Raphaël John Lamarre Townshend

Founder & CEO

Atomic AI

Biography

Raphaël is the founder and CEO of Atomic AI (we are hiring!), an artificial intelligence-driven startup developing the cutting-edge fusion of machine learning and structural biology to unlock RNA drug discovery. He studied his PhD in the Stanford AI Lab, and his areas of focus include machine learning, RNA and structural biology, high performance computing, and computer vision. More broadly, he is interested in connecting the worlds of biology and computation in novel ways.

Interests

Machine Learning
Structural Biology
RNA Biology
High Performance Computing
Computer Vision

Education

PhD in Computer Science, 2014-2020

Stanford University
BS in Electrical Engineering and Computer Science, 2010-2014

University of California, Berkeley

Featured

Raphaël John Lamarre Townshend, Stephan Eismann, Andrew M. Watkins, Ramya Rangan, Maria Karelina, Rhiju Das, Ron O. Dror

August 2021 Science

Geometric Deep Learning of RNA Structure

RNA molecules fold into complex three-dimensional shapes that are difficult to determine experimentally or predict computationally. We introduce a deep-learning method that significantly improves prediction of 3D RNA structures. Understanding these structures may aid in the discovery of drugs for currently untreatable diseases.

Experience

Founder & CEO

Atomic AI

May 2021 – Present California

Using AI to enable the rational design of new molecules and medicines. We are hiring!

Research Scientist Intern

DeepMind

Jun 2019 – Nov 2019 London

Pursued new research in artificial intelligence and structural biology on the Science: AlphaFold team.

Head TA - CS229

Stanford University

Sep 2018 – Dec 2018 California

Led teaching staff of 30 in instructing over 750 students in Stanford’s machine learning course. Designed and lectured new course material.

PhD Fellow

Stanford University

Sep 2014 – Oct 2020 California

Thesis: Geometric Learning of Biomolecular Structure. Lead research group at the intersection of machine learning and structural biology.

Software Engineering Intern

Google

Jun 2014 – Sep 2014 California

Knowledge: Search team.

Undergraduate Student Instructor

University of California, Berkeley

Jun 2012 – Aug 2012 California

Taught Machine Structures course to section and lab of 30 undergraduates. Guest lectured on MapReduce to class of 100.

Undergradute Research Assistant

University of California, Berkeley

May 2012 – Jun 2014 California

Computer vision for large-scale geolocation.

Root Staff Member and Director

University of California, Berkeley

Aug 2011 – Jun 2014 California

Volunteer high-level administrator for computing facility with over 7000 active student users.

Publications

Raphaël John Lamarre Townshend, Martin Vogele, Patricia A. Suriana, Alexander Derry, Alexander Powers, Yianni Laloudakis, Sidhika Balachandar, Brandon Anderson, Stephan Eismann, Risi Kondor, Russ B. Altman, Ron O. Dror

December 2021 In NeurIPS 2021 Datasets and Benchmarks (Best Paper)

ATOM3D: Tasks On Molecules in Three Dimensions

We build a “dataset of datasets” to help explore the possibilities of three-dimensional molecular learning.

Raphaël John Lamarre Townshend, Stephan Eismann, Andrew M. Watkins, Ramya Rangan, Maria Karelina, Rhiju Das, Ron O. Dror

August 2021 Science

Geometric Deep Learning of RNA Structure

RNA molecules fold into complex three-dimensional shapes that are difficult to determine experimentally or predict computationally. We introduce a deep-learning method that significantly improves prediction of 3D RNA structures. Understanding these structures may aid in the discovery of drugs for currently untreatable diseases.

Bowen Jing, Stephan Eismann, Patricia A. Suriana, Raphaël John Lamarre Townshend, Ron O. Dror

May 2021 In ICLR 2021 (Oral)

Learning from Protein Structure with Geometric Vector Perceptrons

We combine graph and geometric aspects of biomolecular structure within a single unified framework.

Naomi R. Latorraca, Matthieu Masureel, Scott A. Hollingsworth, Franziska M. Heydenreich, Carl-Mikael Suomivuori, Connor Brinton, Raphaël John Lamarre Townshend, Michel Bouvier, Brian K. Kobilka, Ron O. Dror

December 2020 Cell

How GPCR Phosphorylation Patterns Orchestrate Arrestin-Mediated Signaling

We investigate the role of GPCR phosphorylation in modulating arrestin binding and conformation, revealing the structural basis for the long-standing “barcode” hypothesis.