Showing 1–12 of 12 results for author: Grudinin, S

SpecMoE: Spectral Mixture-of-Experts Foundation Model for Cross-Species EEG Decoding

Authors: Davy Darankoum, Chloé Habermacher, Julien Volle, Sergei Grudinin

Abstract: Decoding the orchestration of neural activity in electroencephalography (EEG) signals is a central challenge in bridging neuroscience with artificial intelligence. Foundation models have made strides in generalized EEG decoding, yet many existing frameworks primarily relying on separate temporal and spectral masking of raw signals during self-supervised pretraining. Such strategies often tend to b… ▽ More Decoding the orchestration of neural activity in electroencephalography (EEG) signals is a central challenge in bridging neuroscience with artificial intelligence. Foundation models have made strides in generalized EEG decoding, yet many existing frameworks primarily relying on separate temporal and spectral masking of raw signals during self-supervised pretraining. Such strategies often tend to bias learning toward high-frequency oscillations, as low-frequency rhythmic patterns can be easily inferred from the unmasked signal. We introduce a foundation model that utilizes a novel Gaussian-smoothed masking scheme applied to short-time Fourier transform (STFT) maps. By jointly applying time, frequency, and time-frequency Gaussian masks, we make the reconstruction task much more challenging, forcing the model to learn intricate neural patterns across both high- and low-frequency domains. To effectively recover signals under this aggressive masking strategy, we design SpecHi-Net, a U-shaped hierarchical architecture with multiple encoding and decoding stages. To accelerate large-scale pretraining, we partition the data into three subsets, each used to train an independent expert model. We then combine these models through SpecMoE, a mixture of experts framework guided by a learned spectral gating mechanism. SpecMoE achieves state-of-the-art performance across a diverse set of EEG decoding tasks, including sleep staging, emotion recognition, motor imagery classification, abnormal signal detection, and drug effect prediction. Importantly, the model demonstrates strong cross-species and cross-subject generalization, maintaining high accuracy on both human and murine EEG datasets. △ Less

Submitted 30 March, 2026; v1 submitted 17 March, 2026; originally announced March 2026.

Comments: 34 pages (12 pages in the main text and 22 pages in Supplementary Information)

CoSupFormer : A Contrastive Supervised learning approach for EEG signal Classification

Authors: D. Darankoum, C. Habermacher, J. Volle, S. Grudinin

Abstract: Electroencephalography signals (EEGs) contain rich multi-scale information crucial for understanding brain states, with potential applications in diagnosing and advancing the drug development landscape. However, extracting meaningful features from raw EEG signals while handling noise and channel variability remains a major challenge. This work proposes a novel end-to-end deep-learning framework th… ▽ More Electroencephalography signals (EEGs) contain rich multi-scale information crucial for understanding brain states, with potential applications in diagnosing and advancing the drug development landscape. However, extracting meaningful features from raw EEG signals while handling noise and channel variability remains a major challenge. This work proposes a novel end-to-end deep-learning framework that addresses these issues through several key innovations. First, we designed an encoder capable of explicitly capturing multi-scale frequency oscillations covering a wide range of features for different EEG-related tasks. Secondly, to model complex dependencies and handle the high temporal resolution of EEGs, we introduced an attention-based encoder that simultaneously learns interactions across EEG channels and within localized {\em patches} of individual channels. We integrated a dedicated gating network on top of the attention encoder to dynamically filter out noisy and non-informative channels, enhancing the reliability of EEG data. The entire encoding process is guided by a novel loss function, which leverages supervised and contrastive learning, significantly improving model generalization. We validated our approach in multiple applications, ranging from the classification of effects across multiple Central Nervous System (CNS) disorders treatments to the diagnosis of Parkinson's and Alzheimer's disease. Our results demonstrate that the proposed learning paradigm can extract biologically meaningful patterns from raw EEG signals across different species, autonomously select high-quality channels, and achieve robust generalization through innovative architectural and loss design. △ Less

Submitted 24 September, 2025; originally announced September 2025.

