DRPScore & DDPScore

Evaluation of RNA/DNA-protein complex structures using the deep learning method

Home Image

About DRPScore

   RNA-protein complexes are fundamental to numerous cellular processes, including translation and gene regulation. The high-resolution structural determination of RNA-protein complexes is essential to understanding their functions. Therefore, computational methods capable of identifying native-like RNA-protein structures are needed. To address this challenge, we have developed DRPScore, a deep-learning-based approach for identifying native-like RNA-protein structures.

   DRPScore has been tested on representative sets of RNA-protein complexes that exhibit various degrees of binding-induced conformation changes. These range from fully rigid docking (bound-bound) to fully flexible docking (unbound-unbound). Out of the top 20 predictions, DRPScore selects native-like structures with a success rate of 91.67% for bound RNA-protein complexes and 56.14% for unbound complexes. DRPScore consistently outperforms existing methods, achieving a 10.53-15.79% improvement, even in the most challenging unbound cases. Furthermore, DRPScore significantly enhances the accuracy of native interface interaction predictions. DRPScore is expected to be widely useful in modeling and designing RNA-protein complexes.

Home Image

About DDPScore

   Biological processes such as transcription, repair, and regulation require interactions between DNA and proteins. To unravel their functions, it is imperative to determine the high-resolution structures of DNA-protein complexes. However, experimental methods for this purpose are costly and technically demanding. Consequently, there is an urgent need for computational techniques to identify the structures of DNA-protein complexes. Despite technological advancements, accurately identifying DNA-protein complexes through computational methods still poses a challenge.

   Our team has developed a cutting-edge deep-learning approach called DDPScore that assesses DNA-protein complex structures. DDPScore utilizes a 4D convolutional neural network to overcome limited training data. This approach effectively captures local and global features while comprehensively considering the conformational changes arising from the flexibility during the DNA-protein docking process. DDPScore consistently outperformed the available methods in comprehensive DNA-protein complex docking evaluations, even for the flexible docking challenges. DDPScore has a wide range of applications in predicting and designing structures of DNA-protein complexes.

Resources

Related Links

Visitor Information

Country Visit Count IP

Contact

If you have any questions, feel free to contact us at: yjzhaowh@mail.ccnu.edu.cn

Institute of Biophysics and Department of Physics, Central China Normal University, Wuhan 430079, China.

References

  1. Chengwei Zeng#, Yiren Jian#, Soroush Vosoughi, Chen Zeng, and Yunjie Zhao*, Evaluating native-like structures of RNA-protein complexes through the deep learning method. Nature Communications, 2023. 14(1):1060.
  2. Chengwei Zeng#, Yiren Jian#, Chen Zhuo, Anbang Li, Chen Zeng and Yunjie Zhao*, Evaluation of DNA-protein complex structures using the deep learning method, Physical Chemistry Chemical Physics, 2024. 26(1):130-143.