Proteins of well-defined structures can be designed without backbone readjustment by a statistical model

Zhou, Xiaoqun; Xiong, Peng; Wang, Meng; Ma, Ronghua; Zhang, Jiahai; Chen, Quan

doi:10.1016/j.jsb.2016.08.002

Cited by 13 publications

(18 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In practice, the generation of diverse sequences with Rosetta often requires manually manipulating amino acid identities at key positions [7,9], adjusting the energy function [43,44], or explicitly modeling perturbations of the protein backbone [45,46,47,48]. Design methods that account for flexibility of the protein backbone often use "softer" potentials [44,49], such as statistical potentials that are derived from data [50,51,50,52,53,54], but these methods often do not perform as favorably as well-parameterized "hard" molecular mechanics force fields.…”

Section: Introductionmentioning

confidence: 99%

Protein Sequence Design with a Learned Potential

Anand

Eguchi

Mathews

et al. 2020

Preprint

View full text Add to dashboard Cite

The primary challenge of fixed-backbone protein sequence design is to find a distribution of sequences that fold to the backbone of interest. In practice, state-of-the-art protocols often find viable but highly convergent solutions. In this study, we propose a novel method for fixed-backbone protein sequence design using a learned deep neural network potential. We train a convolutional neural network (CNN) to predict a distribution over amino acids at each residue position conditioned on the local structural environment around the residues. Our method for sequence design involves iteratively sampling from this conditional distribution. We demonstrate that this approach is able to produce feasible, novel designs with quality on par with the state-of-the-art, while achieving greater design diversity. In terms of generalizability, our method produces plausible and variable designs for a de novo TIM-barrel structure, showcasing its practical utility in design applications for which there are no known native structures.

show abstract

Section: Introductionmentioning

confidence: 99%

Protein Sequence Design with a Learned Potential

Anand

Eguchi

Mathews

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…30,31 Recently, two statistical potentials for protein design have been developed, 32,33 and the ABACUS potential 34 has been successfully used in designing proteins. 33,35 While these statistical potentials have a physical basis, machine learning especially deep-learning neural network has recently become a popular method to analyze big data sets, extract complex features, and make accurate predictions. 36 Deep-learning neural network, as a machine learning technique, is becoming increasingly powerful with the development of new algorithms and computer hardware, and has been applied to learning massive data sets in a variety of fields such as image recognition, 37 language processing, 38 and game playing.…”

Section: Introductionmentioning

confidence: 99%

Computational Protein Design with Deep Learning Neural Networks

Wang

Cao

Zhang

et al. 2018

Sci Rep

144

142

View full text Add to dashboard Cite

Computational protein design has a wide variety of applications. Despite its remarkable success, designing a protein for a given structure and function is still a challenging task. On the other hand, the number of solved protein structures is rapidly increasing while the number of unique protein folds has reached a steady number, suggesting more structural information is being accumulated on each fold. Deep learning neural network is a powerful method to learn such big data set and has shown superior performance in many machine learning fields. In this study, we applied the deep learning neural network approach to computational protein design for predicting the probability of 20 natural amino acids on each residue in a protein. A large set of protein structures was collected and a multi-layer neural network was constructed. A number of structural properties were extracted as input features and the best network achieved an accuracy of 38.3%. Using the network output as residue type restraints improves the average sequence identity in designing three natural proteins using Rosetta. Moreover, the predictions from our network show ~3% higher sequence identity than a previous method. Results from this study may benefit further development of computational protein design methods.

show abstract

“…The idea of data-driven CPD has been explored before. First, any statistical potential can be placed into this category of techniques, such that almost any existing CPD method can be thought of as partially data-driven (39)(40)(41)(42)(43)(44)(45)(46)(47). A fundamental difference between dTERMen and prior statistical approaches is that dTERMen goes beyond simple geometric descriptors and analyzes apparent sequence preferences in the context of larger well-defined backbone motifs, relying on their apparent quasidigital nature (i.e., the "TERM hypothesis").…”

mentioning

confidence: 99%

A general-purpose protein design framework based on mining sequence–structure relationships in known protein structures

Zhou

Panaitiu

Grigoryan

2019

Proc. Natl. Acad. Sci. U.S.A.

107

View full text Add to dashboard Cite

Current state-of-the-art approaches to computational protein design (CPD) aim to capture the determinants of structure from physical principles. While this has led to many successful designs, it does have strong limitations associated with inaccuracies in physical modeling, such that a reliable general solution to CPD has yet to be found. Here, we propose a design framework—one based on identifying and applying patterns of sequence–structure compatibility found in known proteins, rather than approximating them from models of interatomic interactions. We carry out extensive computational analyses and an experimental validation for our method. Our results strongly argue that the Protein Data Bank is now sufficiently large to enable proteins to be designed by using only examples of structural motifs from unrelated proteins. Because our method is likely to have orthogonal strengths relative to existing techniques, it could represent an important step toward removing remaining barriers to robust CPD.

show abstract

Proteins of well-defined structures can be designed without backbone readjustment by a statistical model

Cited by 13 publications

References 33 publications

Protein Sequence Design with a Learned Potential

Protein Sequence Design with a Learned Potential

Computational Protein Design with Deep Learning Neural Networks

A general-purpose protein design framework based on mining sequence–structure relationships in known protein structures

Contact Info

Product

Resources

About