Comments: 20 pages (14 pages Main text and 6 pages Supplementary Material)

Challenges in Non-Polymeric Crystal Structure Prediction: Why a Geometric, Permutation-Invariant Loss is Needed

Authors: Emmanuel Jehanno, Romain Menegaux, Julien Mairal, Sergei Grudinin

Abstract: Crystalline structure prediction is an essential prerequisite for designing materials with targeted properties. Yet, it is still an open challenge in materials design and drug discovery. Despite recent advances in computational materials science, accurately predicting three-dimensional non-polymeric crystal structures remains elusive. In this work, we focus on the molecular assembly problem, where… ▽ More Crystalline structure prediction is an essential prerequisite for designing materials with targeted properties. Yet, it is still an open challenge in materials design and drug discovery. Despite recent advances in computational materials science, accurately predicting three-dimensional non-polymeric crystal structures remains elusive. In this work, we focus on the molecular assembly problem, where a set $\mathcal{S}$ of identical rigid molecules is packed to form a crystalline structure. Such a simplified formulation provides a useful approximation to the actual problem. However, while recent state-of-the-art methods have increasingly adopted sophisticated techniques, the underlying learning objective remains ill-posed. We propose a better formulation that introduces a loss function capturing key geometric molecular properties while ensuring permutation invariance over $\mathcal{S}$. Remarkably, we demonstrate that within this framework, a simple regression model already outperforms prior approaches, including flow matching techniques, on the COD-Cluster17 benchmark, a curated non-polymeric subset of the Crystallography Open Database (COD). △ Less

Submitted 26 September, 2025; v1 submitted 31 August, 2025; originally announced September 2025.

PETIMOT: A Novel Framework for Inferring Protein Motions from Sparse Data Using SE(3)-Equivariant Graph Neural Networks

Authors: Valentin Lombard, Sergei Grudinin, Elodie Laine

Abstract: Proteins move and deform to ensure their biological functions. Despite significant progress in protein structure prediction, approximating conformational ensembles at physiological conditions remains a fundamental open problem. This paper presents a novel perspective on the problem by directly targeting continuous compact representations of protein motions inferred from sparse experimental observa… ▽ More Proteins move and deform to ensure their biological functions. Despite significant progress in protein structure prediction, approximating conformational ensembles at physiological conditions remains a fundamental open problem. This paper presents a novel perspective on the problem by directly targeting continuous compact representations of protein motions inferred from sparse experimental observations. We develop a task-specific loss function enforcing data symmetries, including scaling and permutation operations. Our method PETIMOT (Protein sEquence and sTructure-based Inference of MOTions) leverages transfer learning from pre-trained protein language models through an SE(3)-equivariant graph neural network. When trained and evaluated on the Protein Data Bank, PETIMOT shows superior performance in time and accuracy, capturing protein dynamics, particularly large/slow conformational changes, compared to state-of-the-art flow-matching approaches and traditional physics-based models. △ Less

Submitted 19 March, 2025; originally announced April 2025.

Journal ref: LMRL Workshop at ICLR 2025

BAnG: Bidirectional Anchored Generation for Conditional RNA Design

Authors: Roman Klypa, Alberto Bietti, Sergei Grudinin

Abstract: Designing RNA molecules that interact with specific proteins is a critical challenge in experimental and computational biology. Existing computational approaches require a substantial amount of previously known interacting RNA sequences for each specific protein or a detailed knowledge of RNA structure, restricting their utility in practice. To address this limitation, we develop RNA-BAnG, a deep… ▽ More Designing RNA molecules that interact with specific proteins is a critical challenge in experimental and computational biology. Existing computational approaches require a substantial amount of previously known interacting RNA sequences for each specific protein or a detailed knowledge of RNA structure, restricting their utility in practice. To address this limitation, we develop RNA-BAnG, a deep learning-based model designed to generate RNA sequences for protein interactions without these requirements. Central to our approach is a novel generative method, Bidirectional Anchored Generation (BAnG), which leverages the observation that protein-binding RNA sequences often contain functional binding motifs embedded within broader sequence contexts. We first validate our method on generic synthetic tasks involving similar localized motifs to those appearing in RNAs, demonstrating its benefits over existing generative approaches. We then evaluate our model on biological sequences, showing its effectiveness for conditional RNA sequence design given a binding protein. △ Less

Submitted 23 June, 2025; v1 submitted 28 February, 2025; originally announced February 2025.

