no code implementations • 24 Apr 2024 • Dmitrii Zhemchuzhnikov, Sergei Grudinin
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.
no code implementations • 28 Mar 2024 • Dmitrii Zhemchuzhnikov, Sergei Grudinin
Effective recognition of spatial patterns and learning their hierarchy is crucial in modern spatial data analysis.
no code implementations • 26 Jul 2021 • Dmitrii Zhemchuzhnikov, Ilia Igashov, Sergei Grudinin
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.
no code implementations • 16 May 2021 • Elodie Laine, Stephan Eismann, Arne Elofsson, Sergei Grudinin
The potential of deep learning has been recognized in the protein structure prediction community for some time, and became indisputable after CASP13.
1 code implementation • 16 Nov 2020 • Ilia Igashov, Nikita Pavlichenko, Sergei Grudinin
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.
Ranked #1 on Protein Fold Quality Estimation on CASP13 MQA (Pearson Correlation Global metric)
Protein Folding Quality Prediction Protein Fold Quality Estimation
no code implementations • 29 Oct 2018 • Guillaume Pagès, Sergei Grudinin
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.
1 code implementation • 18 Jan 2018 • Georgy Derevyanko, Sergei Grudinin, Yoshua Bengio, Guillaume Lamoureux
Additional testing on decoys from the CASP12, CAMEO, and 3DRobot datasets confirms that the network performs consistently well across a variety of protein structures.