Biology subjects

Vandergheynst, P.

Publications and source records attributed to Vandergheynst, P..

6 recordsLinked to original sources

bioRxiv2026

Learning gene interactions from tabular gene expression data using Graph Neural Networks

Gene interactions form complex networks underlying disease susceptibility and therapeutic response. While bulk transcriptomic datasets offer rich resources for studying these interactions, applying Graph Neural Networks (GNNs) to such data remains limited by a lack of methodological guidance, especially for constructing gene interaction graphs. We present REGEN (REconstruction of GEne Networks), a GNN-based framework that simultaneously learns latent gene interaction networks from bulk transcriptomic profiles and predicts patient vital status. Evaluated across seven cancer types in the TCGA cohort, REGEN outperforms baseline models in five datasets and provides robust network inference. By systematically comparing strategies for initializing gene-gene adjacency matrices, we derive practical guidelines for GNN application to bulk transcriptomics. Analysis of the learned kidney cancer gene-network reveals cancer-related pathways and biomarkers, validating the models biological relevance. Together, we establish a principled approach for applying GNNs to bulk transcriptomics, enabling improved phenotype prediction and meaningful gene network discovery.

bioinformatics↗

bioRxiv2025

Conditional Deep Learning Model Reveals Translation Elongation Determinants during Amino Acid Deprivation

Translation elongation plays a key role in cellular homeostasis, and dysregulation of this process has been implicated in various diseases and metabolic disorders. Uncovering the causes of intragenic heterogeneity of translation, especially in contexts of different amino acid deprivations, could help increase our understanding of these disorders and pave the way for novel therapeutics. Ribosome profiling provides accurate measurements for the genome-wide ribosome footprints, which could be utilized to investigate these mechanisms. Here we present Riboclette, a conditional deep learning model featuring a dual output head that uses the mRNA sequence input to accurately predict the ribosome footprint profiles across six amino acid deprivation conditions. Exploiting standard interpretability methods, we identify specific codons related to deprived amino acids, poly-basic regions, and negatively charged amino acids as the primary drivers of the stalling response. Moreover, we use Riboclette to extract motif level drivers for ribosome stalling by performing in silico perturbation experiments. The extracted motifs highlight the cumulative contribution of deprived codons in triggering ribosome stalling, which, depending on the condition, have been identified to affect translation up to ten codons downstream. Moreover, motifs precisely explain stalling at different codon positions, allowing for the differentiation between expected determinants of rare stalling events. Our framework offers an accurate and explainable method for understanding the effect of different amino acid deprivation conditions at a codon resolution to help elucidate the impact of intragenic variations on the regulation of translation elongation.

bioinformatics↗

bioRxiv2025

Enhancing protein graph representations through static-dynamic fusion

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 dynamics trajectories provides new opportunities for understanding the dynamic behavior of proteins; however, computational methods for utilizing this dynamic information remain limited. We propose a novel graph representation that integrates both static structural information and dynamic correlations from molecular dynamics trajectories, enabling more comprehensive modeling of proteins. By applying relational graph neural networks (RGNNs) to process this heterogeneous representation, we demonstrate significant improvements over structure-based approaches across three distinct tasks: atomic adaptability prediction, binding site detection, and binding affinity prediction. Our results validate that combining static and dynamic information provides complementary signals for understanding proteinligand interactions, offering new possibilities for drug design and structural biology applications.

bioinformatics↗

bioRxiv2024

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

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, and in turn, predict the speed of translation. The proposed method, RiboGL, combines graph and recurrent neural networks to account for both graph and sequence-based features. The model takes a graph representing the secondary structure of the mRNA sequence as input, which incorporates both sequence and structural codon neighbors. In our experiments, RiboGL greatly outperforms the state-of-the-art RiboMIMO model for ribosome density prediction. We also conduct ablation studies to justify the design choices made in building the pipeline. Additionally, we use gradient-based interpretability to understand how the codon context and the structural neighbors affect the ribosome density at the A-site. By individually analyzing the genes in the dataset, we elucidate how structural neighbors could also potentially play a role in defining the ribosome density. Importantly, since these neighbors can be far away in the sequence, a recurrent model alone could not easily extract this information. This study lays the foundation for understanding how the mRNA secondary structure can be exploited for ribosome density prediction, and how in the future other graph modalities such as features from the nascent polypeptide can be used to further our understanding of translation in general.

