Deep4mC: systematic assessment and computational prediction for DNA N4-methylcytosine sites by deep learning

Abstract DNA N4-methylcytosine (4mC) modification represents a novel epigenetic regulation. It involves in various cellular processes, including DNA replication, cell cycle and gene expression, among others. In addition to experimental identification of 4mC sites, in silico prediction of 4mC sites in the genome has emerged as an alternative and promising approach. In this study, we first reviewed the current progress in the computational prediction of 4mC sites and systematically evaluated the predictive capacity of eight conventional machine learning algorithms as well as 12 feature types commonly used in previous studies in six species. Using a representative benchmark dataset, we investigated the contribution of feature selection and stacking approach to the model construction, and found that feature optimization and proper reinforcement learning could improve the performance. We next recollected newly added 4mC sites in the six species’ genomes and developed a novel deep learning-based 4mC site predictor, namely Deep4mC. Deep4mC applies convolutional neural networks with four representative features. For species with small numbers of samples, we extended our deep learning framework with a bootstrapping method. Our evaluation indicated that Deep4mC could obtain high accuracy and robust performance with the average area under curve (AUC) values greater than 0.9 in all species (range: 0.9005–0.9722). In comparison, Deep4mC achieved an AUC value improvement from 10.14 to 46.21% when compared to previous tools in these six species. A user-friendly web server (https://bioinfo.uth.edu/Deep4mC) was built for predicting putative 4mC sites in a genome.

Download Full-text

Light Field Image Quality Enhancement by a Lightweight Deformable Deep Learning Framework for Intelligent Transportation Systems

Electronics ◽

10.3390/electronics10101136 ◽

2021 ◽

Vol 10 (10) ◽

pp. 1136

Author(s):

David Augusto Ribeiro ◽

Juan Casavílca Silva ◽

Renata Lopes Rosa ◽

Muhammad Saadi ◽

Shahid Mumtaz ◽

...

Keyword(s):

Deep Learning ◽

Image Quality ◽

Intelligent Transportation Systems ◽

Light Field ◽

State Of The Art ◽

Intelligent Transportation ◽

Transportation Systems ◽

Machine Learning Algorithms ◽

Learning Framework ◽

Reconstruction Methods

Light field (LF) imaging has multi-view properties that help to create many applications that include auto-refocusing, depth estimation and 3D reconstruction of images, which are required particularly for intelligent transportation systems (ITSs). However, cameras can present a limited angular resolution, becoming a bottleneck in vision applications. Thus, there is a challenge to incorporate angular data due to disparities in the LF images. In recent years, different machine learning algorithms have been applied to both image processing and ITS research areas for different purposes. In this work, a Lightweight Deformable Deep Learning Framework is implemented, in which the problem of disparity into LF images is treated. To this end, an angular alignment module and a soft activation function into the Convolutional Neural Network (CNN) are implemented. For performance assessment, the proposed solution is compared with recent state-of-the-art methods using different LF datasets, each one with specific characteristics. Experimental results demonstrated that the proposed solution achieved a better performance than the other methods. The image quality results obtained outperform state-of-the-art LF image reconstruction methods. Furthermore, our model presents a lower computational complexity, decreasing the execution time.

Download Full-text

MetamORF: A repository of unique short Open Reading Frames identified by both experimental and computational approaches for gene-level and meta-analysis

10.1101/2020.11.12.380055 ◽

2020 ◽

Author(s):

Sebastien A. Choteau ◽

Audrey Wagner ◽

Philippe Pierre ◽

Lionel Spinelli ◽

Christine Brun

Keyword(s):

