scholarly journals 3D Structure From 2D Microscopy Images Using Deep Learning

2021 ◽  
Vol 1 ◽  
Author(s):  
Benjamin Blundell ◽  
Christian Sieben ◽  
Suliana Manley ◽  
Ed Rosten ◽  
QueeLim Ch’ng ◽  
...  
Keyword(s):  
Deep Learning ◽  
Single Molecule ◽  
Structural Model ◽  
Protein Complexes ◽  
3D Structure ◽  
Data Set ◽  
Localization Microscopy ◽  
Single Structure ◽  
Microscopy Images ◽  
Single Molecule Localization Microscopy

Understanding the structure of a protein complex is crucial in determining its function. However, retrieving accurate 3D structures from microscopy images is highly challenging, particularly as many imaging modalities are two-dimensional. Recent advances in Artificial Intelligence have been applied to this problem, primarily using voxel based approaches to analyse sets of electron microscopy images. Here we present a deep learning solution for reconstructing the protein complexes from a number of 2D single molecule localization microscopy images, with the solution being completely unconstrained. Our convolutional neural network coupled with a differentiable renderer predicts pose and derives a single structure. After training, the network is discarded, with the output of this method being a structural model which fits the data-set. We demonstrate the performance of our system on two protein complexes: CEP152 (which comprises part of the proximal toroid of the centriole) and centrioles.

A literature review of localization methods and emergence of deep learning in single-molecule localization microscopy

2020 ◽  
Author(s):  
Anish Mukherjee
Keyword(s):  
Deep Learning ◽  
Single Molecule ◽  
Super Resolution ◽  
Point Sources ◽  
Learning Approaches ◽  
Localization Algorithm ◽  
Localization Microscopy ◽  
Trade Offs ◽  
Emitter Localization ◽  
Single Molecule Localization Microscopy

The quality of super-resolution images largely depends on the performance of the emitter localization algorithm used to localize point sources. In this article, an overview of the various techniques which are used to localize point sources in single-molecule localization microscopy are discussed and their performances are compared. This overview can help readers to select a localization technique for their application. Also, an overview is presented about the emergence of deep learning methods that are becoming popular in various stages of single-molecule localization microscopy. The state of the art deep learning approaches are compared to the traditional approaches and the trade-offs of selecting an algorithm for localization are discussed.

scholarly journals Caveolae and scaffold detection from single molecule localization microscopy data using deep learning

2019 ◽  
Author(s):  
Ismail M. Khater ◽  
Stephane T. Aroca-Ouellette ◽  
Fanrui Meng ◽  
Ivan Robert Nabi ◽  
Ghassan Hamarneh
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Random Forest ◽  
Single Molecule ◽  
Adaptor Protein ◽  
Point Clouds ◽  
Learning Models ◽  
Localization Microscopy ◽  
Biological Structures ◽  
Single Molecule Localization Microscopy

AbstractCaveolae are plasma membrane invaginations whose formation requires caveolin-1 (Cav1), the adaptor protein polymerase I, and the transcript release factor (PTRF or CAVIN1). Caveolae have an important role in cell functioning, signaling, and disease. In the absence of CAVIN1/PTRF, Cav1 forms non-caveolar membrane domains called scaffolds. In this work, we train machine learning models to automatically distinguish between caveolae and scaffolds from single molecule localization microscopy (SMLM) data. We apply machine learning algorithms to discriminate biological structures from SMLM data. Our work is the first that is leveraging machine learning approaches (including deep learning models) to automatically identifying biological structures from SMLM data. In particular, we develop and compare three binary classification methods to identify whether or not a given 3D cluster of Cav1 proteins is a caveolae. The first uses a random forest classifier applied to 28 hand-crafted/designed features, the second uses a convolutional neural net (CNN) applied to a projection of the point clouds onto three planes, and the third uses a PointNet model, a recent development that can directly take point clouds as its input. We validate our methods on a dataset of super-resolution microscopy images of PC3 prostate cancer cells labeled for Cav1. Specifically, we have images from two cell populations: 10 PC3 and 10 CAVIN1/PTRF-transfected PC3 cells (PC3-PTRF cells) that form caveolae. We obtained a balanced set of 1714 different cellular structures. Our results show that both the random forest on hand-designed features and the deep learning approach achieve high accuracy in distinguishing the intrinsic features of the caveolae and non-caveolae biological structures. More specifically, both random forest and deep CNN classifiers achieve classification accuracy reaching 94% on our test set, while the PointNet model only reached 83% accuracy. We also discuss the pros and cons of the different approaches.

