A new artificial intelligence model developed by USC researchers and published in Nature methods can predict with accuracy how different proteins might bind to DNA for different types of proteins, a technological advance that promises to shorten the time needed to develop new drugs and other medical treatments.
The tool, called Deep Predictor of Binding Specificity (DeepPBS), is a geometric deep learning model designed to predict protein-DNA binding specificity based on complex protein-DNA structures. DeepPBS allows scientists and researchers to input the data structure of a protein-DNA complex into an online computing tool.
“Structures of protein-DNA complexes contain proteins that are usually bound to a single DNA sequence. To understand gene regulation, it is important to have access to the binding specificity of a protein to each DNA sequence or region of the genome” , said Remo. Rohs, professor and founding director of the Department of Quantitative and Computational Biology at the USC Dornsife College of Letters, Arts and Sciences. “DeepPBS is an AI tool that replaces the need for high-throughput sequencing or structural biology experiments to reveal the specificity of protein-DNA binding.”
AI analyzes, predicts proteins–DNA structures
DeepPBS uses a geometric deep learning model, a type of machine learning approach that analyzes data using geometric structures. The AI tool is designed to capture the chemical properties and geometric contexts of protein DNA to predict binding specificity.
Using this data, DeepPBS produces spatial graphs that illustrate protein structure and the relationship between protein and DNA representations. DeepPBS can also predict binding specificity between different protein families, unlike many existing methods that are limited to one family of proteins.
“It is important that researchers have a method available that works universally for all proteins and is not limited to a well-studied protein family. This approach also allows us to design new proteins,” said Rohs.
Major progress in predicting protein structure
The field of protein structure prediction has developed rapidly since the advent of DeepMind’s AlphaFold, which can predict protein structure from sequence. These tools have led to an increase in structural data available for analysis by scientists and researchers. DeepPBS works in combination with structure prediction methods to predict specificity for proteins without available experimental structures.
Rohs said the applications of DeepPBS are numerous. This new research method could lead to accelerating the design of new drugs and treatments for specific mutations in cancer cells, but also to new discoveries in synthetic biology and applications in RNA research.
About the study: In addition to Rohs, other study authors include Raktim Mitra of USC; Jinsen Li of USC; Jared Sagendorf of the University of California, San Francisco; Yibei Jiang of USC; Ari Cohen of USC; and Tsu-Pei Chiu of USC; as well as Cameron Glasscock of the University of Washington.
This research was primarily supported by NIH grant R35GM130376.
