Michaël Defferrard’s research while affiliated with Swiss Federal Institute of Technology in Lausanne and other places

The shape of neuronal morphologies plays a critical role in determining their dynamical properties and the functionality of the brain. With an abundance of neuronal morphology reconstructions, a robust definition of cell types is important to understand their role in brain functionality. However, an objective morphology classification scheme is hard to establish due to disagreements on the definition of cell types, on which subjective views of field experts show significant differences. The robust grouping of neurons based on their morphological shapes is important for generative models and for establishing a link between anatomical properties and other modalities, such as biophysical and transcriptomic information. We combine deep learning techniques with a variety of mathematical descriptions of neurons and evaluate the classification accuracy of different methods. We demonstrate that various methodologies, including graph neural networks, topological morphology descriptors, and morphometrics, consistently perform with the highest accuracy for a variety of datasets. Based on these methods, we present a robust classification of both inhibitory and excitatory cell types in the rodent cortex and propose a generalized scheme for a consistent classification of neurons into classes.

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.

We introduce ChebLieNet, a group-equivariant method on (anisotropic) manifolds. Surfing on the success of graph- and group-based neural networks, we take advantage of the recent developments in the geometric deep learning field to derive a new approach to exploit any anisotropies in data. Via discrete approximations of Lie groups, we develop a graph neural network made of anisotropic convolutional layers (Chebyshev convolutions), spatial pooling and unpooling layers, and global pooling layers. Group equivariance is achieved via equivariant and invariant operators on graphs with anisotropic left-invariant Riemannian distance-based affinities encoded on the edges. Thanks to its simple form, the Riemannian metric can model any anisotropies, both in the spatial and orientation domains. This control on anisotropies of the Riemannian metrics allows to balance equivariance (anisotropic metric) against invariance (isotropic metric) of the graph convolution layers. Hence we open the doors to a better understanding of anisotropic properties. Furthermore, we empirically prove the existence of (data-dependent) sweet spots for anisotropic parameters on CIFAR10. This crucial result is evidence of the benefice we could get by exploiting anisotropic properties in data. We also evaluate the scalability of this approach on STL10 (image data) and ClimateNet (spherical data), showing its remarkable adaptability to diverse tasks.

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 Summary Finely 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.

A major challenge in single-particle cryo-electron microscopy (cryo-EM) is that the orientations adopted by the 3D particles prior to imaging are unknown; yet, this knowledge is essential for high-resolution reconstruction. We present a method to recover these orientations directly from the acquired set of 2D projections. Our approach consists of two steps: (i) the estimation of distances between pairs of projections, and (ii) the recovery of the orientation of each projection from these distances. In step (i), pairwise distances are estimated by a Siamese neural network trained on synthetic cryo-EM projections from resolved bio-structures. In step (ii), orientations are recovered by minimizing the difference between the distances estimated from the projections and the distances induced by the recovered orientations. We evaluated the method on synthetic cryo-EM datasets. Current results demonstrate that orientations can be accurately recovered from projections that are shifted and corrupted with a high level of noise. The accuracy of the recovery depends on the accuracy of the distance estimator. While not yet deployed in a real experimental setup, the proposed method offers a novel learning-based take on orientation recovery in SPA. Our code is available at https://github.com/JelenaBanjac/protein-reconstruction

Designing a convolution for a spherical neural network requires a delicate tradeoff between efficiency and rotation equivariance. DeepSphere, a method based on a graph representation of the sampled sphere, strikes a controllable balance between these two desiderata. This contribution is twofold. First, we study both theoretically and empirically how equivariance is affected by the underlying graph with respect to the number of vertices and neighbors. Second, we evaluate DeepSphere on relevant problems. Experiments show state-of-the-art performance and demonstrates the efficiency and flexibility of this formulation. Perhaps surprisingly, comparison with previous work suggests that anisotropic filters might be an unnecessary price to pay. Our code is available at https://github.com/deepsphere

We present simplicial neural networks (SNNs), a generalization of graph neural networks to data that live on a class of topological spaces called simplicial complexes. These are natural multi-dimensional extensions of graphs that encode not only pairwise relationships but also higher-order interactions between vertices - allowing us to consider richer data, including vector fields and n-fold collaboration networks. We define an appropriate notion of convolution that we leverage to construct the desired convolutional neural networks. We test the SNNs on the task of imputing missing data on coauthorship complexes.

We present an approach for tracking fast spatiotemporal cortical dynamics in which we combine white matter connectivity data with source-projected electroencephalographic (EEG) data. We employ the mathematical framework of graph signal processing in order to derive the Fourier modes of the brain structural connectivity graph, or “network harmonics” . These network harmonics are naturally ordered by smoothness. Smoothness in this context can be understood as the amount of variation along the cortex, leading to a multi-scale representation of brain connectivity. We demonstrate that network harmonics provide a sparse representation of the EEG signal, where, at certain times, the smoothest 15 network harmonics capture 90% of the signal power. This suggests that network harmonics are functionally meaningful, which we demonstrate by using them as a basis for the functional EEG data recorded from a face detection task. There, only 13 network harmonics are sufficient to track the large-scale cortical activity during the processing of the stimuli with a 50 ms resolution, reproducing well-known activity in the fusiform face area as well as revealing co-activation patterns in somatosensory/motor and frontal cortices that an unconstrained ROI-by-ROI analysis fails to capture. The proposed approach is simple and fast, provides a means of integration of multimodal datasets, and is tied to a theoretical framework in mathematics and physics. Thus, network harmonics point towards promising research directions both theoretically - for example in exploring the relationship between structure and function in the brain - and practically - for example for network tracking in different tasks and groups of individuals, such as patients.

We present an approach for tracking fast spatiotemporal cortical dynamics in which we combine white matter connectivity data with source-projected electroencephalographic (EEG) data. We employ the mathematical framework of graph signal processing; in order to derive the Fourier modes of the brain structural connectivity graph, or "network harmonics". These network harmonics are naturally ordered by smoothness. Smoothness in this context can be understood as the amount of variation along the cortex, leading to a multi-scale representation of brain connectivity. We demonstrate that network harmonics provide a sparse representation of the EEG signal, where, at certain times, the smoothest 15 network harmonics capture 90% of the signal power. This suggests that network harmonics are functionally meaningful, which we demonstrate by using them as a basis for the functional EEG data recorded from a face detection task. There, only 13 network harmonics are sufficient to track the large-scale cortical activity during the processing of the stimuli with a 50 ms resolution, reproducing well-known activity in the fusiform face area as well as revealing co-activation patterns in somatosensory/motor and frontal cortices that an unconstrained ROI-by-ROI analysis fails to capture. The proposed approach is simple and fast, provides a means of integration of multimodal datasets, and is tied to a theoretical framework in mathematics and physics. Thus, network harmonics point towards promising research directions both theoretically - for example in exploring the relationship between structure and function in the brain - and practically - for example for network tracking in different tasks and groups of individuals, such as patients.

Bilateral trade agreements confer preferred trading status between participating countries, enabling increased trade and potential economic growth. Predicting such trade flows often serve as important economic indicators used by economists and policy makers with impactful ramifications in economic policies adopted by respective countries. However, traditional approaches to predicting potential trade partners is through the use of gravity methods which are cumbersome to define due to the exponentially growing number of constants that need to be considered. In this work, we present a framework for directly predicting bilateral trade partners from observed trade records using graph representation learning. Furthermore, we show as a downstream task that modelling bilateral trade as a graph allows for the classification of countries into various income levels. Empirically, we observe accuracies of up to 98% for predicting trading partners and 68% on income level classification.