scholarly journals Comprehensive evaluation of deep learning architectures for prediction of DNA/RNA sequence binding specificities

2019 ◽  
Vol 35 (14) ◽  
pp. i269-i277 ◽  
Author(s):  
Ameni Trabelsi ◽  
Mohamed Chaabane ◽  
Asa Ben-Hur
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Rna Binding ◽  
Binding Specificity ◽  
Training Data ◽  
Supplementary Information ◽  
Recurrent Networks ◽  
Dna And Rna ◽  
Learning Architectures ◽  
Dna And Rna Binding

Abstract Motivation Deep learning architectures have recently demonstrated their power in predicting DNA- and RNA-binding specificity. Existing methods fall into three classes: Some are based on convolutional neural networks (CNNs), others use recurrent neural networks (RNNs) and others rely on hybrid architectures combining CNNs and RNNs. However, based on existing studies the relative merit of the various architectures remains unclear. Results In this study we present a systematic exploration of deep learning architectures for predicting DNA- and RNA-binding specificity. For this purpose, we present deepRAM, an end-to-end deep learning tool that provides an implementation of a wide selection of architectures; its fully automatic model selection procedure allows us to perform a fair and unbiased comparison of deep learning architectures. We find that deeper more complex architectures provide a clear advantage with sufficient training data, and that hybrid CNN/RNN architectures outperform other methods in terms of accuracy. Our work provides guidelines that can assist the practitioner in choosing an appropriate network architecture, and provides insight on the difference between the models learned by convolutional and recurrent networks. In particular, we find that although recurrent networks improve model accuracy, this comes at the expense of a loss in the interpretability of the features learned by the model. Availability and implementation The source code for deepRAM is available at https://github.com/MedChaabane/deepRAM. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning

2015 ◽  
Vol 33 (8) ◽  
pp. 831-838 ◽  
Author(s):  
Babak Alipanahi ◽  
Andrew Delong ◽  
Matthew T Weirauch ◽  
Brendan J Frey
Keyword(s):  
Deep Learning ◽  
Binding Proteins ◽  
Rna Binding ◽  
Rna Binding Proteins ◽  
Dna And Rna ◽  
Dna And Rna Binding

scholarly journals VIDHOP, viral host prediction with Deep Learning

2019 ◽  
Author(s):  
Florian Mock ◽  
Adrian Viehweger ◽  
Emanuel Barth ◽  
Manja Marz
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Viral Genome ◽  
Influenza A ◽  
Deep Neural Networks ◽  
Ebola Virus ◽  
Training Data ◽  
Supplementary Information ◽  
Virus Species ◽  
Rotavirus A

AbstractMotivationZoonosis, the natural transmission of infections from animals to humans, is a far-reaching global problem. The recent outbreaks of Zika virus, Ebola virus and Corona virus are examples of viral zoonosis, which occur more frequently due to globalization. In the case of a virus outbreak, it is helpful to know which host organism was the original carrier of the virus. Once the reservoir or intermediate host is known, it can be isolated to prevent further spreading of the viral infection. Recent approaches aim to predict a viral host based on the viral genome, often in combination with the potential host genome and arbitrarily selected features. These methods have a clear limitation in either the number of different hosts they can predict or the accuracy of their prediction.ResultsHere, we present a fast and accurate deep learning approach for viral host prediction, which is based on the viral genome sequence only. To ensure a high prediction accuracy, we developed an effective selection approach for the training data to avoid biases due to a highly unbalanced number of known sequences per virus-host combinations. We tested our deep neural network on three different virus species (influenza A, rabies lyssavirus, rotavirus A). We reached for each virus species an AUG between 0.93 and 0.98, outperforming previous approaches and allowing highly accurate predictions while only using fractions (100-400 bp) of the viral genome sequences. We show that deep neural networks are suitable to predict the host of a virus, even with a limited amount of sequences and highly unbalanced available data. The deep neural networks trained for this approach build the core of the virus-host predicting tool VIDHOP (Virus Deep learning HOst Prediction).AvailabilityThe trained models for the prediction of the host for the viruses influenza A, rabies lyssavirus, rotavirus A are implemented in the tool VIDHOP. This tool is freely available under https://github.com/flomock/vidhop.Supplementary informationSupplementary data are available at DOI 10.17605/OSF.IO/UXT7N

scholarly journals Laplacian networks: bounding indicator function smoothness for neural networks robustness

