{"id":"W4392154586","doi":"10.7554/elife.91415.2","title":"Sensitive remote homology search by local alignment of small positional embeddings from protein language models","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Smith–Waterman algorithm; Sequence alignment; Nearest neighbor search; Pattern recognition (psychology); Search algorithm; Artificial intelligence; Structural alignment; Homology (biology); Curse of dimensionality; Computational biology; Algorithm; Peptide sequence; Biology; Amino acid; Genetics; 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":[0.0008502095,0.0007859198,0.0008646329,0.0009255507,0.0002871701,0.0009353186,0.001011359,0.0009845978,0.003265104],"category_scores_gemma":[0.003910471,0.0004115492,0.0006172321,0.0008579693,0.0004827954,0.002183057,0.001531007,0.001006457,0.001579818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006835714,"about_ca_system_score_gemma":0.0007580915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001927061,"about_ca_topic_score_gemma":0.002881011,"domain_scores_codex":[0.9993072,0.0002668649,0.00004233673,0.0001481097,0.0001691481,0.00006642905],"domain_scores_gemma":[0.9987986,0.000681977,0.0001247278,0.000179865,0.0001435474,0.00007111007],"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":[0.001447985,0.0004840827,0.003204682,0.0004301503,0.0001811113,0.0003968149,0.0001766123,0.5669482,0.06451821,0.02671887,0.008251091,0.3272423],"study_design_scores_gemma":[0.00001239934,0.0000307616,0.00009967785,0.000003633377,0.000003918578,0.00001982358,0.00001531474,0.9910092,0.004069134,0.004449392,0.000281738,0.000004964808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1763496,0.0003561198,0.8116002,0.0003365551,0.0000657534,0.00009491245,0.0005118905,0.008438722,0.002246256],"genre_scores_gemma":[0.6950009,0.0001433535,0.2997246,0.0001764521,0.000034835,0.0001378029,0.00199718,0.0005489073,0.002235948],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003265104,"threshold_uncertainty_score":0.01092291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01249906618572183,"score_gpt":0.2495174648558003,"score_spread":0.2370183986700785,"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."}}