Before and after AlphaFold2: An overview of protein structure prediction

Frontiers in Bioinformatics, Journal Year: 2023, Volume and Issue: 3

Published: Feb. 28, 2023

Three-dimensional protein structure is directly correlated with its function and determination critical to understanding biological processes addressing human health life science problems in general. Although new structures are experimentally obtained over time, there still a large difference between the number of sequences placed Uniprot those resolved tertiary structure. In this context, studies have emerged predict by methods based on template or free modeling. last years, different been combined overcome their individual limitations, until emergence AlphaFold2, which demonstrated that predicting high accuracy at unprecedented scale possible. Despite current impact field, AlphaFold2 has limitations. Recently, language models promised revolutionize structural biology allowing discovery only from evolutionary patterns present sequence. Even though these do not reach accuracy, they already covered some being able more than 200 million proteins metagenomic databases. mini-review, we provide an overview breakthroughs prediction before after emergence.

Language: Английский

---

The Art and Science of Molecular Docking

Annual Review of Biochemistry, Journal Year: 2024, Volume and Issue: 93(1), P. 389 - 410

Published: April 10, 2024

Molecular docking has become an essential part of a structural biologist's and medicinal chemist's toolkits. Given chemical compound the three-dimensional structure molecular target—for example, protein—docking methods fit into target, predicting compound's bound binding energy. Docking can be used to discover novel ligands for target by screening large virtual libraries. also provide useful starting point structure-based ligand optimization or investigating ligand's mechanism action. Advances in computational methods, including both physics-based machine learning approaches, as well complementary experimental techniques, are making even more powerful tool. We review how works it drive drug discovery biological research. describe its current limitations ongoing efforts overcome them.

Language: Английский

---

AlphaFold2 structures guide prospective ligand discovery

Science, Journal Year: 2024, Volume and Issue: 384(6702)

Published: May 16, 2024

AlphaFold2 (AF2) models have had wide impact but mixed success in retrospective ligand recognition. We prospectively docked large libraries against unrefined AF2 of the σ

Language: Английский

---

AlphaFold, allosteric, and orthosteric drug discovery: Ways forward

Drug Discovery Today, Journal Year: 2023, Volume and Issue: 28(6), P. 103551 - 103551

Published: March 11, 2023

Drug discovery is arguably a highly challenging and significant interdisciplinary aim. The stunning success of the artificial intelligence-powered AlphaFold, whose latest version buttressed by an innovative machine-learning approach that integrates physical biological knowledge about protein structures, raised drug hopes unsurprisingly, have not come to bear. Even though accurate, models are rigid, including pockets. AlphaFold's mixed performance poses question how its power can be harnessed in discovery. Here we discuss possible ways going forward wielding strengths, while bearing mind what AlphaFold cannot do. For kinases receptors, input enriched active (ON) state better chance rational design success.

Language: Английский

---

DynamicBind: predicting ligand-specific protein-ligand complex structure with a deep equivariant generative model

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: Feb. 5, 2024

While significant advances have been made in predicting static protein structures, the inherent dynamics of proteins, modulated by ligands, are crucial for understanding function and facilitating drug discovery. Traditional docking methods, frequently used studying protein-ligand interactions, typically treat proteins as rigid. molecular simulations can propose appropriate conformations, they're computationally demanding due to rare transitions between biologically relevant equilibrium states. In this study, we present DynamicBind, a deep learning method that employs equivariant geometric diffusion networks construct smooth energy landscape, promoting efficient different DynamicBind accurately recovers ligand-specific conformations from unbound structures without need holo-structures or extensive sampling. Remarkably, it demonstrates state-of-the-art performance virtual screening benchmarks. Our experiments reveal accommodate wide range large conformational changes identify cryptic pockets unseen targets. As result, shows potential accelerating development small molecules previously undruggable targets expanding horizons computational

Language: Английский

---

How accurately can one predict drug binding modes using AlphaFold models?

