009", "GSM242010", "GSM242011", "GSM242012", "GSM242013", "GSM242014", "GSM242015", "GSM242016", "GSM242017", "GSM242018", "GSM242019", "GSM242020", "GSM242021", "GSM242022", "GSM242023", "GSM242024", "GSM242025", "GSM242026", "GSM242027"], "sample_count": 29, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Gene expression abnormalities in histologically normal breast epithelium of breast cancer patients", "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:30930932:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:85a14ea2bb6e2221e58c00d8e429c49cc087ff3b8140f93e2e284c97b92bd5ee", "bytes": 3142, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T1", "version": null, "note": "The 54 candidate breast cancer-related genes and betweenness.", "structure": {"pmcid": "PMC6428707", "section_index": 11, "section_title": "The Top 54 Genes on PPI Shortest Paths", "row_count": 55, "column_count": 4}, "table": {"label": "Table 1", "caption": "The 54 candidate breast cancer-related genes and betweenness.", "rows": [["hgnc_symbol", "ensp", "Betweenness", "Reference"], ["MAGOH", "ENSP00000360525", "1777", "Kataoka et al., 2001"], ["CBL", "ENSP00000264033", "1548", "Thien and Langdon, 2001"], ["RPS3", "ENSP00000433821", "1380", "Jang et al., 2004"], ["FGFR1", "ENSP00000393312", "1286", "Pirvola et al., 2002"], ["RHOA", "ENSP00000400175", "1237", "Strutt et al., 1997"], ["EP300", "ENSP00000263253", "1048", "Gayther et al., 2000"], ["RAC1", "ENSP00000348461", "871", "Gu et al., 2003"], ["CDK1", "ENSP00000378699", "852", "Santamaría et al., 2007"], ["CDH1", "ENSP00000261769", "848", "Konishi et al., 2004"], ["EGFR", "ENSP00000275493", "815", "Kobayashi et al., 2005"], ["JUN", "ENSP00000360266", "811", "Curran and Franza, 1988"], ["NOTCH1", "ENSP00000277541", "803", "Nicolas et al., 2003"], ["HCFC1", "ENSP00000309555", "795", "Jolly et al., 2015"], ["OGT", "ENSP00000362824", "786", "Sodi et al., 2015"], ["PPP1CB", "ENSP00000296122", "786", "Alquobaili et al., 2009"], ["CFTR", "ENSP00000003084", "767", "Zhang et al., 2013"], ["ERBB2", "ENSP00000269571", "763", "Blackwell et al., 2010"], ["HIF1A", "ENSP00000338018", "762", "Ponente et al., 2017"], ["ESR1", "ENSP00000206249", "745", "Robinson et al., 2013"], ["HDAC1", "ENSP00000362649", "705", "Kawai et al., 2003"], ["RPS27A", "ENSP00000272317", "672", "Wang et al., 2014"], ["RELA", "ENSP00000384273", "658", "Xia et al., 2010"], ["CREB1", "ENSP00000387699", "582", "Chhabra et al., 2007"], ["CCNB1", "ENSP00000256442", "565", "Ding et al., 2014"], ["MAPK8", "ENSP00000353483", "561", "Slattery et al., 2015"], ["SRC", "ENSP00000350941", "559", "Zhang et al., 2013"], ["OPTN", "ENSP00000263036", "558", "Jeffrey et al., 1999"], ["ITGB1", "ENSP00000303351", "553", "Yang et al., 2016"], ["RPS2", "ENSP00000341885", "549", "Douglas, 1997"], ["NFKB1", "ENSP00000226574", "512", "Curran et al., 2002"], ["MT-ATP6", "ENSP00000354632", "508", "You et al., 2009"], ["MT-CO3", "ENSP00000354982", "508", ""], ["ATP5A1", "ENSP00000282050", "508", "Lotz et al., 2014"], ["WDR5", "ENSP00000351446", "466", "Dai et al., 2015"], ["CREBBP", "ENSP00000262367", "466", "Gupta et al., 2014"], ["RAN", "ENSP00000376176", "445", "Yuen et al., 2013"], ["HNRNPK", "ENSP00000365439", "429", ""], ["BTRC", "ENSP00000359206", "408", ""], ["PXN", "ENSP00000228307", "406", "Sp et al., 2017"], ["CYC1", "ENSP00000317159", "394", "Han et al., 2016"], ["CYCS", "ENSP00000307786", "391", ""], ["SHC1", "ENSP00000401303", "383", "Wagner et al., 2004"], ["MEF2A", "ENSP00000346389", "381", ""], ["NCOR2", "ENSP00000384018", "362", "Green et al., 2008"], ["LIN7A", "ENSP00000447488", "347", "Gruel et al., 2016"], ["PCNA", "ENSP00000368438", "336", "Kato et al., 2002"], ["YAP1", "ENSP00000282441", "335", "Yu et al., 2013"], ["MPP5", "ENSP00000261681", "331", "Van Rossum et al., 2006"], ["AMOT", "ENSP00000361027", "331", "Zhang and Fan, 