2020
DOI: 10.3389/fphy.2019.00247
|View full text |Cite
|
Sign up to set email alerts
|

Applications and Challenges of Machine Learning to Enable Realistic Cellular Simulations

Abstract: In this perspective, we examine three key aspects of an end-to-end pipeline for realistic cellular simulations: reconstruction and segmentation of cellular structures; generation of cellular structures; and mesh generation, simulation, and data analysis. We highlight some of the relevant prior work in these distinct but overlapping areas, with a particular emphasis on current use of machine learning technologies, as well as on future opportunities.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0

Year Published

2020
2020
2021
2021

Publication Types

Select...
5
2

Relationship

2
5

Authors

Journals

citations
Cited by 8 publications
(6 citation statements)
references
References 153 publications
0
6
0
Order By: Relevance
“…STED-FCS/fluorescence cross-correlation spectroscopy can also detect changes in intermolecular interactions ( Lanzanò et al, 2017 ). In addition to the development of new measurement techniques, molecular dynamics simulations based on experimental data will become increasingly important in the future ( Okabe, 2020a ; Reshetniak et al, 2020a ; Vasan et al, 2020 ). Spine morphology and intra-spine structures, which affect diffusion, are closely related.…”
Section: Discussionmentioning
confidence: 99%
“…STED-FCS/fluorescence cross-correlation spectroscopy can also detect changes in intermolecular interactions ( Lanzanò et al, 2017 ). In addition to the development of new measurement techniques, molecular dynamics simulations based on experimental data will become increasingly important in the future ( Okabe, 2020a ; Reshetniak et al, 2020a ; Vasan et al, 2020 ). Spine morphology and intra-spine structures, which affect diffusion, are closely related.…”
Section: Discussionmentioning
confidence: 99%
“…During the segmentation process, the algorithm or researcher must carefully separate boundary signal from noise. Various schemes ranging from manual tracing, thresholding and edge-detection, to deeplearning based approaches have been employed to perform image segmentation [32,33].…”
Section: Workflow Steps From Image To Modelmentioning
confidence: 99%
“…Recent ultrastructural analyses have shown that the ER is a highly dynamic, tubular network that occupies roughly 10% of the cytosolic volume and extends from the nucleus to the cell periphery 59 . Currently, geometries used in spatial models typically do not capture the complexity of the organelle ultrastructure 53 , however, advancements in meshing algorithms and modeling pipelines pave the way for more complex geometries as model inputs 60,61 . To represent the potential effect of the convoluted ultrastructure of the SR membrane, we introduce an SR flux amplification factor to our model.…”
Section: Cell Shape Changes Pm-sr Distances In 3d Two-dimensional Immentioning
confidence: 99%