{"id":"W4404404222","doi":"10.1101/2024.11.12.623336","title":"scMoE: single-cell Multi-Modal Multi-Task Learning via Sparse Mixture-of-Experts","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":"Kootenay Association for Science & Technology","funders":"","keywords":"Modal; Task (project management); Computer science; Multi-task learning; Artificial intelligence; Chemistry; Engineering; Systems engineering; Polymer chemistry","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0004442014,0.0009461248,0.0007992748,0.0002629199,0.0001657386,0.0001840329,0.0007757886,0.001392203,0.00002288987],"category_scores_gemma":[0.0001741673,0.001014963,0.0005152459,0.0003146468,0.0002581769,0.00001053153,0.00088168,0.001192251,0.00005379509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001269343,"about_ca_system_score_gemma":0.0005116199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001298966,"about_ca_topic_score_gemma":0.00001946208,"domain_scores_codex":[0.9960739,0.0002141078,0.0008481403,0.001688564,0.0003899352,0.0007853661],"domain_scores_gemma":[0.9973744,0.00003004206,0.0004595955,0.001304928,0.0004804543,0.0003506335],"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":[0.00009377102,0.0007745099,0.003775957,0.0008240723,0.0002500275,0.00006021048,0.00003582546,0.000547761,0.9933996,0.00001032695,0.0002134172,0.00001457878],"study_design_scores_gemma":[0.001191792,0.0002599066,0.001500032,0.0003975476,0.0002107758,1.091869e-7,0.000007254437,0.003402327,0.9810154,8.482046e-7,0.01084524,0.001168722],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9645633,0.009699977,0.02163469,0.00006020313,0.002790219,0.0007431462,0.0002241489,0.0002585358,0.00002575965],"genre_scores_gemma":[0.9814562,0.0004844998,0.01657429,0.0001405902,0.0007956614,0.0001004123,0.000008030037,0.0003314443,0.0001089316],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01689282,"threshold_uncertainty_score":0.9999042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01757847579605136,"score_gpt":0.2219249404461912,"score_spread":0.2043464646501399,"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."}}