{"id":"W2906587988","doi":"10.1093/bioinformatics/bty1035","title":"Systematic selection of chemical fingerprint features improves the Gibbs energy prediction of biochemical reactions","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"King Abdullah University of Science and Technology","keywords":"Computer science; Software; Feature selection; Fingerprint (computing); Data mining; Artificial intelligence; Gibbs free energy; Machine learning; Selection (genetic algorithm); Energy (signal processing); Feature (linguistics); Mathematics; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008497892,0.0001207537,0.0002502573,0.00007327445,0.0001041119,0.00005158412,0.0003798216,0.00009785516,0.0000932679],"category_scores_gemma":[0.0008048728,0.00007646588,0.00006090121,0.0002631949,0.0004359791,0.0001968057,0.0001188913,0.0000828929,0.00002219073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004128465,"about_ca_system_score_gemma":0.00006569422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000121361,"about_ca_topic_score_gemma":0.000003255532,"domain_scores_codex":[0.998443,0.00007963125,0.0007810456,0.0001212717,0.0003890244,0.0001860475],"domain_scores_gemma":[0.9985431,0.0001701957,0.000671542,0.0003427905,0.000230218,0.00004214405],"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":[0.00001553299,0.00002459715,0.00003478667,0.00184799,0.000007664,2.163404e-8,0.000526068,0.00003959874,0.9959447,0.001030777,0.0004821595,0.00004606582],"study_design_scores_gemma":[0.00008166583,0.0001062283,0.0005178548,0.0004842706,0.00002997225,0.00002906835,0.0001368591,0.05349075,0.9448508,0.0001542857,0.00005013029,0.00006811691],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.979021,0.00002956861,0.01817588,0.0001106545,0.0008069561,0.0002980074,0.000033691,0.0001158381,0.001408376],"genre_scores_gemma":[0.9802278,0.000005201362,0.01949979,0.00002978287,0.0001357958,0.00002075594,0.000005509312,0.000007622624,0.00006779936],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05345115,"threshold_uncertainty_score":0.3118188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007192771495173785,"score_gpt":0.2300551491919414,"score_spread":0.2228623776967676,"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."}}