2021 ◽  
Vol 10 ◽  
Author(s):  
Carlos Lassance ◽  
Vincent Gripon ◽  
Antonio Ortega
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Supervised Learning ◽  
Indicator Function ◽  
Training Data ◽  
Theoretical Justification ◽  
The Past ◽  
Noisy Examples

For the past few years, deep learning (DL) robustness (i.e. the ability to maintain the same decision when inputs are subject to perturbations) has become a question of paramount importance, in particular in settings where misclassification can have dramatic consequences. To address this question, authors have proposed different approaches, such as adding regularizers or training using noisy examples. In this paper we introduce a regularizer based on the Laplacian of similarity graphs obtained from the representation of training data at each layer of the DL architecture. This regularizer penalizes large changes (across consecutive layers in the architecture) in the distance between examples of different classes, and as such enforces smooth variations of the class boundaries. We provide theoretical justification for this regularizer and demonstrate its effectiveness to improve robustness on classical supervised learning vision datasets for various types of perturbations. We also show it can be combined with existing methods to increase overall robustness.

Alteration of DNA and RNA Binding Activity of Human Telomere Binding Proteins Occurs during Cellular Senescence

1995 ◽  
Vol 218 (1) ◽  
pp. 241-247 ◽  
Author(s):  
Karen Hubbard ◽  
Sridevi N. Dhanaraj ◽  
Khalid A. Sethi ◽  
Janice Rhodes ◽  
Jeffrey Wilusz ◽  
...  
Keyword(s):  
Cellular Senescence ◽  
Binding Proteins ◽  
Rna Binding ◽  
Binding Activity ◽  
Dna And Rna ◽  
Human Telomere ◽  
Dna And Rna Binding

scholarly journals Patch-Based Change Detection Method for SAR Images with Label Updating Strategy

2021 ◽  
Vol 13 (7) ◽  
pp. 1236
Author(s):  
Yuanjun Shu ◽  
Wei Li ◽  
Menglong Yang ◽  
Peng Cheng ◽  
Songchen Han
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Change Detection ◽  
Detection Method ◽  
Training Data ◽  
Synthetic Aperture ◽  
Learning Method ◽  
Sar Images ◽  
Two Stage ◽  
Second Stage

Convolutional neural networks (CNNs) have been widely used in change detection of synthetic aperture radar (SAR) images and have been proven to have better precision than traditional methods. A two-stage patch-based deep learning method with a label updating strategy is proposed in this paper. The initial label and mask are generated at the pre-classification stage. Then a two-stage updating strategy is applied to gradually recover changed areas. At the first stage, diversity of training data is gradually restored. The output of the designed CNN network is further processed to generate a new label and a new mask for the following learning iteration. As the diversity of data is ensured after the first stage, pixels within uncertain areas can be easily classified at the second stage. Experiment results on several representative datasets show the effectiveness of our proposed method compared with several existing competitive methods.

scholarly journals Borrelia burgdorferiSpoVG DNA- and RNA-Binding Protein Modulates the Physiology of the Lyme Disease Spirochete

2018 ◽  
Vol 200 (12) ◽  
Author(s):  
Christina R. Savage ◽  
Brandon L. Jutras ◽  
Aaron Bestor ◽  
Kit Tilly ◽  
Patricia A. Rosa ◽  
...  
Keyword(s):  
Lyme Disease ◽  
Rna Binding ◽  
Culture Conditions ◽  
Altered Expression ◽  
Content Type ◽  
Protein Levels ◽  
Dna And Rna ◽  
Physiological Alterations ◽  
Bacterial Replication ◽  
Dna And Rna Binding

ABSTRACTThe SpoVG protein ofBorrelia burgdorferi, the Lyme disease spirochete, binds to specific sites of DNA and RNA. The bacterium regulates transcription ofspoVGduring the natural tick-mammal infectious cycle and in response to some changes in culture conditions. Bacterial levels ofspoVGmRNA and SpoVG protein did not necessarily correlate, suggesting that posttranscriptional mechanisms also control protein levels. Consistent with this, SpoVG binds to its own mRNA, adjacent to the ribosome-binding site. SpoVG also binds to two DNA sites in theglpFKDoperon and to two RNA sites inglpFKDmRNA; that operon encodes genes necessary for glycerol catabolism and is important for colonization in ticks. In addition, spirochetes engineered to dysregulatespoVGexhibited physiological alterations.IMPORTANCEB. burgdorferipersists in nature by cycling between ticks and vertebrates. Little is known about how the bacterium senses and adapts to each niche of the cycle. The present studies indicate thatB. burgdorfericontrols production of SpoVG and that this protein binds to specific sites of DNA and RNA in the genome and transcriptome, respectively. Altered expression ofspoVGexerts effects on bacterial replication and other aspects of the spirochete's physiology.

