Chaitanya K. Joshi

PhD Student

University of Cambridge, UK

I’m a 3rd year PhD student at the Department of Computer Science and Technology, University of Cambridge, supervised by Prof. Pietro Liò and supported by the A*STAR National Science Scholarship and the Qualcomm Innovation Fellowship. I’ve previously interned at Prescient Design, Genentech with Dr. Andreas Loukas and at FAIR Chemistry, Meta AI with Dr. Zachary Ulissi. I co-organize the Learning on Graphs Conference.

My research explores the intersection of:

Geometric deep learning: GNNs, Transformers and generative models for 3D biomolecular structure, theoretical understanding, and scaling up.
Applications to RNA design: I’m developing gRNAde, a toolkit for 3D RNA inverse design, which we experimentally validate with collaborators.

Download my CV.

Interests

Geometric Deep Learning
Generative Modelling
RNA Design

Education

PhD in Computer Science, 2022 – Present
University of Cambridge, UK
B.Eng. in Computer Science, 2015 – 2019
Nanyang Technological University, Singapore

Selected Publications

See all publications

Chaitanya K. Joshi, Arian R. Jamasb, Ramon Viñas, Charles Harris, Simon Mathis, Pietro Liò

January 2024 Computational Biology Workshop, ICML 2023

gRNAde: Geometric Deep Learning for 3D RNA Inverse Design

gRNAde is a geometric deep learning pipeline for 3D RNA inverse design, analogous to ProteinMPNN. gRNAde outperforms physically-based Rosetta and is significantly faster. (Invited book chapter for Methods in Molecular Biology)

Alexandre Duval, Simon V. Mathis, Chaitanya K. Joshi, Victor Schmidt, Santiago Miret, Fragkiskos D. Malliaros, Taco Cohen, Pietro Liò, Yoshua Bengio, Michael Bronstein

December 2023 arXiv preprint

A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems

A ‘Hitchhiker’s Guide’ for getting started with deep neural networks for 3D structural biology & chemistry – we wrote it without the goal of publishing at particular venues – as if we could travel back in time and learn from it if we were starting our PhDs today! 🤗

Chaitanya K. Joshi, Cristian Bodnar, Simon V. Mathis, Taco Cohen, Pietro Liò

July 2023 International Conference on Machine Learning (ICML)

On the Expressive Power of Geometric Graph Neural Networks

We propose a Geometric Weisfeiler-Leman test to study the expressive power of Geometric Graph Neural Networks and demonstrate the advantages of equivariant GNNs over invariant GNNs. (Full paper at ICML 2023, and presented as an Oral at NeurIPS 2022 Workshop)

Featured Blogposts

See all blogposts

Chaitanya K. Joshi

May 1, 2024 6 min read

Getting started with 3D RNA modelling as a machine learner

A currated reading + watch list for beginners to get started with RNA modelling and desing.

Chaitanya K. Joshi

Last updated on Jun 21, 2021 12 min read

Transformers are Graph Neural Networks

Exploring the connection between Transformer models such as GPT and BERT for Natural Language Processing, and Graph Neural Networks. (80,000+ readers on The Gradient, featured in Probabilistic ML textbook and classes at Stanford, Cambridge, Oxford.)

Chaitanya K. Joshi

Last updated on Jul 31, 2019 5 min read

Community: NTU Valedictorian Speech

My Valedictorian speech at the NTU Convocation 2019

Contact

chaitanya.joshi@cl.cam.ac.uk
15 JJ Thomson Ave, Cambridge, Cambridgeshire CB3 0FD
Office SE12, William Gates Building, Computer Laboratory, University of Cambridge
Follow me on Twitter
Connect on LinkedIn