scholarly journals MethylSPWNet and MethylCapsNet: Biologically Motivated Organization of DNAm Neural Networks, Inspired by Capsule Networks

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Joshua J. Levy ◽  
Youdinghuan Chen ◽  
Nasim Azizgolshani ◽  
Curtis L. Petersen ◽  
Alexander J. Titus ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cpg Island ◽  
Regulation Of Gene Expression ◽  
Gene Promoter ◽  
Biological Knowledge ◽  
Learning Approaches ◽  
Biologically Relevant ◽  
Prior Biological Knowledge ◽  
User Friendly

AbstractDNA methylation (DNAm) alterations have been heavily implicated in carcinogenesis and the pathophysiology of diseases through upstream regulation of gene expression. DNAm deep-learning approaches are able to capture features associated with aging, cell type, and disease progression, but lack incorporation of prior biological knowledge. Here, we present modular, user-friendly deep-learning methodology and software, MethylCapsNet and MethylSPWNet, that group CpGs into biologically relevant capsules—such as gene promoter context, CpG island relationship, or user-defined groupings—and relate them to diagnostic and prognostic outcomes. We demonstrate these models’ utility on 3,897 individuals in the classification of central nervous system (CNS) tumors. MethylCapsNet and MethylSPWNet provide an opportunity to increase DNAm deep-learning analyses’ interpretability by enabling a flexible organization of DNAm data into biologically relevant capsules.

scholarly journals Investigation of Capsule-Inspired Neural Network Approaches for DNA Methylation

2020 ◽  
Author(s):  
Joshua J. Levy ◽  
Youdinghuan Chen ◽  
Nasim Azizgolshani ◽  
Curtis L. Peterson ◽  
Alexander J. Titus ◽  
...  
Keyword(s):  
Dna Methylation ◽  
Deep Learning ◽  
Cpg Island ◽  
Gene Promoter ◽  
Biological Knowledge ◽  
Learning Approaches ◽  
Biologically Relevant ◽  
Prior Biological Knowledge ◽  
Learning Software ◽  
Network Approaches

AbstractDNA methylation (DNAm) alterations are implicated with aging and diseases by regulating gene expression. DNAm deep-learning approaches can capture features associated with aging, cell type, and disease progression, but lack incorporation of prior biological knowledge. We present deep-learning software, MethylCapsNet and MethylSPWNet, that group CpGs into user-specified or predefined biologically relevant groupings (eg. gene promoter or CpG island context) related to diagnostic and prognostic outcomes. We train our models on a cohort (n=3,897) to classify central nervous system tumors and compare to existing approaches. Our methodology presents opportunities to increase interpretability of disease mechanisms through utilization of biologically relevant annotations.

scholarly journals Fashion Product Classification through Deep Learning and Computer Vision

2019 ◽  
Vol 9 (7) ◽  
pp. 1385 ◽  
Author(s):  
Luca Donati ◽  
Eleonora Iotti ◽  
Giulio Mordonini ◽  
Andrea Prati
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Feature Extraction ◽  
Deep Learning ◽  
Template Matching ◽  
Learning Approaches ◽  
Visual Classification ◽  
Product Classification ◽  
Processing Techniques

Visual classification of commercial products is a branch of the wider fields of object detection and feature extraction in computer vision, and, in particular, it is an important step in the creative workflow in fashion industries. Automatically classifying garment features makes both designers and data experts aware of their overall production, which is fundamental in order to organize marketing campaigns, avoid duplicates, categorize apparel products for e-commerce purposes, and so on. There are many different techniques for visual classification, ranging from standard image processing to machine learning approaches: this work, made by using and testing the aforementioned approaches in collaboration with Adidas AG™, describes a real-world study aimed at automatically recognizing and classifying logos, stripes, colors, and other features of clothing, solely from final rendering images of their products. Specifically, both deep learning and image processing techniques, such as template matching, were used. The result is a novel system for image recognition and feature extraction that has a high classification accuracy and which is reliable and robust enough to be used by a company like Adidas. This paper shows the main problems and proposed solutions in the development of this system, and the experimental results on the Adidas AG™ dataset.

scholarly journals MethylNet: An Automated and Modular Deep Learning Approach for DNA Methylation Analysis

2019 ◽  
Author(s):  
Joshua J. Levy ◽  
Alexander J. Titus ◽  
Curtis L. Petersen ◽  
Youdinghuan Chen ◽  
Lucas A. Salas ◽  
...  
Keyword(s):  
Dna Methylation ◽  
Deep Learning ◽  
Multiple Hypothesis Testing ◽  
Cellular Heterogeneity ◽  
Learning Approaches ◽  
Disease Heterogeneity ◽  
Epigenetic Regulator ◽  
User Friendly ◽  
Dna Methylation Analysis ◽  
Linear Nature

