{"id":"W4221138137","doi":"10.1016/j.compbiolchem.2022.107664","title":"Transfer learning with molecular graph convolutional networks for accurate modeling and representation of bioactivities of ligands targeting GPCRs without sufficient data","year":2022,"lang":"en","type":"article","venue":"Computational Biology and Chemistry","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Natural Science Research of Jiangsu Higher Education Institutions of China; National Natural Science Foundation of China","keywords":"Graph; Representation (politics); G protein-coupled receptor; Computer science; Drug discovery; Transfer of learning; Ligand (biochemistry); Convolutional neural network; Artificial intelligence; Computational biology; Machine learning; Theoretical computer science; Chemistry; Bioinformatics; Receptor; Biology; Biochemistry","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":[0.0004121143,0.00009787814,0.0001805203,0.00004719996,0.0001910574,0.00001556895,0.0002426608,0.00003681606,0.000002778345],"category_scores_gemma":[0.00004691418,0.00009743272,0.00002865624,0.0001846949,0.0001709272,0.0001643878,0.0002585297,0.000131915,9.890422e-9],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001098859,"about_ca_system_score_gemma":0.000105937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000791918,"about_ca_topic_score_gemma":1.609805e-7,"domain_scores_codex":[0.9990359,0.00008500392,0.0002478481,0.0003723146,0.0001433771,0.0001155822],"domain_scores_gemma":[0.9990557,0.0005427357,0.0001145935,0.000120681,0.0001360874,0.00003014603],"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":[0.00008719745,0.00003329907,0.002329617,0.00004458817,0.00005760609,5.41046e-7,0.0001763903,0.9775239,0.01016626,0.00906519,0.000003410472,0.0005119474],"study_design_scores_gemma":[0.0004791812,0.00007652045,0.0002763948,0.00001215589,0.00001689356,0.00002082767,0.0003019545,0.9859706,0.005287429,0.007446013,0.000008314852,0.0001037294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.478267,0.0003207053,0.521212,0.00007935053,0.00001633834,0.0000544591,0.0000342501,0.000008998025,0.000006908252],"genre_scores_gemma":[0.9678957,0.00001169291,0.03142188,0.00003209475,0.0000150125,0.00001876385,0.0005963661,0.000005350739,0.000003149869],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4897902,"threshold_uncertainty_score":0.3973191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02991083804504967,"score_gpt":0.3056978403825742,"score_spread":0.2757870023375245,"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."}}