Prediction of amino acid side chain conformation using a deep neural network

By Ke Liu, Xiangyan Sun, Jun Ma, Zhenyu Zhou, Qilin Dong, Shengwen Peng, Junqiu Wu, Suocheng Tan, Günter Blobel, Jie Fan. 2017

17 citations recorded by the source corpus.

A deep neural network based architecture was constructed to predict amino acid side chain conformation with unprecedented accuracy. Amino acid side chain conformation prediction is essential for protein homology modeling and protein design. Current widely-adopted methods use physics-based energy functions to evaluate side chain conformation. Here, using a deep neural network architecture without physics-based assumptions, we have demonstrated that side chain conformation prediction accuracy can be improved by more than 25%, especially for aromatic residues compared with current standard methods. More strikingly, the prediction method presented here is robust enough to identify individual conformational outliers from high resolution structures in a protein data bank without providing its structural factors. We envisage that our amino acid side chain predictor could be used as a quality check step for future protein structure model validation and many other potential applications such as side chain assignment in Cryo-electron microscopy, crystallography model auto-building, protein folding and small molecule ligand docking.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. Jinbo Xu
2. Namrata Anand
3. Matthew McPartlon
4. Sheng Wang

In Materials Chemistry

1. Jinbo Xu
2. Tudor Achim
3. Namrata Anand
4. Matthew McPartlon
5. Sheng Wang
6. Jianzhu Ma
7. Zhiyong Wang
8. Siqi Sun

In Molecular Biology

1. Jinbo Xu
2. Tudor Achim
3. Namrata Anand
4. Matthew McPartlon
5. Sheng Wang
6. Badri Adhikari
7. Jianzhu Ma
8. David T. Jones

Citations in the corpus

• Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models (2022, background): “Rotamer packing has benefited from machine learning approaches [28, 14, 1, 32, 3].”
• Deep Learning in Protein Structural Modeling and Design (2020, unknown): “Side-chain prediction is often embedded in high-resolution structure prediction methods, traditionally with dead-end elimination167 or preferential sampling from backbone-dependent side-chain rotamer libraries.168 Liu et al.169 specifically trained a 3D CNN to evaluate the probability score for diff”
• An end-to-end deep learning method for rotamer-free protein side-chain packing (2022, background): “Several machine learning (ML) methods have been proposed for the task of side-chain prediction [22, 21, 30, 31, 34, 20, 32].”