{"id":"W4403761643","doi":"10.1101/2024.10.24.620111","title":"scMoE: single-cell mixture of experts for learning hierarchical, cell-type-specific, and interpretable representations from heterogeneous scRNA-seq data","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Type (biology); Computer science; Cell type; Artificial intelligence; Cell; Chemistry; Biology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002622291,0.0005165265,0.0005390238,0.0001355994,0.0001493178,0.0002506687,0.0008063779,0.0006949019,0.0000218827],"category_scores_gemma":[0.0001500416,0.0005537982,0.0001746219,0.0001668652,0.000199302,0.00001376324,0.001360781,0.0005904366,0.00000486747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004129775,"about_ca_system_score_gemma":0.0002863362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008577254,"about_ca_topic_score_gemma":0.00000891638,"domain_scores_codex":[0.9970047,0.0001300538,0.0005972312,0.001621976,0.0002252941,0.0004206896],"domain_scores_gemma":[0.9973546,0.00008634562,0.0002894252,0.001746777,0.0003134119,0.0002094768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001876038,0.0002266125,0.0009359482,0.0004885991,0.0001813908,0.00001459929,0.00003936047,0.0002810963,0.9958175,0.00001291905,0.00179857,0.00001574079],"study_design_scores_gemma":[0.0005902469,0.0002254313,0.0001515061,0.000285025,0.0001801714,7.16871e-8,0.00001416556,0.002035306,0.9699023,0.00001136478,0.02599434,0.0006100871],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.965719,0.0213965,0.008940606,0.00008891095,0.001432818,0.0006929789,0.001599938,0.00009566674,0.00003354257],"genre_scores_gemma":[0.9823674,0.00202612,0.01448465,0.00008848649,0.0006614454,0.00006620999,0.00007399053,0.0001824179,0.00004930489],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02591528,"threshold_uncertainty_score":0.9996914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02640327145346393,"score_gpt":0.2405601743918022,"score_spread":0.2141569029383383,"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."}}