{"id":"W2608113649","doi":"10.1021/acs.energyfuels.6b03251","title":"Multiobjective Feature Selection Approach to Quantitative Structure Property Relationship Models for Predicting the Octane Number of Compounds Found in Gasoline","year":2017,"lang":"en","type":"article","venue":"Energy & Fuels","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Quantitative structure–activity relationship; Overfitting; Feature selection; Octane rating; Computer science; Feature (linguistics); Selection (genetic algorithm); Octane; Biochemical engineering; Data mining; Artificial intelligence; Machine learning; Gasoline; Chemistry; Artificial neural network; Engineering","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":[0.001367986,0.00105923,0.001231117,0.001305118,0.0003044963,0.0007039574,0.0008568492,0.0007415023,0.0007478003],"category_scores_gemma":[0.001610905,0.0003755983,0.001422032,0.0009135072,0.0003168139,0.0003914523,0.0004667713,0.0007317578,0.0001459584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006322809,"about_ca_system_score_gemma":0.0009000628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005319068,"about_ca_topic_score_gemma":0.00358955,"domain_scores_codex":[0.9995182,0.0001975779,0.00003489051,0.00008542631,0.0001216756,0.00004233226],"domain_scores_gemma":[0.9992747,0.000461916,0.00007374825,0.00002800545,0.0001456706,0.00001600989],"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":[0.00005178499,0.0001123859,0.001323055,0.0000625235,0.0001042695,0.00006608989,0.00002623795,0.9396119,0.002290182,0.0009332349,0.0004536569,0.0549646],"study_design_scores_gemma":[0.000003066675,0.00003034046,0.000203865,0.000002173599,0.000009165315,0.000005263619,0.000002930841,0.9992307,0.0002478607,0.0001854488,0.00007665678,0.000002441152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09136013,0.0007625286,0.9056829,0.0002698923,0.00003360634,0.0001291053,0.0002166545,0.0004563325,0.001088762],"genre_scores_gemma":[0.8518272,0.0003886871,0.1451368,0.0001250032,0.00003768736,0.0004555449,0.0005149626,0.00003375182,0.001480343],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005319068,"threshold_uncertainty_score":0.01057619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05887820100235833,"score_gpt":0.3401538926426298,"score_spread":0.2812756916402714,"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."}}