bioinformatics↗

bioRxiv2023

Exploring "dark matter" protein folds using deep learning

De novo protein design aims to explore uncharted sequence-and structure areas to generate novel proteins that have not been sampled by evolution. One of the main challenges in de novo design involves crafting "designable" structural templates that can guide the sequence search towards adopting the target structures. Here, we present an approach to learn patterns of protein structure based on a convolutional variational autoencoder, dubbed Genesis. We coupled Genesis with trRosetta to design sequences for a set of protein folds and found that Genesis is capable of reconstructing native-like distance-and angle distributions for five native folds and three novel, so-called "dark-matter" folds as a demonstration of generalizability. We used a high-throughput assay to characterize protease resistance of the designs, obtaining encouraging success rates for folded proteins and further biochemically characterized folded designs. The Genesis framework enables the exploration of the protein sequence and fold space within minutes and is not bound to specific protein topologies. Our approach addresses the backbone designability problem, showing that structural patterns in proteins can be efficiently learned by small neural networks and could ultimately contribute to the de novo design of proteins with new functions.

bioinformatics↗

bioRxiv2021

RosettaSurf - a surface-centric computational design approach

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 with geometric (shape) and chemical (electrostatics) features of the underlying protein structure. Protein surfaces are dependent on their chemical composition and, ultimately determine protein function, acting as the interface that engages in interactions with other molecules. In the past, such representations were utilized to compare protein structures on global and local scales and have shed light on functional properties of proteins. Here we describe RosettaSurf, a surface-centric computational design protocol, that focuses on the molecular surface shape and electrostatic properties as means for protein engineering, offering a unique approach for the design of proteins and their functions. The RosettaSurf protocol combines the explicit optimization of molecular surface features with a global scoring function during the sequence design process, diverging from the typical design approaches that rely solely on an energy scoring function. With this computational approach, we attempt to address a fundamental problem in protein design related to the design of functional sites in proteins, even when structurally similar templates are absent in the characterized structural repertoire. Surface-centric design exploits the premise that molecular surfaces are, to a certain extent, independent of the underlying sequence and backbone configuration, meaning that different sequences in different proteins may present similar surfaces. We benchmarked RosettaSurf on various sequence recovery datasets and showcased its design capabilities by generating epitope mimics that were biochemically validated. Overall, our results indicate that the explicit optimization of surface features may lead to new routes for the design of functional proteins. Author SummaryFinely orchestrated protein-protein interactions are at the heart of virtually all fundamental cellular processes. Altering these processes or encoding new functions in proteins has been a long-standing goal in computational protein design. Protein design methods commonly rely on scoring functions that seek to identify amino acid sequences that optimize structural configurations of atoms while minimizing a variety of physics-based and statistical terms. The objectives of the large majority of computational design protocols have been focused on obtaining a predefined structural conformation. However, routinely introducing a functional aspect on designer proteins has been more challenging. Our results suggest that the molecular surface features can be a useful optimization parameter to guide the design process towards functional surfaces that mimic known protein binding sites and interact with their intended targets. Specifically, we demonstrate that our design method can optimize experimental libraries through computational screening, creating a basis for highly specific protein binders, as well as design a potent immunogen that engages with site-specific antibodies. The ability to create proteins with novel functions will be transformative for biomedical applications, providing many opportunities for the design of novel immunogens, protein components for synthetic biology, and other protein-based biotechnologies.

bioinformatics↗