Accurate structure prediction of biomolecular interactions with AlphaFold 3.
Ontology highlight
ABSTRACT:
SUBMITTER: Abramson J
PROVIDER: S-EPMC11168924 | biostudies-literature | 2024 Jun
REPOSITORIES: biostudies-literature
Publications
Accurate structure prediction of biomolecular interactions with AlphaFold 3.
Abramson Josh J Adler Jonas J Dunger Jack J Evans Richard R Green Tim T Pritzel Alexander A Ronneberger Olaf O Willmore Lindsay L Ballard Andrew J AJ Bambrick Joshua J Bodenstein Sebastian W SW Evans David A DA Hung Chia-Chun CC O'Neill Michael M Reiman David D Tunyasuvunakool Kathryn K Wu Zachary Z Žemgulytė Akvilė A Arvaniti Eirini E Beattie Charles C Bertolli Ottavia O Bridgland Alex A Cherepanov Alexey A Congreve Miles M Cowen-Rivers Alexander I AI Cowie Andrew A Figurnov Michael M Fuchs Fabian B FB Gladman Hannah H Jain Rishub R Khan Yousuf A YA Low Caroline M R CMR Perlin Kuba K Potapenko Anna A Savy Pascal P Singh Sukhdeep S Stecula Adrian A Thillaisundaram Ashok A Tong Catherine C Yakneen Sergei S Zhong Ellen D ED Zielinski Michal M Žídek Augustin A Bapst Victor V Kohli Pushmeet P Jaderberg Max M Hassabis Demis D Jumper John M JM
Nature 20240508 8016
The introduction of AlphaFold 2<sup>1</sup> has spurred a revolution in modelling the structure of proteins and their interactions, enabling a huge range of applications in protein modelling and design<sup>2-6</sup>. Here we describe our AlphaFold 3 model with a substantially updated diffusion-based architecture that is capable of predicting the joint structure of complexes including proteins, nucleic acids, small molecules, ions and modified residues. The new AlphaFold model demonstrates substa ...[more]
Similar Datasets
Project description:Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. Through an enormous experimental effort1-4, the structures of around 100,000 unique proteins have been determined5, but this represents a small fraction of the billions of known protein sequences6,7. Structural coverage is bottlenecked by the months to years of painstaking effort required to determine a single protein structure. Accurate computational approaches are needed to address this gap and to enable large-scale structural bioinformatics. Predicting the three-dimensional structure that a protein will adopt based solely on its amino acid sequence-the structure prediction component of the 'protein folding problem'8-has been an important open research problem for more than 50 years9. Despite recent progress10-14, existing methods fall far short of atomic accuracy, especially when no homologous structure is available. Here we provide the first computational method that can regularly predict protein structures with atomic accuracy even in cases in which no similar structure is known. We validated an entirely redesigned version of our neural network-based model, AlphaFold, in the challenging 14th Critical Assessment of protein Structure Prediction (CASP14)15, demonstrating accuracy competitive with experimental structures in a majority of cases and greatly outperforming other methods. Underpinning the latest version of AlphaFold is a novel machine learning approach that incorporates physical and biological knowledge about protein structure, leveraging multi-sequence alignments, into the design of the deep learning algorithm.
| S-EPMC8371605 | biostudies-literature
Project description:AlphaFold can predict the structures of monomeric and multimeric proteins with high accuracy but has a limit on the number of chains and residues it can fold. Here we show that a combination of AlphaFold and all-atom symmetric docking simulations enables highly accurate prediction of the structure of complex symmetrical assemblies. We present a method to predict the structure of complexes with cubic - tetrahedral, octahedral and icosahedral - symmetry from sequence. Focusing on proteins where AlphaFold can make confident predictions on the subunit structure, 27 cubic systems were assembled with a median TM-score of 0.99 and a DockQ score of 0.72. 21 had TM-scores of above 0.9 and were categorized as acceptable- to high-quality according to DockQ. The resulting models are energetically optimized and can be used for detailed studies of intermolecular interactions in higher-order symmetrical assemblies. The results demonstrate how explicit treatment of structural symmetry can significantly expand the size and complexity of AlphaFold predictions.
