Modeling conformational states of proteins with AlphaFold

Current Opinion in Structural Biology, Год журнала: 2023, Номер 81, С. 102645 - 102645

Опубликована: Июнь 29, 2023

Язык: Английский

---

Direct prediction of intrinsically disordered protein conformational properties from sequence

Nature Methods, Год журнала: 2024, Номер 21(3), С. 465 - 476

Опубликована: Янв. 31, 2024

Abstract Intrinsically disordered regions (IDRs) are ubiquitous across all domains of life and play a range functional roles. While folded generally well described by stable three-dimensional structure, IDRs exist in collection interconverting states known as an ensemble. This structural heterogeneity means that largely absent from the Protein Data Bank, contributing to lack computational approaches predict ensemble conformational properties sequence. Here we combine rational sequence design, large-scale molecular simulations deep learning develop ALBATROSS, deep-learning model for predicting dimensions IDRs, including radius gyration, end-to-end distance, polymer-scaling exponent asphericity, directly sequences at proteome-wide scale. ALBATROSS is lightweight, easy use accessible both locally installable software package point-and-click-style interface via Google Colab notebooks. We first demonstrate applicability our predictors examining generalizability sequence–ensemble relationships IDRs. Then, leverage high-throughput nature characterize sequence-specific biophysical behavior within between proteomes.

Язык: Английский

---

High-throughput prediction of protein conformational distributions with subsampled AlphaFold2

Nature Communications, Год журнала: 2024, Номер 15(1)

Опубликована: Март 27, 2024

Abstract This paper presents an innovative approach for predicting the relative populations of protein conformations using AlphaFold 2, AI-powered method that has revolutionized biology by enabling accurate prediction structures. While 2 shown exceptional accuracy and speed, it is designed to predict proteins’ ground state limited in its ability conformational landscapes. Here, we demonstrate how can directly different subsampling multiple sequence alignments. We tested our against nuclear magnetic resonance experiments on two proteins with drastically amounts available data, Abl1 kinase granulocyte-macrophage colony-stimulating factor, predicted changes their more than 80% accuracy. Our worked best when used qualitatively effects mutations or evolution landscape well-populated states proteins. It thus offers a fast cost-effective way at even single-point mutation resolution, making useful tool pharmacology, analysis experimental results, evolution.

Язык: Английский

---

Enhanced Sampling with Machine Learning

Annual Review of Physical Chemistry, Год журнала: 2024, Номер 75(1), С. 347 - 370

Опубликована: Фев. 22, 2024

Molecular dynamics (MD) enables the study of physical systems with excellent spatiotemporal resolution but suffers from severe timescale limitations. To address this, enhanced sampling methods have been developed to improve exploration configurational space. However, implementing these is challenging and requires domain expertise. In recent years, integration machine learning (ML) techniques into different domains has shown promise, prompting their adoption in as well. Although ML often employed various fields primarily due its data-driven nature, more natural many common underlying synergies. This review explores merging MD by presenting shared viewpoints. It offers a comprehensive overview this rapidly evolving field, which can be difficult stay updated on. We highlight successful strategies such dimensionality reduction, reinforcement learning, flow-based methods. Finally, we discuss open problems at exciting ML-enhanced interface.

Язык: Английский

---

Navigating the landscape of enzyme design: from molecular simulations to machine learning

Chemical Society Reviews, Год журнала: 2024, Номер 53(16), С. 8202 - 8239

Опубликована: Янв. 1, 2024

Global environmental issues and sustainable development call for new technologies fine chemical synthesis waste valorization. Biocatalysis has attracted great attention as the alternative to traditional organic synthesis. However, it is challenging navigate vast sequence space identify those proteins with admirable biocatalytic functions. The recent of deep-learning based structure prediction methods such AlphaFold2 reinforced by different computational simulations or multiscale calculations largely expanded 3D databases enabled structure-based design. While approaches shed light on site-specific enzyme engineering, they are not suitable large-scale screening potential biocatalysts. Effective utilization big data using machine learning techniques opens up a era accelerated predictions. Here, we review applications machine-learning guided We also provide our view challenges perspectives effectively employing design integrating molecular learning, importance database construction algorithm in attaining predictive ML models explore fitness landscape

Язык: Английский

---

Approximating Projections of Conformational Boltzmann Distributions with AlphaFold2 Predictions: Opportunities and Limitations

Journal of Chemical Theory and Computation, Год журнала: 2024, Номер 20(3), С. 1434 - 1447

Опубликована: Янв. 12, 2024

Protein thermodynamics is intimately tied to biological function and can enable processes such as signal transduction, enzyme catalysis, molecular recognition. The relative free energies of conformations that contribute these functional equilibria evolved for the physiology organism. Despite importance understanding developing treatments disease, computational experimental methods capable quantifying energetic determinants are limited systems modest size. Recently, it has been demonstrated artificial intelligence system AlphaFold2 be manipulated produce structurally valid protein conformational ensembles. Here, we extend studies explore extent which contact distance distributions approximate projections Boltzmann distributions. For this purpose, examine joint probability inter-residue distances along functionally relevant collective variables several systems. Our suggest normalized correlate with conformation probabilities obtained other but they suffer from peak broadening. We also find sensitive point mutations. Overall, anticipate our findings will valuable community seeks model changes in large biomolecular

