Discovery of Phase Separation Proteins With AI



Team

Yi-Wei Li

Yi-Wei Li is a professor in Huazhong University of Science and Technology , Wuhan, China. He graduated from Huazhong University of Science and Technology in 2016 with a degree in biomedical engineering, and has worked as a visiting doctoral student in the Department of Applied Physics at Harvard University, as a postdoctoral fellow at Massachusetts Institute of Technology (MIT), and as a joint postdoctoral fellow at the Harvard School of Engineering and Applied Sciences. Dr. Yi-Wei Li's research focuses on the construction of functional microtissues and organoids, focusing on the related biomechanical and biophysical problems therein, and constructing high-throughput single-cell mechanical and histological analysis techniques to serve this research.

Wei Li

Wei Li is a professor in School of Artificial Intelligence and Automation in Huazhong University of Science and Technology, Wuhan, China. She received the B.S. degree in 1997, the M.S. degree in 2000, and the Ph.D. degree in Control Science and Engineering in 2003, from Huazhong University of Science and Technology, Wuhan, China. Her research interests include Biomedical signal analysis, Small-sample pattern recognition, Model interpretability, Neural image analysis.

Zhang Peng

Zhang Peng is a Postdoctoral Researcher with the Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology. He received the B.S. degree in biomedical engineering and the Ph.D. degree in control science and engineering from the Huazhong University of Science and Technology, Wuhan, China, in 2011 and 2018, respectively. His primary research focuses on artificial intelligence in medicine, physiological signal processing and analysis.

Code

LRECA code contains two parts: protein phase separation characterization and traceability.

The RCNN_model folder contains the characterization code. Specifically, it contains the code for LLPS and PDB, phaspDB_reviewed and PDB, phaspDB_highthroughput and PDB, mydata_1507 and PDB dataset training. The RCNN_ECA_saliency folder contains the feature traceability code. It specifically contains the LCRs_process, saliency_functi, and save_model folders. The LCRs_process folder contains read_LCRs_segment.py for comparative analysis with existing LCRs segments, and split_LCRs_segment.py for generating segments based on the probability density of the contribution value at each position of the amino acid sequence and highlighting the amino acid segment with the largest contribution value; The method folder in the saliency_functio folder contains the code for generating the contribution value at each position of the amino acid sequence, the statics folder contains the code for statistically analyzing the contribution value at each position of the amino acid sequence, and the RCNN_ECA_save_model.py file is used to save the trained model and parameters; The save_model folder saves the trained models and parameters for characterization detection.

DownLoad