| S-EPMC10719378 | biostudies-literature
Project description:Thermostability enhancement is a fundamental aspect of protein engineering as a biocatalyst's half-life is key for its industrial and biotechnological application, particularly at high temperatures and under harsh conditions. Thermostability changes upon mutation originate from modifications of the free energy of unfolding (ΔGu), making thermostabilization extremely challenging to predict with computational methods. In this contribution, we combine global conformational sampling with energy prediction using AlphaFold and Rosetta to develop a new computational protocol for the quantitative prediction of thermostability changes upon laboratory evolution of acyltransferase LovD and lipase LipA. We highlight how using an ensemble of protein conformations rather than a single three-dimensional model is mandatory for accurate thermostability predictions. By comparing our approaches with existing ones, we show that ensembles based on AlphaFold models provide more accurate and robust calculated thermostability trends than ensembles based solely on crystallographic structures as the latter introduce a strong distortion (scaffold bias) in computed thermostabilities. Eliminating this bias is critical for computer-guided enzyme design and evaluating the effect of multiple mutations on protein stability.
| S-EPMC9930118 | biostudies-literature
Project description:Collagen α1(XI) is a minor fibrillar collagen involved in the critical regulation of collagen fibrils such as nucleation, assembly, and regulation of fibril diameter. The amino propeptide domain of the collagen α1(XI) is retained on the surface of the collagen fibril for an extended period of time and may play a crucial role in the interaction with extracellular matrix glycosaminoglycans and other proteins during the process of fibrillogenesis. Understanding the mechanism of action of this protein will ultimately help us understand the organization and assembly of the extracellular matrix that underlies the structural integrity of connective tissues.
| S-EPMC10586751 | biostudies-literature
Project description:Experimental structure determination can be accelerated with artificial intelligence (AI)-based structure-prediction methods such as AlphaFold. Here, an automatic procedure requiring only sequence information and crystallographic data is presented that uses AlphaFold predictions to produce an electron-density map and a structural model. Iterating through cycles of structure prediction is a key element of this procedure: a predicted model rebuilt in one cycle is used as a template for prediction in the next cycle. This procedure was applied to X-ray data for 215 structures released by the Protein Data Bank in a recent six-month period. In 87% of cases our procedure yielded a model with at least 50% of Cα atoms matching those in the deposited models within 2 Å. Predictions from the iterative template-guided prediction procedure were more accurate than those obtained without templates. It is concluded that AlphaFold predictions obtained based on sequence information alone are usually accurate enough to solve the crystallographic phase problem with molecular replacement, and a general strategy for macromolecular structure determination that includes AI-based prediction both as a starting point and as a method of model optimization is suggested.
| S-EPMC9986801 | biostudies-literature
Project description:Alternative splicing is an important mechanism that enhances protein functional diversity. To date, our understanding of alternative splicing variants has been based on mRNA transcript data, but due to the difficulty in predicting protein structures, protein tertiary structures have been largely unexplored. However, with the release of AlphaFold, which predicts three-dimensional models of proteins, this challenge is rapidly being overcome. Here, we present a dataset of 315 predicted structures of abnormal isoforms in 18 uveal melanoma patients based on second- and third-generation transcriptome-sequencing data. This information comprises a high-quality set of structural data on recurrent aberrant isoforms that can be used in multiple types of studies, from those aimed at revealing potential therapeutic targets to those aimed at recognizing of cancer neoantigens at the atomic level.
| S-EPMC10403560 | biostudies-literature
Project description:The inhibition of protein-protein interactions is a growing strategy in drug development. In addition to structured regions, many protein loop regions are involved in protein-protein interactions and thus have been identified as potential drug targets. To effectively target such regions, protein structure is critical. Loop structure prediction is a challenging subgroup in the field of protein structure prediction because of the reduced level of conservation in protein sequences compared to the secondary structure elements. AlphaFold 2 has been suggested to be one of the greatest achievements in the field of protein structure prediction. The AlphaFold 2 predicted protein structures near the X-ray resolution in the Critical Assessment of protein Structure Prediction (CASP 14) competition in 2020. The purpose of this work is to survey the performance of AlphaFold 2 in specifically predicting protein loop regions. We have constructed an independent dataset of 31,650 loop regions from 2613 proteins (deposited after the AlphaFold 2 was trained) with both experimentally determined structures and AlphaFold 2 predicted structures. With extensive evaluation using our dataset, the results indicate that AlphaFold 2 is a good predictor of the structure of loop regions, especially for short loop regions. Loops less than 10 residues in length have an average Root Mean Square Deviation (RMSD) of 0.33 Å and an average the Template Modeling score (TM-score) of 0.82. However, we see that as the number of residues in a given loop increases, the accuracy of AlphaFold 2's prediction decreases. Loops more than 20 residues in length have an average RMSD of 2.04 Å and an average TM-score of 0.55. Such a correlation between accuracy and length of the loop is directly linked to the increase in flexibility. Moreover, AlphaFold 2 does slightly over-predict α-helices and β-strands in proteins.
