Predicting enhancer-promoter interactions by deep learning and matching heuristic

2020 ◽  
Author(s):  
Xiaoping Min ◽  
Congmin Ye ◽  
Xiangrong Liu ◽  
Xiangxiang Zeng
Keyword(s):  
Dna Sequences ◽  
Predictive Performance ◽  
Proposed Model ◽  
Computational Speed ◽  
Benchmark Datasets ◽  
Multiple Cell ◽  
Novel Method ◽  
Comparative Results ◽  
Genome Scale ◽  
Gated Recurrent Unit

Abstract Enhancer-promoter interactions (EPIs) play an important role in transcriptional regulation. Recently, machine learning-based methods have been widely used in the genome-scale identification of EPIs due to their promising predictive performance. In this paper, we propose a novel method, termed EPI-DLMH, for predicting EPIs with the use of DNA sequences only. EPI-DLMH consists of three major steps. First, a two-layer convolutional neural network is used to learn local features, and an bidirectional gated recurrent unit network is used to capture long-range dependencies on the sequences of promoters and enhancers. Second, an attention mechanism is used for focusing on relatively important features. Finally, a matching heuristic mechanism is introduced for the exploration of the interaction between enhancers and promoters. We use benchmark datasets in evaluating and comparing the proposed method with existing methods. Comparative results show that our model is superior to currently existing models in multiple cell lines. Specifically, we found that the matching heuristic mechanism introduced into the proposed model mainly contributes to the improvement of performance in terms of overall accuracy. Additionally, compared with existing models, our model is more efficient with regard to computational speed.

scholarly journals DeeReCT-TSS: A novel meta-learning-based method annotates TSS in multiple cell types based on DNA sequences and RNA-seq data

2021 ◽  
Author(s):  
Juexiao Zhou ◽  
Bin Zhang ◽  
Haoyang Li ◽  
Longxi Zhou ◽  
Zhongxiao Li ◽  
...  
Keyword(s):  
Dna Sequences ◽  
Cell Types ◽  
Rna Seq ◽  
Sources Of Information ◽  
Genome Wide ◽  
A Genome ◽  
Meta Learning ◽  
Multiple Cell ◽  
Different Cell Types ◽  
Genome Scale

The accurate annotation of TSSs and their usage is critical for the mechanistic understanding of gene regulation under different biological contexts. To fulfill this, specific high-throughput experimental technologies have been developed to capture TSSs in a genome-wide manner. Various computational tools have also been developed for in silico prediction of TSSs solely based on genomic sequences. Most of these tools have drastic false positive predictions when applied on the genome-scale. Here, we present DeeReCT-TSS, a deep-learning-based method that is capable of TSSs identification across the whole genome based on DNA sequences and conventional RNA-seq data. We show that by effectively incorporating these two sources of information, DeeReCT-TSS significantly outperforms other solely sequence-based methods on the precise annotation of TSSs used in different cell types. Furthermore, we develop a meta-learning-based extension for simultaneous transcription start site (TSS) annotation on 10 cell types, which enables the identification of cell-type-specific TSS. Finally, we demonstrate the high precision of DeeReCT-TSS on two independent datasets from the ENCODE project by correlating our predicted TSSs with experimentally defined TSS chromatin states.

scholarly journals A Novel Deep Learning Method for Recognition and Classification of Brain Tumors from MRI images

Diagnostics ◽  
2021 ◽  
Vol 11 (5) ◽  
pp. 744
Author(s):  
Momina Masood ◽  
Tahira Nazir ◽  
Marriam Nawaz ◽  
Awais Mehmood ◽  
Junaid Rashid ◽  
...  
Keyword(s):  
Brain Tumor ◽  
Brain Tumors ◽  
Abnormal Growth ◽  
Irregular Shapes ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Domain Expertise ◽  
Comparative Results ◽  
Bounding Boxes

A brain tumor is an abnormal growth in brain cells that causes damage to various blood vessels and nerves in the human body. An earlier and accurate diagnosis of the brain tumor is of foremost important to avoid future complications. Precise segmentation of brain tumors provides a basis for surgical planning and treatment to doctors. Manual detection using MRI images is computationally complex in cases where the survival of the patient is dependent on timely treatment, and the performance relies on domain expertise. Therefore, computerized detection of tumors is still a challenging task due to significant variations in their location and structure, i.e., irregular shapes and ambiguous boundaries. In this study, we propose a custom Mask Region-based Convolution neural network (Mask RCNN) with a densenet-41 backbone architecture that is trained via transfer learning for precise classification and segmentation of brain tumors. Our method is evaluated on two different benchmark datasets using various quantitative measures. Comparative results show that the custom Mask-RCNN can more precisely detect tumor locations using bounding boxes and return segmentation masks to provide exact tumor regions. Our proposed model achieved an accuracy of 96.3% and 98.34% for segmentation and classification respectively, demonstrating enhanced robustness compared to state-of-the-art approaches.

scholarly journals A Spatiotemporal Convolutional Gated Recurrent Unit Network for Mean Wave Period Field Forecasting

2021 ◽  
Vol 9 (4) ◽  
pp. 383
Author(s):  
Ting Yu ◽  
Jichao Wang
Keyword(s):  
Lead Time ◽  
Wave Period ◽  
Data Driven ◽  
Lead Times ◽  
Proposed Model ◽  
Data Driven Approach ◽  
Mean Wave Period ◽  
Scattering Index ◽  
Gated Recurrent Unit ◽  
Methods Numerical

