Related references
Note: Only part of the references are listed.
Article
Biotechnology & Applied Microbiology
Ali Madani et al.
Summary: A generative deep-learning model called ProGen is capable of designing artificial proteins with specific enzymatic activities. This model was trained on a large dataset of protein sequences and can generate protein sequences with predictable functions. ProGen can be further fine-tuned to improve the controllable generation of proteins from specific families, and artificial proteins generated by ProGen showed similar catalytic efficiencies to natural lysozymes.
NATURE BIOTECHNOLOGY
(2023)
Article
Biochemistry & Molecular Biology
Yao Cheng et al.
Summary: MetalNet is a co-evolution-based pipeline that can systematically predict metal-binding sites in proteomes. By applying MetalNet to proteomes of four prokaryotic species, we successfully predicted 4,849 potential metalloproteins, greatly expanding the currently annotated metalloproteomes. MetalNet also accurately identified known zinc-binding sites in the human spliceosome complex. This tool provides a unique and valuable resource for studying hidden metalloproteomes and metal biology.
NATURE CHEMICAL BIOLOGY
(2023)
Article
Biochemical Research Methods
Maarten L. Hekkelman et al.
Summary: Artificial intelligence-based protein structure prediction has greatly impacted biomolecular sciences. However, the predicted protein models in the AlphaFold database lack coordinates for small molecules and ions necessary for structure and function. The AlphaFill algorithm addresses this issue by transplanting missing small molecules and ions from experimentally determined structures to predicted protein models.
Review
Biochemical Research Methods
Yongfan Ming et al.
Summary: The design of enzyme catalytic stability is important in medicine and industry, but traditional methods are time-consuming and costly. Complementary computational tools using AI algorithms such as natural language processing, machine learning, and deep learning have been developed to address this issue. However, challenges in designing enzyme catalytic stability include insufficient data, large search space, inaccurate prediction, low experimental efficiency, and complex design process. The design of enzyme catalytic stability involves adjusting the flexibility and stability of the enzyme structure by designing its amino acid sequence, thereby controlling its catalytic stability.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Chemistry, Physical
Bodhi P. Vani et al.
Summary: AlphaFold2-RAVE is an efficient protocol to obtain Boltzmann-ranked ensembles from sequence by using structural outputs from AlphaFold2 as initializations for AI-augmented molecular dynamics. The method has demonstrated good results on different proteins and is available as open-source code.
JOURNAL OF CHEMICAL THEORY AND COMPUTATION
(2023)
Article
Chemistry, Physical
Artur Meller et al.
Summary: This study investigates whether AlphaFold can be used to accelerate cryptic pocket discovery. The results show that AlphaFold is able to sample the open state in 6 out of 10 known cryptic pocket cases. Simulations from AlphaFold-generated structures successfully sample cryptic pocket opening, while simulations from ligand-free experimental structures fail to do so. Overall, AlphaFold plays a useful role in cryptic pocket discovery.
JOURNAL OF CHEMICAL THEORY AND COMPUTATION
(2023)
Article
Multidisciplinary Sciences
Andy Hsien-Wei Yeh et al.
Summary: We have successfully designed an artificial luciferase with high selectivity and catalytic efficiency using a deep-learning-based approach. This achievement is a major milestone in computational enzyme design and has broad applications in biomedical research.
Article
Biotechnology & Applied Microbiology
Kolja Stahl et al.
Summary: Limitations of Alphafold2 structure prediction are overcome by incorporating experimentally determined distance constraints using AlphaLink. This modified version improves prediction for challenging targets by utilizing sparse experimental contacts and can predict distinct protein conformations. Experimental data on residue-residue contacts obtained through crosslinking mass spectrometry validates the improved performance. The noise-tolerant framework for integrating data allows accurate characterization of protein structures from in-cell data.
NATURE BIOTECHNOLOGY
(2023)
Article
Multidisciplinary Sciences
David E. Kim et al.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2023)
Article
Multidisciplinary Sciences
Tianhao Yu et al.
Summary: CLEAN is a machine learning algorithm based on contrastive learning that can accurately predict functional annotations of enzymes, especially for less-studied or uncharacterized proteins with multiple activities. It can confidently annotate understudied enzymes, correct mislabeled enzymes, and identify promiscuous enzymes with multiple EC numbers. This tool is of great significance in predicting the functions of uncharacterized enzymes.
Article
Multidisciplinary Sciences
Zeming Lin et al.
Summary: Recent advances in machine learning have allowed for the prediction of protein structure from multiple sequence alignments. By using a large language model, we are able to directly infer full atomic-level protein structure from primary sequence. This has led to a significant acceleration in high-resolution structure prediction, enabling the characterization of a large number of metagenomic proteins. Utilizing this capability, we have constructed the ESM Metagenomic Atlas, which provides insights into the diversity of natural proteins.
Editorial Material
Biochemical Research Methods
Abbas Ourmazd et al.
Editorial Material
Biochemical Research Methods
Minkyung Baek et al.
Editorial Material
Biochemical Research Methods
David T. Jones et al.
Article
Multidisciplinary Sciences
Namrata Anand et al.
Summary: In this study, a machine learning method and a neural network potential were used to design proteins. The model learned from crystal structure data and was able to automatically generate protein sequences that were experimentally stable. The findings demonstrate the feasibility of using a completely learned approach for protein sequence design.
NATURE COMMUNICATIONS
(2022)
Article
Multidisciplinary Sciences
Hongyuan Lu et al.
Summary: Plastic waste is an ecological challenge, and enzymatic degradation offers a potentially green and scalable route for plastic recycling. Engineered PETase shows superior activity in hydrolyzing postconsumer PET, and a closed-loop recycling process is demonstrated.
Review
Multidisciplinary Sciences
Sarah L. Lovelock et al.
Summary: Designing efficient enzymes has a profound impact on chemistry, biotechnology, and medicine. Recent advances in protein engineering and computational methods have made it possible to optimize protein structures and generate efficient enzymes through laboratory evolution. Emerging methods like deep learning hold promise for improving the accuracy of protein design models.
Article
Biology
Diego del Alamo et al.
Summary: This article presents an approach to drive AlphaFold2 to sample multiple conformations of membrane proteins and demonstrates that this approach can generate accurate models. The results suggest the need for the next generation of deep learning algorithms to be designed to predict ensembles of biophysically relevant states.
Editorial Material
Chemistry, Multidisciplinary
Fahmi Himo et al.
Summary: The article discusses the use of the cluster approach in elucidating enzyme reaction mechanisms, highlighting its strengths and weaknesses, and advocates for its preference as the method of choice in investigating enzymatic reaction mechanisms.
COMMUNICATIONS CHEMISTRY
(2022)
Article
Physics, Multidisciplinary
James P. Roney et al.
Summary: Predicting a protein's 3D structure has been a challenge in structural biology, but recent approaches like AlphaFold have made significant progress by combining deep learning and coevolutionary data. We provide evidence that AlphaFold has learned a biophysical energy function and uses coevolution data to solve the global search problem of finding a low-energy conformation. AlphaFold's learned energy function accurately ranks the quality of candidate protein structures without using coevolution data.
PHYSICAL REVIEW LETTERS
(2022)
Article
Multidisciplinary Sciences
Jue Wang et al.
Summary: This article presents a deep learning approach for scaffolding protein structures with functional sites without needing to specify their fold or secondary structure. The authors describe two methods: constrained hallucination, which optimizes sequences to include the desired functional site, and inpainting, which fills in additional sequence and structure to create a viable protein scaffold. These methods were successfully used in designing and validating various protein structures, such as immunogens, receptor traps, metalloproteins, enzymes, and protein-binding proteins.
Article
Multidisciplinary Sciences
Noelia Ferruz et al.
Summary: Protein design aims to create customized novel proteins to address environmental and biomedical challenges. In this study, the authors utilize advancements in natural language processing and generative Transformers to train ProtGPT2, a language model that explores uncharted regions of the protein space while designing proteins with nature-like properties.