| S-EPMC9312937 | biostudies-literature
Project description:The ability to predict a protein's three-dimensional conformation represents a crucial starting point for investigating evolutionary connections with other members of the corresponding protein family, examining interactions with other proteins, and potentially utilizing this knowledge for the purpose of rational drug design. In this work, we evaluated the feasibility of improving AlphaFold2's three-dimensional protein predictions by developing a novel pipeline (AlphaMod) that incorporates AlphaFold2 with MODELLER, a template-based modeling program. Additionally, our tool can drive a comprehensive quality assessment of the tertiary protein structure by incorporating and comparing a set of different quality assessment tools. The outcomes of selected tools are combined into a composite score (BORDASCORE) that exhibits a meaningful correlation with GDT_TS and facilitates the selection of optimal models in the absence of a reference structure. To validate AlphaMod's results, we conducted evaluations using two distinct datasets summing up to 72 targets, previously used to independently assess AlphaFold2's performance. The generated models underwent evaluation through two methods: i) averaging the GDT_TS scores across all produced structures for a single target sequence, and ii) a pairwise comparison of the best structures generated by AlphaFold2 and AlphaMod. The latter, within the unsupervised setups, shows a rising accuracy of approximately 34% over AlphaFold2. While, when considering the supervised setup, AlphaMod surpasses AlphaFold2 in 18% of the instances. Finally, there is an 11% correspondence in outcomes between the diverse methodologies. Consequently, AlphaMod's best-predicted tertiary structures in several cases exhibited a significant improvement in the accuracy of the predictions with respect to the best models obtained by AlphaFold2. This pipeline paves the way for the integration of additional data and AI-based algorithms to further improve the reliability of the predictions.
| S-EPMC10690423 | biostudies-literature
Project description:AlphaFold-Multimer has emerged as the state-of-the-art tool for predicting the quaternary structure of protein complexes (assemblies or multimers) since its release in 2021. To further enhance the AlphaFold-Multimer-based complex structure prediction, we developed a new quaternary structure prediction system (MULTICOM) to improve the input fed to AlphaFold-Multimer and evaluate and refine the outputs generated by AlphaFold2-Multimer. Specifically, MULTICOM samples diverse multiple sequence alignments (MSAs) and templates for AlphaFold-Multimer to generate structural models by using both traditional sequence alignments and new Foldseek-based structure alignments, ranks structural models through multiple complementary metrics, and refines the structural models via a Foldseek structure alignment-based refinement method. The MULTICOM system with different implementations was blindly tested in the assembly structure prediction in the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) in 2022 as both server and human predictors. Our server (MULTICOM_qa) ranked 3 rd among 26 CASP15 server predictors and our human predictor (MULTICOM_human) ranked 7 th among 87 CASP15 server and human predictors. The average TM-score of the first models predicted by MULTICOM_qa for CASP15 assembly targets is ∼0.76, 5.3% higher than ∼0.72 of the standard AlphaFold-Multimer. The average TM-score of the best of top 5 models predicted by MULTICOM_qa is ∼0.80, about 8% higher than ∼0.74 of the standard AlphaFold-Multimer. Moreover, the novel Foldseek Structure Alignment-based Model Generation (FSAMG) method based on AlphaFold-Multimer outperforms the widely used sequence alignment-based model generation. The source code of MULTICOM is available at: https://github.com/BioinfoMachineLearning/MULTICOM3 .
| S-EPMC10245707 | biostudies-literature
Project description:De novo protein design enhances our understanding of the principles that govern protein folding and interactions, and has the potential to revolutionize biotechnology through the engineering of novel protein functionalities. Despite recent progress in computational design strategies, de novo design of protein structures remains challenging, given the vast size of the sequence-structure space. AlphaFold2 (AF2), a state-of-the-art neural network architecture, achieved remarkable accuracy in predicting protein structures from amino acid sequences. This raises the question whether AF2 has learned the principles of protein folding sufficiently for de novo design. Here, we sought to answer this question by inverting the AF2 network, using the prediction weight set and a loss function to bias the generated sequences to adopt a target fold. Initial design trials resulted in de novo designs with an overrepresentation of hydrophobic residues on the protein surface compared to their natural protein family, requiring additional surface optimization. In silico validation of the designs showed protein structures with the correct fold, a hydrophilic surface and a densely packed hydrophobic core. In vitro validation showed that 7 out of 39 designs were folded and stable in solution with high melting temperatures. In summary, our design workflow solely based on AF2 does not seem to fully capture basic principles of de novo protein design, as observed in the protein surface's hydrophobic vs. hydrophilic patterning. However, with minimal post-design intervention, these pipelines generated viable sequences as assessed experimental characterization. Thus, such pipelines show the potential to contribute to solving outstanding challenges in de novo protein design.
| S-EPMC10204179 | biostudies-literature