{"id":"W4382516992","doi":"10.1021/acs.analchem.3c00921","title":"Bridging the Gap between Differential Mobility, Log <i>S</i>, and Log <i>P</i> Using Machine Learning and SHAP Analysis","year":2023,"lang":"en","type":"article","venue":"Analytical Chemistry","topic":"Analytical Chemistry and Chromatography","field":"Chemistry","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Hong Kong Government; Government of Ontario; Ontario Ministry of Research, Innovation and Science; Government of Canada; Deutsche Forschungsgemeinschaft; Ontario Centres of Excellence","keywords":"Chemistry; Solubility; Partition coefficient; Analytical Chemistry (journal); Mean squared error; Aqueous solution; Statistics; Chromatography; Mathematics; Physical chemistry","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000292115,0.0004536346,0.0007287783,0.0000752382,0.000489682,0.0002105611,0.000344977,0.0003486104,0.001267468],"category_scores_gemma":[0.0002401091,0.000366845,0.0004355864,0.001259551,0.0007915627,0.00008753612,0.0005676473,0.0009496887,0.000009307207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004492338,"about_ca_system_score_gemma":0.00003271132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008552886,"about_ca_topic_score_gemma":0.000004545841,"domain_scores_codex":[0.9973164,0.00003372308,0.000565221,0.0008851922,0.0004869257,0.0007124943],"domain_scores_gemma":[0.998322,0.0005273142,0.0001545834,0.0004928947,0.00006767667,0.0004355732],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005738817,0.000151902,0.7510085,0.001240962,0.003115312,0.0001032174,0.0001001467,0.0001982768,0.2430114,0.00009999222,0.0002886257,0.0006242784],"study_design_scores_gemma":[0.001532323,0.00002591963,0.01047109,0.0001820156,0.01038113,0.0001030807,0.0006797804,0.6997811,0.2711935,0.001465134,0.002472409,0.001712454],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9936308,0.0003427096,0.0004051987,0.0003833661,0.000009180884,0.00004214843,0.0001032938,0.0002419321,0.004841381],"genre_scores_gemma":[0.997414,0.0001446147,0.000029161,0.00005322763,0.0003836027,0.000006787317,0.0003030033,0.00003973564,0.0016259],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7405374,"threshold_uncertainty_score":0.9998783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02530241784934581,"score_gpt":0.2755753976153228,"score_spread":0.2502729797659771,"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."}}