Deep learning for reconstructing protein structures from cryo-EM density maps: Recent advances and future directions

Giri, Nabin; Roy, Raj; Cheng, Jianlin

doi:10.1016/j.sbi.2023.102536

Cited by 35 publications

(32 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current explosive growth in computational resources coincides with a rapid development of advanced light sources, 52 neutron scattering facilities, 53 (in cell) NMR, 54 and cryoEM and cryo-electron tomography techniques, 55,56 all of which generate large data sets. For example, the LCLS-II free electron X-ray laser facility at SLAC has recently come online, with a nearly 10000-fold increase in pulse frequency compared to the existing LCLS beamline.…”

Section: Facilitiesmentioning

confidence: 99%

“…The current explosive growth in computational resources coincides with a rapid development of advanced light sources, neutron scattering facilities, (in cell) NMR, and cryoEM and cryo-electron tomography techniques, , all of which generate large data sets. For example, the LCLS-II free electron X-ray laser facility at SLAC has recently come online, with a nearly 10000-fold increase in pulse frequency compared to the existing LCLS beamline. , Exascale computing will play a key role in guiding and analyzing the resulting high fidelity experiments that hold the potential to reveal biomolecular structure and dynamics, producing “movies” of complex molecular-level processes in action.…”

Section: Integration With Major Experimental Facilitiesmentioning

confidence: 99%

See 1 more Smart Citation

All-Atom Biomolecular Simulation in the Exascale Era

Beck,

Carloni,

Asthagiri

2024

J. Chem. Theory Comput.

View full text Add to dashboard Cite

Exascale supercomputers have opened the door to dynamic simulations, facilitated by AI/ML techniques, that model biomolecular motions over unprecedented length and time scales. This new capability holds the potential to revolutionize our understanding of fundamental biological processes. Here we report on some of the major advances that were discussed at a recent CECAM workshop in Pisa, Italy, on the topic with a primary focus on atomic-level simulations. First, we highlight examples of current large-scale biomolecular simulations and the future possibilities enabled by crossing the exascale threshold. Next, we discuss challenges to be overcome in optimizing the usage of these powerful resources. Finally, we close by listing several grand challenge problems that could be investigated with this new computer architecture.

show abstract

Section: Facilitiesmentioning

confidence: 99%

Section: Integration With Major Experimental Facilitiesmentioning

confidence: 99%

All-Atom Biomolecular Simulation in the Exascale Era

Beck,

Carloni,

Asthagiri

2024

J. Chem. Theory Comput.

View full text Add to dashboard Cite

show abstract

“…194 The need of curated datasets for training is also a crucial point for the development of more accurate tools. 194,193 Another vibrant potential future direction is the development of integrative methods that synergistically combine various biophysical techniques, such as cryo-EM, x-ray crystallography, and NMR spectroscopy, to provide a more complete experimental understanding of protein dynamics and function. Indeed, the incorporation of cryo-EM data into iterative AlphaFold runs yield improvements on the prediction of 3D structures.…”

Section: Summary and Future Directionsmentioning

confidence: 99%

“…111 Nowadays, given the early stage of development of this exciting field, it is important to bear in mind that future tools incorporating latest technologies such as graph neural networks will potentially overcome limitations faced by current methods. 194 The need of curated datasets for training is also a crucial point for the development of more accurate tools. 194,193 Another vibrant potential future direction is the development of integrative methods that synergistically combine various biophysical techniques, such as cryo-EM, x-ray crystallography, and NMR spectroscopy, to provide a more complete experimental understanding of protein dynamics and function.…”

Section: Summary and Future Directionsmentioning

confidence: 99%

“…Furthermore, the integration of machine learning, particularly deep learning, and artificial intelligence‐based methods into cryo‐EM techniques could potentially address challenges faced by current methods by providing better feature extraction and classification methods 193 . Deep learning methods are already integrated in several tools for cryo‐EM 3D reconstruction and atomic model building, 194,195 including many heterogeneous reconstruction algorithms for continuous heterogeneity analysis 111 . Nowadays, given the early stage of development of this exciting field, it is important to bear in mind that future tools incorporating latest technologies such as graph neural networks will potentially overcome limitations faced by current methods 194 .…”

Section: Summary and Future Directionsmentioning

confidence: 99%

See 1 more Smart Citation

Computational biophysics meets cryo‐EM revolution in the search for the functional dynamics of biomolecular systems

Costa,

Gur,

Krieger

et al. 2023

WIREs Comput Mol Sci

View full text Add to dashboard Cite

There is a variety of experimental and computational techniques available to explore protein dynamics, each presenting advantages and limitations. One promising experimental technique that is driving the development of computational methods is cryo‐electron microscopy (cryo‐EM). Cryo‐EM provides molecular‐level structural data and first estimates of conformational landscape from single particle analysis but cannot track real‐time protein dynamics and may contain uncertainties in atomic positions especially at highly dynamic regions. Molecular simulations offer atomic‐level insights into protein dynamics; however, their computing time requirements limit the conformational sampling accuracy, and it is often hard, to assess by full‐atomic simulations the cooperative movements of biological interest for large assemblies such as those resolved by cryo‐EM. Coarse‐grained (CG) simulations permit us to explore such systems, but at the costs of lower resolution and potentially incomplete sampling of conformational space. On the other hand, analytical methods may circumvent sampling limitations. In particular, elastic network models‐based normal mode analyses (ENM‐NMA) provide unique solutions for the complete mode spectra near equilibrium states, even for systems of megadaltons, and may thus deliver information on mechanisms of motions relevant to biological function. Yet, they lack atomic resolution as well as temporal information for non‐equilibrium systems. Given the complementary nature of these methods, the integration of molecular simulations and ENM‐NMA into hybrid methodologies has gained traction. This review presents the current state‐of‐the‐art in structure‐based computations and how they are helping us gain a deeper understanding of biological mechanisms, with emphasis on the development of hybrid methods accompanying the advances in cryo‐EM.This article is categorized under: Structure and Mechanism > Computational Biochemistry and Biophysics

show abstract

Beyond AlphaFold2: The Impact of AI for the Further Improvement of Protein Structure Prediction

Genc,

McGuffin

2024

Methods in Molecular Biology

View full text Add to dashboard Cite

Deep learning for reconstructing protein structures from cryo-EM density maps: Recent advances and future directions

Cited by 35 publications

References 42 publications

All-Atom Biomolecular Simulation in the Exascale Era

All-Atom Biomolecular Simulation in the Exascale Era

Computational biophysics meets cryo‐EM revolution in the search for the functional dynamics of biomolecular systems

Beyond AlphaFold2: The Impact of AI for the Further Improvement of Protein Structure Prediction

Contact Info

Product

Resources

About