scholarly journals Caveolae and scaffold detection from single molecule localization microscopy data using deep learning

PLoS ONE ◽  
2019 ◽  
Vol 14 (8) ◽  
pp. e0211659 ◽  
Author(s):  
Ismail M. Khater ◽  
Stephane T. Aroca-Ouellette ◽  
Fanrui Meng ◽  
Ivan Robert Nabi ◽  
Ghassan Hamarneh
Keyword(s):  
Deep Learning ◽  
Single Molecule ◽  
Localization Microscopy ◽  
Microscopy Data ◽  
Single Molecule Localization Microscopy

scholarly journals Single-Molecule Localization Microscopy to Study Protein Organization in the Filamentous Fungus Trichoderma atroviride

Molecules ◽  
2020 ◽  
Vol 25 (14) ◽  
pp. 3199
Author(s):  
Alexander W.A.F. Reismann ◽  
Lea Atanasova ◽  
Susanne Zeilinger ◽  
Gerhard J. Schütz
Keyword(s):  
Single Molecule ◽  
Filamentous Fungus ◽  
Mammalian Cells ◽  
Hyphal Growth ◽  
Trichoderma Atroviride ◽  
Localization Microscopy ◽  
Family Protein ◽  
Mycoparasitic Fungus ◽  
Microscopy Images ◽  
Single Molecule Localization Microscopy

Single-molecule localization microscopy has boosted our understanding of biological samples by offering access to subdiffraction resolution using fluorescence microscopy methods. While in standard mammalian cells this approach has found wide-spread use, its application to filamentous fungi has been scarce. This is mainly due to experimental challenges that lead to high amounts of background signal because of ample autofluorescence. Here, we report the optimization of labeling, imaging and data analysis protocols to yield the first single-molecule localization microscopy images of the filamentous fungus Trichoderma atroviride. As an example, we show the spatial distribution of the Sur7 tetraspanin-family protein Sfp2 required for hyphal growth and cell wall stability in this mycoparasitic fungus.

scholarly journals Accelerating multicolor spectroscopic single-molecule localization microscopy using deep learning

2020 ◽  
Vol 11 (5) ◽  
pp. 2705
Author(s):  
Sunil Kumar Gaire ◽  
Yang Zhang ◽  
Hongyu Li ◽  
Ray Yu ◽  
Hao F. Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Single Molecule ◽  
Localization Microscopy ◽  
Single Molecule Localization Microscopy

scholarly journals A real-time compression library for microscopy images

2017 ◽  
Author(s):  
Bálint Balázs ◽  
Joran Deschamps ◽  
Marvin Albert ◽  
Jonas Ries ◽  
Lars Hufnagel
Keyword(s):  
Real Time ◽  
Single Molecule ◽  
Imaging Techniques ◽  
Intrinsic Noise ◽  
Light Sheet ◽  
Localization Microscopy ◽  
Time Compression ◽  
Light Sheet Microscopy ◽  
Microscopy Images ◽  
Single Molecule Localization Microscopy

AbstractFluorescence imaging techniques such as single molecule localization microscopy, high-content screening and light-sheet microscopy are producing ever-larger datasets, which poses increasing challenges in data handling and data sharing. Here, we introduce a real-time compression library that allows for very fast (beyond 1 GB/s) compression and de-compression of microscopy datasets during acquisition. In addition to an efficient lossless mode, our algorithm also includes a lossy option, which limits pixel deviations to the intrinsic noise level of the image and yields compression ratio of up to 100-fold. We present a detailed performance analysis of the different compression modes for various biological samples and imaging modalities.

Sign in / Sign up

Export Citation Format

Share Document