Download | - View final version: Geometric deep learning for protein–protein interaction predictions (PDF, 2.0 MiB)
|
---|
DOI | Resolve DOI: https://doi.org/10.1109/ACCESS.2022.3201543 |
---|
Author | Search for: St-Pierre Lemieux, Gabriel1; Search for: Paquet, Eric1ORCID identifier: https://orcid.org/0000-0001-6515-2556; Search for: Viktor, Herna L.ORCID identifier: https://orcid.org/0000-0003-1914-5077; Search for: Michalowski, Wojtek |
---|
Affiliation | - National Research Council of Canada. Digital Technologies
|
---|
Funder | Search for: National Research Council of Canada through the Artificial Intelligence for Design (AI4Design) Challenge Program |
---|
Format | Text, Article |
---|
Subject | protein-protein interaction; geometric deep learning; spectral convolutional neural network; graph convolutional neural network; macromolecular surface; heat kernel; wave kernel |
---|
Abstract | This work introduces novel approaches, based on geometrical deep learning, for predicting protein–protein interactions. A dataset containing both interacting and non-interacting proteins is selected from the Negatome Database. Interactions are predicted from a graph representing the proteins’ three-dimensional macromolecular surfaces. The nodes are described with heat and wave kernel signatures. Twenty-one neural network architectures are proposed and compared; these are based on graph convolutional neural networks, spectral convolutional neural networks, and a novel spatio–spectral spatialized-gated convolutional neural network. The experimental results demonstrate the accuracy and the efficiency of the proposed architectures. |
---|
Publication date | 2022-08-25 |
---|
Publisher | IEEE |
---|
Licence | |
---|
In | |
---|
Language | English |
---|
Peer reviewed | Yes |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | 6615a79a-66fc-4640-881f-9aa94c806c3e |
---|
Record created | 2022-09-26 |
---|
Record modified | 2023-03-16 |
---|