{"id":"W4396593457","doi":"10.1093/bib/bbae178","title":"Scoring alignments by embedding vector similarity","year":2024,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; McMaster University; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Similarity (geometry); Embedding; Computer science; Artificial intelligence; Pattern recognition (psychology); Vector (molecular biology); Computational biology; Information retrieval; Natural language processing; Biology; Genetics; Gene","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":[0.002164083,0.001284724,0.001279131,0.004618503,0.0005919729,0.002329873,0.001325535,0.0013116,0.00672996],"category_scores_gemma":[0.01443119,0.0005296047,0.0008581742,0.004525224,0.0008645946,0.004412708,0.002496788,0.001464038,0.004357555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005926747,"about_ca_system_score_gemma":0.0008263628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008690817,"about_ca_topic_score_gemma":0.00169517,"domain_scores_codex":[0.9961266,0.001000227,0.0004148679,0.0007887346,0.001466495,0.0002030798],"domain_scores_gemma":[0.994683,0.001805953,0.0007947219,0.001060992,0.00141321,0.0002422296],"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":[0.0004815164,0.0002850698,0.01409321,0.0006284268,0.0003455619,0.0002741009,0.000379375,0.09295846,0.03350672,0.06077902,0.02405871,0.7722098],"study_design_scores_gemma":[0.00008176427,0.0003854259,0.005078888,0.00008998411,0.00007534482,0.000609464,0.0003303624,0.8264522,0.024632,0.1252799,0.01686229,0.0001222899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05389835,0.000704483,0.9352205,0.0002342107,0.0002460246,0.0001812711,0.001101661,0.00394009,0.004473339],"genre_scores_gemma":[0.3190398,0.000599891,0.670464,0.000111421,0.0001618234,0.0002462537,0.004420277,0.0008923968,0.004064148],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00672996,"threshold_uncertainty_score":0.02251399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009462677953894515,"score_gpt":0.2545989355001942,"score_spread":0.2451362575462997,"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."}}