Related papers: E(3)-equivariant models cannot learn chirality: Fi…
In this paper, we develop SE3Set, an SE(3) equivariant hypergraph neural network architecture tailored for advanced molecular representation learning. Hypergraphs are not merely an extension of traditional graphs; they are pivotal for…
Generative Adversarial Networks (GANs) have many potential medical imaging applications. Due to the limited memory of Graphical Processing Units (GPUs), most current 3D GAN models are trained on low-resolution medical images, these models…
Visual imitation learning with 3D point clouds has advanced robotic manipulation by providing geometry-aware, appearance-invariant observations. However, point cloud-based policies remain highly sensitive to sensor noise, pose…
Chirality is ubiquitous in nature and fundamental in science, from particle physics to metamaterials.The most established technique of chiral discrimination - photoabsorption circular dichroism - relies on the magnetic properties of a…
Graph are a ubiquitous data representation, as they represent a flexible and compact representation. For instance, the 3D structure of RNA can be efficiently represented as $\textit{2.5D graphs}$, graphs whose nodes are nucleotides and…
Convolutional neural networks (CNNs) allow for parameter sharing and translational equivariance by using convolutional kernels in their linear layers. By restricting these kernels to be SO(3)-steerable, CNNs can further improve parameter…
Chirality pervades natural processes from the atomic to the cosmic scales, crucially impacting molecular chemistry and pharmaceutics. Traditional chirality sensing methods face challenges in sensitivity and efficiency, prompting the quest…
Structure-informed protein representation learning is essential for effective protein function annotation and \textit{de novo} design. However, the presence of inherent noise in both crystal and AlphaFold-predicted structures poses…
We address the problem of 3D rotation equivariance in convolutional neural networks. 3D rotations have been a challenging nuisance in 3D classification tasks requiring higher capacity and extended data augmentation in order to tackle it. We…
Recent advances in computational modelling of atomic systems, spanning molecules, proteins, and materials, represent them as geometric graphs with atoms embedded as nodes in 3D Euclidean space. In these graphs, the geometric attributes…
We consider molecule generation in 3D space using language models (LMs), which requires discrete tokenization of 3D molecular geometries. Although tokenization of molecular graphs exists, that for 3D geometries is largely unexplored. Here,…
Three-dimensional geometric data offer an excellent domain for studying representation learning and generative modeling. In this paper, we look at geometric data represented as point clouds. We introduce a deep AutoEncoder (AE) network with…
Molecular property prediction is an important problem in drug discovery and materials science. As geometric structures have been demonstrated necessary for molecular property prediction, 3D information has been combined with various graph…
Proteins are miniature machines whose function depends on their three-dimensional (3D) structure. Determining this structure computationally remains an unsolved grand challenge. A major bottleneck involves selecting the most accurate…
Geometric graph neural networks (GNNs) that respect E(3) symmetries have achieved strong performance on small molecule modeling, but they face scalability and expressiveness challenges when applied to large biomolecules such as RNA and…
Molecular chirality plays fundamental roles in biology. The chiral response of a molecule occurs at a specific spectral position, determined by its molecular structure. This fingerprint can be transferred to other spectral regions via the…
Molecular property prediction, crucial for early drug candidate screening and optimization, has seen advancements with deep learning-based methods. While deep learning-based methods have advanced considerably, they often fall short in fully…
Chirality in inorganic nanoparticles and nanostructures has gained increasing scientific interest, because of the possibility to tune their ability to interact differently with left- and right-handed circularly polarized light. In some…
Colloidal membranes, self assembled monolayers of aligned rod like molecules, offer a template for designing membranes with definite shapes and curvature, and possibly new functionalities in the future. Often the constituent rods, due to…
Designing molecules that bind to specific target proteins is a fundamental task in drug discovery. Recent models leverage geometric constraints to generate ligand molecules that bind cohesively with specific protein pockets. However, these…