From Epilepsy Seizures Classification to Detection: A Deep Learning-based Approach for Raw EEG Signals

Authors: Davy Darankoum, Manon Villalba, Clelia Allioux, Baptiste Caraballo, Carine Dumont, Eloise Gronlier, Corinne Roucard, Yann Roche, Chloe Habermacher, Sergei Grudinin, Julien Volle

Abstract: Epilepsy represents the most prevalent neurological disease in the world. One-third of people suffering from mesial temporal lobe epilepsy (MTLE) exhibit drug resistance, urging the need to develop new treatments. A key part in anti-seizure medication (ASM) development is the capability of detecting and quantifying epileptic seizures occurring in electroencephalogram (EEG) signals, which is crucia… ▽ More Epilepsy represents the most prevalent neurological disease in the world. One-third of people suffering from mesial temporal lobe epilepsy (MTLE) exhibit drug resistance, urging the need to develop new treatments. A key part in anti-seizure medication (ASM) development is the capability of detecting and quantifying epileptic seizures occurring in electroencephalogram (EEG) signals, which is crucial for treatment efficacy evaluation. In this study, we introduced a seizure detection pipeline based on deep learning models applied to raw EEG signals. This pipeline integrates: a new pre-processing technique which segments continuous raw EEG signals without prior distinction between seizure and seizure-free activities; a post-processing algorithm developed to reassemble EEG segments and allow the identification of seizures start/end; and finally, a new evaluation procedure based on a strict seizure events comparison between predicted and real labels. Models training have been performed using a data splitting strategy which addresses the potential for data leakage. We demonstrated the fundamental differences between a seizure classification and a seizure detection task and showed the differences in performance between the two tasks. Finally, we demonstrated the generalization capabilities across species of our best architecture, combining a Convolutional Neural Network and a Transformer encoder. The model was trained on animal EEGs and tested on human EEGs with a F1-score of 93% on a balanced Bonn dataset. △ Less

Submitted 2 November, 2025; v1 submitted 4 October, 2024; originally announced October 2024.

Comments: 25 pages, 3 tables, 5 figures

On the Fourier analysis in the SO(3) space : EquiLoPO Network

Authors: Dmitrii Zhemchuzhnikov, Sergei Grudinin

Abstract: Analyzing volumetric data with rotational invariance or equivariance is an active topic in current research. Existing deep-learning approaches utilize either group convolutional networks limited to discrete rotations or steerable convolutional networks with constrained filter structures. This work proposes a novel equivariant neural network architecture that achieves analytical Equivariance to Loc… ▽ More Analyzing volumetric data with rotational invariance or equivariance is an active topic in current research. Existing deep-learning approaches utilize either group convolutional networks limited to discrete rotations or steerable convolutional networks with constrained filter structures. This work proposes a novel equivariant neural network architecture that achieves analytical Equivariance to Local Pattern Orientation on the continuous SO(3) group while allowing unconstrained trainable filters - EquiLoPO Network. Our key innovations are a group convolutional operation leveraging irreducible representations as the Fourier basis and a local activation function in the SO(3) space that provides a well-defined mapping from input to output functions, preserving equivariance. By integrating these operations into a ResNet-style architecture, we propose a model that overcomes the limitations of prior methods. A comprehensive evaluation on diverse 3D medical imaging datasets from MedMNIST3D demonstrates the effectiveness of our approach, which consistently outperforms state of the art. This work suggests the benefits of true rotational equivariance on SO(3) and flexible unconstrained filters enabled by the local activation function, providing a flexible framework for equivariant deep learning on volumetric data with potential applications across domains. Our code is publicly available at https://gricad-gitlab.univ-grenoble-alpes.fr/GruLab/ILPO/-/tree/main/EquiLoPO. △ Less

Submitted 19 March, 2025; v1 submitted 24 April, 2024; originally announced April 2024.

