{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001783723,0.000147315,0.0001239602,0.0000468374,0.00006322275,0.00008788988,0.0001417322,0.00009726277,0.000006442954],"category_scores_gemma":[0.00004763418,0.0001460016,0.0000571175,0.0001017774,0.00004369226,0.000003211322,0.0001647186,0.00008951901,0.00001534562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002758355,"about_ca_system_score_gemma":0.00003741962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003930751,"about_ca_topic_score_gemma":0.000008679184,"domain_scores_codex":[0.9991474,0.000009296484,0.0002891708,0.0001778619,0.0001131617,0.000263173],"domain_scores_gemma":[0.9997008,0.00001593103,0.00004072253,0.0001757725,0.0000192585,0.00004752504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007016661,0.0001725335,0.01218011,0.001195187,0.0004991301,0.00002625951,0.004293318,0.001271898,0.7597428,0.002016545,0.1607211,0.05781097],"study_design_scores_gemma":[0.0008816347,0.0002746296,0.004040022,0.0003250897,0.0000478644,0.00004802787,0.0005220185,0.03189268,0.1613576,0.0006802338,0.7989491,0.0009811894],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9846124,0.00519861,0.004107151,0.000494993,0.0005303552,0.0002399383,0.00009301555,0.00002328656,0.004700273],"genre_scores_gemma":[0.9923869,0.0008417465,0.005443493,0.0008328621,0.0001042645,0.00001640229,0.00005131818,0.0000223865,0.0003006519],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6382279,"threshold_uncertainty_score":0.5953773,"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."}}