Meta Analysis ◽

Open Reading Frames ◽

Gene Transcript ◽

Computational Approaches ◽

Cellular Processes ◽

A Genome ◽

Definition Of ◽

User Friendly ◽

Database Content ◽

Reading Frames

ABSTRACTThe development of high-throughput technologies revealed the existence of non-canonical short open reading frames (sORFs) on most eukaryotic RNAs. They are ubiquitous genetic elements highly conserved across species and suspected to be involved in numerous cellular processes. MetamORF (http://metamorf.hb.univ-amu.fr/) aims to provide a repository of unique sORFs identified in the human and mouse genomes with both experimental and computational approaches. By gathering publicly available sORF data, normalizing it and summarizing redundant information, we were able to identify a total of 1,162,675 unique sORFs. Despite the usual characterization of ORFs as short, upstream or downstream, there is currently no clear consensus regarding the definition of these categories. Thus, the data has been reprocessed using a normalized nomenclature. MetamORF enables new analyses at loci, gene, transcript and ORF levels, that should offer the possibility to address new questions regarding sORF functions in the future. The repository is available through an user-friendly web interface, allowing easy browsing, visualization, filtering over multiple criteria and export possibilities. sORFs could be searched starting from a gene, a transcript, an ORF ID, or looking in a genome area. The database content has also been made available through track hubs at UCSC Genome Browser.

Download Full-text

Brain age prediction using deep learning uncovers associated sequence variants

Nature Communications ◽

10.1038/s41467-019-13163-9 ◽

2019 ◽

Vol 10 (1) ◽

Cited By ~ 18

Author(s):

B. A. Jonsson ◽

G. Bjornsdottir ◽

T. E. Thorgeirsson ◽

L. M. Ellingsen ◽

G. Bragi Walters ◽

...

Keyword(s):

Deep Learning ◽

Genome Wide Association Study ◽

Structural Mri ◽

Machine Learning Algorithms ◽

Age Difference ◽

Sequence Variants ◽

Uk Biobank ◽

A Genome ◽

The Uk ◽

Brain Age

AbstractMachine learning algorithms can be trained to estimate age from brain structural MRI. The difference between an individual’s predicted and chronological age, predicted age difference (PAD), is a phenotype of relevance to aging and brain disease. Here, we present a new deep learning approach to predict brain age from a T1-weighted MRI. The method was trained on a dataset of healthy Icelanders and tested on two datasets, IXI and UK Biobank, utilizing transfer learning to improve accuracy on new sites. A genome-wide association study (GWAS) of PAD in the UK Biobank data (discovery set: $$N=12378$$N=12378, replication set: $$N=4456$$N=4456) yielded two sequence variants, rs1452628-T ($$\beta =-0.08$$β=−0.08, $$P=1.15\times{10}^{-9}$$P=1.15×10−9) and rs2435204-G ($$\beta =0.102$$β=0.102, $$P=9.73\times 1{0}^{-12}$$P=9.73×10−12). The former is near KCNK2 and correlates with reduced sulcal width, whereas the latter correlates with reduced white matter surface area and tags a well-known inversion at 17q21.31 (H2).

Download Full-text

A deep learning framework combined with word embedding to identify DNA replication origins

Scientific Reports ◽

10.1038/s41598-020-80670-x ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Feng Wu ◽

Runtao Yang ◽

Chengjin Zhang ◽

Lina Zhang

Keyword(s):

