The power and pitfalls of AlphaFold2 for structure prediction beyond rigid globular proteins

Nature Chemical Biology, Год журнала: 2024, Номер 20(8), С. 950 - 959

Опубликована: Июнь 21, 2024

Язык: Английский

---

A coarse‐grained model for disordered and multi‐domain proteins

Protein Science, Год журнала: 2024, Номер 33(11)

Опубликована: Окт. 16, 2024

Many proteins contain more than one folded domain, and such modular multi-domain help expand the functional repertoire of proteins. Because their larger size often substantial dynamics, it may be difficult to characterize conformational ensembles by simulations. Here, we present a coarse-grained model for that is both fast provides an accurate description global properties in solution. We show accuracy one-bead-per-residue depends on how interaction sites domains are represented. Specifically, find excessive domain-domain interactions if located at position C

Язык: Английский

---

GōMartini 3: From large conformational changes in proteins to environmental bias corrections

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Апрель 16, 2024

ABSTRACT Coarse-grained modeling has become an important tool to supplement experimental measurements, allowing access spatio-temporal scales beyond all-atom based approaches. The GōMartini model combines structure- and physics-based coarse-grained approaches, balancing computational efficiency accurate representation of protein dynamics with the capabilities studying proteins in different biological environments. This paper introduces enhanced model, which a virtual-site implementation Gō models Martini 3. been extensively tested by community since release new version Martini. work demonstrates diverse case studies, ranging from protein-membrane binding protein-ligand interactions AFM force profile calculations. is also versatile, as it can address recent inaccuracies reported model. Lastly, discusses advantages, limitations, future perspectives 3 its combination models.

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

---

Rescaling protein-protein interactions improves Martini 3 for flexible proteins in solution

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

Опубликована: Авг. 5, 2024

Multidomain proteins with flexible linkers and disordered regions play important roles in many cellular processes, but characterizing their conformational ensembles is difficult. We have previously shown that the coarse-grained model, Martini 3, produces too compact solution, may part be remedied by strengthening protein–water interactions. Here, we show decreasing strength of protein–protein interactions leads to improved agreement experimental data on a wide set systems. 'symmetry' between rescaling breaks down when studying or within membranes; protein-protein better preserves binding specificity lipid membranes, whereas protein-water oligomerization transmembrane helices. conclude improves accuracy 3 for IDPs multidomain proteins, both solution presence membrane. authors generated molecular dynamics simulations

Язык: Английский

---

Explainable chemical artificial intelligence from accurate machine learning of real-space chemical descriptors

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

Опубликована: Май 21, 2024

Abstract Machine-learned computational chemistry has led to a paradoxical situation in which molecular properties can be accurately predicted, but they are difficult interpret. Explainable AI (XAI) tools used analyze complex models, highly dependent on the technique and origin of reference data. Alternatively, interpretable real-space employed directly, often expensive compute. To address this dilemma between explainability accuracy, we developed SchNet4AIM, SchNet-based architecture capable dealing with local one-body (atomic) two-body (interatomic) descriptors. The performance SchNet4AIM is tested by predicting wide collection quantities ranging from atomic charges delocalization indices pairwise interaction energies. accuracy speed breaks bottleneck that prevented use chemical descriptors systems. We show group indices, arising our physically rigorous atomistic predictions, provide reliable indicators supramolecular binding events, thus contributing development Chemical Artificial Intelligence (XCAI) models.

Язык: Английский

---

Deep learning for protein structure prediction and design—progress and applications

Molecular Systems Biology, Год журнала: 2024, Номер 20(3), С. 162 - 169

Опубликована: Янв. 30, 2024

Abstract Proteins are the key molecular machines that orchestrate all biological processes of cell. Most proteins fold into three-dimensional shapes critical for their function. Studying 3D shape can inform us mechanisms underlie in living cells and have practical applications study disease mutations or discovery novel drug treatments. Here, we review progress made sequence-based prediction protein structures with a focus on go beyond single monomer structures. This includes application deep learning methods complexes, different conformations, evolution these to design. These developments create new opportunities research will impact across many areas biomedical research.

Язык: Английский

---

A coarse-grained model for disordered and multi-domain proteins

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Фев. 7, 2024

Abstract Many proteins contain more than one folded domain, and such modular multi-domain help expand the functional repertoire of proteins. Because their larger size often substantial dynamics, it may be difficult to characterize conformational ensembles by simulations. Here, we present a coarse-grained model for that is both fast provides an accurate description global properties in solution. We show accuracy one-bead-per-residue depends on how interaction sites domains are represented. Specifically, find excessive domain-domain interactions if located at position C α atoms. also centre mass residue, obtain good agreement between simulations experiments across wide range then optimize our previously described CALVADOS using this centre-of-mass representation, validate resulting independent data. Finally, use revised simulate phase separation disordered proteins, examine stability differ dilute dense phases. Our results provide starting point understanding regions these affect propensity self-associate undergo separation.

Язык: Английский

---

AlphaFold2 Predicts Whether Proteins Interact Amidst Confounding Structural Compatibility

Journal of Chemical Information and Modeling, Год журнала: 2024, Номер 64(5), С. 1473 - 1480

Опубликована: Фев. 19, 2024

Predicting whether two proteins physically interact is one of the holy grails computational biology, galvanized by rapid advancements in deep learning. AlphaFold2, although not developed with this goal, promising respect. Here, I test prediction capability AlphaFold2 on a very challenging data set, where are structurally compatible, even when they do interact. achieves high discrimination between interacting and non-interacting proteins, cases misclassifications can either be rescued revisiting input sequences or suggest false positives negatives set. thus impaired compatibility protein structures has potential to applied large scale.

Язык: Английский

---

Predicting protein conformational motions using energetic frustration analysis and AlphaFold2

Proceedings of the National Academy of Sciences, Год журнала: 2024, Номер 121(35)

Опубликована: Авг. 20, 2024

Proteins perform their biological functions through motion. Although high throughput prediction of the three-dimensional static structures proteins has proved feasible using deep-learning-based methods, predicting conformational motions remains a challenge. Purely data-driven machine learning methods encounter difficulty for addressing such because available laboratory data on are still limited. In this work, we develop method generating protein allosteric by integrating physical energy landscape information into methods. We show that local energetic frustration, which represents quantification features governing dynamics, can be utilized to empower AlphaFold2 (AF2) predict motions. Starting from ground state structures, integrative generates alternative as well pathways motions, progressive enhancement frustration in input multiple sequence alignment sequences. For model adenylate kinase, generated consistent with experimental and molecular dynamics simulation data. Applying another two KaiB ribose-binding protein, involve large-amplitude changes, also successfully generate conformations. how extract overall AF2 topography, been considered many black box. Incorporating knowledge structure algorithms provides useful strategy address challenges dynamic proteins.

Язык: Английский

---