{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36978709", "kind": "science-record", "revision": 3, "content_hash": "sha256:f57438bacb12396a04d64ec30b7f9a1df4302a5be138b5f2b9b3413a359ef8b3", "created_at": "2026-11-01T19:01:38Z", "updated_at": "2026-11-01T22:09:09Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Development of a Molecular-Subtype-Associated Immune Prognostic Signature That Can Be Recognized by MRI Radiomics Features in Bladder Cancer.", "doi": "10.3390/bioengineering10030318", "pmid": "36978709", "authors": ["Shenghua Liu", "Haotian Chen", "Zongtai Zheng", "Yanyan He", "Xudong Yao"], "journal": "Bioengineering (Basel, Switzerland)", "year": 2023, "abstract": "Background: Bladder cancer (BLCA) is highly heterogeneous with distinct molecular subtypes. This research aimed to investigate the heterogeneity of different molecular subtypes from a tumor microenvironment perspective and develop a molecular-subtype-associated immune prognostic signature that can be recognized by MRI radiomics features. Methods: Individuals with BLCA in The Cancer Genome Atlas (TCGA) and IMvigor210 were classified into luminal and basal subtypes according to the UNC classification. The proportions of tumor-infiltrating immune cells (TIICs) were examined using The Cell Type Identification by Estimating Relative Subsets of RNA Transcripts algorithm. Immune-linked genes that were expressed differentially between luminal and basal subtypes and associated with prognosis were selected to develop the immune prognostic signature (IPS) and utilized for the classification of the selected individuals into low- and high-risk groups. Functional enrichment analysis (GSEA) was performed on the IPS. The data from RNA-sequencing and MRI images of 111 BLCA samples in our center were utilized to construct a least absolute shrinkage and selection operator (LASSO) model for the prediction of patients' IPSs. Results: Half of the TIICs showed differential distributions between the luminal and basal subtypes. IPS was highly associated with molecular subtypes, critical immune checkpoint gene expression, prognoses, and immunotherapy response. The prognostic value of the IPS was further verified through several validation data sets (GSE32894, GSE31684, GSE13507, and GSE48277) and meta-analysis. GSEA revealed that some oncogenic pathways were co-enriched in the group at high risk. A novel performance of a LASSO model developed as per ten radiomics features was achieved in terms of IPS prediction in both the validation (area under the curve (AUC): 0.810) and the training (AUC: 0.839) sets. Conclusions: Dysregulation of TIICs contributed to the heterogeneity between the luminal and basal subtypes. The IPS can facilitate molecular subtyping, prognostic evaluation, and personalized immunotherapy. A LASSO model developed as per the MRI radiomics features can predict the IPSs of affected individuals.", "claims": [{"id": "claim-method", "statement": "In this study, the LASSO algorithm was used via the R package “glmnet” for radiomics signature development.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36978709", "locator": "sections[12] \"2.10. Feature Selection and Radiomics Signature Development\" paragraph 2", "quote": "In this study, the LASSO algorithm was used via the R package “glmnet” for radiomics signature development."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36978709", "locator": "sections[28] \"Data Availability Statement\" paragraph 2", "quote": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request."}], "state": "complete"}, {"id": "claim-target-result", "statement": "A novel performance of a LASSO model developed as per ten radiomics features was achieved in terms of IPS prediction in both the validation (area under the curve (AUC): 0.810) and the training (AUC: 0.839) sets.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36978709", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "A novel performance of a LASSO model developed as per ten radiomics features was achieved in terms of IPS prediction in both the validation (area under the curve (AUC): 0.810) and the training (AUC: 0.839) sets."