Deep learning in single-molecule imaging and analysis: recent advances and prospects

Liu, Xiaolong; Jiang, Yifei; Cui, Yanxiang; Yuan, Jinghe; Fang, Xiaohong

doi:10.1039/d2sc02443h

Cited by 7 publications

(5 citation statements)

References 120 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning has emerged as a powerful tool for analyzing single-molecule fluorescence imaging data, particularly for handling large volumes of complex and noisy data [ 80 , 81 ]. Specifically, deep learning algorithms, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), excel in recognizing patterns and features in images that may be challenging for manual identification.…”

Section: Analysis Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Trends in Single-Molecule Total Internal Reflection Fluorescence Imaging and Their Biological Applications with Lab-on-a-Chip Technology

Colson,

Kwon,

Nam

et al. 2023

Sensors

View full text Add to dashboard Cite

Single-molecule imaging technologies, especially those based on fluorescence, have been developed to probe both the equilibrium and dynamic properties of biomolecules at the single-molecular and quantitative levels. In this review, we provide an overview of the state-of-the-art advancements in single-molecule fluorescence imaging techniques. We systematically explore the advanced implementations of in vitro single-molecule imaging techniques using total internal reflection fluorescence (TIRF) microscopy, which is widely accessible. This includes discussions on sample preparation, passivation techniques, data collection and analysis, and biological applications. Furthermore, we delve into the compatibility of microfluidic technology for single-molecule fluorescence imaging, highlighting its potential benefits and challenges. Finally, we summarize the current challenges and prospects of fluorescence-based single-molecule imaging techniques, paving the way for further advancements in this rapidly evolving field.

show abstract

Section: Analysis Methodsmentioning

confidence: 99%

“…Nonetheless, challenges exist, such as the need for large, annotated datasets, which can be time-consuming and costly to generate, as well as the risk of overfitting or underfitting models, potentially leading to inaccurate or unreliable results. Liu et al summarized the deep learning application in single-molecule analysis [ 80 ].…”

Section: Analysis Methodsmentioning

confidence: 99%

Trends in Single-Molecule Total Internal Reflection Fluorescence Imaging and Their Biological Applications with Lab-on-a-Chip Technology

Colson,

Kwon,

Nam

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Analysis of protein colocalization data has recently been improved with the introduction of Bayesian or machine-learning approaches. , For example, Huang and co-workers developed a deep-learning convolutional neural network (DLCNN) that automatically distinguished between receptor monomers and larger complexes based on images of fluorescent spots. The main idea behind a DLCNN is to identify patterns or features in an image by applying filters to the image, which are mathematically convoluted with the image to produce feature maps.…”

Section: Single Molecule Studiesmentioning

confidence: 99%

Fluorescence-Based Detection of Proteins and Their Interactions in Live Cells

Stoneman

Raicu

2023

J. Phys. Chem. B

View full text Add to dashboard Cite

Recent advances in fluorescence-based microscopy techniques, such as single molecule fluorescence, Forster resonance energy transfer (FRET), fluorescence intensity fluctuations analysis, and super-resolution microscopy have expanded our ability to study proteins in greater detail within their native cellular environment and to investigate the roles that protein interactions play in biological functions, such as inter-and intracellular signaling and cargo transport. In this Perspective, we provide an up-to-date overview of the current state of the art in fluorescencebased detection of proteins and their interactions in living cells with an emphasis on recent developments that have facilitated the characterization of the spatial and temporal organization of proteins into oligomeric complexes in the presence and absence of natural and artificial ligands. Further advancements in this field will only deepen our understanding of the underlying mechanisms of biological processes and help develop new therapeutic targets.

show abstract

“…MD simulations can be used in conjunction with information from smFRET experiments to create an automated FRET-assisted structural model that can increase the accuracy of an integrated structure, as well as allow for FRET-assisted coarse-grained structural modeling and MD simulation-based refinement [130]. Recently, ML developments in single-molecule imaging automation and single-molecule feature recognition, including smFRET intensity trace analysis, have been reviewed [131].…”

Section: Ai-augmented Cryo-em and Smfret Approaches Expand The Univer...mentioning

confidence: 99%

From Deep Mutational Mapping of Allosteric Protein Landscapes to Deep Learning of Allostery and Hidden Allosteric Sites: Zooming in on “Allosteric Intersection” of Biochemical and Big Data Approaches

Verkhivker

Alshahrani

Gupta

et al. 2023

IJMS

View full text Add to dashboard Cite

The recent advances in artificial intelligence (AI) and machine learning have driven the design of new expert systems and automated workflows that are able to model complex chemical and biological phenomena. In recent years, machine learning approaches have been developed and actively deployed to facilitate computational and experimental studies of protein dynamics and allosteric mechanisms. In this review, we discuss in detail new developments along two major directions of allosteric research through the lens of data-intensive biochemical approaches and AI-based computational methods. Despite considerable progress in applications of AI methods for protein structure and dynamics studies, the intersection between allosteric regulation, the emerging structural biology technologies and AI approaches remains largely unexplored, calling for the development of AI-augmented integrative structural biology. In this review, we focus on the latest remarkable progress in deep high-throughput mining and comprehensive mapping of allosteric protein landscapes and allosteric regulatory mechanisms as well as on the new developments in AI methods for prediction and characterization of allosteric binding sites on the proteome level. We also discuss new AI-augmented structural biology approaches that expand our knowledge of the universe of protein dynamics and allostery. We conclude with an outlook and highlight the importance of developing an open science infrastructure for machine learning studies of allosteric regulation and validation of computational approaches using integrative studies of allosteric mechanisms. The development of community-accessible tools that uniquely leverage the existing experimental and simulation knowledgebase to enable interrogation of the allosteric functions can provide a much-needed boost to further innovation and integration of experimental and computational technologies empowered by booming AI field.

show abstract

Deep learning in single-molecule imaging and analysis: recent advances and prospects

Abstract: Single-molecule microscopy is advantageous to characterizing heterogeneous dynamics on the molecular level. However, there are several challenges that currently hinder the wide application of single molecule imaging in bio-chemical studies,...

Cited by 7 publications

References 120 publications

Trends in Single-Molecule Total Internal Reflection Fluorescence Imaging and Their Biological Applications with Lab-on-a-Chip Technology

Trends in Single-Molecule Total Internal Reflection Fluorescence Imaging and Their Biological Applications with Lab-on-a-Chip Technology

Fluorescence-Based Detection of Proteins and Their Interactions in Live Cells

From Deep Mutational Mapping of Allosteric Protein Landscapes to Deep Learning of Allostery and Hidden Allosteric Sites: Zooming in on “Allosteric Intersection” of Biochemical and Big Data Approaches

Contact Info

Product

Resources

About