Share This Author
MoleculeNet: A Benchmark for Molecular Machine Learning
MoleculeNet benchmarks demonstrate that learnable representations are powerful tools for molecular machine learning and broadly offer the best performance, however, this result comes with caveats.
Strategies for Pre-training Graph Neural Networks
A new strategy and self-supervised methods for pre-training Graph Neural Networks (GNNs) that avoids negative transfer and improves generalization significantly across downstream tasks, leading up to 9.4% absolute improvements in ROC-AUC over non-pre-trained models and achieving state-of-the-art performance for molecular property prediction and protein function prediction.
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
Graph Convolutional Policy Network (GCPN) is proposed, a general graph convolutional network based model for goal-directed graph generation through reinforcement learning that can achieve 61% improvement on chemical property optimization over state-of-the-art baselines while resembling known molecules, and achieve 184% improved on the constrained property optimization task.
CHARMM-GUI Input Generator for NAMD, GROMACS, AMBER, OpenMM, and CHARMM/OpenMM Simulations Using the CHARMM36 Additive Force Field
The optimal simulation protocol for each program has been implemented in CHARMM-GUI and is expected to be applicable to the remainder of the additive C36 FF including the proteins, nucleic acids, carbohydrates, and small molecules.
Molecular graph convolutions: moving beyond fingerprints
- S. Kearnes, Kevin McCloskey, Marc Berndl, V. Pande, Patrick F. Riley
- Computer ScienceJournal of Computer-Aided Molecular Design
- 2 March 2016
Molecular graph convolutions are described, a machine learning architecture for learning from undirected graphs, specifically small molecules, that represent a new paradigm in ligand-based virtual screening with exciting opportunities for future improvement.
Random-coil behavior and the dimensions of chemically unfolded proteins.
It appears that the mean dimensions of the large majority of chemically denatured proteins are effectively indistinguishable from themean dimensions of a random-coil ensemble.
MDTraj: A Modern Open Library for the Analysis of Molecular Dynamics Trajectories.
OpenMM 7: Rapid development of high performance algorithms for molecular dynamics
OpenMM is a molecular dynamics simulation toolkit with a unique focus on extensibility, which makes it an ideal tool for researchers developing new simulation methods, and also allows those new methods to be immediately available to the larger community.
Exploring the helix-coil transition via all-atom equilibrium ensemble simulations.
The ensemble folding of two 21-residue alpha-helical peptides has been studied using all-atom simulations under several variants of the AMBER potential in explicit solvent and extensive sampling results in complete convergence to ensemble equilibrium.
Low Data Drug Discovery with One-Shot Learning
- H. Altae-Tran, Bharath Ramsundar, Aneesh S. Pappu, V. Pande
- Computer ScienceACS central science
- 10 November 2016
This work demonstrates how one-shot learning can be used to significantly lower the amounts of data required to make meaningful predictions in drug discovery applications and introduces a new architecture, the iterative refinement long short-term memory, that significantly improves learning of meaningful distance metrics over small-molecules.