Prediction of amino acid side chain conformation using a deep neural network
This work addresses a key bottleneck in protein structure prediction and design, offering a robust tool for quality checks and applications like Cryo-EM and docking, though it is incremental as it builds on existing deep learning approaches.
The authors tackled the problem of predicting amino acid side chain conformation, which is crucial for protein modeling and design, and achieved over 25% improvement in accuracy compared to standard methods, particularly for aromatic residues.
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.