AbstractBackgroundDNA methylation (DNAm) is an epigenetic regulator of gene expression programs that can be altered by environmental exposures, aging, and in pathogenesis. Traditional analyses that associate DNAm alterations with phenotypes suffer from multiple hypothesis testing and multi-collinearity due to the high-dimensional, continuous, interacting and non-linear nature of the data. Deep learning analyses have shown much promise to study disease heterogeneity. DNAm deep learning approaches have not yet been formalized into user-friendly frameworks for execution, training, and interpreting models. Here, we describe MethylNet, a DNAm deep learning method that can construct embeddings, make predictions, generate new data, and uncover unknown heterogeneity with minimal user supervision.ResultsThe results of our experiments indicate that MethylNet can study cellular differences, grasp higher order information of cancer sub-types, estimate age and capture factors associated with smoking in concordance with known differences.ConclusionThe ability of MethylNet to capture nonlinear interactions presents an opportunity for further study of unknown disease, cellular heterogeneity and aging processes.

scholarly journals DeepOS: pan-cancer prognosis estimation from RNA-sequencing data

2021 ◽  
Author(s):  
Marie PAVAGEAU ◽  
Louis REBAUD ◽  
Daphne MOREL ◽  
Stergios CHRISTODOULIDIS ◽  
Eric DEUTSCH ◽  
...  
Keyword(s):  
Deep Learning ◽  
Rna Sequencing ◽  
Mean Squared Error ◽  
Cancer Prognosis ◽  
Biological Knowledge ◽  
Survival Prediction ◽  
Sequencing Data ◽  
Biologically Relevant ◽  
Pan Cancer ◽  
Prognosis Estimation

RNA sequencing (RNAseq) analysis offers a tumor centered approach of growing interest for personalizing cancer care. However, existing methods , including deep learning models, struggle to reach satisfying performances on survival prediction based upon pan-cancer RNAseq data. Here, we present DeepOS, a novel deep learning model that predicts overall survival (OS) from pancancer RNAseq with a concordance index of 0.715 and a survival AUC of 0.752 across 33 TCGA tumor types whilst tested on an unseen test cohort. DeepOS notably uses (i) prior biological knowledge to condense inputs dimensionality, (ii) transfer learning to enlarge its training capacity through pretraining on organ prediction, and (iii) mean squared error adapted to survival loss function; all of which contributed to improve the model performances. Interpretation showed that DeepOS learned biologically relevant prognosis biomarkers. Altogether, DeepOS achieved unprecedented and consistent performances on pan-cancer prognosis estimation from individual RNA-seq data.

scholarly journals Deep Learning Approaches to Automated Video Classification of Upper Limb Tension Test

Healthcare ◽  
2021 ◽  
Vol 9 (11) ◽  
pp. 1579
Author(s):  
Wansuk Choi ◽  
Seoyoon Heo
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
High Performance ◽  
Model Fit ◽  
Fine Tuning ◽  
Learning Approaches ◽  
Video Classification ◽  
Video Clips ◽  
Performance Computing

The purpose of this study was to classify ULTT videos through transfer learning with pre-trained deep learning models and compare the performance of the models. We conducted transfer learning by combining a pre-trained convolution neural network (CNN) model into a Python-produced deep learning process. Videos were processed on YouTube and 103,116 frames converted from video clips were analyzed. In the modeling implementation, the process of importing the required modules, performing the necessary data preprocessing for training, defining the model, compiling, model creation, and model fit were applied in sequence. Comparative models were Xception, InceptionV3, DenseNet201, NASNetMobile, DenseNet121, VGG16, VGG19, and ResNet101, and fine tuning was performed. They were trained in a high-performance computing environment, and validation and loss were measured as comparative indicators of performance. Relatively low validation loss and high validation accuracy were obtained from Xception, InceptionV3, and DenseNet201 models, which is evaluated as an excellent model compared with other models. On the other hand, from VGG16, VGG19, and ResNet101, relatively high validation loss and low validation accuracy were obtained compared with other models. There was a narrow range of difference between the validation accuracy and the validation loss of the Xception, InceptionV3, and DensNet201 models. This study suggests that training applied with transfer learning can classify ULTT videos, and that there is a difference in performance between models.

scholarly journals Investigating Deep Learning Approaches on the Security Analysis of Cryptographic Algorithms

