PrismNet (Protein-RNA Interaction by Sructure-informed Modeling using deep neural NETwork) is a deep learning tools that integrates experimental in vivo RNA structures and RBP binding sites for matched cells to accurately predict conditional RBP binding sites in different cellular context. PrismNet web server could predict “RNA centric” binding RBPs (in our 168 human databases) and “protein centric” binding RNA (one sequence or even whole transcriptome) based on RNA matched structures in cells.
Reference
Sun, L., Xu, K., Huang, W., Yang, Y.T., Li, P., Tang, L., Xiong, T., and Zhang, Q.C. (2021). Predicting dynamic cellular protein-RNA interactions by deep learning using in vivo RNA structures. Cell Res 31, 495-516.
Xu, Y., Zhu, J., Huang, W., Xu, K., Yang, R., Zhang, Q.C., and Sun, L. (2023). PrismNet: predicting protein–RNA interaction using in vivo RNA structural information. Nucleic Acids Research, gkad353.