{"id":"W2903325756","doi":"10.1038/s41467-018-07616-w","title":"Determining molecular properties with differential mobility spectrometry and machine learning","year":2018,"lang":"en","type":"article","venue":"Nature Communications","topic":"Mass Spectrometry Techniques and Applications","field":"Chemistry","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lab_Bell (Canada); University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; Ontario Centres of Excellence","keywords":"Differential (mechanical device); Mass spectrometry; Computer science; Chemistry; Physics; Chromatography","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":[0.00007785392,0.0001492349,0.0001489982,0.00007622126,0.0004664987,0.00006837118,0.0005955228,0.0001738184,0.0004858287],"category_scores_gemma":[0.00007400266,0.0001199358,0.00003497068,0.0002717925,0.0003725762,0.00006390596,0.0003837056,0.001040758,0.00000398052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004340398,"about_ca_system_score_gemma":0.00002173582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002456244,"about_ca_topic_score_gemma":0.0001104247,"domain_scores_codex":[0.9992358,0.0000335934,0.000158511,0.0002530416,0.0001391206,0.0001799481],"domain_scores_gemma":[0.9983584,0.00006361037,0.00009113691,0.001312878,0.0001079201,0.00006603869],"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":[0.00003956104,0.0003717612,0.05298207,0.00007819675,0.0001071169,0.000001997199,0.0002997571,9.09933e-7,0.89697,0.04319003,0.00007709858,0.005881547],"study_design_scores_gemma":[0.0009237889,0.0003722891,0.01500099,0.0002085245,0.000203561,0.0001378411,0.0003635365,0.01239496,0.907952,0.002570406,0.05891651,0.0009556132],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9502606,0.002509971,0.002063443,0.001170919,0.00001191756,0.0001743307,0.00001951611,0.0004458364,0.04334347],"genre_scores_gemma":[0.9788857,0.0002021449,0.0204146,0.00005462882,0.00004476468,0.0000915599,0.00004920007,0.0000247035,0.0002326855],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05883941,"threshold_uncertainty_score":0.5319483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01671205305136441,"score_gpt":0.2683570363125881,"score_spread":0.2516449832612236,"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."}}