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "A novel performance of a LASSO model developed as per ten radiomics features was achieved in terms of IPS prediction in both the validation (area under the curve (AUC): 0.810) and the training (AUC: 0.839) sets.", "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:36978709"], "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:GSE13507"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:group_comparison_wilcoxon", "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:GSE13507"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:group_comparison_wilcoxon"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36978709", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/bioengineering10030318", "sha256": "sha256:a5251e83050cd011b19c290212dcf9acb7ed15929795fd005c6993c54ef355b8", "bytes": 50293, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/bioengineering10030318", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10045524", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE13507", "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=GSE13507", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE13507", "version": null, "note": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM340537", "GSM340538", "GSM340539", "GSM340540", "GSM340541", "GSM340542", "GSM340543", "GSM340544", "GSM340545", "GSM340546", "GSM340547", "GSM340548", "GSM340549", "GSM340550", "GSM340551", "GSM340552", "GSM340553", "GSM340554", "GSM340555", "GSM340556", "GSM340557", "GSM340558", "GSM340559", "GSM340560", "GSM340561", "GSM340562", "GSM340563", "GSM340564", "GSM340565", "GSM340566", "GSM340567", "GSM340568", "GSM340569", "GSM340570", "GSM340571", "GSM340572", "GSM340573", "GSM340574", "GSM340575", "GSM340576", "GSM340577", "GSM340578", "GSM340579", "GSM340580", "GSM340581", "GSM340582", "GSM340583", "GSM340584", "GSM340585", "GSM340586", "GSM340587", "GSM340588", "GSM340589", "GSM340590", "GSM340591", "GSM340592", "GSM340593", "GSM340594", "GSM340595", "GSM340596", "GSM340597", "GSM340598", "GSM340599", "GSM340600", "GSM340601", "GSM340602", "GSM340603", "GSM340604", "GSM340605", "GSM340606", "GSM340607", "GSM340608", "GSM340609", "GSM340610", "GSM340611", "GSM340612", "GSM340613", "GSM340614", "GSM340615", "GSM340616", "GSM340617", "GSM340618", "GSM340619", "GSM340620", "GSM340621", "GSM340622", "GSM340623", "GSM340624", "GSM340625", "GSM340626", "GSM340627", "GSM340628", "GSM340629", "GSM340630", "GSM340631", "GSM340632", "GSM340633", "GSM340634", "GSM340635", "GSM340636", "GSM340637", "GSM340638", "GSM340639", "GSM340640", "GSM340641", "GSM340642", "GSM340643", "GSM340644", "GSM340645", "GSM340646", "GSM340647", "GSM340648", "GSM340649", "GSM340650", "GSM340651", "GSM340652", "GSM340653", "GSM340654", "GSM340655", "GSM340656", "GSM340657", "GSM340658", "GSM340659", "GSM340660", "GSM340661", "GSM340662", "GSM340663", "GSM340664", "GSM340665", "GSM340666", "GSM340667", "GSM340668", "GSM340669", "GSM340670", "GSM340671", "GSM340672", "GSM340673", "GSM340674", "GSM340675", "GSM340676", "GSM340677", "GSM340678", "GSM340679", "GSM340680", "GSM340681", "GSM340682", "GSM340683", "GSM340684", "GSM340685", "GSM340686", "GSM340687", "GSM340688", "GSM340689", "GSM340690", "GSM340691", "GSM340692", "GSM340693", "GSM340694", "GSM340695", "GSM340696", "GSM340697", "GSM340698", "GSM340699", "GSM340700", "GSM340701", "GSM340702", "GSM340703", "GSM340704", "GSM340705", "GSM340706", "GSM340707", "GSM340708", "GSM340709", "GSM340710", "GSM340711", "GSM340712", "GSM340713", "GSM340714", "GSM340715", "GSM340716", "GSM340717", "GSM340718", "GSM340719", "GSM340720", "GSM340721", "GSM340722", "GSM340723", "GSM340724", "GSM340725", "GSM340726", "GSM340727", "GSM340728", "GSM340729", "GSM340730", "GSM340731", "GSM340732", "GSM340733", "GSM340734", "GSM340735", "GSM340736", "GSM340737", "GSM340738", "GSM340739", "GSM340740", "GSM340741", "GSM340742", "GSM340743", "GSM340744", "GSM340745", "GSM340746", "GSM340747", "GSM340748", "GSM340749", "GSM340750", "GSM340751", "GSM340752", "GSM340753", "GSM340754", "GSM340755", "GSM340756", "GSM340757", "GSM340758", "GSM340759", "GSM340760", "GSM340761", "GSM340762", "GSM340763", "GSM340764", "GSM340765", "GSM340766", "GSM340767", "GSM340768", "GSM340769", "GSM340770", "GSM340771", "GSM340772", "GSM340773", "GSM340774", "GSM340775", "GSM340776", "GSM340777", "GSM340778", "GSM340779", "GSM340780", "GSM340781", "GSM340782", "GSM340783", "GSM340784", "GSM340785", "GSM340786", "GSM340787", "GSM340788", "GSM340789", "GSM340790", "GSM340791", "GSM340792"], "sample_count": 256, "group_sizes": null, "group_sizes_basis": null, "platform": "6102", "taxon": "Homo sapiens", "title": "Predective Value of Prognosis-Related Gene Expression Study in Primary Bladder 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:GSE31684", "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=GSE31684", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31684", "version": null, "note": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM786491", "GSM786492", "GSM786493", "GSM786494", "GSM786495", "GSM786496", "GSM786497", "GSM786498", "GSM786499", "GSM786500", "GSM786501", "GSM786502", "GSM786503", "GSM786504", "GSM786505", "GSM786506", "GSM786507", "GSM786508", "GSM786509", "GSM786510", "GSM786511", "GSM786512", "GSM786513", "GSM786514", "GSM786515", "GSM786516", "GSM786517", "GSM786518", "GSM786519", "GSM786520", "GSM786521", "GSM786522", "GSM786523", "GSM786524", "GSM786525", "GSM786526", "GSM786527", "GSM786528", "GSM786529", "GSM786530", "GSM786531", "GSM786532", "GSM786533", "GSM786534", "GSM786535", "GSM786536", "GSM786537", "GSM786538", "GSM786539", "GSM786540", "GSM786541", "GSM786542", "GSM786543", "GSM786544", "GSM786545", "GSM786546", "GSM786547", "GSM786548", "GSM786549", "GSM786550", "GSM786551", "GSM786552", "GSM786553", "GSM786554", "GSM786555", "GSM786556", "GSM786557", "GSM786558", "GSM786559", "GSM786560", "GSM786561", "GSM786562", "GSM786563", "GSM786564", "GSM786565", "GSM786566", "GSM786567", "GSM786568", "GSM786569", "GSM786570", "GSM786571", "GSM786572", "GSM786573", "GSM786574", "GSM786575", "GSM786576", "GSM786577", "GSM786578", "GSM786579", "GSM786580", "GSM786581", "GSM786582", "GSM786583"], "sample_count": 93, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Combination of a novel gene expression signature with a clinical nomogram improves the prediction of survival in high-risk bladder 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:GSE32894", "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=GSE32894", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32894", "version": null, "note": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM814052", "GSM814053", "GSM814054", "GSM814055", "GSM814056", "GSM814057", "GSM814058", "GSM814059", "GSM814060", "GSM814061", "GSM814062", "GSM814063", "GSM814064", "GSM814065", "GSM814066", "GSM814067", "GSM814068", "GSM814069", "GSM814070", "GSM814071", "GSM814072", "GSM814073", "GSM814074", "GSM814075", "GSM814076", "GSM814077", "GSM814078", "GSM814079", "GSM814080", "GSM814081", "GSM814082", "GSM814083", "GSM814084", "GSM814085", "GSM814086", "GSM814087", "GSM814088", "GSM814089", "GSM814090", "GSM814091", "GSM814092", "GSM814093", "GSM814094", "GSM814095", "GSM814096", "GSM814097", "GSM814098", "GSM814099", "GSM814100", "GSM814101", "GSM814102", "GSM814103", "GSM814104", "GSM814105", "GSM814106", "GSM814107", "GSM814108", "GSM814109", "GSM814110", "GSM814111", "GSM814112", "GSM814113", "GSM814114", "GSM814115", "GSM814116", "GSM814117", "GSM814118", "GSM814119", "GSM814120", "GSM814121", "GSM814122", "GSM814123", "GSM814124", "GSM814125", "GSM814126", "GSM814127", "GSM814128", "GSM814129", "GSM814130", "GSM814131", "GSM814132", "GSM814133", "GSM814134", "GSM814135", "GSM814136", "GSM814137", "GSM814138", "GSM814139", "GSM