How good are AlphaFold models for docking-based virtual screening?

iScience, Год журнала: 2022, Номер 26(1), С. 105920 - 105920

Опубликована: Дек. 30, 2022

A crucial component in structure-based drug discovery is the availability of high-quality three-dimensional structures protein target. Whenever experimental were not available, homology modeling has been, so far, method choice. Recently, AlphaFold (AF), an artificial-intelligence-based structure prediction method, shown impressive results terms model accuracy. This outstanding success prompted us to evaluate how accurate AF models are from perspective docking-based discovery. We compared high-throughput docking (HTD) performance with their corresponding PDB using a benchmark set 22 targets. The showed consistently worse four programs and two consensus techniques. Although shows remarkable ability predict architecture, this might be enough guarantee that can reliably used for HTD, post-modeling refinement strategies key increase chances success.

Язык: Английский

---

Are Deep Learning Structural Models Sufficiently Accurate for Virtual Screening? Application of Docking Algorithms to AlphaFold2 Predicted Structures

Journal of Chemical Information and Modeling, Год журнала: 2023, Номер 63(6), С. 1668 - 1674

Опубликована: Март 9, 2023

Machine learning-based protein structure prediction algorithms, such as RosettaFold and AlphaFold2, have greatly impacted the structural biology field, arousing a fair amount of discussion around their potential role in drug discovery. While there are few preliminary studies addressing usage these models virtual screening, none them focus on prospect hit-finding real-world screen with model based low prior information. In order to address this, we developed an AlphaFold2 version where exclude all templates more than 30% sequence identity from model-building process. previous study, used those conjunction state-of-the-art free energy perturbation methods demonstrated that it is possible obtain quantitatively accurate results. this work, using structures rigid receptor-ligand docking studies. Our results indicate out-of-the-box Alphafold2 not ideal scenario for screening campaigns; fact, strongly recommend include some post-processing modeling drive binding site into realistic holo model.

Язык: Английский

---

AlphaFold2 structures guide prospective ligand discovery

Science, Год журнала: 2024, Номер 384(6702)

Опубликована: Май 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

Язык: Английский

---

Recent Advances in Alchemical Binding Free Energy Calculations for Drug Discovery

ACS Medicinal Chemistry Letters, Год журнала: 2023, Номер 14(3), С. 244 - 250

Опубликована: Фев. 16, 2023

Rigorous physics-based methods to calculate binding free energies of protein–ligand complexes have become a valued component structure-based drug design. Relative and absolute energy calculations been deployed prospectively in support solving diverse discovery challenges. Here we review recent applications fragment growing linking, scaffold hopping, pose validation, virtual screening, covalent enzyme inhibition, positional analogue scanning. Furthermore, discuss the merits using protein models highlight efforts replace costly with predictions from machine learning trained on limited number perturbation or thermodynamic integration thereby allowing for extended chemical space exploration.

Язык: Английский

---

From byte to bench to bedside: molecular dynamics simulations and drug discovery

BMC Biology, Год журнала: 2023, Номер 21(1)

Опубликована: Дек. 29, 2023

Molecular dynamics (MD) simulations and computer-aided drug design (CADD) have advanced substantially over the past two decades, thanks to continuous computer hardware software improvements. Given these advancements, MD are poised become even more powerful tools for investigating dynamic interactions between potential small-molecule drugs their target proteins, with significant implications pharmacological research.

