相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
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.
Article
Biochemistry & Molecular Biology
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)
Article
Biochemical Research Methods
Milot Mirdita et al.
Summary: ColabFold combines fast homology search and optimized model utilization to offer accelerated prediction of protein structures and complexes, with a processing speed that is 40-60 times faster. It serves as a free and accessible platform for protein folding, capable of predicting close to 1,000 structures per day.
Article
Biochemistry & Molecular Biology
Mehmet Akdel et al.
Summary: This study evaluates the performance of AlphaFold2 in structural biology applications and finds that it performs well and can partially replace experimentally determined structures, which is of great significance for life science research.
NATURE STRUCTURAL & MOLECULAR BIOLOGY
(2022)
Article
Multidisciplinary Sciences
Shyamal Mosalaganti et al.
Summary: This study combines artificial intelligence-based structure prediction with in situ structural biology to reveal the structure and function of the human nuclear pore complex (NPC) scaffold. The findings demonstrate the importance of linker nucleoporins in establishing the higher-order structure of the scaffold and suggest that it widens the central pore rather than stabilizing the fusion of the inner and outer nuclear membranes.
Editorial Material
Chemistry, Multidisciplinary
Gerard J. Kleywegt et al.
Editorial Material
Biochemistry & Molecular Biology
Anastassis Perrakis et al.
Summary: AlphaFold is the most ground-breaking application of AI in science so far, promising to revolutionize structural biology, but caution is advised in its implementation.
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
Kathryn Tunyasuvunakool et al.
Summary: Using the AlphaFold method, the structural coverage of the proteome has been significantly expanded, covering 98.5% of human proteins with 58% of residues having confident predictions and 36% having very high confidence. Introducing new metrics to interpret the dataset and identify disordered regions, this study aims to provide high-quality predictions for generating biological hypotheses.
Article
Biochemistry & Molecular Biology
Claudia Millan et al.
Summary: This study introduces a new method (reLLG) for evaluating protein structure models that does not require diffraction data. Calibration against CASP14 targets showed that reLLG is a robust measure of model and group ranking. Additionally, refinements by CASP groups often lead to improved accuracy in models.
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS
(2021)
Article
Biochemistry & Molecular Biology
Lisa N. Kinch et al.
Summary: An evolutionary-based definition and classification of target evaluation units (EUs) were presented for CASP14, with targets split into categories based on existing templates and server performance. Analysis of sequence and structure similarity, as well as server performance, highlighted trends in target difficulty for the 84 experimental models submitted. The study assigned EUs to tertiary structure assessment categories based on their evolutionary relationship to existing ECOD fold space, showing overlapping clusters and the complexity of server performance in predicting target structures.
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS
(2021)
Article
Biochemistry & Molecular Biology
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)
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.
Editorial Material
Multidisciplinary Sciences
Werner Kuehlbrandt
Article
Biochemical Research Methods
Valerio Mariani et al.
