{"id":"W4405966587","doi":"10.1101/2024.12.15.628538","title":"scMusketeers: Addressing imbalanced cell type annotation and batch effect reduction with a modular autoencoder","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":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Agence Nationale de la Recherche","keywords":"Autoencoder; Modular design; Reduction (mathematics); Annotation; Computer science; Artificial intelligence; Mathematics; Programming language; Deep learning","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":[0.0002855409,0.0004690169,0.000352218,0.0001223597,0.0001205204,0.0002410494,0.000183063,0.0005441348,0.000003152921],"category_scores_gemma":[0.00004425715,0.0004383511,0.00008571821,0.0002333655,0.0001204151,0.00001090016,0.00018971,0.0004978726,0.000009036977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006737482,"about_ca_system_score_gemma":0.0003758805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003253067,"about_ca_topic_score_gemma":0.000002255459,"domain_scores_codex":[0.9980455,0.0001120214,0.0002714726,0.001011467,0.000213789,0.0003457242],"domain_scores_gemma":[0.9988,0.00001117185,0.0001626891,0.0006098261,0.0002731689,0.0001431572],"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":[0.0002064109,0.00004965269,0.001016483,0.0009582723,0.0001246682,0.00001767215,0.00001468443,0.0006243652,0.9968358,0.00001077287,0.0001322828,0.0000089203],"study_design_scores_gemma":[0.000724353,0.0004821466,0.003415219,0.0006548408,0.0002366975,1.567468e-7,0.000004240309,0.003704968,0.9893732,0.000002953346,0.0007209398,0.0006803058],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9922064,0.004221379,0.001663309,0.00007325714,0.001107123,0.0005204252,0.00005272508,0.0001375212,0.00001784552],"genre_scores_gemma":[0.9947517,0.0004214833,0.003958687,0.00006782859,0.00056919,0.00007194101,0.000005013706,0.000136405,0.00001776095],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007462636,"threshold_uncertainty_score":0.9998068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009837039127077415,"score_gpt":0.2149439797237196,"score_spread":0.2051069405966421,"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."}}