Improving protein fold recognition using triplet network and ensemble deep learning
| Autor: | Dong-Jun Yu, Long-Chen Shen, Yan Liu, Yi-Heng Zhu, Jiangning Song, Ke Han, Ying Zhang |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Models
Molecular Protein Folding Fold (higher-order function) Protein Conformation Computer science Sensitivity and Specificity Convolutional neural network 03 medical and health sciences Deep Learning 0302 clinical medicine Discriminative model Feature (machine learning) Databases Protein Molecular Biology 030304 developmental biology 0303 health sciences business.industry Deep learning Computational Biology Proteins Reproducibility of Results Pattern recognition Complement (complexity) Benchmark (computing) Problem Solving Protocol Embedding Neural Networks Computer Artificial intelligence business Algorithms 030217 neurology & neurosurgery Information Systems |
| Zdroj: | Brief Bioinform |
| ISSN: | 1477-4054 1467-5463 |
| DOI: | 10.1093/bib/bbab248 |
| Popis: | Protein fold recognition is a critical step toward protein structure and function prediction, aiming at providing the most likely fold type of the query protein. In recent years, the development of deep learning (DL) technique has led to massive advances in this important field, and accordingly, the sensitivity of protein fold recognition has been dramatically improved. Most DL-based methods take an intermediate bottleneck layer as the feature representation of proteins with new fold types. However, this strategy is indirect, inefficient and conditional on the hypothesis that the bottleneck layer’s representation is assumed as a good representation of proteins with new fold types. To address the above problem, in this work, we develop a new computational framework by combining triplet network and ensemble DL. We first train a DL-based model, termed FoldNet, which employs triplet loss to train the deep convolutional network. FoldNet directly optimizes the protein fold embedding itself, making the proteins with the same fold types be closer to each other than those with different fold types in the new protein embedding space. Subsequently, using the trained FoldNet, we implement a new residue–residue contact-assisted predictor, termed FoldTR, which improves protein fold recognition. Furthermore, we propose a new ensemble DL method, termed FSD_XGBoost, which combines protein fold embedding with the other two discriminative fold-specific features extracted by two DL-based methods SSAfold and DeepFR. The Top 1 sensitivity of FSD_XGBoost increases to 74.8% at the fold level, which is ~9% higher than that of the state-of-the-art method. Together, the results suggest that fold-specific features extracted by different DL methods complement with each other, and their combination can further improve fold recognition at the fold level. The implemented web server of FoldTR and benchmark datasets are publicly available at http://csbio.njust.edu.cn/bioinf/foldtr/. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|