Язык: Английский

---

Advancing structural biology through breakthroughs in AI

Current Opinion in Structural Biology, Год журнала: 2023, Номер 80, С. 102601 - 102601

Опубликована: Май 12, 2023

Язык: Английский

---

Alchemical Transformations and Beyond: Recent Advances and Real-World Applications of Free Energy Calculations in Drug Discovery

Journal of Chemical Information and Modeling, Год журнала: 2024, Номер 64(19), С. 7214 - 7237

Опубликована: Окт. 3, 2024

Computational methods constitute efficient strategies for screening and optimizing potential drug molecules. A critical factor in this process is the binding affinity between candidate molecules targets, quantified as free energy. Among various estimation methods, alchemical transformation stand out their theoretical rigor. Despite challenges force field accuracy sampling efficiency, advancements algorithms, software, hardware have increased application of energy perturbation (FEP) calculations pharmaceutical industry. Here, we review practical applications FEP discovery projects since 2018, covering both ligand-centric residue-centric transformations. We show that relative steadily achieved chemical real-world applications. In addition, discuss alternative physics-based simulation incorporation deep learning into calculations.

Язык: Английский

---

Using AlphaFold and Experimental Structures for the Prediction of the Structure and Binding Affinities of GPCR Complexes via Induced Fit Docking and Free Energy Perturbation

Journal of Chemical Theory and Computation, Год журнала: 2023, Номер 20(1), С. 477 - 489

Опубликована: Дек. 15, 2023

Free energy perturbation (FEP) remains an indispensable method for computationally assaying prospective compounds in advance of synthesis. However, before FEP can be deployed prospectively, it must demonstrate retrospective recapitulation known experimental data where the subtle details atomic ligand-receptor model are consequential. An open question is whether AlphaFold models serve as useful initial regime there exists a congeneric series chemical matter but no structures available either target or close homologues. As provided without bound ligand, we employ induced fit docking to refine presence one more ligands. In this work, first validate performance our latest technology, IFD-MD, on set public GPCR with 95% cross-docks producing pose ligand RMSD ≤ 2.5 Å top two predictions. We then apply IFD-MD and somatostatin receptor family GPCRs. use produced prior availability any structure from family. arrive at FEP-validated SSTR2, SSTR4, SSTR5, RMSE around 1 kcal/mol, explore challenges validation under scenarios limited data, ample categorical data.

Язык: Английский

---

Quality Assessment of Selected Protein Structures Derived from Homology Modeling and AlphaFold

Pharmaceuticals, Год журнала: 2023, Номер 16(12), С. 1662 - 1662

Опубликована: Ноя. 29, 2023

With technology advancing, many prediction algorithms have been developed to facilitate the modeling of inherently dynamic and flexible macromolecules such as proteins. Improvements in protein structures attracted a great deal attention due advantages they offer, e.g., drug design. While trusted experimental methods, X-ray crystallography, NMR spectroscopy, electron microscopy, are preferred structure analysis techniques, silico approaches also being widely used. Two computational which on opposite ends spectrum with respect their modus operandi, i.e., homology AlphaFold, established provide high-quality structures. Here, comparative study quality either predicted by or AlphaFold is presented based characteristics determined studies using validation servers fulfill purpose. Although able predict structures, high-confidence parts sometimes observed be disagreement data. On other hand, while obtained from successful incorporating all aspects used template, this method may struggle accurately model absence suitable template. In general, although both methods produce models, criteria superior each different thus discussed detail.

Язык: Английский

---

AlphaFold2 structures template ligand discovery

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2023, Номер unknown

Опубликована: Дек. 21, 2023

AlphaFold2 (AF2) and RosettaFold have greatly expanded the number of structures available for structure-based ligand discovery, even though retrospective studies cast doubt on their direct usefulness that goal. Here, we tested unrefined AF2 models prospectively, comparing experimental hit-rates affinities from large library docking against vs same screens targeting receptors. In σ2 5-HT2A receptors, struggled to recapitulate ligands had previously found receptors' structures, consistent with published results. Prospective models, however, yielded similar hit rates both receptors versus experimentally-derived structures; hundreds molecules were prioritized each model structure receptor. The success was achieved despite differences in orthosteric pocket residue conformations targets structures. Intriguingly, receptor most potent, subtype-selective agonists discovered via model, not structure. To understand this a molecular perspective, cryoEM determined one more potent selective emerge Our findings suggest may sample are relevant much extending domain applicability discovery.

Язык: Английский

---