2015"], ["RANGAP1", "ENSP00000348577", "323", ""], ["FOS", "ENSP00000306245", "316", "Langer et al., 2006"], ["STAT1", "ENSP00000354394", "313", "Khodarev et al., 2010"], ["AR", "ENSP00000363822", "308", "Subik et al., 2010"], ["SUMO2", "ENSP00000405965", "297", "Subramonian et al., 2014"]], "row_count": 55, "column_count": 4, "numeric_cells": 158, "header_rows": 1, "locator": "section[11]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:30930932:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d36377d2da5c8fa063713152e11f27073b25d0fd0e0ecfab616fa217a475be9a", "bytes": 861, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T2", "version": null, "note": "Results of the GO enrichment analysis.", "structure": {"pmcid": "PMC6428707", "section_index": 12, "section_title": "Function Gene Enrichment Analysis", "row_count": 11, "column_count": 4}, "table": {"label": "Table 2", "caption": "Results of the GO enrichment analysis.", "rows": [["Go term entry ID", "Description", "p-value", "Count"], ["GO:0071407", "Cellular response to organic cyclic compound", "1.217E-12", "16"], ["GO:0006979", "Response to oxidative stress", "9.108E-11", "13"], ["GO:0048511", "Rhythmic process", "1.467E-10", "12"], ["GO:0071396", "Cellular response to lipid", "1.897E-10", "14"], ["GO:0048732", "Heart development", "2.055E-10", "14"], ["GO:0009612", "Gland development", "2.349E-10", "13"], ["GO:0009314", "Response to mechanical stimulus", "3.549E-10", "10"], ["GO:0009314", "Response to radiation", "3.666E-10", "13"], ["GO:0038095", "Fc-epsilon receptor signaling pathway", "5.244E-10", "9"], ["GO:0000302", "Response to reactive oxygen species", "6.401E-10", "10"]], "row_count": 11, "column_count": 4, "numeric_cells": 30, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:30930932:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:fc963e1ccd1e04b082d84ba6d25e2030ef50b63387f7d59fc6bb8ba1401e549e", "bytes": 792, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#T3", "version": null, "note": "Results of the KEGG enrichment analysis.", "structure": {"pmcid": "PMC6428707", "section_index": 12, "section_title": "Function Gene Enrichment Analysis", "row_count": 11, "column_count": 4}, "table": {"label": "Table 3", "caption": "Results of the KEGG enrichment analysis.", "rows": [["KEGG term entry ID", "Description", "p-value", "Count"], ["hsa05200", "Pathways in cancer", "7.835E-13", "20"], ["hsa05167", "Kaposi’s sarcoma-associated herpesvirus infection", "1.406E-10", "13"], ["hsa05161", "Hepatitis B", "2.393E-10", "12"], ["hsa05168", "Herpes simplex infection", "3.262E-10", "13"], ["hsa05203", "Viral carcinogenesis", "9.155E-10", "13"], ["hsa04520", "Adherens junction", "1.430E-09", "9"], ["hsa05215", "Prostate cancer", "7.949E-09", "9"], ["hsa04024", "cAMP signaling pathway", "9.423E-09", "12"], ["hsa05205", "Proteoglycans in cancer", "1.249E-08", "12"], ["hsa01522", "Endocrine resistance", "1.915E-08", "9"]], "row_count": 11, "column_count": 4, "numeric_cells": 30, "header_rows": 1, "locator": "section[12]/table-wrap[2]#T3"}}, {"id": "asset:table:pmid:30930932:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:838140abbbfa4a0ec00d00d437ee13a3fed1a36f0d3edcfdda59b98d6bfd3262", "bytes": 368, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T4", "version": null, "note": "The performance of the high-risk breast cancer classification model.", "structure": {"pmcid": "PMC6428707", "section_index": 13, "section_title": "High-Risk Breast Cancer Prediction", "row_count": 3, "column_count": 5}, "table": {"label": "Table 4", "caption": "The performance of the high-risk breast cancer classification model.", "rows": [["", "ACC", "Precision", "Recall", "F-measure"], ["Normal and TNBC", "95.394%", "88.889%", "100%", "94.118%"], ["II and III", "86.597%", "80.952%", "100%", "89.474%"]], "row_count": 3, "column_count": 5, "numeric_cells": 8, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T4"}}], "gaps": ["asset:data:geo:GSE15852 