Zobrazeno 1 - 10
of 68
pro vyhledávání: '"Kearnes, Steven"'
Autor:
Kearnes, Steven
Retrospective testing of predictive models does not consider the real-world context in which models are deployed. Prospective validation, on the other hand, enables meaningful comparisons between data generation processes by incorporating trained mod
Externí odkaz:
http://arxiv.org/abs/2009.00707
Retrosynthesis -- the process of identifying a set of reactants to synthesize a target molecule -- is of vital importance to material design and drug discovery. Existing machine learning approaches based on language models and graph neural networks h
Externí odkaz:
http://arxiv.org/abs/2007.13437
Autor:
McCloskey, Kevin, Sigel, Eric A., Kearnes, Steven, Xue, Ling, Tian, Xia, Moccia, Dennis, Gikunju, Diana, Bazzaz, Sana, Chan, Betty, Clark, Matthew A., Cuozzo, John W., Guié, Marie-Aude, Guilinger, John P., Huguet, Christelle, Hupp, Christopher D., Keefe, Anthony D., Mulhern, Christopher J., Zhang, Ying, Riley, Patrick
DNA-encoded small molecule libraries (DELs) have enabled discovery of novel inhibitors for many distinct protein targets of therapeutic value through screening of libraries with up to billions of unique small molecules. We demonstrate a new approach
Externí odkaz:
http://arxiv.org/abs/2002.02530
We present RL-VAE, a graph-to-graph variational autoencoder that uses reinforcement learning to decode molecular graphs from latent embeddings. Methods have been described previously for graph-to-graph autoencoding, but these approaches require sophi
Externí odkaz:
http://arxiv.org/abs/1904.08915
We present a framework, which we call Molecule Deep $Q$-Networks (MolDQN), for molecule optimization by combining domain knowledge of chemistry and state-of-the-art reinforcement learning techniques (double $Q$-learning and randomized value functions
Externí odkaz:
http://arxiv.org/abs/1810.08678
Autor:
Thomas, Nathaniel, Smidt, Tess, Kearnes, Steven, Yang, Lusann, Li, Li, Kohlhoff, Kai, Riley, Patrick
We introduce tensor field neural networks, which are locally equivariant to 3D rotations, translations, and permutations of points at every layer. 3D rotation equivariance removes the need for data augmentation to identify features in arbitrary orien
Externí odkaz:
http://arxiv.org/abs/1802.08219
Autor:
Faber, Felix A., Hutchison, Luke, Huang, Bing, Gilmer, Justin, Schoenholz, Samuel S., Dahl, George E., Vinyals, Oriol, Kearnes, Steven, Riley, Patrick F., von Lilienfeld, O. Anatole
We investigate the impact of choosing regressors and molecular representations for the construction of fast machine learning (ML) models of thirteen electronic ground-state properties of organic molecules. The performance of each regressor/representa
Externí odkaz:
http://arxiv.org/abs/1702.05532
Deep learning methods such as multitask neural networks have recently been applied to ligand-based virtual screening and other drug discovery applications. Using a set of industrial ADMET datasets, we compare neural networks to standard baseline mode
Externí odkaz:
http://arxiv.org/abs/1606.08793
Autor:
Kearnes, Steven, Pande, Vijay
Rapid overlay of chemical structures (ROCS) is a standard tool for the calculation of 3D shape and chemical ("color") similarity. ROCS uses unweighted sums to combine many aspects of similarity, yielding parameter-free models for virtual screening. I
Externí odkaz:
http://arxiv.org/abs/1606.01822
Publikováno v:
J Comput Aided Mol Des (2016)
Molecular "fingerprints" encoding structural information are the workhorse of cheminformatics and machine learning in drug discovery applications. However, fingerprint representations necessarily emphasize particular aspects of the molecular structur
Externí odkaz:
http://arxiv.org/abs/1603.00856