eLife, Journal Year: 2023, Volume and Issue: 12

Published: Dec. 22, 2023

Computational prediction of protein structure has been pursued intensely for decades, motivated largely by the goal using structural models drug discovery. Recently developed machine-learning methods such as AlphaFold 2 (AF2) have dramatically improved prediction, with reported accuracy approaching that experimentally determined structures. To what extent do these advances translate to an ability predict more accurately how drugs and candidates bind their target proteins? Here, we carefully examine utility AF2 predicting binding poses drug-like molecules at largest class targets, G-protein-coupled receptors. We find capture pocket structures much than traditional homology models, errors nearly small differences between same different ligands bound. Strikingly, however, ligand-binding predicted computational docking is not significantly higher when lower without These results important implications all those who might use

Language: Английский

---

Predicting equilibrium distributions for molecular systems with deep learning

Nature Machine Intelligence, Journal Year: 2024, Volume and Issue: 6(5), P. 558 - 567

Published: May 8, 2024

Abstract Advances in deep learning have greatly improved structure prediction of molecules. However, many macroscopic observations that are important for real-world applications not functions a single molecular but rather determined from the equilibrium distribution structures. Conventional methods obtaining these distributions, such as dynamics simulation, computationally expensive and often intractable. Here we introduce framework, called Distributional Graphormer (DiG), an attempt to predict systems. Inspired by annealing process thermodynamics, DiG uses neural networks transform simple towards distribution, conditioned on descriptor system chemical graph or protein sequence. This framework enables efficient generation diverse conformations provides estimations state densities, orders magnitude faster than conventional methods. We demonstrate several tasks, including conformation sampling, ligand catalyst–adsorbate sampling property-guided generation. presents substantial advancement methodology statistically understanding systems, opening up new research opportunities sciences.

Language: Английский

---

A Comprehensive Survey of Prospective Structure-Based Virtual Screening for Early Drug Discovery in the Past Fifteen Years

International Journal of Molecular Sciences, Journal Year: 2022, Volume and Issue: 23(24), P. 15961 - 15961

Published: Dec. 15, 2022

Structure-based virtual screening (SBVS), also known as molecular docking, has been increasingly applied to discover small-molecule ligands based on the protein structures in early stage of drug discovery. In this review, we comprehensively surveyed prospective applications docking judged by solid experimental validations literature over past fifteen years. Herein, systematically analyzed novelty targets and hits, practical protocols screening, following validations. Among 419 case studies reviewed, most screenings were carried out widely studied targets, only 22% less-explored new targets. Regarding software, GLIDE is popular one used while DOCK 3 series showed a strong capacity for large-scale screening. Besides, majority identified hits are promising structural one-quarter better potency than 1 μM, indicating that primary advantage SBVS chemotypes rather highly potent compounds. Furthermore, studies, vitro bioassays validate which might limit further characterization development active Finally, several successful stories with extensive have highlighted, provide unique insights into future discovery campaigns.

Language: Английский

---

Integrating structure-based approaches in generative molecular design

Current Opinion in Structural Biology, Journal Year: 2023, Volume and Issue: 79, P. 102559 - 102559

Published: March 2, 2023

Generative molecular design for drug discovery and development has seen a recent resurgence promising to improve the efficiency of design-make-test-analyse cycle; by computationally exploring much larger chemical spaces than traditional virtual screening techniques. However, most generative models thus far have only utilized small-molecule information train condition de novo molecule generators. Here, we instead focus on approaches that incorporate protein structure into optimization in an attempt maximize predicted on-target binding affinity generated molecules. We summarize these integration principles either distribution learning or goal-directed each case whether approach is structure-explicit implicit with respect model. discuss context this categorization provide our perspective future direction field.

Language: Английский

---

How accurately can one predict drug binding modes using AlphaFold models?

eLife, Journal Year: 2023, Volume and Issue: 12

Published: Aug. 8, 2023

Computational prediction of protein structure has been pursued intensely for decades, motivated largely by the goal using structural models drug discovery. Recently developed machine-learning methods such as AlphaFold 2 (AF2) have dramatically improved prediction, with reported accuracy approaching that experimentally determined structures. To what extent do these advances translate to an ability predict more accurately how drugs and candidates bind their target proteins? Here, we carefully examine utility AF2 predicting binding poses drug-like molecules at largest class targets, G-protein-coupled receptors. We find capture pocket structures much than traditional homology models, errors nearly small differences between same different ligands bound. Strikingly, however, ligand-binding predicted computational docking is not significantly higher when lower without These results important implications all those who might use

Language: Английский

---