Timezone: »

 
Spotlight
EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction
Hannes Stärk · Octavian Ganea · Lagnajit Pattanaik · Regina Barzilay · Tommi Jaakkola

Wed Jul 20 11:35 AM -- 11:40 AM (PDT) @ Hall F
in APP: Chemistry and Drug Discovery »

Predicting how a drug-like molecule binds to a specific protein target is a core problem in drug discovery. An extremely fast computational binding method would enable key applications such as fast virtual screening or drug engineering. Existing methods are computationally expensive as they rely on heavy candidate sampling coupled with scoring, ranking, and fine-tuning steps. We challenge this paradigm with EquiBind, an SE(3)-equivariant geometric deep learning model performing direct-shot prediction of both i) the receptor binding location (blind docking) and ii) the ligand's bound pose and orientation. EquiBind achieves significant speed-ups and better quality compared to traditional and recent baselines. Further, we show extra improvements when coupling it with existing fine-tuning techniques at the cost of increased running time. Finally, we propose a novel and fast fine-tuning model that adjusts torsion angles of a ligand's rotatable bonds based on closed form global minima of the von Mises angular distance to a given input atomic point cloud, avoiding previous expensive differential evolution strategies for energy minimization.

Keywords: APP: Chemistry and Drug Discovery · DL: Attention Mechanisms · DL: Graph Neural Networks · MISC: Representation Learning

Author Information

Hannes Stärk (MIT)
Hannes Stärk

I am a PhD student at MIT with an M.Sc. Informatics from TU Munich. I work on graph/geometric machine learning and self-supervised learning, often with applications to proteins and smaller molecules. At MIT CSAIL I am advised by Prof. Tommi Jaakkola and Prof. Regina Barzilay.

Octavian Ganea (MIT)
Lagnajit Pattanaik (Massachusetts Institute of Technology)
Regina Barzilay (MIT CSAIL)
Regina Barzilay

Regina Barzilay is an Israeli-American computer scientist. She is a professor at the Massachusetts Institute of Technology and a faculty lead for artificial intelligence at the MIT Jameel Clinic. Her research interests are in natural language processing and applications of deep learning to chemistry and oncology.

Tommi Jaakkola (MIT)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors