Smart de novo Macromolecular Structure Modeling from Cryo-EM Maps

Si, Dong; Chen, Jason; Nakamura, Andrew; Chang, Luca; Guan, Haowen

doi:10.1016/j.jmb.2023.167967

Cited by 3 publications

(6 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Predicting a protein's structure using only its amino acid sequence without using templates is really called ab initio method, where ab initio means "from the beginning" in Latin. 60 As shown in Figure 2b, in ab initio protein structure prediction, the method first generates initial low-resolution models utilizing knowledge-based potentials or fragment libraries. These models are then systematically refined through a series of Monte Carlo simulations, which involve the assembly and optimization of protein fragments to achieve more accurate and detailed structural predictions.…”

Section: Ab Initio Protein Structure Prediction Methodsmentioning

confidence: 99%

“…Predicting a protein's structure using only its amino acid sequence without using templates is really called ab initio method, where ab initio means “from the beginning” in Latin 60 . As shown in Figure 2b, in ab initio protein structure prediction, the method first generates initial low‐resolution models utilizing knowledge‐based potentials or fragment libraries.…”

Section: Structure Resolution and Prediction Of K+ Ion Channelsmentioning

confidence: 99%

See 1 more Smart Citation

Computational methods for unlocking the secrets of potassium channels: Structure, mechanism, and drug design

Wang,

Zhang,

Tong

et al. 2024

WIREs Comput Mol Sci

View full text Add to dashboard Cite

Potassium (K+) channels play vital roles in various physiological functions, including regulating K+ flow in cell membranes, impacting nervous system signal transduction, neuronal firing, muscle contraction, neurotransmitters, and enzyme secretion. Their activation and switch‐off are directly linked to diseases like arrhythmias, atrial fibrillation, and pain etc. Although the experimental methods play important roles in the studying the structure and function of K+ channels, they are still some limitations to enclose the dynamic molecular processes and the corresponding mechanisms of conformational changes during ion transport, permeation, and gating control. Relatively, computational methods have obvious advantages in studying such problems compared with experimental methods. Recently, more and more three‐dimensional structures of K+ channels have been disclosed based on experimental methods and in silico prediction methods, which provide a good chance to study the molecular mechanism of conformational changes related to the functional regulations of K+ channels. Based on these structural details, molecular dynamics simulations together with related methods such as enhanced sampling and free energy calculations, have been widely used to reveal the conformational dynamics, ion conductance, ion channel gating, and ligand binding mechanisms. Additionally, the accessibility of structures also provides a large space for structure‐based drug design. This review mainly addresses the recent progress of computational methods in the structure, mechanism, and drug design of K+ channels. After summarizing the progress in these fields, we also give our opinion on the future direction in the area of K+ channel research combined with the cutting edge of computational methods.This article is categorized under: Molecular and Statistical Mechanics > Molecular Dynamics and Monte‐Carlo Methods Structure and Mechanism > Computational Biochemistry and Biophysics Data Science > Chemoinformatics

show abstract

Section: Ab Initio Protein Structure Prediction Methodsmentioning

confidence: 99%

Section: Structure Resolution and Prediction Of K+ Ion Channelsmentioning

confidence: 99%

Computational methods for unlocking the secrets of potassium channels: Structure, mechanism, and drug design

Wang,

Zhang,

Tong

et al. 2024

WIREs Comput Mol Sci

View full text Add to dashboard Cite

show abstract

“…Each node in the system receives a collection of weighted inputs, and if the summed input surpasses a specific threshold determined by an activation function, the node transmits an output. Depending on how layers of the network are arranged, the ANN can learn high-level representations for classification tasks [ 70 ]. ANNs are trained by a process called backpropagation, in which the output of the ANN is compared to the expected outcome at each layer.…”

Section: DL Algorithmsmentioning

confidence: 99%

“…Thus, manual inspection is still required to evaluate the model in the context of the experimental map, as even high-confidence predictions can be modeled incorrectly [ 190 ]. Furthermore, as AlphaFold2 relies on experimentally determined structures deposited in the PDB, the algorithm may produce incorrect folds when there is a lack of homological structures [ 70 ]. Further developments are needed to improve the prediction accuracy of mutated residues, regions involved in ligand binding, and dynamic interactions [ 189 , 190 ].…”

Section: Applications Of Ai-based Protein Structure Prediction To Ato...mentioning

confidence: 99%

“…Consequently, this has led to improved accuracy and performance of DL techniques for cryo-EM image processing. In addition, developments in computer hardware, particularly of graphic processing units are arranged, the ANN can learn high-level representations for classification tasks [70]. ANNs are trained by a process called backpropagation, in which the output of the ANN is compared to the expected outcome at each layer.…”

Section: Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Novel Artificial Intelligence-Based Approaches for Ab Initio Structure Determination and Atomic Model Building for Cryo-Electron Microscopy

DiIorio,

Kulczyk

2023

Micromachines

View full text Add to dashboard Cite

Single particle cryo-electron microscopy (cryo-EM) has emerged as the prevailing method for near-atomic structure determination, shedding light on the important molecular mechanisms of biological macromolecules. However, the inherent dynamics and structural variability of biological complexes coupled with the large number of experimental images generated by a cryo-EM experiment make data processing nontrivial. In particular, ab initio reconstruction and atomic model building remain major bottlenecks that demand substantial computational resources and manual intervention. Approaches utilizing recent innovations in artificial intelligence (AI) technology, particularly deep learning, have the potential to overcome the limitations that cannot be adequately addressed by traditional image processing approaches. Here, we review newly proposed AI-based methods for ab initio volume generation, heterogeneous 3D reconstruction, and atomic model building. We highlight the advancements made by the implementation of AI methods, as well as discuss remaining limitations and areas for future development.

show abstract

New frontier of cryo-electron microscopy technology

Sun

Zhang

2023

Journal of Molecular Biology

View full text Add to dashboard Cite

Smart de novo Macromolecular Structure Modeling from Cryo-EM Maps

Cited by 3 publications

References 56 publications

Computational methods for unlocking the secrets of potassium channels: Structure, mechanism, and drug design

Computational methods for unlocking the secrets of potassium channels: Structure, mechanism, and drug design

Novel Artificial Intelligence-Based Approaches for Ab Initio Structure Determination and Atomic Model Building for Cryo-Electron Microscopy

New frontier of cryo-electron microscopy technology

Contact Info

Product

Resources

About