Alexander Derry

The paper uses language modeling to create a comprehensive representation of protein biology, enabling structure prediction and discovery of high-affinity protein interactions.

This paper introduces PARSE, a method for protein functional site annotation using local structure embeddings, achieving high accuracy in predicting catalytic residues and novel functions.

The paper uses self-supervised deep learning to cluster local 3D protein structures, creating a motif lexicon that improves structure prediction, drug off-target prediction, and variant analysis.

ESM3, a 98-billion-parameter multimodal protein language model tokenized across sequence, structure, and function, designs a bright green fluorescent protein at 58% sequence identity to known fluorescent proteins.

COLLAPSE learns deep representations of protein structural sites using 3D atomic positions and evolutionary signals, achieving state-of-the-art performance in function prediction and site annotation.

This study evaluates how training data composition affects protein structure analysis algorithms across three tasks, finding that including diverse structure types improves performance.

This paper designs protein sequences using a deep neural network trained on crystal structures, producing stable designs that match high-resolution structures.

This paper develops a knowledge graph embedding method to identify drug repurposing opportunities for rare diseases by integrating biomedical literature and validating hypotheses through external sources.