{"id":"W4405625946","doi":"10.1093/bioinformatics/btag415","title":"Fitness translocation: improving variant effect prediction with biologically-grounded data augmentation","year":2024,"lang":"en","type":"preprint","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Bottleneck; Fitness function; Computer science; Fitness landscape; Sequence (biology); Function (biology); Machine learning; Selection (genetic algorithm); Computational biology; Artificial intelligence; Biology; Genetics; Medicine; Genetic algorithm; Population","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":[0.002170249,0.001847669,0.000950278,0.0008451726,0.0004704018,0.001096686,0.001542566,0.001369987,0.002033878],"category_scores_gemma":[0.00773899,0.0004716433,0.001299975,0.0007016594,0.0009518524,0.001851723,0.001747039,0.002211949,0.001026709],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005490595,"about_ca_system_score_gemma":0.000859574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002406211,"about_ca_topic_score_gemma":0.003807913,"domain_scores_codex":[0.9991091,0.000290976,0.00004955574,0.000342486,0.0001504321,0.00005745218],"domain_scores_gemma":[0.9973329,0.001718966,0.0001412525,0.0004815175,0.0002321878,0.00009317109],"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":[0.00092984,0.0005294028,0.01722771,0.0005451192,0.0004243802,0.0004513791,0.0002342239,0.6954806,0.03808768,0.007816045,0.01382875,0.2244449],"study_design_scores_gemma":[0.00004342614,0.0001119713,0.000660379,0.00002163714,0.00003012767,0.00007183883,0.00002615922,0.9819619,0.006472619,0.008965655,0.001612931,0.00002127505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2494156,0.002009798,0.7228919,0.001513295,0.0003318328,0.0001918744,0.005118016,0.01540427,0.003123304],"genre_scores_gemma":[0.6675661,0.0004806704,0.3147086,0.0008253235,0.0001276033,0.0003057289,0.01298467,0.00113986,0.001861576],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002406211,"threshold_uncertainty_score":0.01147753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02251479689590924,"score_gpt":0.2593764694314939,"score_spread":0.2368616725355847,"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."}}