Uncertainty quantification in fault detection using convolutional neural networks

Geophysics ◽  
2021 ◽  
pp. 1-45
Author(s):  
Runhai Feng ◽  
Dario Grana ◽  
Niels Balling
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Reservoir Characterization ◽  
Epistemic Uncertainty ◽  
Confidence Regions ◽  
Training Data ◽  
Model Parameters ◽  
Sigmoid Function ◽  
Learning Tools

Segmentation of faults based on seismic images is an important step in reservoir characterization. With the recent developments of deep-learning methods and the availability of massive computing power, automatic interpretation of seismic faults has become possible. The likelihood of occurrence for a fault can be quantified using a sigmoid function. Our goal is to quantify the fault model uncertainty that is generally not captured by deep-learning tools. We propose to use the dropout approach, a regularization technique to prevent overfitting and co-adaptation in hidden units, to approximate the Bayesian inference and estimate the principled uncertainty over functions. Particularly, the variance of the learned model has been decomposed into aleatoric and epistemic parts. The proposed method is applied to a real dataset from the Netherlands F3 block with two different dropout ratios in convolutional neural networks. The aleatoric uncertainty is irreducible since it relates to the stochastic dependency within the input observations. As the number of Monte-Carlo realizations increases, the epistemic uncertainty asymptotically converges and the model standard deviation decreases, because the variability of model parameters is better simulated or explained with a larger sample size. This analysis can quantify the confidence to use fault predictions with less uncertainty. Additionally, the analysis suggests where more training data are needed to reduce the uncertainty in low confidence regions.

Convolutional Neural Network

2022 ◽  
pp. 1559-1575
Author(s):  
Mário Pereira Véstias
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Machine Learning Model ◽  
Artificial Neural

Machine learning is the study of algorithms and models for computing systems to do tasks based on pattern identification and inference. When it is difficult or infeasible to develop an algorithm to do a particular task, machine learning algorithms can provide an output based on previous training data. A well-known machine learning model is deep learning. The most recent deep learning models are based on artificial neural networks (ANN). There exist several types of artificial neural networks including the feedforward neural network, the Kohonen self-organizing neural network, the recurrent neural network, the convolutional neural network, the modular neural network, among others. This article focuses on convolutional neural networks with a description of the model, the training and inference processes and its applicability. It will also give an overview of the most used CNN models and what to expect from the next generation of CNN models.

scholarly journals Empirical Evaluation of the Effect of Optimization and Regularization Techniques on the Generalization Performance of Deep Convolutional Neural Network

2020 ◽  
Vol 10 (21) ◽  
pp. 7817
Author(s):  
Ivana Marin ◽  
Ana Kuzmanic Skelin ◽  
Tamara Grujic
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Empirical Evaluation ◽  
Training Data ◽  
Generalization Performance ◽  
Deep Model ◽  
Unseen Data ◽  
Regularization Techniques ◽  
Learning Architectures

The main goal of any classification or regression task is to obtain a model that will generalize well on new, previously unseen data. Due to the recent rise of deep learning and many state-of-the-art results obtained with deep models, deep learning architectures have become one of the most used model architectures nowadays. To generalize well, a deep model needs to learn the training data well without overfitting. The latter implies a correlation of deep model optimization and regularization with generalization performance. In this work, we explore the effect of the used optimization algorithm and regularization techniques on the final generalization performance of the model with convolutional neural network (CNN) architecture widely used in the field of computer vision. We give a detailed overview of optimization and regularization techniques with a comparative analysis of their performance with three CNNs on the CIFAR-10 and Fashion-MNIST image datasets.

Sign in / Sign up

Export Citation Format

Share Document