{"id":"W4394886568","doi":"10.1039/d4dd00049h","title":"A 3d convolutional neural network autoencoder for predicting solvent configuration changes in condensed phase biomass reactions","year":2024,"lang":"en","type":"article","venue":"Digital Discovery","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Alliance de recherche numérique du Canada; Alberta Innovates; Canada First Research Excellence Fund; University of Alberta","keywords":"Solvent; Phase (matter); Kinetics; Molecule; Autoencoder; Convolution (computer science); Chemical physics; Thermodynamics; Artificial neural network; Materials science; Chemistry; Computational chemistry; Organic chemistry; Computer science; Physics; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008909967,0.0001076417,0.0000882442,0.00004825386,0.00004358256,0.0001631251,0.00004111167,0.00007409509,0.000004044114],"category_scores_gemma":[0.00006510529,0.0001019582,0.00006419259,0.0001027793,0.00003369706,0.00003563648,0.00001883047,0.00005587122,0.000002487953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002040592,"about_ca_system_score_gemma":0.00004764366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001025577,"about_ca_topic_score_gemma":0.00002568917,"domain_scores_codex":[0.9993147,0.000008975443,0.0001594651,0.000272501,0.00005954322,0.0001848423],"domain_scores_gemma":[0.9998054,0.0000100664,0.00003016624,0.00009575513,0.00003038999,0.00002821764],"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":[0.00008695179,0.00006782575,0.0001122656,0.00007980214,0.0000466646,0.000002216974,0.00002550911,0.003807812,0.9907848,0.0004235553,0.001989103,0.002573476],"study_design_scores_gemma":[0.003183222,0.001153639,0.002144619,0.0004221829,0.0001024496,0.0001604945,0.0002147302,0.1531035,0.442434,0.0005320038,0.3955481,0.001001022],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9498679,0.001516888,0.04546182,0.0003883959,0.001593748,0.0003635753,0.0004812247,0.00006442696,0.00026199],"genre_scores_gemma":[0.9959962,0.00003024548,0.0001246192,0.00003740846,0.001117242,0.00005913604,0.001389777,0.00001619715,0.001229221],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5483508,"threshold_uncertainty_score":0.4157736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01251784356694986,"score_gpt":0.2582208862837292,"score_spread":0.2457030427167794,"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."}}