{"id":"W4392850383","doi":"10.7554/elife.91415.3.sa0","title":"eLife assessment: Sensitive remote homology search by local alignment of small positional embeddings from protein language models","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Homology (biology); Computational biology; Computer science; Homology modeling; Artificial intelligence; Biology; Genetics; Amino acid; Biochemistry","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"],"consensus_categories":[],"category_scores_codex":[0.000571433,0.0004625648,0.0006601608,0.00008742391,0.00004732815,0.00003399598,0.0003857575,0.0006596884,0.0002930003],"category_scores_gemma":[0.00005158436,0.0004144235,0.0002825791,0.00009798609,0.0001923821,0.000004115939,0.0006255532,0.0007680728,0.00004968122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001009941,"about_ca_system_score_gemma":0.0004091754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001618286,"about_ca_topic_score_gemma":0.00008268459,"domain_scores_codex":[0.9974193,0.0002464802,0.000702298,0.0006371241,0.0006078127,0.0003869879],"domain_scores_gemma":[0.9986383,0.00004453939,0.0002752355,0.0006008937,0.0003102289,0.0001307705],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006236724,0.00011583,0.000001546873,0.003898201,0.0009601259,0.00005451979,0.0002227391,0.0009049026,0.0686465,0.0005531059,0.9168037,0.007776518],"study_design_scores_gemma":[0.001250153,0.001486991,0.0000119539,0.008093952,0.0008654197,0.0002122021,0.0005134241,0.1900176,0.1681762,0.0007251443,0.6265861,0.002060857],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.01748339,0.04264342,0.7950788,0.02885317,0.001195306,0.004033127,0.01974232,0.0001628245,0.09080768],"genre_scores_gemma":[0.04229027,0.006295814,0.19392,0.01566412,0.001429029,0.0001489539,0.1834088,0.0003885672,0.5564544],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6011587,"threshold_uncertainty_score":0.9998308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01232071802511107,"score_gpt":0.3136820755788423,"score_spread":0.3013613575537312,"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."}}