{"id":"W4410871804","doi":"10.1016/j.csbj.2025.05.041","title":"Phylogenetic tree-based amino acid sequence generation for proteomics data analysis of unknown species","year":2025,"lang":"en","type":"article","venue":"Computational and Structural Biotechnology Journal","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Science and Technology Agency; Yakult Honsha; Canadian Glycomics Network; Japan Society for the Promotion of Science; Core Research for Evolutional Science and Technology; Japan Science and Technology Corporation","keywords":"Phylogenetic tree; Computational biology; Tree (set theory); Biology; Proteomics; Sequence (biology); Sequence analysis; Phylogenetics; Evolutionary biology; Bioinformatics; Genetics; Gene; Mathematics; Combinatorics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001497777,0.0001196982,0.0002435483,0.0003214999,0.0001951312,0.00002744648,0.0002672659,0.0001463364,0.00000442047],"category_scores_gemma":[0.0001291367,0.00009874769,0.00007846738,0.000325144,0.0002397597,0.000005164352,0.0001394471,0.00009600914,5.340742e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000012998,"about_ca_system_score_gemma":0.0001015279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001535547,"about_ca_topic_score_gemma":0.0000267403,"domain_scores_codex":[0.999189,0.0000266015,0.0002784413,0.0002952234,0.00007664248,0.0001340455],"domain_scores_gemma":[0.9993966,0.00002218899,0.000170411,0.0002150679,0.000170919,0.00002477535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005464304,0.000009669792,0.003107208,0.00001369264,0.0007783693,5.298729e-7,0.000004452296,0.003644158,0.976729,0.006902849,0.0001837301,0.008571719],"study_design_scores_gemma":[0.001216926,0.0003737819,0.05508066,0.00001124913,0.0007621337,0.00002713213,0.00004140045,0.2853703,0.6447393,0.009281189,0.002842791,0.0002531018],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7794633,0.001539179,0.2172254,0.001328839,0.0001096985,0.0001244941,0.0001918955,0.000004712972,0.00001252653],"genre_scores_gemma":[0.932335,0.0002725699,0.06650094,0.0001234755,0.00007395886,0.000005166582,0.000637236,0.000003742034,0.00004791508],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3319897,"threshold_uncertainty_score":0.4026814,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0350744130741434,"score_gpt":0.2978396512673604,"score_spread":0.262765238193217,"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."}}