{"id":"W4322505572","doi":"10.1016/j.csbj.2023.02.047","title":"Exploring the variable space of shallow machine learning models for reversed-phase retention time prediction","year":2023,"lang":"en","type":"article","venue":"Computational and Structural Biotechnology Journal","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"CancerCare Manitoba; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Artificial intelligence; Convolutional neural network; Machine learning; Computer science; Deep learning; Feature (linguistics); Feature engineering; Partial least squares regression; Predictive modelling; Pattern recognition (psychology)","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":[0.0001467273,0.00008306475,0.000108742,0.00008305132,0.0004350756,0.000019444,0.0001147688,0.00009061902,0.0000225969],"category_scores_gemma":[0.0000446087,0.00006284306,0.00004607044,0.0001726548,0.00009330012,0.0001586822,0.00005453715,0.0003376113,8.553312e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000255934,"about_ca_system_score_gemma":0.00001853102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002643519,"about_ca_topic_score_gemma":1.249877e-7,"domain_scores_codex":[0.9994179,0.000009139073,0.0002177928,0.000137817,0.00009106185,0.000126282],"domain_scores_gemma":[0.999552,0.00008560236,0.0001710923,0.00007199626,0.00009294549,0.00002641938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001374024,0.0000150002,0.0001259777,0.00007446358,0.00009134985,0.000002283059,0.0001337008,0.5035565,0.3745464,0.08659295,0.0001945877,0.03452943],"study_design_scores_gemma":[0.0003858435,0.00004866916,0.00004321825,0.00002651389,0.00001532171,0.0001101799,0.00005166022,0.7330485,0.01142684,0.2541873,0.0006018321,0.00005418022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6536049,0.00007389642,0.3440197,0.001819429,0.00003585049,0.0001160106,0.0001061195,0.0001750207,0.00004910123],"genre_scores_gemma":[0.9207867,0.0002908579,0.07837903,0.000009748469,0.00007375037,0.00004349264,0.0001727747,0.00001217517,0.0002314338],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3631195,"threshold_uncertainty_score":0.3346294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04925559435816243,"score_gpt":0.2734498413254288,"score_spread":0.2241942469672664,"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."}}