The ability to design efficient enzymes from scratch would have a profound effect on
chemistry, biotechnology and medicine. Rapid progress in protein engineering over the past …

Due to their high target specificity and binding affinity, therapeutic antibodies are currently
the largest class of biotherapeutics. The traditional largely empirical antibody development …

We consider the problem of predicting a protein sequence from its backbone atom
coordinates. Machine learning approaches to this problem to date have been limited by the …

Construction of a scaffold structure that supports a desired motif, conferring protein function,
shows promise for the design of vaccines and enzymes. But a general solution to this motif …

Deep learning generative approaches provide an opportunity to broadly explore protein
structure space beyond the sequences and structures of natural proteins. Here, we use deep …

There has been considerable recent progress in protein structure prediction using deep
neural networks to predict inter-residue distances from amino acid sequences,–. Here we …

1Program in Molecular Biophysics, Johns Hopkins University, Baltimore, MD, USA,
2Department of Chemical and Biomolecular Engineering, Johns Hopkins University …

Self-supervised pretraining on protein sequences has led to state-of-the art performance on
protein function and fitness prediction. However, sequence-only methods ignore the rich …

Proteins are macromolecules that perform essential functions in all living organisms.
Designing novel proteins with specific structures and desired functions has been a long …

Protein design often begins with the knowledge of a desired function from a motif which motif-
scaffolding aims to construct a functional protein around. Recently, generative models have …