Publications by Pierre Vandergheynst

Boosting Protein Graph Representations through Static-Dynamic Fusion

Pierre Vandergheynst, Bruno Emanuel Ferreira De Sousa Correia, Daniel Probst

Machine learning for protein modeling faces significant challenges due to proteins' inherently dynamic nature, yet most graph-based machine learning methods rely solely on static structural information. Recently, the growing availability of molecular dynam ...

2025

MARBLE: interpretable representations of neural population dynamics using geometric deep learning

Pierre Vandergheynst

The dynamics of neuron populations commonly evolve on low-dimensional manifolds. Thus, we need methods that learn the dynamical processes over neural manifolds to infer interpretable and consistent latent representations. We introduce a representation lear ...

2025

Interpreting and comparing neural activity across systems by geometric deep learning

Pierre Vandergheynst, Adám Gosztolai

NATURE PORTFOLIO2025

Beyond fine-tuning: LoRA modules boost near-OOD detection and LLM security

Pierre Vandergheynst, Milos Vasic, Francesco Craighero, Renata Khasanova

Under resource constraints, LLMs are usually fine- tuned with additional knowledge using Parameter Efficient Fine-Tuning (PEFT), using Low-Rank Adaptation (LoRA) modules. In fact, LoRA injects a new set of small trainable matrices to adapt an LLM to a new ...

2024

Beyond fine-tuning: LoRA modules boost near-OOD detection and LLM security

Pierre Vandergheynst, Milos Vasic, Francesco Craighero, Renata Khasanova

Under resource constraints, LLMs are usually fine-tuned with additional knowledge using Parameter Efficient Fine-Tuning (PEFT), using Low-Rank Adaptation (LoRA) modules. In fact, LoRA injects a new set of small trainable matrices to adapt an LLM to a new t ...

2024

Exploring “dark-matter” protein folds using deep learning

Pierre Vandergheynst, Bruno Emanuel Ferreira De Sousa Correia, Sandrine Madeleine Suzanne Georgeon, Casper Alexander Goverde, Andreas Loukas, Stéphane Rosset, Zander Harteveld, Alexandra Krina Van Hall-Beauvais

De novo protein design explores uncharted sequence and structure space to generate novel proteins not sampled by evolution. A main challenge in de novo design involves crafting “designable” structural templates to guide the sequence searches toward adoptin ...

2024

Molecular set representation learning

Pierre Vandergheynst, Maria Boulougouri, Daniel Probst

Computational representation of molecules can take many forms, including graphs, string encodings of graphs, binary vectors or learned embeddings in the form of real-valued vectors. These representations are then used in downstream classification and regre ...

Springer Science and Business Media LLC2024

Towards improving full-length ribosome density prediction by bridging sequence and graph-based representations

Pierre Vandergheynst, Felix Naef, Cédric Gobet, Francesco Craighero, Mohan Vamsi Nallapareddy

Translation elongation plays an important role in regulating protein concentrations in the cell, and dysregulation of this process has been linked to several human diseases. In this study, we use data from ribo-seq experiments to model ribosome densities, ...

PMLR2024

RosettaSurf-A surface-centric computational design approach

Pierre Vandergheynst, Bruno Emanuel Ferreira De Sousa Correia, Andreas Scheck, Andreas Loukas, Jaume Bonet Martinez, Stéphane Rosset, Michaël Defferrard

Proteins are typically represented by discrete atomic coordinates providing an accessible framework to describe different conformations. However, in some fields proteins are more accurately represented as near-continuous surfaces, as these are imprinted wi ...

PUBLIC LIBRARY SCIENCE2022

Generalised Implicit Neural Representations

Pierre Vandergheynst

We consider the problem of learning implicit neural representations (INRs) for signals on non-Euclidean domains. In the Euclidean case, INRs are trained on a discrete sampling of a signal over a regular lattice. Here, we assume that the continuous signal e ...

2022