Rosetta Commons Research Experience for Undergraduates (REU) AI for Biomolecular Structure Prediction and Design Interns in this geographically-distributed REU program participate in research using…

Two new studies add to a remarkable body of evidence for benefit

The official home of the Python Programming Language

Our findings indicate that young children with AIPL1-related retinal dystrophy benefited substantially from subretinal administration of rAAV8.hRKp.AIPL1, with improved visual acuity and functional vi...

The ribosome biases the conformations sampled by nascent polypeptide chains along folding pathways towards biologically active states. A hallmark of the co-translational folding (coTF) of many protein...

A major challenge for many rare-event sampling strategies is the identification of progress coordinates that capture the slowest relevant motions. Machine-learning methods that can identify progress coordinates in an unsupervised manner have therefore been of great interest to the simulation community. Here, we developed a general method for identifying progress coordinates “on-the-fly” during weighted ensemble (WE) rare-event sampling via deep learning (DL) of outliers among sampled conformations. Our method identifies outliers in a latent space model of the system’s sampled conformations that is periodically trained using a convolutional variational autoencoder. As a proof of principle, we applied our DL-enhanced WE method to simulate the NTL9 protein folding process. To enable rapid tests, our simulations propagated discrete-state synthetic molecular dynamics trajectories using a generative, fine-grained Markov state model. Results revealed that our on-the-fly DL of outliers enhanced the efficiency of WE by >3-fold in estimating the folding rate constant. Our efforts are a significant step forward in the unsupervised learning of slow coordinates during rare event sampling.

Nature Biotechnology - The Protein Design Archive (PDA): insights from 40 years of protein design