{"id":"W4385488459","doi":"10.1109/ijcnn54540.2023.10191737","title":"Approximating the Atomic Composition of Drug-like Molecules from Quantum Derived Properties: Inverse Design","year":2023,"lang":"en","type":"article","venue":"","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Inverse; Outlier; Molecule; Computer science; Feature (linguistics); Composition (language); Set (abstract data type); Molecular descriptor; Biological system; Artificial intelligence; Mathematics; Quantitative structure–activity relationship; Machine learning; Physics; Quantum mechanics; Geometry","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":[0.001089612,0.0004050917,0.0007707025,0.0005527544,0.0001942452,0.0006549896,0.0007378071,0.0006013121,0.0006549201],"category_scores_gemma":[0.002715387,0.000446629,0.0009734143,0.0003701926,0.0007571155,0.0008511364,0.0004412534,0.000663877,0.0001900616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006184283,"about_ca_system_score_gemma":0.0007046913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001307831,"about_ca_topic_score_gemma":0.001391516,"domain_scores_codex":[0.9996686,0.0001225904,0.0000131813,0.00004794842,0.0001233335,0.00002428601],"domain_scores_gemma":[0.9991498,0.0005124031,0.0001086952,0.0001236576,0.00008865492,0.00001681581],"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":[0.00006964939,0.00006008684,0.001135133,0.0001097161,0.0000426952,0.00004283075,0.00004038069,0.9325223,0.009375112,0.01202481,0.000186554,0.04439073],"study_design_scores_gemma":[0.000006849315,0.00004445288,0.0001159203,0.000004103943,0.000006904351,0.00001824353,0.000004283707,0.9939732,0.002109788,0.003332963,0.0003780436,0.000005100494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05027819,0.0002551879,0.9476089,0.0001738682,0.00001421688,0.00003778915,0.0000423187,0.0002498041,0.001339728],"genre_scores_gemma":[0.6948538,0.0003746576,0.3031982,0.0001299651,0.00001730677,0.0001191695,0.0001579543,0.00006995192,0.001078965],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001307831,"threshold_uncertainty_score":0.005762517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05802356266896726,"score_gpt":0.274417231319642,"score_spread":0.2163936686506747,"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."}}