{"id":"W4386348348","doi":"10.1101/2023.08.30.555602","title":"Scoring alignments by embedding vector similarity","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Leverage (statistics); Similarity (geometry); Embedding; Computer science; Cosine similarity; Artificial intelligence; Context (archaeology); Sequence alignment; Sequence (biology); Source code; Machine learning; Pattern recognition (psychology); Data mining; Natural language processing; Peptide sequence; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002016672,0.001051665,0.001153609,0.004270803,0.0004265115,0.001846071,0.00108459,0.001190751,0.00522969],"category_scores_gemma":[0.01156016,0.000353318,0.000551396,0.003839519,0.0008637157,0.002802082,0.001897562,0.001247074,0.002753851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005794904,"about_ca_system_score_gemma":0.0006905734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007369476,"about_ca_topic_score_gemma":0.001176078,"domain_scores_codex":[0.9963291,0.001145174,0.0003176507,0.0006956625,0.001315596,0.0001968362],"domain_scores_gemma":[0.9945847,0.001924776,0.0009022302,0.0009372891,0.001352989,0.0002979993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007394806,0.0004415064,0.02281391,0.000627825,0.0003979301,0.0003184367,0.0002433372,0.218324,0.04232641,0.06840023,0.02231862,0.6230483],"study_design_scores_gemma":[0.00004702891,0.0002224084,0.003323542,0.00005204921,0.0000310438,0.0002563281,0.000122012,0.9131021,0.0163076,0.06106327,0.005418625,0.00005392344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.105955,0.0008361143,0.8832623,0.0003022683,0.0002202222,0.0001497449,0.001031296,0.003457882,0.004785147],"genre_scores_gemma":[0.5616884,0.0003658874,0.4305202,0.00009924666,0.0001414018,0.0001406901,0.002924575,0.0005485596,0.003570867],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00522969,"threshold_uncertainty_score":0.01749504,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01342372707161297,"score_gpt":0.2529786501048142,"score_spread":0.2395549230332013,"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."}}