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 Comparative Analysis on Machine Learning and Deep Learning to Predict Post-Induction Hypotension

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4575 ◽  
Author(s):  
Jihyun Lee ◽  
Jiyoung Woo ◽  
Ah Reum Kang ◽  
Young-Seob Jeong ◽  
Woohyun Jung ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Feature Selection ◽  
Deep Learning ◽  
Random Forest ◽  
Tracheal Intubation ◽  
Feature Engineering ◽  
Learning Models ◽  
Raw Data ◽  
Vital Records

Hypotensive events in the initial stage of anesthesia can cause serious complications in the patients after surgery, which could be fatal. In this study, we intended to predict hypotension after tracheal intubation using machine learning and deep learning techniques after intubation one minute in advance. Meta learning models, such as random forest, extreme gradient boosting (Xgboost), and deep learning models, especially the convolutional neural network (CNN) model and the deep neural network (DNN), were trained to predict hypotension occurring between tracheal intubation and incision, using data from four minutes to one minute before tracheal intubation. Vital records and electronic health records (EHR) for 282 of 319 patients who underwent laparoscopic cholecystectomy from October 2018 to July 2019 were collected. Among the 282 patients, 151 developed post-induction hypotension. Our experiments had two scenarios: using raw vital records and feature engineering on vital records. The experiments on raw data showed that CNN had the best accuracy of 72.63%, followed by random forest (70.32%) and Xgboost (64.6%). The experiments on feature engineering showed that random forest combined with feature selection had the best accuracy of 74.89%, while CNN had a lower accuracy of 68.95% than that of the experiment on raw data. Our study is an extension of previous studies to detect hypotension before intubation with a one-minute advance. To improve accuracy, we built a model using state-of-art algorithms. We found that CNN had a good performance, but that random forest had a better performance when combined with feature selection. In addition, we found that the examination period (data period) is also important.

scholarly journals A Novel Deep Learning Based Sentiment Analysis of Movie using Hybrid CNN_SVM Algorithm

2019 ◽  
Vol 8 (4) ◽  
pp. 12391-12394
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Deep Learning ◽  
Random Forest ◽  
Sentiment Analysis ◽  
Business Strategy ◽  
Performance Metrics ◽  
Classification Models ◽  
Learning Models ◽  
Meaningful Information

Data flow in web is becoming high and vast, extracting useful and meaningful information from the same is especially significant. The extracted information can be utilized for enhanced decision making. The information provided by the end-users is normally in the form of comments with respect to different products and services. Sentiment analysis is effectively carried out in these kinds of compact review to give away the people’s opinion of any products. This analyzed data will be efficient to improve the business strategy. In our work the collected online movie reviews are analyzed by using machine learning sentiment classification models like Random Forest, Naive Bayes, KNN and SVM. The work has been extended with CNN and hybrid CNN-SVM deep learning models to achieve higher performance. Comparing the workings of all the above classification models for sentiment analysis based upon various performance metrics is the main objective of the paper.

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 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.

scholarly journals Machine-learning based spectral classification for spectroscopic single-molecule localization microscopy

2019 ◽  
Vol 44 (23) ◽  
pp. 5864 ◽  
Author(s):  
Zheyuan Zhang ◽  
Yang Zhang ◽  
Leslie Ying ◽  
Cheng Sun ◽  
Hao F. Zhang
Keyword(s):  
Machine Learning ◽  
Single Molecule ◽  
Spectral Classification ◽  
Localization Microscopy ◽  
Single Molecule Localization Microscopy

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
Sign in / Sign up

Export Citation Format

Share Document