{"id":"W4386811498","doi":"10.1007/978-3-031-42608-7_3","title":"$$\\textbf{CHA}_2$$: CHemistry Aware Convex Hull Autoencoder Towards Inverse Molecular Design","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Defence Research and Development Canada; National Research Council Canada","funders":"","keywords":"Autoencoder; Computer science; Representation (politics); Chemical space; Subspace topology; Convex hull; Space (punctuation); Inverse; Theoretical computer science; Artificial intelligence; Algorithm; Regular polygon; Mathematics; Deep learning; Drug discovery; Chemistry","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":[0.0001911349,0.0006326905,0.0004493923,0.0003385223,0.0001846199,0.0007960515,0.0008049484,0.0008299066,0.02753643],"category_scores_gemma":[0.0005778612,0.0003340231,0.0003348396,0.0004619866,0.0003530995,0.0008015995,0.0007951735,0.001097219,0.0155479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000293306,"about_ca_system_score_gemma":0.0004167689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001634429,"about_ca_topic_score_gemma":0.002610754,"domain_scores_codex":[0.9998612,0.00001834119,0.000004760931,0.00002780192,0.00007689375,0.00001095872],"domain_scores_gemma":[0.999874,0.00004658962,0.000005669064,0.00002759002,0.00003963584,0.000006398774],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007426463,0.00007242063,0.00007281134,0.0002510709,0.00003114131,0.00006977867,0.00003072161,0.1089175,0.0239324,0.05988501,0.1114678,0.695195],"study_design_scores_gemma":[0.00001168048,0.00003647143,0.0001320407,0.00004844627,0.00001158638,0.0001165545,0.000008075117,0.832422,0.02537955,0.03455702,0.10725,0.00002667266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001178672,0.0004933269,0.9734169,0.0003413437,0.0003130676,0.00002561183,0.0003425532,0.002868244,0.02102031],"genre_scores_gemma":[0.05960931,0.001821719,0.7826546,0.0007816828,0.0003748149,0.0001553321,0.002718078,0.00290725,0.1489772],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02753643,"threshold_uncertainty_score":0.0921185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0380096339275969,"score_gpt":0.2894601118650777,"score_spread":0.2514504779374808,"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."}}