814140", "GSM814141", "GSM814142", "GSM814143", "GSM814144", "GSM814145", "GSM814146", "GSM814147", "GSM814148", "GSM814149", "GSM814150", "GSM814151", "GSM814152", "GSM814153", "GSM814154", "GSM814155", "GSM814156", "GSM814157", "GSM814158", "GSM814159", "GSM814160", "GSM814161", "GSM814162", "GSM814163", "GSM814164", "GSM814165", "GSM814166", "GSM814167", "GSM814168", "GSM814169", "GSM814170", "GSM814171", "GSM814172", "GSM814173", "GSM814174", "GSM814175", "GSM814176", "GSM814177", "GSM814178", "GSM814179", "GSM814180", "GSM814181", "GSM814182", "GSM814183", "GSM814184", "GSM814185", "GSM814186", "GSM814187", "GSM814188", "GSM814189", "GSM814190", "GSM814191", "GSM814192", "GSM814193", "GSM814194", "GSM814195", "GSM814196", "GSM814197", "GSM814198", "GSM814199", "GSM814200", "GSM814201", "GSM814202", "GSM814203", "GSM814204", "GSM814205", "GSM814206", "GSM814207", "GSM814208", "GSM814209", "GSM814210", "GSM814211", "GSM814212", "GSM814213", "GSM814214", "GSM814215", "GSM814216", "GSM814217", "GSM814218", "GSM814219", "GSM814220", "GSM814221", "GSM814222", "GSM814223", "GSM814224", "GSM814225", "GSM814226", "GSM814227", "GSM814228", "GSM814229", "GSM814230", "GSM814231", "GSM814232", "GSM814233", "GSM814234", "GSM814235", "GSM814236", "GSM814237", "GSM814238", "GSM814239", "GSM814240", "GSM814241", "GSM814242", "GSM814243", "GSM814244", "GSM814245", "GSM814246", "GSM814247", "GSM814248", "GSM814249", "GSM814250", "GSM814251", "GSM814252", "GSM814253", "GSM814254", "GSM814255", "GSM814256", "GSM814257", "GSM814258", "GSM814259", "GSM814260", "GSM814261", "GSM814262", "GSM814263", "GSM814264", "GSM814265", "GSM814266", "GSM814267", "GSM814268", "GSM814269", "GSM814270", "GSM814271", "GSM814272", "GSM814273", "GSM814274", "GSM814275", "GSM814276", "GSM814277", "GSM814278", "GSM814279", "GSM814280", "GSM814281", "GSM814282", "GSM814283", "GSM814284", "GSM814285", "GSM814286", "GSM814287", "GSM814288", "GSM814289", "GSM814290", "GSM814291", "GSM814292", "GSM814293", "GSM814294", "GSM814295", "GSM814296", "GSM814297", "GSM814298", "GSM814299", "GSM814300", "GSM814301", "GSM814302", "GSM814303", "GSM814304", "GSM814305", "GSM814306", "GSM814307", "GSM814308", "GSM814309", "GSM814310", "GSM814311", "GSM814312", "GSM814313", "GSM814314", "GSM814315", "GSM814316", "GSM814317", "GSM814318", "GSM814319", "GSM814320", "GSM814321", "GSM814322", "GSM814323", "GSM814324", "GSM814325", "GSM814326", "GSM814327", "GSM814328", "GSM814329", "GSM814330", "GSM814331", "GSM814332", "GSM814333", "GSM814334", "GSM814335", "GSM814336", "GSM814337", "GSM814338", "GSM814339", "GSM814340", "GSM814341", "GSM814342", "GSM814343", "GSM814344", "GSM814345", "GSM814346", "GSM814347", "GSM814348", "GSM814349", "GSM814350", "GSM814351", "GSM814352", "GSM814353", "GSM814354", "GSM814355", "GSM814356", "GSM814357", "GSM814358", "GSM814359"], "sample_count": 308, "group_sizes": null, "group_sizes_basis": null, "platform": "6947", "taxon": "Homo sapiens", "title": "A Molecular Taxonomy of Urothelial Carcinoma", "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:GSE48277", "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=GSE48277", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE48277", "version": null, "note": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1164253", "GSM1164254", "GSM1164255", "GSM1164256", "GSM1164257", "GSM1164258", "GSM1164259", "GSM1164260", "GSM1164261", "GSM1164262", "GSM1164263", "GSM1164264", "GSM1164265", "GSM1164266", "GSM1164267", "GSM1164268", "GSM1164269", "GSM1164270", "GSM1164271", "GSM1164272", "GSM1164273", "GSM1164274", "GSM1164275", "GSM1164276", "GSM1164277", "GSM1164278", "GSM1164279", "GSM1164280", "GSM1164281", "GSM1164282", "GSM1167333", "GSM1167334", "GSM1167335", "GSM1167336", "GSM1167337", "GSM1167338", "GSM1167339", "GSM1167340", "GSM1167341", "GSM1167342", "GSM1167343", "GSM1167344", "GSM1167345", "GSM1167346", "GSM1167347", "GSM1167348", "GSM1167349", "GSM1167350", "GSM1167351", "GSM1167352", "GSM1167353", "GSM1167354", "GSM1167355", "GSM1167356", "GSM1167357", "GSM1167358", "GSM1167359", "GSM1167360", "GSM1167361", "GSM1167362", "GSM1167363", "GSM1167364", "GSM1167365", "GSM1167366", "GSM1167367", "GSM1167368", "GSM1167369", "GSM1167370", "GSM1167371", "GSM1167372", "GSM1167373", "GSM1167374", "GSM1167375", "GSM1167376", "GSM1167377", "GSM1167378", "GSM1167379", "GSM1167380", "GSM1167381", "GSM1167382", "GSM1167383", "GSM1167384", "GSM1167385", "GSM1167386", "GSM1167387", "GSM1167388", "GSM1167389", "GSM1167390", "GSM1167391", "GSM1167392", "GSM1167393", "GSM1167394", "GSM1167395", "GSM1167396", "GSM1167397", "GSM1167398", "GSM1167399", "GSM1167400", "GSM1167401", "GSM1167402", "GSM1167403", "GSM1167404", "GSM1167405", "GSM1167406", "GSM1167407", "GSM1167408", "GSM1167409", "GSM1167410", "GSM1167411", "GSM1167412", "GSM1167413", "GSM1167414", "GSM1167415", "GSM1167416", "GSM1167417", "GSM1167418", "GSM1167419", "GSM1167420", "GSM1167421", "GSM1167422", "GSM1167423", "GSM1167424", "GSM1167425", "GSM1167426", "GSM1167427", "GSM1167428", "GSM1167429", "GSM1167430", "GSM1167431", "GSM1167432", "GSM1167433", "GSM1167434", "GSM1167435", "GSM1167436", "GSM1167437", "GSM1167438", "GSM1167439", "GSM1167440", "GSM1167441", "GSM1167442", "GSM1167443", "GSM1167444", "GSM1167445", "GSM1167446", "GSM1167447", "GSM1167448", "GSM1167449", "GSM1167450", "GSM1167451", "GSM1167452", "GSM1167453", "GSM1167454", "GSM1167455", "GSM1167456", "GSM1167457", "GSM1167458", "GSM1167459", "GSM1167460", "GSM1167461", "GSM1167462", "GSM1167463", "GSM1167464", "GSM1167465", "GSM1167466", "GSM1167467", "GSM1167468", "GSM1167469", "GSM1167470", "GSM1167471", "GSM1167472", "GSM1167473", "GSM1167474", "GSM1169026", "GSM1169027", "GSM1169028", "GSM1169029", "GSM1169030", "GSM1169031", "GSM1169032", "GSM1169033", "GSM1169034", "GSM1169035", "GSM1169036", "GSM1169037", "GSM1169038", "GSM1169039", "GSM1169040", "GSM1169041", "GSM1169042", "GSM1169043", "GSM1173901", "GSM1173902", "GSM1173903", "GSM1173904", "GSM1173905", "GSM1173906", "GSM1173907", "GSM1173908", "GSM1173909", "GSM1173910", "GSM1173911", "GSM1173912", "GSM1173913", "GSM1173914", "GSM1173915", "GSM1173916", "GSM1173917", "GSM1173918", "GSM1173919", "GSM1173920", "GSM1173921", "GSM1173922", "GSM1173923", "GSM1173924", "GSM1173925", "GSM1173926", "GSM1173927", "GSM1173928", "GSM1173929", "GSM1173930", "GSM1173931", "GSM1173932", "GSM1173933", "GSM1173934", "GSM1173935", "GSM1173936", "GSM1173937", "GSM1173938", "GSM1173939", "GSM1173940", "GSM1173941", "GSM1173942", "GSM1173943", "GSM1173944", "GSM1173945", "GSM1173946", "GSM1173947", "GSM1173948", "GSM1173949", "GSM1173950", "GSM1173951", "GSM1173952", "GSM1173953", "GSM1173954", "GSM1173955", "GSM1173956", "GSM1173957", "GSM1173968", "GSM1173969", "GSM1173970", "GSM1173971", "GSM1173972", "GSM1173973", "GSM1173974", "GSM1173975", "GSM1173976", "GSM1173977", "GSM1173978", "GSM1173979", "GSM1173980", "GSM1173981", "GSM1173982", "GSM1173983", "GSM1173986", "GSM1173987", "GSM1173988", "GSM1173989", "GSM1173990", "GSM1173991", "GSM1173992", "GSM1173993", "GSM1173994", "GSM1173995", "GSM1173996", "GSM1173997", "GSM1173998", "GSM1173999", "GSM1174000", "GSM1174001", "GSM1174002", "GSM1174003", "GSM1174004", "GSM1174005", "GSM1174006", "GSM1174007", "GSM1174008", "GSM1174009", "GSM1174010", "GSM1174011", "GSM1174012", "GSM1174013", "GSM1174014", "GSM1174015", "GSM1174016", "GSM1174017", "GSM1174018", "GSM1174019", "GSM1174020", "GSM1174021", "GSM1174022", "GSM1174023", "GSM1174024", "GSM1174025", "GSM1174026", "GSM1174027", "GSM1174028", "GSM1261392", "GSM1261393", "GSM1261394", "GSM1261395", "GSM1261396", "GSM1261397", "GSM1261398", "GSM1261399", "GSM1261400", "GSM1261401", "GSM1261402", "GSM1261403", "GSM1261404", "GSM1261405", "GSM1261406", "GSM1261407", "GSM1261408", "GSM1261409", "GSM1261410", "GSM1261411", "GSM1261412", "GSM1261413", "GSM1261414", "GSM1263201", "GSM1263202", "GSM1263203", "GSM1263204", "GSM1263205", "GSM1263206", "GSM1263207", "GSM1263208", "GSM1263209", "GSM1263210", "GSM1263211", "GSM1263212", "GSM1263213", "GSM1263214", "GSM1263215", "GSM1263216", "GSM1263217", "GSM1263218", "GSM1263219", "GSM1263220"], "sample_count": 