Cyril Malbranke

Predicting host-pathogen interactions using a proteome-scale language model

The paper introduces ProteomeLM-HPI, a language model adapted to predict cross-species host-pathogen interactions using proteome context and fine-tuning.

ProteomeLM: A proteome-scale language model enables accurate and rapid prediction of protein-protein interactions and gene essentiality across taxa

ProteomeLM predicts protein-protein interactions and gene essentiality across species using a proteome-scale language model, outperforming existing methods in speed and accuracy.

Out-of-equilibrium selection pressure enhances inference from protein sequence data

The paper shows that fluctuating selection pressures improve coevolution-based inference of protein structure and function from sequence data.

Rubisco is slow across the tree of life

The paper characterizes over 250 Rubisco variants from bacteria and archaea, showing they rarely exceed 30 reactions per second at 30°C and predicting rates for all sequenced variants using machine learning.

ProtMamba: a homology-aware but alignment-free protein state space model

ProtMamba is a homology-aware, alignment-free protein language model that outperforms state-of-the-art models in homolog-conditioned sequence generation.

Computational design of novel Cas9 PAM-interacting domains using evolution-based modelling and structural quality assessment

The paper designs novel Cas9 PAM-interacting domains using a combination of evolutionary modeling, physics-based scoring, and machine learning, identifying functional variants with up to 20% sequence divergence from the wild-type.

Improving sequence-based modeling of protein families using secondary structure quality assessment

The paper introduces two scoring functions to assess the quality of secondary structures in generated protein sequences and shows improved detection of non-functional sequences.