Cryptography ◽  
2021 ◽  
Vol 5 (4) ◽  
pp. 30
Author(s):  
Bang Yuan Chong ◽  
Iftekhar Salam
Keyword(s):  
Deep Learning ◽  
Security Analysis ◽  
Data Encryption ◽  
Classification Model ◽  
Learning Approaches ◽  
Secret Key ◽  
Data Encryption Standard ◽  
Random Guess ◽  
Better Than

This paper studies the use of deep learning (DL) models under a known-plaintext scenario. The goal of the models is to predict the secret key of a cipher using DL techniques. We investigate the DL techniques against different ciphers, namely, Simplified Data Encryption Standard (S-DES), Speck, Simeck and Katan. For S-DES, we examine the classification of the full key set, and the results are better than a random guess. However, we found that it is difficult to apply the same classification model beyond 2-round Speck. We also demonstrate that DL models trained under a known-plaintext scenario can successfully recover the random key of S-DES. However, the same method has been less successful when applied to modern ciphers Speck, Simeck, and Katan. The ciphers Simeck and Katan are further investigated using the DL models but with a text-based key. This application found the linear approximations between the plaintext–ciphertext pairs and the text-based key.

Arrhythmia Diagnosis through ECG Signal Classification Using A Hybrid CNN-LSTM Model: Comparison with current Deep Learning Approaches (Preprint)

2020 ◽  
Author(s):  
Nicos Maglaveras ◽  
Georgios Petmezas ◽  
Vassilis Kilintzis ◽  
Leandros Stefanopoulos ◽  
Andreas Tzavelis ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cardiac Arrhythmias ◽  
Model Comparison ◽  
Temporal Dynamics ◽  
Experimental Studies ◽  
Signal Classification ◽  
Ecg Signal ◽  
Learning Approaches ◽  
Different Types

BACKGROUND Electrocardiogram (ECG) recording and interpretation is the most common method used for the diagnosis of cardiac arrhythmias, nonetheless this process requires significant expertise and effort from the doctors’ perspective. Automated ECG signal classification could be a useful technique for the accurate detection and classification of several types of arrhythmias within a short timeframe. OBJECTIVE To review current approaches using state-of-the-art CNNs and deep learning methodologies in arrhythmia detection via ECG feature classification techniques and propose an optimised architecture capable of different types of arrhythmia diagnosis using publicly existing annotated arrhythmia databases from the MIT-BIH databases available at PHYSIONET (physionet.org) . METHODS A hybrid CNN-LSTM deep learning model is proposed to classify beats derived from two large ECG databases. The approach is proposed after a systematic review of current AI/DL methods applied in different types of arrhythmia diagnosis using the same public MIT-BIH databases. In the proposed architecture the CNN part carries out feature extraction and dimensionality reduction, and the LSTM part performs classification of the encoded ECG beat signals. RESULTS In experimental studies conducted with the MIT-BIH Arrhythmia and the MIT-BIH Atrial Fibrillation Databases average accuracies of 96.82% and 96.65% were noted respectively. CONCLUSIONS The proposed system can be used for arrhythmia diagnosis in clinical and mHealth applications managing a number of prevalent arrhythmias such as VT, AFIB, LBBB etc. The capability of CNNs to reduce the ECG beat signal’s size and extract its main features can be effectively combined with the LSTMs’ capability to learn the temporal dynamics of the input data for the accurate and automatic recognition of several types of cardiac arrhythmias. CLINICALTRIAL Not applicable.

scholarly journals A High-Accuracy Model Average Ensemble of Convolutional Neural Networks for Classification of Cloud Image Patches on Small Datasets

2019 ◽  
Vol 9 (21) ◽  
pp. 4500 ◽  
Author(s):  
Phung ◽  
Rhee
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Classification Accuracy ◽  
Complete Solution ◽  
Large Data ◽  
High Accuracy ◽  
Learning Approaches ◽  
Model Average ◽  
Image Patches

Research on clouds has an enormous influence on sky sciences and related applications, and cloud classification plays an essential role in it. Much research has been conducted which includes both traditional machine learning approaches and deep learning approaches. Compared with traditional machine learning approaches, deep learning approaches achieved better results. However, most deep learning models need large data to train due to the large number of parameters. Therefore, they cannot get high accuracy in case of small datasets. In this paper, we propose a complete solution for high accuracy of classification of cloud image patches on small datasets. Firstly, we designed a suitable convolutional neural network (CNN) model for small datasets. Secondly, we applied regularization techniques to increase generalization and avoid overfitting of the model. Finally, we introduce a model average ensemble to reduce the variance of prediction and increase the classification accuracy. We experiment the proposed solution on the Singapore whole-sky imaging categories (SWIMCAT) dataset, which demonstrates perfect classification accuracy for most classes and confirms the robustness of the proposed model.

Sign in / Sign up

Export Citation Format

Share Document