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. (To appear in ICML 2023, and presented as an Oral at NeurIPS 2022 Workshop)

We propose gRNAde, a geometric deep learning pipeline for 3D RNA inverse design conditioned on multiple backbone conformations.

HYFA (Hypergraph Factorisation) jointly imputates multi-tissue and cell-type gene expression via a specialised graph neural network operating on a hypergraph of individuals, metagenes, and tissues. (To appear in Nature Machine Intelligence)

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.)