{"id":"W4409487820","doi":"10.1016/j.commatsci.2025.113904","title":"Hyperparameter optimization and neural architecture search algorithms for graph Neural Networks in cheminformatics","year":2025,"lang":"en","type":"article","venue":"Computational Materials Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cheminformatics; Hyperparameter; Computer science; Artificial neural network; Graph; Machine learning; Artificial intelligence; Algorithm; Theoretical computer science; Chemistry; Computational chemistry","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001225893,0.001848364,0.001425642,0.001669505,0.0005205006,0.00126367,0.001960985,0.001621551,0.00522969],"category_scores_gemma":[0.004659387,0.0007235321,0.001557244,0.00231159,0.0006654527,0.001603252,0.001398276,0.002721377,0.00193975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001450986,"about_ca_system_score_gemma":0.001639117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007934097,"about_ca_topic_score_gemma":0.01084458,"domain_scores_codex":[0.9994211,0.0002164187,0.00005011524,0.000125576,0.0001449564,0.00004181284],"domain_scores_gemma":[0.9989759,0.0006045048,0.00009490177,0.00007898901,0.0002063935,0.00003932963],"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":[0.00005634147,0.00007868643,0.000837195,0.00099003,0.0001936547,0.00007425417,0.00004704683,0.6674415,0.0009916062,0.02912782,0.01436171,0.2858001],"study_design_scores_gemma":[0.00002254944,0.00004247678,0.0003033967,0.0002378703,0.0000594272,0.00005924951,0.00002066709,0.9465158,0.0008302417,0.03759231,0.01428987,0.0000261331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007214175,0.04206025,0.9349911,0.001939301,0.0004140386,0.0001248468,0.0005718252,0.001829435,0.01085508],"genre_scores_gemma":[0.2339682,0.06740274,0.6808702,0.001560878,0.0007426572,0.0008700354,0.003509536,0.001142306,0.009933474],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007934097,"threshold_uncertainty_score":0.01749504,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01394716815543814,"score_gpt":0.2929557971174436,"score_spread":0.2790086289620055,"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."}}