Deep Learning ◽

Dna Replication ◽

Machine Learning Algorithms ◽

Word Embedding ◽

Correct Identification ◽

Replication Origins ◽

Gene Sequences ◽

Replication Process ◽

Similarity Reduction ◽

Learning Framework

AbstractThe DNA replication influences the inheritance of genetic information in the DNA life cycle. As the distribution of replication origins (ORIs) is the major determinant to precisely regulate the replication process, the correct identification of ORIs is significant in giving an insightful understanding of DNA replication mechanisms and the regulatory mechanisms of genetic expressions. For eukaryotes in particular, multiple ORIs exist in each of their gene sequences to complete the replication in a reasonable period of time. To simplify the identification process of eukaryote’s ORIs, most of existing methods are developed by traditional machine learning algorithms, and target to the gene sequences with a fixed length. Consequently, the identification results are not satisfying, i.e. there is still great room for improvement. To break through the limitations in previous studies, this paper develops sequence segmentation methods, and employs the word embedding technique, ‘Word2vec’, to convert gene sequences into word vectors, thereby grasping the inner correlations of gene sequences with different lengths. Then, a deep learning framework to perform the ORI identification task is constructed by a convolutional neural network with an embedding layer. On the basis of the analysis of similarity reduction dimensionality diagram, Word2vec can effectively transform the inner relationship among words into numerical feature. For four species in this study, the best models are obtained with the overall accuracy of 0.975, 0.765, 0.885, 0.967, the Matthew’s correlation coefficient of 0.940, 0.530, 0.771, 0.934, and the AUC of 0.975, 0.800, 0.888, 0.981, which indicate that the proposed predictor has a stable ability and provide a high confidence coefficient to classify both of ORIs and non-ORIs. Compared with state-of-the-art methods, the proposed predictor can achieve ORI identification with significant improvement. It is therefore reasonable to anticipate that the proposed method will make a useful high throughput tool for genome analysis.

Download Full-text

Deep Learning for Deep Waters: An Expert-in-the-Loop Machine Learning Framework for Marine Sciences

Journal of Marine Science and Engineering ◽

10.3390/jmse9020169 ◽

2021 ◽

Vol 9 (2) ◽

pp. 169

Author(s):

Igor Ryazanov ◽

Amanda T. Nylund ◽

Debabrota Basu ◽

Ida-Maja Hassellöv ◽

Alexander Schliep

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Machine Learning Algorithms ◽

Full Potential ◽

Acoustic Data ◽

Learning Framework ◽

Machine Learning Methods ◽

Deep Waters ◽

The One ◽

Relative Scarcity

Driven by the unprecedented availability of data, machine learning has become a pervasive and transformative technology across industry and science. Its importance to marine science has been codified as one goal of the UN Ocean Decade. While increasing amounts of, for example, acoustic marine data are collected for research and monitoring purposes, and machine learning methods can achieve automatic processing and analysis of acoustic data, they require large training datasets annotated or labelled by experts. Consequently, addressing the relative scarcity of labelled data is, besides increasing data analysis and processing capacities, one of the main thrust areas. One approach to address label scarcity is the expert-in-the-loop approach which allows analysis of limited and unbalanced data efficiently. Its advantages are demonstrated with our novel deep learning-based expert-in-the-loop framework for automatic detection of turbulent wake signatures in echo sounder data. Using machine learning algorithms, such as the one presented in this study, greatly increases the capacity to analyse large amounts of acoustic data. It would be a first step in realising the full potential of the increasing amount of acoustic data in marine sciences.

Download Full-text

Deep learning framework for leaf damage identification

Concurrent Engineering ◽

10.1177/1063293x21994953 ◽

2021 ◽

pp. 1063293X2199495

Author(s):

Eddy Sánchez-DelaCruz ◽

Juan P Salazar López ◽

David Lara Alabazares ◽

Edgar Tello Leal ◽

Mirta Fuentes-Ramos

Keyword(s):

Image Processing ◽

Deep Learning ◽

Crop Production ◽

Damage Identification ◽

Machine Learning Algorithms ◽

Leaf Damage ◽

Nutritional Deficiencies ◽

Learning Framework ◽

Valencia Orange ◽

Local Plants

Foliar disease is common problem in plants; it appears as an abnormal change in the plant’s characteristics, such as the presence of lesions and discolorations, among others. These problems may be related to plant growth, which causes a decrease in crop production, impacting the agricultural economy. The causes of leaf damage can be variable, such as bacteria, viruses, nutritional deficiencies, or even consequences of climate change. Motivated to find a solution for this problem, we aim that using image processing and machine learning algorithms (MLA), these symptomatic characteristics of the leaf can be used to classify diseases. Then, contributions of this research are (i) the use of image processing methods in the feature extraction (characteristics), and (ii) the combination of assembled algorithms with deep learning to classify foliar features of Valencia orange (Citrus Sinensis) tree leaves. Combining these two classification approaches, we get optimal rates in binary datasets and highly competitive percentages in multiclass sets. This, using a database of images of three types of foliar damage of local plants. Result of combination of these two classification strategies is an exceptional reliable alternative for leaf damage identification of orange and other citrus plants.

