USTC establishes new method for de novo protein design

The team of Professor Liu Haiyan and Associate Professor Chen Quan of the University of Science and Technology of China adopted a data-driven strategy to open up a new route for protein de novo design.
The time was published in Nature on February 10
.

Protein is the basis of life and the main executor of life functions.
Its structure and function are determined by amino acid sequences
.

At present, almost all proteins that can form stable three-dimensional structures are natural proteins, and their amino acid sequences are formed by long-term natural evolution

Relevant teams from University of Science and Technology of China have been deeply engaged in basic research and applied basic research in the direction of computational structural biology for a long time; Academician Shi Yunyu is a pioneer in this field in China; Professor Liu Haiyan and Associate Professor Chen Quan have been committed to developing data-driven proteins for more than ten years.
The design method , after long-term unremitting efforts, established and experimentally verified the ABACUS model for designing the amino acid sequence given the main chain structure, and then developed the SCUBA model that can de novo design the new main chain structure when the amino acid sequence is pending (Figure 1)
.

SCUBA adopts a new statistical learning strategy, based on kernel density estimation (or nearest neighbor counting, NC) and neural network fitting (NN) methods, to obtain the analytic energy function in the form of neural network from raw structural data, which enables high fidelity It reflects the high-dimensional correlation between different structural variables in the actual protein structure.

Figure 1.
Principles of protein design with the SCUBA model
.

(a) The minima on the energy surface of the SCUBA main chain corresponds to the designable main chain structure of the protein, that is, the lowest free energy structure under a specific amino acid sequence; (b) The statistical energy term represented by neural network in SCUBA; (c) and (d ) A method framework for learning analytical energy functions from protein structure raw data using a nearest neighbor counting (NC)-neural network (NN) approach

Theoretical calculations and experiments have proved that the use of SCUBA to design the main chain structure can break through the limitation that only natural fragments can be used to splicing new main chain structures, significantly expand the structural diversity of de novo proteins, and then design proteins different from known natural proteins.
Novel structure
.

The "SCUBA model + ABACUS model" constitutes a complete tool chain for de novo design of artificial proteins with new structures and sequences.

Figure 2.
High-resolution crystal structure (sky blue) of de novo designed protein compared to the design model (green)
.

The Nature reviewers argue, "Unlike existing methods, which either use parametric equations to describe the space of pre-defined helical structures, or fragment assembly-based methods rely on known protein fragments.

S CUBA methods allow in principle Arbitrary backbone structures are explored and then populated with sequences, allowing one to design a wider range of protein geometries than observed in nature"; "Protein de novo design remains challenging, and the high-resolution design of six different proteins in this work is An important achievement showing that this approach works well"; "The number of successful designs reported in this study is impressive and provides strong evidence that the underlying technology is robust
.

The neural-based The energy terms of the networks are novel because they characterize multidimensional features beyond the reach of more traditional statistical methods, which are sufficiently novel and practical

Professor Liu Haiyan and Associate Professor Chen Quan of the Department of Life Science and Medicine of our school are the corresponding authors of the paper
.

Doctoral students Huang Bin, Xu Yang and Hu Xiuhong are the co-first authors of the paper

The research work was supported by grants from the Ministry of Science and Technology, the National Natural Science Foundation of China and the Chinese Academy of Sciences

Original link: https:// class="MsoNormal p_text_indent_0 p_text_indent_2" >

(Ministry of Life Science and Medicine, Hefei National Research Center for Microscale Matter Science, Key Laboratory of Membraneless Organelles and Cell Dynamics, Ministry of Education, Research Department)