Язык: Английский

---

AlphaFold prediction of structural ensembles of disordered proteins

Nature Communications, Год журнала: 2025, Номер 16(1)

Опубликована: Фев. 14, 2025

Abstract Deep learning methods of predicting protein structures have reached an accuracy comparable to that high-resolution experimental methods. It is thus possible generate accurate models the native states hundreds millions proteins. An open question, however, concerns whether these advances can be translated disordered proteins, which should represented as structural ensembles because their heterogeneous and dynamical nature. To address this problem, we introduce AlphaFold-Metainference method use AlphaFold-derived distances restraints in molecular dynamics simulations construct ordered The results obtained using illustrate possibility making predictions conformational properties proteins deep trained on large databases available for folded

Язык: Английский

---

AlphaFold2 and Deep Learning for Elucidating Enzyme Conformational Flexibility and Its Application for Design

JACS Au, Год журнала: 2023, Номер 3(6), С. 1554 - 1562

Опубликована: Июнь 6, 2023

The recent success of AlphaFold2 (AF2) and other deep learning (DL) tools in accurately predicting the folded three-dimensional (3D) structure proteins enzymes has revolutionized structural biology protein design fields. 3D indeed reveals key information on arrangement catalytic machinery which elements gate active site pocket. However, comprehending enzymatic activity requires a detailed knowledge chemical steps involved along cycle exploration multiple thermally accessible conformations that adopt when solution. In this Perspective, some studies showing potential AF2 elucidating conformational landscape are provided. Selected examples developments AF2-based DL methods for discussed, as well few enzyme cases. These show allowing routine computational efficient enzymes.

Язык: Английский

---

Exploring Kinase Asp-Phe-Gly (DFG) Loop Conformational Stability with AlphaFold2-RAVE

Journal of Chemical Information and Modeling, Год журнала: 2023, Номер 64(7), С. 2789 - 2797

Опубликована: Ноя. 20, 2023

Kinases compose one of the largest fractions human proteome, and their misfunction is implicated in many diseases, particular, cancers. The ubiquitousness structural similarities kinases make specific effective drug design difficult. In conformational variability due to evolutionarily conserved Asp-Phe-Gly (DFG) motif adopting out conformations relative stabilities thereof are key structure-based for ATP competitive drugs. These extremely sensitive small changes sequence provide an important problem sampling method development. Since invention AlphaFold2, world has noticeably changed. spite it being limited crystal-like structure prediction, several methods have also leveraged its underlying architecture improve dynamics enhanced ensembles, including AlphaFold2-RAVE. Here, we extend AlphaFold2-RAVE apply a set kinases: wild type DDR1 three mutants with single point mutations that known behave drastically differently. We show able efficiently recover stability using transferable learned order parameters potentials, thereby supplementing AlphaFold2 as tool exploration Boltzmann-weighted protein (Meller, A.; Bhakat, S.; Solieva, Bowman, G. R. Accelerating Cryptic Pocket Discovery Using AlphaFold. J. Chem. Theory Comput. 2023, 19, 4355–4363).

Язык: Английский

---

Information Bottleneck Approach for Markov Model Construction

Journal of Chemical Theory and Computation, Год журнала: 2024, Номер 20(12), С. 5352 - 5367

Опубликована: Июнь 11, 2024

Markov state models (MSMs) have proven valuable in studying dynamics of protein conformational changes via statistical analysis molecular (MD) simulations. In MSMs, the complex configuration space is coarse-grained into states, with modeled by a series Markovian transitions among these states at discrete lag times. Constructing model specific time necessitates defining that circumvent significant internal energy barriers, enabling relaxation within time. This process effectively coarse-grains and space, integrating out rapid motions metastable states. Thus, MSMs possess multi-resolution nature, where granularity can be adjusted according to time-resolution, offering flexibility capturing system dynamics. work introduces continuous embedding approach for conformations using predictive information bottleneck (SPIB), framework unifies dimensionality reduction partitioning continuous, machine learned basis set. Without explicit optimization VAMP-based scores, SPIB demonstrates state-of-the-art performance identifying slow dynamical processes constructing models. Through applications well-validated mini-proteins, showcases unique advantages compared competing methods. It autonomously self-consistently adjusts number based on specified minimal resolution, eliminating need manual tuning. While maintaining efficacy properties, excels accurately distinguishing numerous well-populated macrostates. contrasts existing methods, which often emphasize expense incorporating sparsely populated Furthermore, SPIB's ability learn low-dimensional underlying enhances interpretation dynamic pathways. With benefits, we propose as an easy-to-implement methodology end-to-end construction.

Язык: Английский

---