Download Full-text

A hybrid deep learning framework for predicting the protein-protein interaction between virus and host

10.21203/rs.3.rs-506156/v1 ◽

2021 ◽

Author(s):

Lei Deng ◽

Wenjuan Nie ◽

Jiaojiao Zhao ◽

Jingpu Zhang

Keyword(s):

Deep Learning ◽

Viral Infection ◽

Protein Interaction ◽

Protein Sequence ◽

Independent Set ◽

Relevant Information ◽

Machine Learning Algorithms ◽

Sequence Information ◽

Protein Protein Interaction ◽

Learning Framework

Abstract Background: Viral infection and diseases are caused by various viruses involved in the protein-protein interaction (PPI) between virus and host, which are a threat to human health. Studying the virus-host PPI is beneficial to apprehending the mechanism of viral infection and developing new treatment drugs. Although several computational methods for predicting the virus-host PPI have been proposed, most of them are supported by the machine learning algorithms, making the hidden high-level feature difficult to be extracted. Results: We proposed a novel hybrid deep learning framework combined with four CNN layers and LSTM to predict the virus-host PPI only using protein sequence information. CNN can extract the nonlinear position-related features of protein sequence, and LSTM can obtain the long-term relevant information. L1-regularized logistic regression is applied to eliminate the noise and redundant information. Our model achieved the best performance on the benchmark dataset and independent set compared with other existing methods. Conclusion: Our method, through the hybrid deep neural network, is useful for predicting virus-host PPI using protein sequence alone, and achieved the best prediction performance compared with other existing methods, which is promising on the virus-host PPI prediction

Download Full-text

Robust Malware Detection using Residual Attention Network

10.36227/techrxiv.13385291 ◽

2020 ◽

Author(s):

Shamika Ganesan ◽

vinayakumar R ◽

Moez Krichen ◽

Sowmya V ◽

Roobaea Alroobaea ◽

...

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Learning Algorithms ◽

Malware Detection ◽

Machine Learning Algorithms ◽

Detection Methods ◽

Attention Network ◽

Conventional Machine

In this paper, we explore the use of an attention based mechanism known as Residual Attention for malware detection and compare this with existing CNN based methods and conventional Machine Learning algorithms with the help of GIST features. The proposed method outperformed traditional malware detection methods which use Machine Learning and CNN based Deep Learning algorithms, by demonstrating an accuracy of 99.25%.

Download Full-text

Automating Visual Blockage Classification of Culverts with Deep Learning

Applied Sciences ◽

10.3390/app11167561 ◽

2021 ◽

Vol 11 (16) ◽

pp. 7561

Author(s):

Umair Iqbal ◽

Johan Barthelemy ◽

Wanqing Li ◽

Pascal Perez

Keyword(s):

