{"id":"W4293236691","doi":"10.1101/2022.04.25.489390","title":"satmut_utils: a simulation and variant calling package for multiplexed assays of variant effect","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"National Institutes of Health; Cancer Prevention and Research Institute of Texas","keywords":"Computational biology; Computer science; Saturated mutagenesis; Coding region; Scalability; Biology; Gene; Data mining; Genetics; Database","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":[0.003031807,0.002008479,0.001319099,0.000851203,0.0007791285,0.001322634,0.004116354,0.001670442,0.02031918],"category_scores_gemma":[0.007195269,0.001363408,0.002404909,0.0008337374,0.0007477023,0.001121953,0.001481644,0.002926769,0.004041287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009450137,"about_ca_system_score_gemma":0.002125891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004481597,"about_ca_topic_score_gemma":0.004330287,"domain_scores_codex":[0.9988092,0.0003580323,0.0001228622,0.0002355396,0.0003728671,0.0001014012],"domain_scores_gemma":[0.9966683,0.002402464,0.0002047282,0.0002636083,0.0003566038,0.0001044471],"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":[0.001813393,0.0006278014,0.01518664,0.002439201,0.001390401,0.0009329815,0.0006959461,0.6725866,0.04968888,0.0372167,0.1168506,0.1005709],"study_design_scores_gemma":[0.0002152343,0.0001123907,0.0007872463,0.00005495155,0.00007590961,0.0001081015,0.00002775826,0.9490596,0.02141415,0.008615899,0.01944496,0.00008371899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.04818072,0.0004636465,0.7620631,0.0004314635,0.0004637004,0.0003730112,0.01276248,0.1694079,0.005853964],"genre_scores_gemma":[0.1943462,0.0005213129,0.7271893,0.0007845476,0.00011277,0.002570202,0.02093882,0.04839059,0.005146252],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.02031918,"threshold_uncertainty_score":0.06797445,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01487390752711631,"score_gpt":0.242858551761135,"score_spread":0.2279846442340187,"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."}}