Khabre branded placeholder image

science

Reinforcement Learning Finds New Cardiac Reentry Mechanisms

A bioRxiv preprint reports that reinforcement learning identified previously unreported ways to initiate reentry in models of excitable tissue. Learned stimulation patterns produced unidirectional propagation in cardiac monolayers, while whole-heart experiments offered preliminary evidence that they can influence early wave propagation.

Khabre branded placeholder image

science

ForceFlowAb Brings Physics Guidance to Antibody CDR Design

A bioRxiv preprint presents ForceFlowAb, a mixture-of-experts flow-matching model that designs antibody CDR sequences and structures with force-field guidance. The authors report more favourable antibody–antigen interaction-energy results than two comparison methods in CDR-H3 and six-CDR design tasks.

Khabre branded placeholder image

science

Preprint maps how lipid nanoparticles disrupt model endosomal membranes

A bioRxiv preprint used giant unilamellar vesicles to visualise how two ionisable-lipid nanoparticles interact with model endosomal membranes. The results suggest that apparent pKa alone does not predict the pH at which functional membrane engagement occurs.