NATURE COMMUNICATIONS
(2022)
Article
Biochemistry & Molecular Biology
Guillem Casadevall et al.
Summary: This study evaluates the potential of Alphafold2 in assessing the effect of mutations on the conformational heterogeneity of TrpB enzymes and develops a template-based approach. The results demonstrate the possible application of Alphafold2 combined with molecular dynamics simulations in computational enzyme design.
Article
Multidisciplinary Sciences
B. I. M. Wicky et al.
Summary: Deep learning generative approaches can generate diverse and novel protein structures beyond natural protein sequences and structures. These structures differ considerably from previously solved structures and have potential applications in designing complex components for nanomachines and biomaterials.
Article
Multidisciplinary Sciences
J. Dauparas et al.
Summary: This article introduces a deep learning-based protein sequence design method, ProteinMPNN, which has shown outstanding performance in both theoretical and experimental tests, suggesting its wide applicability.
Article
Biochemical Research Methods
Richard A. Stein et al.
Summary: This study presents a general approach to drive Alphafold2 to model alternate protein conformations through manipulation of the multiple sequence alignment. The applicability of this approach is demonstrated through the investigation of membrane proteins, expanding the potential uses of Alphafold2.
PLOS COMPUTATIONAL BIOLOGY
(2022)
Review
Chemistry, Multidisciplinary
Silvia Osuna
Summary: Recent computational enzyme design methods focus on key enzymatic features such as conformational dynamics and mutated states. These strategies aim to redistribute the relative stabilities of conformational states through population shift, revealing potential mutation hotspots at active sites and distal positions for the first time.
WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL MOLECULAR SCIENCE
(2021)
Review
Biochemistry & Molecular Biology
Sergey Ovchinnikov et al.
Summary: Researchers have been intrigued by the marvelous ways proteins carry out biochemical processes through their three-dimensional structures. Designing proteins with new functionality or shapes through structure-based modeling methods has shown significant progress, and incorporating data-derived approaches using deep learning methods could be a game changer in the field.
CURRENT OPINION IN CHEMICAL BIOLOGY
(2021)
Article
Chemistry, Multidisciplinary
Christoph K. Winkler et al.
Summary: Biocatalysis, using defined enzymes for organic transformations, has become a common tool in organic synthesis and industry. The high activity and selectivity observed in biotransformations are achieved through precise control of the active site and catalyst. Enzyme engineering allows adaptation of catalysts to different reactions, providing opportunities for novel transformations and increasing efficiency.
ACS CENTRAL SCIENCE
(2021)
Article
Multidisciplinary Sciences
Ivan Anishchenko et al.
Summary: Recent progress in protein structure prediction using deep neural networks has shown that these networks can be used to design new proteins with novel functions, by generating new folded proteins with sequences unrelated to those of naturally occurring proteins.
News Item
Chemistry, Multidisciplinary
Cecilia Clementi
Article
Multidisciplinary Sciences
Christoffer Norn et al.
Summary: The protein design problem aims to find an appropriate amino acid sequence for a desired protein structure, with optimization over all possible sequences and structures using protein structure prediction and backpropagation. The trRosetta model is more effective than Rosetta single-point energy estimations, and combining trRosetta and Rosetta models can result in more funneled energy landscapes.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2021)
Article
Biochemical Research Methods
Alex Hawkins-Hooker et al.
PLoS Computational Biology
(2021)
Article
Chemistry, Physical
Miguel A. Maria-Solano et al.
Summary: This study focuses on the tryptophan synthase complex and develops a rational approach to identify key amino acid residues for enhancing the activity of TrpB through allosteric effects. Experimental validation shows that the designed TrpB exhibits superior stand-alone activity comparable to enhancements obtained through experimental laboratory evolution. This work indicates that distal active site prediction for enhanced function in computational enzyme design is now achievable.
Review
Chemistry, Multidisciplinary
Aldo Glielmo et al.
