Proteins play many critical roles by interacting with other proteins, nucleic acids, and organic molecules. The disruption or deregulation of their interactions often leads to disease. Understanding protein structures and interactions can facilitate a mechanistic understanding of their function and provide a tractable way of modulating interactions for disease treatment. Our group will develop artificial intelligence-based computational methods for 1) biomolecular modeling to reveal interactions between biomolecules in both molecular and cellular level, and 2) design of interaction modulators as potential biomolecular therapeutics. The outcomes will lead to a deeper understanding of structural mechanisms for biomolecular interactions and their functions, and provide an efficient way to design novel therapeutics targeting disease-related biomolecular interactions.
- M. Baek, et al, Accurate prediction of protein structures and interactions using a three-track neural network, Science, 373 (6557), 871-876 (2021).
- I. R. Humphreys†, J. Pei†, M. Baek†, A. Krishnakumar†, et al, Computed structures of core eukaryotic protein complexes, Science, 374 (6573), eabm4805 (2021). (†co-first authors).
- M. Baek, I. Anishchenko, H. Park, I. R. Humphreys, D. Baker*, Protein oligomer modeling guided by predicted inter-chain contacts in CASP14, Proteins: Structure, Function, and Bioinformatics, 89 (12), 1824-1833 (2021).
- I. Anishchenko†, M. Baek†, H. Park†, et al., Protein tertiary structure prediction and refinement using deep learning and Rosetta in CASP14, Proteins: Structure, Function, and Bioinformatics, 89 (12), 1722-1733 (2021) (†co-first authors).
- M. Baek, T. Park, L. Heo, C. Park, and C. Seok*, GalaxyHomomer: A web server for protein homo-oligomer structure prediction from a monomer sequence or structure, Nucleic Acids Res. 45 (W1), W320-W324 (2017).