Publications related to G–PLIP: Knowledge graph neural network for structure-free protein–ligand bioactivity prediction

Related publications (15)

Dynamical features of smooth muscle actin pathological mutants: The arginine-257(258)-Cysteine cases

The R257(8)C mutation in smooth muscle actins, ACTG2 and ACTA2, is the most frequent cause of severe genetic diseases: namely, visceral myopathy, and familial thoracic aortic aneurysms and dissections, which respectively, stem from impairment of the viscer ...

ELSEVIER2025

Boon and Bane of Local Solid State Chemistry on the Performance of LSM-Based Solid Oxide Electrolysis Cells

Hanna Christine Türk

Advanced Energy Materials published by Wiley-VCH GmbH.High-temperature solid oxide cells are highly efficient energy converters. However, their lifetime is limited by rapid deactivation. Little is known about the local, atomic scale transformation that dri ...

2025

Eflop: a Sparsity-aware Metric for Evaluating Computational Cost in Spiking and Non-spiking Neural Networks

Liza Carol Andrea Dunbar

Deploying energy-efficient deep neural networks on energy-constrained edge devices is an important research topic in both machine learning and circuit design communities. Both artificial neural networks (ANNs) and spiking neural networks (SNNs) have been p ...

IOP Publishing Ltd2025

How Gradient Descent Balances Features: A Dynamical Analysis For Two-Layer Neural Networks

Volkan Cevher, Fanghui Liu, Zhenyu Zhu

This paper investigates the fundamental regression task of learning k neurons (a.k.a. teachers) from Gaussian input, using two-layer ReLU neural networks with width m (a.k.a. students) and m, k = O(1), trained via gradient descent under proper initializati ...

2025

Subtle variations in a client protein determine bacterial Hsp90 dependence

Mathieu Rebeaud

Chaperones ensure protein homeostasis and are conserved across species. The ATP-dependent chaperone Hsp90 is present from bacteria to eukaryotes, where it stabilizes and activates a wide range of substrate proteins called clients. However, what determines ...

Elsevier BV2025

Engineering novel protein interactions with therapeutic potential using deep learning-guided surface design

Anthony Marchand

Proteins are foundational biomolecules of life playing a crucial role in a myriad of biological processes. Their function often requires interplay with other biomolecules, including proteins themselves. Protein-protein interactions (PPIs) are essential for ...

EPFL2024

A Versatile Method for Site-Specific Chemical Installation of Aromatic Posttranslational Modification Analogs into Proteins

Bouchra Bouri, Hilal Lashuel, Rajasekhar Kolla, Shaswati Mandal

Posttranslational modifications (PTMs) of proteins play central roles in regulating the protein structure, interactome, and functions. A notable modification site is the aromatic side chain of Tyr, which undergoes modifications such as phosphorylation and ...

2024

Hydrophobic Interaction and its Small Molecule effect

Ting Mao

Protein stabilization has a crucial rule sustaining biological functionality, disease prevention, and pharmaceutical formulation stabilization, and yet its stabilization mechanism by small molecules such as amino acids is not fully understood. In this work ...

EPFL2024

Mechanism of Chromatin Ubiquitination by PRC1 on the Single-Molecule Level

Alexandra Teslenko

Multicellular eukaryotic organisms contain identical genetic information within each cell, stored within the nucleus as chromatin fibers. The regulation of gene expression allows cell-type-specific temporal and spatial gene activation or repression despite ...

EPFL2024

DNA methylation by CcrM contributes to genome maintenance in the Agrobacterium tumefaciens plant pathogen

Giovanna Ambrosini, Nicolas Jean Philippe Guex, Christian Iseli

The cell cycle-regulated DNA methyltransferase CcrM is conserved in most Alphaproteobacteria, but its role in bacteria with complex or multicentric genomes remains unexplored. Here, we compare the methylome, the transcriptome and the phenotypes of wild-typ ...

OXFORD UNIV PRESS2024

Supramolecular Architectures of Dendritic Polymers Provide Irreversible Inhibitor to Block Viral Infection

Francesco Stellacci, Matteo Gasbarri, Heyun Wang

In Nature, most known objects can perform their functions only when in supramolecular self-assembled from, e.g. protein complexes and cell membranes. Here, a dendritic polymer is presented that inhibits severe acute respiratory syndrome coronavirus 2 (SARS ...

Wiley2024

Navigating the Loop: From Control Systems to Neural Networks and Back

Clara Lucía Galimberti

The work presented in this thesis lies at the intersection of Machine Learning (ML) and control theory. The first part is dedicated to the design of Deep Neural Network (DNN) architectures with specific numerical properties, inspired by dynamical systems m ...

EPFL2024

De novo designed proteins: a study in engineering novel folds and functions

Alexandra Krina Van Hall-Beauvais

Proteins control nearly every facet of life on a molecular level. Proteins are formed from linear strings of amino acids, which fold into three-dimensional structures that can enact functions. Evolution has created highly efficient proteins in diverse fold ...

EPFL2023

Brain mitochondrial diversity and network organization predict anxiety-like behavior in male mice

Maria del Carmen Sandi Perez

The brain and behavior are under energetic constraints, limited by mitochondrial energy transformation capacity. However, the mitochondria-behavior relationship has not been systematically studied at a brain-wide scale. Here we examined the association bet ...

Nature Research2023

Neural-prior stochastic block model

Lenka Zdeborová, Odilon Marie Cyprien Duranthon

The stochastic block model (SBM) is widely studied as a benchmark for graph clustering aka community detection. In practice, graph data often come with node attributes that bear additional information about the communities. Previous works modeled such data ...

2023