{"id":"W2996945591","doi":"10.1007/978-3-031-28401-4_4","title":"All SMILES Variational Autoencoder for Molecular Property Prediction and Optimization","year":2023,"lang":"en","type":"book-chapter","venue":"Challenges and advances in computational chemistry and physics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Variation Biotechnologies (Canada)","funders":"","keywords":"Autoencoder; Bijection; Computer science; Molecular graph; Decoding methods; Pooling; Theoretical computer science; Graph; Set (abstract data type); Disjoint sets; Artificial intelligence; Representation (politics); Algorithm; Artificial neural network; Pattern recognition (psychology); Mathematics; Combinatorics","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":[0.0001830604,0.0002539246,0.0002488314,0.00002584333,0.00008845615,0.0000756931,0.0001321058,0.0001375719,0.000002078111],"category_scores_gemma":[0.0000275561,0.0002372706,0.00004303678,0.00003362144,0.0000964141,0.0004387228,0.0001679935,0.0001657856,3.547539e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003113235,"about_ca_system_score_gemma":0.00007734908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.375308e-7,"about_ca_topic_score_gemma":4.835503e-7,"domain_scores_codex":[0.9987156,0.00001900935,0.0002664127,0.000612241,0.0002497779,0.0001369361],"domain_scores_gemma":[0.9989322,0.0005884679,0.0001566829,0.0001134255,0.0001432491,0.00006596663],"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":[0.00000874708,0.00001341541,9.709887e-7,0.0003370851,0.00002435566,0.000002038744,0.0001444331,0.6422603,0.000003315569,0.2907015,0.000007567101,0.06649625],"study_design_scores_gemma":[0.0002098093,0.00001787619,0.00003678002,0.0001050036,0.000009604852,0.000007292079,0.000006973457,0.5378466,0.000005796497,0.4593333,0.002274616,0.0001463959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001950464,0.009599353,0.9818512,0.0009790065,0.0001254723,0.0002569352,0.0001225455,0.00007035387,0.006975618],"genre_scores_gemma":[0.002495548,0.0466351,0.9422138,0.0003038713,0.000825519,0.0001853732,0.001356164,0.0001065859,0.005878026],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1686318,"threshold_uncertainty_score":0.9675614,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04122788488646575,"score_gpt":0.2922831907735833,"score_spread":0.2510553058871176,"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."}}