{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001570972,0.0007876498,0.0006430495,0.00195579,0.0005808757,0.0006337541,0.0007462494,0.0007162252,0.001892856],"category_scores_gemma":[0.004062311,0.0003731606,0.000807137,0.002153229,0.000311811,0.0009307771,0.0007106257,0.0007707363,0.000818635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000426737,"about_ca_system_score_gemma":0.0006280608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008368619,"about_ca_topic_score_gemma":0.001075146,"domain_scores_codex":[0.9993562,0.000283848,0.00006718246,0.000138472,0.0001140404,0.00004023149],"domain_scores_gemma":[0.9987649,0.0005433559,0.0001897565,0.0001545089,0.0002697619,0.00007773752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001907978,0.0006705334,0.02026271,0.001206492,0.0005128402,0.0009867117,0.000674362,0.07613692,0.3485631,0.007728407,0.006122276,0.5352278],"study_design_scores_gemma":[0.00007919582,0.0002820713,0.006848206,0.00005504291,0.0001152539,0.0004469091,0.0001232968,0.9246835,0.05472935,0.006240366,0.006347232,0.00004969243],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.114073,0.0004357729,0.8767747,0.0002249055,0.00005524966,0.0002085351,0.001377781,0.006189517,0.000660654],"genre_scores_gemma":[0.1796452,0.0001922919,0.816112,0.00006917102,0.00001867186,0.000157037,0.003205997,0.0003421004,0.0002574602],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00195579,"threshold_uncertainty_score":0.008308172,"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."}}