{"id":"W3088989048","doi":"10.1101/2020.09.28.317040","title":"Understanding the origins of loss of protein function by analyzing the effects of thousands of variants on activity and abundance","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"National Institutes of Health; Novo Nordisk Fonden; Novo Nordisk","keywords":"Loss function; Function (biology); Abundance (ecology); Biology; Protein folding; Protein function; Amino acid; Computational biology; Genetics; Evolutionary biology; Biochemistry; Phenotype; Ecology; Gene","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":[0.000922373,0.0004263062,0.000436351,0.0007009492,0.0002636636,0.0006433271,0.0003722723,0.0003865619,0.001018888],"category_scores_gemma":[0.001907431,0.000185514,0.0003591616,0.0007983069,0.0007703978,0.0006142518,0.000332351,0.0006505842,0.0001699507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000547435,"about_ca_system_score_gemma":0.0001914959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001181671,"about_ca_topic_score_gemma":0.001322161,"domain_scores_codex":[0.9996543,0.00006908255,0.00003540829,0.0001193992,0.00008858944,0.00003326781],"domain_scores_gemma":[0.9989151,0.000559943,0.0002947558,0.0001218057,0.00005385597,0.00005458964],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0007483683,0.0002070891,0.2113572,0.0002481757,0.000413003,0.0004957219,0.0002097065,0.06115188,0.7028766,0.004146155,0.0003580472,0.0177881],"study_design_scores_gemma":[0.0000359919,0.0002659246,0.3183274,0.00002617895,0.0001996984,0.0008111856,0.0002595315,0.3737045,0.298313,0.006027642,0.001939285,0.00008963549],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9916329,0.0002324,0.00732738,0.0000543389,0.000004508466,0.000004909516,0.0003009611,0.00007081002,0.0003718132],"genre_scores_gemma":[0.9961389,0.00008359906,0.003373524,0.00001657534,0.000002397833,0.000006317864,0.0002762878,0.00002627064,0.00007615491],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001181671,"threshold_uncertainty_score":0.004877985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01307839083545592,"score_gpt":0.2188263054493502,"score_spread":0.2057479146138942,"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."}}