{"id":"W4408454493","doi":"10.1101/2025.03.09.642228","title":"<i>ProteoSync</i> , a program for ortholog selection, automated sequence alignment and conservation projection onto protein atomic coordinates","year":2025,"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":"Sinai Health System; Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"","keywords":"Selection (genetic algorithm); Projection (relational algebra); Sequence (biology); Computational biology; Computer science; Conserved sequence; Sequence alignment; Biology; Algorithm; Genetics; Artificial intelligence; Peptide sequence; 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":[0.002370591,0.002349041,0.001394248,0.00266918,0.001394493,0.001790412,0.002491387,0.0006054787,0.03765614],"category_scores_gemma":[0.003895966,0.001364174,0.001099238,0.001696885,0.001145422,0.001770808,0.003357839,0.002746877,0.02173273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009426856,"about_ca_system_score_gemma":0.002715184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00399633,"about_ca_topic_score_gemma":0.005152149,"domain_scores_codex":[0.9989781,0.0001520715,0.00008597891,0.0002164059,0.0004800466,0.00008742172],"domain_scores_gemma":[0.9991397,0.000257942,0.000119379,0.0001909966,0.0001879802,0.0001040358],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005021797,0.000213608,0.002835351,0.001182377,0.0003306552,0.0007194065,0.0004355049,0.007225326,0.03372829,0.03521451,0.7766554,0.1409574],"study_design_scores_gemma":[0.0007630542,0.0001107945,0.005778715,0.0003351207,0.0001006452,0.001674581,0.0001080027,0.2403938,0.08558881,0.05151335,0.6132624,0.0003707885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.006610025,0.0002112737,0.5606061,0.0006107917,0.0002686883,0.0003647699,0.02943847,0.392648,0.009241813],"genre_scores_gemma":[0.05228011,0.0004405402,0.7082588,0.0005793855,0.000176421,0.001517254,0.07735132,0.1465916,0.01280449],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.03765614,"threshold_uncertainty_score":0.1259723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009620870331512902,"score_gpt":0.2600677491958133,"score_spread":0.2504468788643004,"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."}}