349, "group_sizes": null, "group_sizes_basis": null, "platform": "10558;6947;14951", "taxon": "Homo sapiens", "title": "Identification of distinct basal and luminal subsets of human bladder cancers with different sensitivities to frontline chemotherapy", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE13507 not downloaded", "asset:data:geo:GSE13507 licence not read", "asset:data:geo:GSE31684 not downloaded", "asset:data:geo:GSE31684 licence not read", "asset:data:geo:GSE32894 not downloaded", "asset:data:geo:GSE32894 licence not read", "asset:data:geo:GSE48277 not downloaded", "asset:data:geo:GSE48277 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Wilcoxon"}}, {"id": "method-2", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "ANOVA"}}, {"id": "method-3", "family": null, "specific": null, "label": "Least absolute shrinkage and selection operator (LASSO)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "In this study, the LASSO algorithm was used via the R package “glmnet” for radiomics signature development."}}], "targets": [], "gaps": ["method.reader_named_unmapped", "method.group_comparison_wilcoxon"]}, "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": false, "required_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: wilcoxon."}, "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": ["GSE32894", "GSE31684", "GSE13507", "GSE48277"], "resolved_accessions": ["GSE32894", "GSE31684", "GSE13507", "GSE48277"], "statements": ["The data sets used and/or analyzed during the current study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE32894, GSE31684, GSE13507, GSE48277 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:36978709", "data:geo:GSE13507"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "group_comparison_wilcoxon", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE13507"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:35:05Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 14905, "completion_tokens": 2230, "cached_tokens": 188}}, "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:36978709", "type": "paper", "label": "pmid:36978709"}, {"id": "source:pmid:36978709", "type": "manuscript", "label": "PMID 36978709 full text"}, {"id": "data:geo:GSE13507", "type": "dataset", "label": "GEO GSE13507"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36978709", "type": "paper", "label": "pmid:36978709"}, {"id": "source:pmid:36978709", "type": "manuscript", "label": "PMID 36978709 full text"}, {"id": "data:geo:GSE13507", "type": "dataset", "label": "GEO GSE13507"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36978709", "type": "extraction", "used": ["source:pmid:36978709"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE13507", "type": "accession_resolution", "used": ["data:geo:GSE13507"], "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:36978709", "parent_hash": "sha256:c06531c90ab13e64517434026b2b0881231910bcded6bba52d287f74fff71d78", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE13507 licence not read", "asset:data:geo:GSE13507 not downloaded", "asset:data:geo:GSE31684 licence not read", "asset:data:geo:GSE31684 not downloaded", "asset:data:geo:GSE32894 licence not read", "asset:data:geo:GSE32894 not downloaded", "asset:data:geo:GSE48277 licence not read", "asset:data:geo:GSE48277 not downloaded", "execution.not_run", "method.group_comparison_wilcoxon", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:group_comparison_wilcoxon"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["SEA) was performed on the IPS. The data from RNA-sequencing and MRI images of 111 BLCA samples in our ce"], "order_basis": "paper_text_order:1128", "id": "assay:1"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Wilcoxon"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:27:51+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}}}