Research

For billions of years, nature has been conducting the greatest experiment of all time. Imagine one-day gaining access to the detailed notes from these experiments. Today, with worldwide expeditions to collect samples from all habitats, single-cell sequencing of unculturable microbes and the rapid drop in sequencing costs, we can finally tap into nature and gain access to these notes.

Making use of this data, our lab is interested in:

01

A unified statistical model of protein evolution — integrating phylogenetic, genomic, structural, and functional constraints.

Recent Publications

Expanding the scope of protein language modeling to protein-protein interactions with MSA Pairformer.Akiyama Y, et al. 2026. GitHub

Hit or Miss: Understanding Emergence and Absence of Homo-oligomeric Contacts in Protein Language Models.Zhang Z, et al. 2025.

Differentiable Search of Evolutionary Trees from Leaves.Hettiarachchi R, et al. 2023. GitHub

Genomic language model predicts protein co-regulation and function.Hwang Y, et al. 2023. GitHub

End-to-end learning of multiple sequence alignments with differentiable Smith–Waterman.Petti S, et al. 2022. GitHub

Protein language models learn evolutionary statistics of interacting sequence motifs.Zhang Z, Wayment-Steele HK, et al. 2024. GitHub

Disentanglement of Entropy and Coevolution using Spectral Regularization.Wang H, et al. 2022. GitHub

Interpreting Potts and Transformer Protein Models Through the Lens of Simplified Attention.Bhattacharya N, et al. 2021. GitHub

The structure-fitness landscape of pairwise relations in generative sequence models.Marshall D, et al. 2020. GitHub

Unified framework for modeling multivariate distributions in biological sequences.Dauparas J, et al. 2019. GitHub

02

Modeling the protein conformational and folding landscape for structure prediction and design.

image credit: Basile Wicky

Recent Publications

Protein Diffusion Models as Statistical Potentials.Roney JP, et al. 2025. GitHub

Implicit modeling of the conformational landscape and sequence allows scoring and generation of stable proteins.Cho Y, et al. 2024. GitHub

State-of-the-Art estimation of protein model accuracy using AlphaFold.Roney JP, et al. 2022. GitHub

Structure-based protein design with deep learning.Ovchinnikov S, et al. 2021.

Protein sequence design by conformational landscape optimization.Norn C, et al. 2021. GitHub

03

Mining metagenomic "dark matter" for new protein families, functions, and interactions — and probing the early evolution of multicellularity.

Recent Publications

CIRPIN: Learning Circular Permutation-Invariant Representations to Uncover Putative Protein Homologs.Kolodziej A, et al. 2025. GitHub

Unraveling the functional dark matter through global metagenomics.Pavlopoulos GA, et al. 2023. Database

SWAMPNN: End-to-end protein structures alignment.Trinquier J, et al. 2022. GitHub

Protein structure determination using metagenome sequence data.Ovchinnikov S, et al. 2017. GitHub

All Publications