MoleculeNet: a benchmark for molecular machine learning† †Electronic supplementary information (ESI) available. See DOI: 10.1039/c7sc02664a
نویسندگان
چکیده
1 Model Training and Hyperparameter Optimization All models were trained on Stanford’s GPU clusters via DeepChem. No model was allowed to train for more than 10 hours(time profile in Table S1. Users can reproduce benchmarks locally by following directions from DeepChem. Hyperparameters were determined using Gaussian Process Optimization via pyGPGO(https://github.com/hawk31/pyGPGO), with max number of iterations set to 20. Optimized hyperparameters for each model are listed, detailed hyperparameters can be found on Deepchem. 1.1 Logistic Regression (Logreg) • Learning rate • L2 regularization • Batch size
منابع مشابه
MoleculeNet: A Benchmark for Molecular Machine Learning
Molecular machine learning has been maturing rapidly over the last few years. Improved methods and the presence of larger datasets have enabled machine learning algorithms to make increasingly accurate predictions about molecular properties. However, algorithmic progress has been limited due to the lack of a standard benchmark to compare the efficacy of proposed methods; most new algorithms are...
متن کاملPhotothermal-enhanced catalysis in core–shell plasmonic hierarchical Cu7S4 microsphere@zeolitic imidazole framework-8† †Electronic supplementary information (ESI) available: Experimental details, calculation of photothermal transduction efficiency, additional analytical data, spectra, and images. See DOI: 10.1039/c6sc03239g Click here for additional data file.
متن کامل
DNA topology influences molecular machine lifetime in human serum† †Electronic supplementary information (ESI) available: DNA sequences, fluorophore and quencher properties, equipment design, and degradation studies. See DOI: 10.1039/c5nr02283e Click here for additional data file.
متن کامل
Piezochromism and hydrochromism through electron transfer: new stories for viologen materials† †Electronic supplementary information (ESI) available: Synthetic procedures, bond data. CCDC 1428498. For ESI and crystallographic data in CIF or other electronic format see DOI: 10.1039/c6sc04579k Click here for additional data file. Click here for additional data file.
Shanghai Key Laboratory of Green Chemi Chemistry and Molecular Engineering, Eas Zhongshan Road, Shanghai 200062, P. R. C Center for High Pressure Science and Tech Road, Shanghai 201203, P. R. China. E-mai State Key Laboratory of Superhard Materia Changchun, Jilin 130012, P. R. China † Electronic supplementary information bond data. CCDC 1428498. For ESI and electronic format see DOI: 10.1039/c6...
متن کاملRhodium-catalyzed C–H functionalization-based approach to eight-membered lactams† †Electronic supplementary information (ESI) available: Data for new compounds and experimental procedures and theoretical studies on mechanisms. CCDC 979559 and 990983. For ESI and crystallographic data in CIF or other electronic format see DOI: 10.1039/c5sc00092k Click here for additional data file. Click here for additional data file.
Laboratory of Molecular Recognition an Zhejiang University, Hangzhou 310027, Zh ac.cn State Key Laboratory of Organometallic C Chemistry, Chinese Academy of Sciences, [email protected] Shanghai Key Laboratory of Magnetic Reson Normal University, Shanghai 200062, P. R. † Electronic supplementary information ( and experimental procedures and theor 979559 and 990983. For ESI and crystallo format s...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره 9 شماره
صفحات -
تاریخ انتشار 2018