Science | ProteinMPNN : 基于深度学习的蛋白序列设计 本文介绍华盛顿大学的蛋白质设计科学家D. Baker在2022年9月15发表在Science研究工作Robust deep learning–based protein sequence design using ProteinMPNN。研究团队开发了一种基于深度学习的蛋白质序列设计方法 ProteinMPNN,它在计算机和实验测试中均具有出色的性能。
Protein sequence design by deep learningThe design of protein sequences that can precisely fold into pre-specified 3D structures is a challenging task. A recently proposed deep-learning algorithm improves such designs when compared with traditional, physics-based protein design approaches....
Current protein design models can natively handle multiple protein chains in their inputs, allowing them to design the sequences of interacting proteins. However, they only poorly handle non-protein entities within the design process, which hampers their versatility and limits their scope of applicabil...
Deep generative models that learn from the distribution of natural protein sequences and structures may enable the design of new proteins with valuable functions. While the majority of today’s models focus on generating either sequences or structures, emerging co-generation methods pr...
Deep learning-based sequence design algorithms The key to finding solutions to the sequence design problem is to maximize the joint probability of amino acids under a fixed backbone, and the joint probability is usually optimized through sampling, due to the discrete nature of amino acid combinations...
Publishes research papers and review articles relevant to the engineering, design and selection of proteins for use in biotechnology and therapy, and for
Deep generative models that learn from the distribution of natural protein sequences and structures may enable the design of new proteins with valuable functions. While the majority of today’s models focus on generating either sequences or structures, emerging co-generation methods promise more ...
protein protein-sequences representation-learning protein-design protein-function-prediction protein-fitness-prediction Updated Sep 30, 2024 Jupyter Notebook dosorio / Peptides Star 82 Code Issues Pull requests An R package to calculate indices and theoretical physicochemical properties of peptides and...
The CASP13 results show that the complex mapping from amino acid sequence to 3D protein structure can be successfully learned by a neural network and generalized to unseen cases. Concurrently, for the protein design problem, progress in the field of deep generative models has spawned a range of...
Protein sequence design with deep generative models Zachary Wu, Kadina E. Johnston, Frances H. Arnold, Kevin K. Yang Current Opinion in Chemical Biology 65 • note • 2021 Structure-based protein design with deep learning Ovchinnikov, Sergey, and Po-Ssu Huang Current opinion in chemical biolo...