Journal ref: conference paper at ICLR 2025

ILPO-NET: Network for the invariant recognition of arbitrary volumetric patterns in 3D

Authors: Dmitrii Zhemchuzhnikov, Sergei Grudinin

Abstract: Effective recognition of spatial patterns and learning their hierarchy is crucial in modern spatial data analysis. Volumetric data applications seek techniques ensuring invariance not only to shifts but also to pattern rotations. While traditional methods can readily achieve translational invariance, rotational invariance possesses multiple challenges and remains an active area of research. Here,… ▽ More Effective recognition of spatial patterns and learning their hierarchy is crucial in modern spatial data analysis. Volumetric data applications seek techniques ensuring invariance not only to shifts but also to pattern rotations. While traditional methods can readily achieve translational invariance, rotational invariance possesses multiple challenges and remains an active area of research. Here, we present ILPO-Net (Invariant to Local Patterns Orientation Network), a novel approach that handles arbitrarily shaped patterns with the convolutional operation inherently invariant to local spatial pattern orientations using the Wigner matrix expansions. Our architecture seamlessly integrates the new convolution operator and, when benchmarked on diverse volumetric datasets such as MedMNIST and CATH, demonstrates superior performance over the baselines with significantly reduced parameter counts - up to 1000 times fewer in the case of MedMNIST. Beyond these demonstrations, ILPO-Net's rotational invariance paves the way for other applications across multiple disciplines. Our code is publicly available at https://gricad-gitlab.univ-grenoble-alpes.fr/GruLab/ILPO/-/tree/main/ILPONet. △ Less

Submitted 24 April, 2024; v1 submitted 28 March, 2024; originally announced March 2024.

Journal ref: Machine Learning and Knowledge Discovery in Databases. Research Track. ECML PKDD 2024. Lecture Notes in Computer Science(), vol 14944. Springer, Cham

6DCNN with roto-translational convolution filters for volumetric data processing

Authors: Dmitrii Zhemchuzhnikov, Ilia Igashov, Sergei Grudinin

Abstract: In this work, we introduce 6D Convolutional Neural Network (6DCNN) designed to tackle the problem of detecting relative positions and orientations of local patterns when processing three-dimensional volumetric data. 6DCNN also includes SE(3)-equivariant message-passing and nonlinear activation operations constructed in the Fourier space. Working in the Fourier space allows significantly reducing t… ▽ More In this work, we introduce 6D Convolutional Neural Network (6DCNN) designed to tackle the problem of detecting relative positions and orientations of local patterns when processing three-dimensional volumetric data. 6DCNN also includes SE(3)-equivariant message-passing and nonlinear activation operations constructed in the Fourier space. Working in the Fourier space allows significantly reducing the computational complexity of our operations. We demonstrate the properties of the 6D convolution and its efficiency in the recognition of spatial patterns. We also assess the 6DCNN model on several datasets from the recent CASP protein structure prediction challenges. Here, 6DCNN improves over the baseline architecture and also outperforms the state of the art. △ Less

Submitted 30 July, 2021; v1 submitted 26 July, 2021; originally announced July 2021.

Protein sequence-to-structure learning: Is this the end(-to-end revolution)?

Authors: Elodie Laine, Stephan Eismann, Arne Elofsson, Sergei Grudinin

Abstract: The potential of deep learning has been recognized in the protein structure prediction community for some time, and became indisputable after CASP13. In CASP14, deep learning has boosted the field to unanticipated levels reaching near-experimental accuracy. This success comes from advances transferred from other machine learning areas, as well as methods specifically designed to deal with protein… ▽ More The potential of deep learning has been recognized in the protein structure prediction community for some time, and became indisputable after CASP13. In CASP14, deep learning has boosted the field to unanticipated levels reaching near-experimental accuracy. This success comes from advances transferred from other machine learning areas, as well as methods specifically designed to deal with protein sequences and structures, and their abstractions. Novel emerging approaches include (i) geometric learning, i.e. learning on representations such as graphs, 3D Voronoi tessellations, and point clouds; (ii) pre-trained protein language models leveraging attention; (iii) equivariant architectures preserving the symmetry of 3D space; (iv) use of large meta-genome databases; (v) combinations of protein representations; (vi) and finally truly end-to-end architectures, i.e. differentiable models starting from a sequence and returning a 3D structure. Here, we provide an overview and our opinion of the novel deep learning approaches developed in the last two years and widely used in CASP14. △ Less

Submitted 13 September, 2021; v1 submitted 16 May, 2021; originally announced May 2021.

