Inter-domain distance prediction based on deep learning for domain assembly

Editorial Material Biochemical Research Methods

The impact of AlphaFold2 one year on

David T. Jones et al.

NATURE METHODS (2022)

添加到收藏夹

Editorial Material Biochemical Research Methods

Protein structure predictions to atomic accuracy with AlphaFold

John Jumper et al.

NATURE METHODS (2022)

添加到收藏夹

Article Biochemistry & Molecular Biology

AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models

Mihaly Varadi et al.

Summary: AlphaFold DB is an openly accessible database with high-accuracy protein-structure predictions, powered by DeepMind's AlphaFold v2.0. It provides programmatic access to a vast number of predicted structures and is expanding to cover more sequences.

NUCLEIC ACIDS RESEARCH (2022)

添加到收藏夹

Article Biochemistry & Molecular Biology

DEMO2: Assemble multi-domain protein structures by coupling analogous template alignments with deep-learning inter-domain restraint prediction

Xiaogen Zhou et al.

Summary: This study introduces a significantly improved method, DEMO2, which combines deep-learning techniques and structure alignments for accurate assembly of multi-domain protein structures. DEMO2 outperforms other prediction methods in large-scale benchmarks and blind experiments.

NUCLEIC ACIDS RESEARCH (2022)

添加到收藏夹

Article Biochemical Research Methods

Structural analogue-based protein structure domain assembly assisted by deep learning

Chun-Xiang Peng et al.

Summary: The accuracy of full-chain protein structure model can be improved by domain assembly assisted by deep learning. In this study, a method called SADA was developed, which utilized structural analogues and differential evolution algorithm to perform domain assembly and achieved higher TM-score compared to state-of-the-art methods.

BIOINFORMATICS (2022)

添加到收藏夹

Review Biochemistry & Molecular Biology

Machine learning in protein structure prediction

Mohammed AlQuraishi

Summary: Prediction of protein structure from sequence has made significant progress in the past two years, driven by the increasing use of neural networks in structure prediction pipelines. These neural networks have optimized the previous energy models and sampling procedures, resulting in algorithms that can now predict protein structures with a median accuracy of 2.1 angstroms.

CURRENT OPINION IN CHEMICAL BIOLOGY (2021)

添加到收藏夹

Article Chemistry, Multidisciplinary

Improved Protein Structure Prediction Using a New Multi-Scale Network and Homologous Templates

Hong Su et al.

Summary: The accuracy of de novo protein structure prediction has been significantly improved in recent years with the introduction of deep learning techniques. The improved version trRosettaX utilizes a new multi-scale network and attention-based module to enhance prediction accuracy. trRosettaX shows significant improvements in contact precision and TM-score compared to trRosetta in CASP and CAMEO tests.

ADVANCED SCIENCE (2021)

添加到收藏夹

Article Multidisciplinary Sciences

CopulaNet: Learning residue co-evolution directly from multiple sequence alignment for protein structure prediction

Fusong Ju et al.

Summary: Residue co-evolution is crucial for predicting protein structure. CopulaNet, a deep learning framework, can directly estimate residue co-evolution from MSA, improving the accuracy and efficiency of protein structure prediction.

NATURE COMMUNICATIONS (2021)

添加到收藏夹

Article Biochemistry & Molecular Biology

Deep learning techniques have significantly impacted protein structure prediction and protein design

Robin Pearce et al.

Summary: The application of deep neural networks in protein structure prediction and design has significantly improved accuracy at the fold level for single-domain proteins. Information stored in neural-network models can advance functional protein design, and the incorporation of deep learning techniques represents an exciting future direction for both fields.

CURRENT OPINION IN STRUCTURAL BIOLOGY (2021)

添加到收藏夹

Review Biochemistry & Molecular Biology

Toward the solution of the protein structure prediction problem

Robin Pearce et al.

Summary: The protein structure prediction problem has been a key task in structural biology since 1973. Traditionally, template-based modeling (TBM) has been the most reliable approach for predicting protein structures, but recent research shows that end-to-end deep machine learning techniques can better solve this problem.

JOURNAL OF BIOLOGICAL CHEMISTRY (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Highly accurate protein structure prediction with AlphaFold

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.

NATURE (2021)

添加到收藏夹

Article Biochemistry & Molecular Biology

High-accuracy protein structure prediction in CASP14

Joana Pereira et al.

Summary: The application of state-of-the-art deep-learning approaches to protein modeling problem has expanded the high-accuracy category in CASP14, evaluating the performance of different groups and introducing new metrics. Despite the significant progress made by AlphaFold2, the second-best method in CASP14 outperformed the best method in CASP13, demonstrating the role of community-based benchmarking in the development of protein structure prediction field.

PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS (2021)

添加到收藏夹

Article Biochemistry & Molecular Biology

Critical assessment of methods of protein structure prediction (CASP)-Round XIV

Andriy Kryshtafovych et al.

Summary: CASP is a community experiment aimed at advancing methods for computing three-dimensional protein structure, including rigorous blind testing and evaluation by independent assessors. In the recent CASP14 experiment, deep-learning methods from one research group consistently delivered computed structures rivaling the corresponding experimental ones in accuracy. These results represent a solution to the classical protein-folding problem, at least for single proteins.

PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS (2021)

添加到收藏夹

Article Biochemistry & Molecular Biology

When homologous sequences meet structural decoys: Accurate contact prediction by tFold in CASP14-(tFold for CASP14 contact prediction)

Tao Shen et al.

Summary: This paper reports the performance and mechanism of the tFold framework in CASP14, achieving outstanding results in the long-range contact prediction task.

PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Accurate prediction of protein structures and interactions using a three-track neural network

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.

SCIENCE (2021)

添加到收藏夹

Article Multidisciplinary Sciences