{"id":"W4409761953","doi":"10.1016/j.cmpb.2025.108809","title":"TransAnno-Net: A Deep Learning Framework for Accurate Cell Type Annotation of Mouse Lung Tissue Using Self-supervised Pretraining","year":2025,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Annotation; Computer science; Artificial intelligence; Deep learning; Lung; Supervised learning; Machine learning; Natural language processing; Medicine; Artificial neural network; Internal medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006226706,0.0001533773,0.0002696155,0.0001157278,0.00006172757,0.00002355721,0.0001114176,0.0002073962,0.000001628341],"category_scores_gemma":[0.00004059182,0.00014094,0.00004478587,0.0003381388,0.00007916627,0.000005672212,0.00002990345,0.0001397371,3.304654e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009858554,"about_ca_system_score_gemma":0.00003616482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000169866,"about_ca_topic_score_gemma":0.000002584728,"domain_scores_codex":[0.9989368,0.0001702642,0.0003219738,0.0003045086,0.00006024328,0.0002061921],"domain_scores_gemma":[0.9995313,0.00009874351,0.00008336628,0.0001362479,0.0001034472,0.00004692673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001490631,0.00009578058,0.002574837,0.0004728119,0.00005065184,8.461898e-7,0.001180266,0.0002064043,0.4418601,0.00004934174,0.000004546345,0.5533553],"study_design_scores_gemma":[0.003265546,0.00249154,0.0004972075,0.0005199271,0.0001600109,0.000005715111,0.000388469,0.7807825,0.204166,0.0005839083,0.006748446,0.0003907531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3240871,0.002290111,0.6729992,0.0000321542,0.0002363285,0.0003237465,0.000001594704,0.00001436118,0.00001533164],"genre_scores_gemma":[0.2563854,0.0002033478,0.7430909,0.00008367032,0.0001176534,0.00001225728,0.00007073925,0.00001478685,0.00002127361],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7805761,"threshold_uncertainty_score":0.5747364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04013244505054804,"score_gpt":0.3669389467809872,"score_spread":0.3268065017304392,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}