Spherical convolutions on molecular graphs for protein model quality assessment

Authors: Ilia Igashov, Nikita Pavlichenko, Sergei Grudinin

Abstract: Processing information on 3D objects requires methods stable to rigid-body transformations, in particular rotations, of the input data. In image processing tasks, convolutional neural networks achieve this property using rotation-equivariant operations. However, contrary to images, graphs generally have irregular topology. This makes it challenging to define a rotation-equivariant convolution oper… ▽ More Processing information on 3D objects requires methods stable to rigid-body transformations, in particular rotations, of the input data. In image processing tasks, convolutional neural networks achieve this property using rotation-equivariant operations. However, contrary to images, graphs generally have irregular topology. This makes it challenging to define a rotation-equivariant convolution operation on these structures. In this work, we propose Spherical Graph Convolutional Network (S-GCN) that processes 3D models of proteins represented as molecular graphs. In a protein molecule, individual amino acids have common topological elements. This allows us to unambiguously associate each amino acid with a local coordinate system and construct rotation-equivariant spherical filters that operate on angular information between graph nodes. Within the framework of the protein model quality assessment problem, we demonstrate that the proposed spherical convolution method significantly improves the quality of model assessment compared to the standard message-passing approach. It is also comparable to state-of-the-art methods, as we demonstrate on Critical Assessment of Structure Prediction (CASP) benchmarks. The proposed technique operates only on geometric features of protein 3D models. This makes it universal and applicable to any other geometric-learning task where the graph structure allows constructing local coordinate systems. △ Less

Submitted 6 January, 2021; v1 submitted 16 November, 2020; originally announced November 2020.

DeepSymmetry : Using 3D convolutional networks for identification of tandem repeats and internal symmetries in protein structures

Authors: Guillaume Pagès, Sergei Grudinin

Abstract: Motivation: Thanks to the recent advances in structural biology, nowadays three-dimensional structures of various proteins are solved on a routine basis. A large portion of these contain structural repetitions or internal symmetries. To understand the evolution mechanisms of these proteins and how structural repetitions affect the protein function, we need to be able to detect such proteins very r… ▽ More Motivation: Thanks to the recent advances in structural biology, nowadays three-dimensional structures of various proteins are solved on a routine basis. A large portion of these contain structural repetitions or internal symmetries. To understand the evolution mechanisms of these proteins and how structural repetitions affect the protein function, we need to be able to detect such proteins very robustly. As deep learning is particularly suited to deal with spatially organized data, we applied it to the detection of proteins with structural repetitions. Results: We present DeepSymmetry, a versatile method based on three-dimensional (3D) convolutional networks that detects structural repetitions in proteins and their density maps. Our method is designed to identify tandem repeat proteins, proteins with internal symmetries, symmetries in the raw density maps, their symmetry order, and also the corresponding symmetry axes. Detection of symmetry axes is based on learning six-dimensional Veronese mappings of 3D vectors, and the median angular error of axis determination is less than one degree. We demonstrate the capabilities of our method on benchmarks with tandem repeated proteins and also with symmetrical assemblies. For example, we have discovered over 10,000 putative tandem repeat proteins that are not currently present in the RepeatsDB database. Availability: The method is available at https://team.inria.fr/nano-d/software/deepsymmetry. It consists of a C++ executable that transforms molecular structures into volumetric density maps, and a Python code based on the TensorFlow framework for applying the DeepSymmetry model to these maps. △ Less

Submitted 29 October, 2018; originally announced October 2018.