Machine Learning ◽

Deep Learning ◽

False Negative ◽

Hydraulic Modeling ◽

Machine Learning Algorithms ◽

Visual Features ◽

Learning Approaches ◽

Learning Models ◽

Conventional Machine

Blockage of culverts by transported debris materials is reported as the salient contributor in originating urban flash floods. Conventional hydraulic modeling approaches had no success in addressing the problem primarily because of the unavailability of peak floods hydraulic data and the highly non-linear behavior of debris at the culvert. This article explores a new dimension to investigate the issue by proposing the use of intelligent video analytics (IVA) algorithms for extracting blockage related information. The presented research aims to automate the process of manual visual blockage classification of culverts from a maintenance perspective by remotely applying deep learning models. The potential of using existing convolutional neural network (CNN) algorithms (i.e., DarkNet53, DenseNet121, InceptionResNetV2, InceptionV3, MobileNet, ResNet50, VGG16, EfficientNetB3, NASNet) is investigated over a dataset from three different sources (i.e., images of culvert openings and blockage (ICOB), visual hydrology-lab dataset (VHD), synthetic images of culverts (SIC)) to predict the blockage in a given image. Models were evaluated based on their performance on the test dataset (i.e., accuracy, loss, precision, recall, F1 score, Jaccard Index, region of convergence (ROC) curve), floating point operations per second (FLOPs) and response times to process a single test instance. Furthermore, the performance of deep learning models was benchmarked against conventional machine learning algorithms (i.e., SVM, RF, xgboost). In addition, the idea of classifying deep visual features extracted by CNN models (i.e., ResNet50, MobileNet) using conventional machine learning approaches was also implemented in this article. From the results, NASNet was reported most efficient in classifying the blockage images with the 5-fold accuracy of 85%; however, MobileNet was recommended for the hardware implementation because of its improved response time with 5-fold accuracy comparable to NASNet (i.e., 78%). Comparable performance to standard CNN models was achieved for the case where deep visual features were classified using conventional machine learning approaches. False negative (FN) instances, false positive (FP) instances and CNN layers activation suggested that background noise and oversimplified labelling criteria were two contributing factors in the degraded performance of existing CNN algorithms. A framework for partial automation of the visual blockage classification process was proposed, given that none of the existing models was able to achieve high enough accuracy to completely automate the manual process. In addition, a detection-classification pipeline with higher blockage classification accuracy (i.e., 94%) has been proposed as a potential future direction for practical implementation.

Download Full-text

Mood Detection from Physical and Neurophysical Data Using Deep Learning Models

Complexity ◽

10.1155/2019/6434578 ◽

2019 ◽

Vol 2019 ◽

pp. 1-15

Author(s):

Zeynep Hilal Kilimci ◽

Aykut Güven ◽

Mitat Uysal ◽

Selim Akyokus

Keyword(s):

Neural Network ◽

Machine Learning ◽

Deep Learning ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Behavioral Data ◽

Support Vector ◽

Learning Models ◽

Physical Data ◽

Conventional Machine

Nowadays, smart devices as a part of daily life collect data about their users with the help of sensors placed on them. Sensor data are usually physical data but mobile applications collect more than physical data like device usage habits and personal interests. Collected data are usually classified as personal, but they contain valuable information about their users when it is analyzed and interpreted. One of the main purposes of personal data analysis is to make predictions about users. Collected data can be divided into two major categories: physical and behavioral data. Behavioral data are also named as neurophysical data. Physical and neurophysical parameters are collected as a part of this study. Physical data contains measurements of the users like heartbeats, sleep quality, energy, movement/mobility parameters. Neurophysical data contain keystroke patterns like typing speed and typing errors. Users’ emotional/mood statuses are also investigated by asking daily questions. Six questions are asked to the users daily in order to determine the mood of them. These questions are emotion-attached questions, and depending on the answers, users’ emotional states are graded. Our aim is to show that there is a connection between users’ physical/neurophysical parameters and mood/emotional conditions. To prove our hypothesis, we collect and measure physical and neurophysical parameters of 15 users for 1 year. The novelty of this work to the literature is the usage of both combinations of physical and neurophysical parameters. Another novelty is that the emotion classification task is performed by both conventional machine learning algorithms and deep learning models. For this purpose, Feedforward Neural Network (FFNN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) neural network are employed as deep learning methodologies. Multinomial Naïve Bayes (MNB), Support Vector Regression (SVR), Decision Tree (DT), Random Forest (RF), and Decision Integration Strategy (DIS) are evaluated as conventional machine learning algorithms. To the best of our knowledge, this is the very first attempt to analyze the neurophysical conditions of the users by evaluating deep learning models for mood analysis and enriching physical characteristics with neurophysical parameters. Experiment results demonstrate that the utilization of deep learning methodologies and the combination of both physical and neurophysical parameters enhances the classification success of the system to interpret the mood of the users. A wide range of comparative and extensive experiments shows that the proposed model exhibits noteworthy results compared to the state-of-art studies.

Download Full-text