@article {Gao236851, author = {Yujuan Gao and Sheng Wang and Minghua Deng and Jinbo Xu}, title = {Real-value and confidence prediction of protein backbone dihedral angles through a hybrid method of clustering and deep learning}, elocation-id = {236851}, year = {2017}, doi = {10.1101/236851}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Background Protein dihedral angles provide a detailed description of protein local conformation. Predicted dihedral angles can be used to narrow down the conformational space of the whole polypeptide chain significantly, thus aiding protein tertiary structure prediction. However, direct angle prediction from sequence alone is challenging.Method In this study, we present a novel method to predict realvalued angles by combining clustering and deep learning. That is, we first generate certain clusters of angles (each assigned a label) and then apply a deep residual neural network to predict the label posterior probability. Finally, we output real-valued prediction by a mixture of the clusters with their predicted probabilities. At the same time, we also estimate the bound of the prediction errors at each residue from the predicted label probabilities.Result In this article, we present a novel method (named RaptorX-Angle) to predict real-valued angles by combining clustering and deep learning. Tested on a subset of PDB25 and the targets in the latest two Critical Assessment of protein Structure Prediction (CASP), our method outperforms the existing state-of-art method SPIDER2 in terms of Pearson Correlation Coefficient (PCC) and Mean Absolute Error (MAE). Our result also shows approximately linear relationship between the real prediction errors and our estimated bounds. That is, the real prediction error can be well approximated by our estimated bounds.Conclusions Our study provides an alternative and more accurate prediction of dihedral angles, which may facilitate protein structure prediction and functional study.}, URL = {https://www.biorxiv.org/content/early/2017/12/20/236851}, eprint = {https://www.biorxiv.org/content/early/2017/12/20/236851.full.pdf}, journal = {bioRxiv} }