Gabriele Orlando

The (implicit) force is with you: an application of the implicit function theorem for automatic protein force fields reparametrization

The paper applies the implicit function theorem to reparameterize molecular force fields for specific protein classes, improving simulation accuracy for amyloid fibrils.

Atomic structures of medin and Aβ fibrils reveal polymorphic remodeling in mixed amyloid systems

This study determines the cryo-EM structures of Aβ40 and medin fibrils in vitro, revealing polymorphic remodeling and mixed amyloid interactions.

In-silico identification of archaeal DNA-binding proteins

The paper develops Xenusia, a neural network tool to identify DNA-binding proteins in archaea using metagenomics data and validates its predictions experimentally.

Data-driven probabilistic definition of the low energy conformational states of protein residues

The paper defines six low energy conformational states for amino acid residues using solution NMR data and introduces a variability parameter to assess conformational state transitions.

In silico design of stable single-domain antibodies with high affinity

This paper introduces EvolveX, a computational pipeline for designing stable single-domain antibodies with high affinity, demonstrating improved binding affinity to human targets.

Integrating physics in deep learning algorithms: A force field as a PyTorch module

The paper introduces MadraX, a differentiable force field implemented as a PyTorch module to enable end-to-end integration with deep learning algorithms in structural biology.

Prediction of disordered regions in proteins with recurrent Neural Networks and protein dynamics

The paper introduces DisoMine, a method predicting intrinsically disordered regions using protein dynamics and sequence context, outperforming existing predictors.

Critical Assessment of Protein Intrinsic Disorder Prediction

The paper evaluates 43 methods for predicting intrinsically disordered regions and binding regions in proteins, finding that deep learning methods outperform older physicochemical approaches but binding prediction remains challenging.