Summary: This review provides a comprehensive overview of the importance of unsupervised learning in analyzing data from atomistic and molecular simulations, discussing state-of-the-art algorithms and methods in feature representation, dimensionality reduction, density estimation, clustering, and kinetic models. The article is well-structured, with detailed discussions in each section on the mathematical and algorithmic foundations, strengths and limitations of each method, and specific applications in analyzing molecular simulation data.
Article
Multidisciplinary Sciences
John Jumper et al.
Summary: Proteins are essential for life, and accurate prediction of their structures is a crucial research problem. Current experimental methods are time-consuming, highlighting the need for accurate computational approaches to address the gap in structural coverage. Despite recent progress, existing methods fall short of atomic accuracy in protein structure prediction.
Article
Multidisciplinary Sciences
Minkyung Baek et al.
Summary: Through the three-track network, we achieved accuracies approaching those of DeepMind in CASP14, enabling rapid solution of challenging x-ray crystallography and cryo-electron microscopy structure modeling problems, and providing insights into the functions of proteins with currently unknown structure.
Article
Computer Science, Artificial Intelligence
Donatas Repecka et al.
Summary: De novo protein design for catalysis of any desired chemical reaction has long been a goal in protein engineering. ProteinGAN, a self-attention-based variant of generative adversarial networks, has been developed to learn natural protein sequence diversity and generate functional protein sequences. This AI approach shows potential in rapidly generating diverse functional proteins within biological constraints.
NATURE MACHINE INTELLIGENCE
(2021)
Article
Multidisciplinary Sciences
Andrew W. Senior et al.
Review
Chemistry, Multidisciplinary
Rory M. Crean et al.
JOURNAL OF THE AMERICAN CHEMICAL SOCIETY
(2020)
Article
Multidisciplinary Sciences
Aron Broom et al.
NATURE COMMUNICATIONS
(2020)
News Item
Multidisciplinary Sciences
Ewen Callaway
Article
Multidisciplinary Sciences
Renee Otten et al.
Review
Computer Science, Artificial Intelligence
Wenhao Gao et al.
Article
Biochemistry & Molecular Biology
Sabin Prajapati et al.
Article
Chemistry, Multidisciplinary
Miguel A. Maria-Solano et al.
JOURNAL OF THE AMERICAN CHEMICAL SOCIETY
(2019)
Review
Chemistry, Multidisciplinary
Miguel A. Maria-Solano et al.
CHEMICAL COMMUNICATIONS
(2018)
Article
Biochemistry & Molecular Biology
Eleanor C. Campbell et al.
CURRENT OPINION IN STRUCTURAL BIOLOGY
(2018)
Review
Multidisciplinary Sciences
Dusan Petrovic et al.
JOURNAL OF THE ROYAL SOCIETY INTERFACE
(2018)
Article
Biochemistry & Molecular Biology
Eleanor Campbell et al.
NATURE CHEMICAL BIOLOGY
(2016)
Article
Multidisciplinary Sciences
Andrew R. Buller et al.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2015)
Review
Chemistry, Multidisciplinary
Katarzyna Swiderek et al.
WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL MOLECULAR SCIENCE
(2014)
Article
Biochemistry & Molecular Biology
Gordon G. Hammes et al.
Article
Multidisciplinary Sciences
James S. Fraser et al.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2011)
Review
Biochemistry & Molecular Biology
Olga Khersonsky et al.
ANNUAL REVIEW OF BIOCHEMISTRY, VOL 79
(2010)
Article
Biochemistry & Molecular Biology
David D. Boehr et al.
NATURE CHEMICAL BIOLOGY
(2009)
Review
Biochemistry & Molecular Biology
Andrew J. Baldwin et al.
NATURE CHEMICAL BIOLOGY
(2009)
Review
Multidisciplinary Sciences
Nobuhiko Tokuriki et al.
Review
Chemistry, Multidisciplinary
Arieh Warshel et al.
Review
Chemistry, Multidisciplinary
S Martí et al.
CHEMICAL SOCIETY REVIEWS
(2004)