{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002438832,0.001172681,0.00100286,0.0005957843,0.0003302683,0.000911642,0.00167322,0.001282853,0.001879049],"category_scores_gemma":[0.00330931,0.0004903939,0.001029052,0.0004840433,0.001009418,0.0009715368,0.001972543,0.001990529,0.0009160087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000958075,"about_ca_system_score_gemma":0.001279442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004298184,"about_ca_topic_score_gemma":0.006354176,"domain_scores_codex":[0.999202,0.0001963772,0.00002985261,0.000264069,0.0002160644,0.00009159175],"domain_scores_gemma":[0.9987822,0.0005299817,0.0001018402,0.0002703842,0.0002308728,0.00008474757],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004630223,0.0001560174,0.002505521,0.0001520328,0.000301104,0.0002311146,0.0001244485,0.7373756,0.05224596,0.008777407,0.0105761,0.1870915],"study_design_scores_gemma":[0.000007414689,0.00002309364,0.000220183,0.000004451404,0.000008344943,0.00002313301,0.000005504819,0.9902287,0.006535998,0.002328962,0.0006065266,0.00000787223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03727967,0.0002876523,0.9554897,0.0003064982,0.00009987865,0.00005738404,0.0003471453,0.005149183,0.000982796],"genre_scores_gemma":[0.5215402,0.0002311365,0.4659534,0.0006814533,0.0001188169,0.0002488684,0.00245655,0.000987787,0.007781804],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004298184,"threshold_uncertainty_score":0.01289791,"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."}}