Deep Learning Approach with Rotate-Shift Invariant Input to Predict Protein Homodimer Structure
| Autor: | Alexander V. Tuzikov, Anna Hadarovich, Alexander Kalinouski |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0303 health sciences
Artificial neural network business.industry Computer science Protein contact map Deep learning 030302 biochemistry & molecular biology Protein structure prediction Convolutional neural network 03 medical and health sciences Macromolecular docking Artificial intelligence business Gradient descent Distance transform Algorithm 030304 developmental biology |
| Zdroj: | Bioinformatics Research and Applications ISBN: 9783030578206 ISBRA |
| Popis: | The ability to predict protein complexes is important for applications in drug design and generating models of high accuracy in the cell. Recently deep learning techniques showed a significant success in protein structure prediction, but a protein docking problem is unsolved yet. We developed a two-staged approach which consists of deep convolutional neural network to predict protein contact map for homodimers and optimization procedure based on gradient descent to build the homodimer structure from the contact map. Neural network uses the distance map calculated as all pairwise Euclidian distances between CB atoms of protein 3D structure as input, which is invariant to rotation and translation. The network has a large receptive filed to capture patterns in contacts between residues. The suggested approach could be generalized to heterodimers because it does not depend on symmetry features inherent in homodimers. The presented algorithm could be also used for scoring protein homodimers models in docking. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|