{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00132884,0.001062209,0.0007111215,0.0004794162,0.0002468579,0.0007890384,0.0008328988,0.000771194,0.00096564],"category_scores_gemma":[0.004183374,0.0004556902,0.0008242276,0.0003088565,0.0006300266,0.0009157027,0.0008629103,0.001309921,0.0003019106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009968699,"about_ca_system_score_gemma":0.001138101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008469264,"about_ca_topic_score_gemma":0.006127048,"domain_scores_codex":[0.999715,0.0001135912,0.00001641333,0.00006879542,0.00004009706,0.00004609197],"domain_scores_gemma":[0.9983953,0.001207548,0.0001091858,0.00007985721,0.0001649743,0.00004325445],"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":[0.000112739,0.00005134123,0.004081655,0.00006505781,0.00005725889,0.00008713021,0.00006417421,0.9496146,0.003869837,0.003715654,0.0003899275,0.03789067],"study_design_scores_gemma":[0.0000015296,0.00001269126,0.0001021887,0.000002380042,0.000003044381,0.00000273513,0.00000267143,0.9982398,0.0003831564,0.001211222,0.00003657359,0.00000202284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3174502,0.0006508325,0.6784771,0.0005391854,0.00003232747,0.00005587624,0.0002234191,0.001414094,0.001156994],"genre_scores_gemma":[0.9429565,0.0001881758,0.05476724,0.0001772453,0.0000167362,0.00008699472,0.0003799063,0.00006558101,0.001361648],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008469264,"threshold_uncertainty_score":0.01683992,"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."}}