not downloaded", "asset:data:geo:GSE15852 licence not read", "asset:data:geo:GSE20194 not downloaded", "asset:data:geo:GSE20194 licence not read", "asset:data:geo:GSE20271 not downloaded", "asset:data:geo:GSE20271 licence not read", "asset:data:geo:GSE31519 not downloaded", "asset:data:geo:GSE31519 licence not read", "asset:data:geo:GSE32646 not downloaded", "asset:data:geo:GSE32646 licence not read", "asset:data:geo:GSE45255 not downloaded", "asset:data:geo:GSE45255 licence not read", "asset:data:geo:GSE9574 not downloaded", "asset:data:geo:GSE9574 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Support Vector Machines"}}, {"id": "method-2", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "PPI"}}, {"id": "method-3", "family": null, "specific": null, "label": "maximum relevance minimum redundancy (mRMR)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We employed the mRMR method (Peng et al., 2005; Li et al., 2012a,b; Zhang et al., 2012; Zou et al., 2016b; Su et al., 2018) to rank the importance of all 12,437 genes examined."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: support_vector_machine."}, "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": ["GSE31519", "GSE9574", "GSE20194", "GSE20271", "GSE32646", "GSE45255", "GSE15852"], "resolved_accessions": ["GSE31519", "GSE9574", "GSE20194", "GSE20271", "GSE32646", "GSE45255", "GSE15852"], "statements": ["The datasets generated for this study can be found in NCBI GEO, GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852."], "basis": "The paper names GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, GSE15852 in NCBI Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "assets": ["source:pmid:30930932", "data:geo:GSE15852", "asset:table:pmid:30930932:1", "asset:table:pmid:30930932:2", "asset:table:pmid:30930932:3", "asset:table:pmid:30930932:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE15852"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:14:18Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 22694, "completion_tokens": 2142, "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:30930932", "type": "paper", "label": "pmid:30930932"}, {"id": "source:pmid:30930932", "type": "manuscript", "label": "PMID 30930932 full text"}, {"id": "data:geo:GSE15852", "type": "dataset", "label": "GEO GSE15852"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30930932", "type": "paper", "label": "pmid:30930932"}, {"id": "source:pmid:30930932", "type": "manuscript", "label": "PMID 30930932 full text"}, {"id": "data:geo:GSE15852", "type": "dataset", "label": "GEO GSE15852"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30930932", "type": "extraction", "used": ["source:pmid:30930932"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE15852", "type": "accession_resolution", "used": ["data:geo:GSE15852"], "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:30930932", "parent_hash": "sha256:1d2dae8f6dadb37407fb0b74b88937a263d6fc35f01f85e1f0ddaaabe7792c10", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE15852 licence not read", "asset:data:geo:GSE15852 not downloaded", "asset:data:geo:GSE20194 licence not read", "asset:data:geo:GSE20194 not downloaded", "asset:data:geo:GSE20271 licence not read", "asset:data:geo:GSE20271 not downloaded", "asset:data:geo:GSE31519 licence not read", "asset:data:geo:GSE31519 not downloaded", "asset:data:geo:GSE32646 licence not read", "asset:data:geo:GSE32646 not downloaded", "asset:data:geo:GSE45255 licence not read", "asset:data:geo:GSE45255 not downloaded", "asset:data:geo:GSE9574 licence not read", "asset:data:geo:GSE9574 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["train_classifier", "cross_validate", "roc_auc"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Support Vector Machines"], "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":"2026-11-04T02:39:19+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}}}