News

Solving the RNA design problem with reinforcement learning

by

We use reinforcement learning to train an agent for computational RNA design: given a target secondary structure, design a sequence that folds to that structure in silico. Our agent uses a novel graph convolutional architecture allowing a single model to be applied to arbitrary target structures of any length. After training it on randomly generated targets, w…

Read more

Variational encoding of complex dynamics

by

Often the analysis of time-dependent chemical and biophysical systems produces high-dimensional time-series data for which it can be difficult to interpret which individual features are most salient. While recent work from our group and others has demonstrated the utility of time-lagged covariate models to study such systems, linearity assumptions can limit th…

Read more

Update to points for incomplete WUs

by

Due to increasing problems with a small group of users intentionally  causing assigned work units to fail we’ve eliminated points for  incomplete work units.  We’ve also imposed stricter requirements for  bonus points.  Neither…

Read more

COVID Moonshot Sprint 10

by

Sprint 10 aims to help optimize the P1 pocket substituent to work around metabolism issues with our current best lead compounds. We’ve been quiet lately, but that’s because we’ve been…

Read more

Overview of the SAMPL6 pKa challenge: evaluating small molecule microscopic and macroscopic pKa predictions

by
The prediction of acid dissociation constants (pK(a)) is a prerequisite for predicting many other properties of a small molecule, such as its protein-ligand binding affinity, distribution coefficient (log D), membrane permeability, and solubility. The prediction of each of these properties requires knowledge of the relevant protonation states and solution free energy penalties of each state. The SAMPL6 pK(a) Challenge was the first time that a separate challenge was conducted for evaluating…
Read more