{"id":"W4411224260","doi":"10.1002/pmic.13971","title":"Validation and Community Sharing of Ocean Spectral Libraries Generated by Machine Learning for Data Independent Acquisition Ocean Metaproteomic Analyses","year":2025,"lang":"en","type":"article","venue":"PROTEOMICS","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Institute of General Medical Sciences; Simons Foundation; National Institutes of Health; National Science Foundation","keywords":"Metaproteomics; Computer science; Metagenomics; Biology","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":[0.00916717,0.0009868555,0.001025535,0.003009315,0.00109547,0.001675899,0.001241577,0.0007327606,0.0006226986],"category_scores_gemma":[0.01156951,0.0004099508,0.001005888,0.002159187,0.0007049754,0.001593091,0.003407609,0.0008850693,0.0006538059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006643194,"about_ca_system_score_gemma":0.001106746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001393897,"about_ca_topic_score_gemma":0.001196068,"domain_scores_codex":[0.9950457,0.001465161,0.0004050098,0.001179471,0.001508687,0.0003960307],"domain_scores_gemma":[0.9914112,0.002104707,0.001050698,0.001842651,0.003056425,0.0005343433],"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":[0.002607832,0.002513772,0.09920157,0.0007272568,0.0007214563,0.0004083774,0.001101975,0.02202486,0.6739206,0.001373715,0.001718629,0.19368],"study_design_scores_gemma":[0.0001984119,0.00173654,0.09885884,0.0001079658,0.0003476553,0.0004840189,0.0008961912,0.3766687,0.5119639,0.00206338,0.006480411,0.0001940487],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9503748,0.0002637144,0.04576522,0.00008131637,0.00004118689,0.0001680426,0.00142951,0.001077684,0.0007984862],"genre_scores_gemma":[0.9005623,0.0002178902,0.08841807,0.0001334485,0.00002147358,0.0003765017,0.009458958,0.0002780941,0.0005332484],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.00916717,"threshold_uncertainty_score":0.04848117,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04776926891472868,"score_gpt":0.3042713573600118,"score_spread":0.2565020884452831,"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."}}