Mean wave period (MWP) is one of the key parameters affecting the design of marine facilities. Currently, there are two main methods, numerical and data-driven methods, for forecasting wave parameters, of which the latter are widely used. However, few studies have focused on MWP forecasting, and even fewer have investigated it with spatial and temporal information. In this study, correlations between ocean dynamic parameters are explored to obtain appropriate input features, significant wave height (SWH) and MWP. Subsequently, a data-driven approach, the convolution gated recurrent unit (Conv-GRU) model with spatiotemporal characteristics, is utilized to field forecast MWP with 1, 3, 6, 12, and 24-h lead times in the South China Sea. Six points at different locations and six consecutive moments at every 12-h intervals are selected to study the forecasting ability of the proposed model. The Conv-GRU model has a better performance than the single gated recurrent unit (GRU) model in terms of root mean square error (RMSE), the scattering index (SI), Bias, and the Pearson’s correlation coefficient (R). With the lead time increasing, the forecast effect shows a decreasing trend, specifically, the experiment displays a relatively smooth forecast curve and presents a great advantage in the short-term forecast of the MWP field in the Conv-GRU model, where the RMSE is 0.121 m for 1-h lead time.

Combination of gated recurrent unit and Network in Network for underwater acoustic target recognition

2021 ◽  
Vol 263 (6) ◽  
pp. 486-492
Author(s):  
Shuang Yang ◽  
Xiangyang Zeng
Keyword(s):  
Information Acquisition ◽  
Target Recognition ◽  
Recognition Rate ◽  
Temporal Correlation ◽  
Feedback Mechanism ◽  
Underwater Acoustic ◽  
Acoustic Information ◽  
Proposed Model ◽  
Acoustic Target ◽  
Gated Recurrent Unit

Underwater acoustic target recognition is an important part of underwater acoustic signal processing and an important technical support for underwater acoustic information acquisition and underwater acoustic information confrontation. Taking into account that the gated recurrent unit (GRU) has an internal feedback mechanism that can reflect the temporal correlation of underwater acoustic target features, a model with gated recurrent unit and Network in Network (NIN) is proposed to recognize underwater acoustic targets in this paper. The proposed model introduces NIN to compress the hidden states of GRU while retaining the original timing characteristics of underwater acoustic target features. The higher recognition rate and faster calculation speed of the proposed model are demonstrated with experiments for raw underwater acoustic signals comparing with the multi-layer stacked GRU model.

scholarly journals LA-GRU: Building Combined Intrusion Detection Model Based on Imbalanced Learning and Gated Recurrent Unit Neural Network

2018 ◽  
Vol 2018 ◽  
pp. 1-13 ◽  
Author(s):  
Binghao Yan ◽  
Guodong Han
Keyword(s):  
Neural Network ◽  
Intrusion Detection ◽  
False Alarm ◽  
False Alarm Rate ◽  
Network Traffic ◽  
Detection Performance ◽  
Imbalanced Learning ◽  
Traffic Distribution ◽  
Proposed Model ◽  
Gated Recurrent Unit

The intrusion detection models (IDMs) based on machine learning play a vital role in the security protection of the network environment, and, by learning the characteristics of the network traffic, these IDMs can divide the network traffic into normal behavior or attack behavior automatically. However, existing IDMs cannot solve the imbalance of traffic distribution, while ignoring the temporal relationship within traffic, which result in the reduction of the detection performance of the IDM and increase the false alarm rate, especially for low-frequency attacks. So, in this paper, we propose a new combined IDM called LA-GRU based on a novel imbalanced learning method and gated recurrent unit (GRU) neural network. In the proposed model, a modified local adaptive synthetic minority oversampling technique (LA-SMOTE) algorithm is provided to handle imbalanced traffic, and then the GRU neural network based on deep learning theory is used to implement the anomaly detection of traffic. The experimental results evaluated on the NSL-KDD dataset confirm that, compared with the existing state-of-the-art IDMs, the proposed model not only obtains excellent overall detection performance with a low false alarm rate but also more effectively solves the learning problem of imbalanced traffic distribution.

scholarly journals Comparing word embedding models for Arabic aspect category detection using a deep learning-based approach

2021 ◽  
Vol 297 ◽  
pp. 01072
Author(s):  
Rajae Bensoltane ◽  
Taher Zaki
Keyword(s):  
Deep Learning ◽  
Vector Representation ◽  
Rule Based ◽  
External Resources ◽  
Unit Model ◽  
Proposed Model ◽  
Feature Based ◽  
The Impact ◽  
Gated Recurrent Unit ◽  
Machine Learning Models

Aspect category detection (ACD) is a task of aspect-based sentiment analysis (ABSA) that aims to identify the discussed category in a given review or sentence from a predefined list of categories. ABSA tasks were widely studied in English; however, studies in other low-resource languages such as Arabic are still limited. Moreover, most of the existing Arabic ABSA work is based on rule-based or feature-based machine learning models, which require a tedious task of feature-engineering and the use of external resources like lexicons. Therefore, the aim of this paper is to overcome these shortcomings by handling the ACD task using a deep learning method based on a bidirectional gated recurrent unit model. Additionally, we examine the impact of using different vector representation models on the performance of the proposed model. The experimental results show that our model outperforms the baseline and related work models significantly by achieving an enhanced F1-score of more than 7%.

scholarly journals A Novel Method to Detect Inner Emotion States of Human using Artificial Neural Networks

2020 ◽  
Vol 8 (6) ◽  
pp. 5820-5825
Keyword(s):  
Physiological Signals ◽  
Classification Rate ◽  
Discrete Emotion ◽  
Novel Approach ◽  
Proposed Model ◽  
Depression Detection ◽  
Novel Method ◽  
Artificial Neural ◽  
Ann Classifier ◽  
Performance Rate

Human computer interaction is a fast growing area of research where in the physiological signals are used to identify human emotion states. Identifying emotion states can be done using various approaches. One such approach which gained interest of research is through physiological signals using EEG. In the present work, a novel approach is proposed to elicit emotion states using 3-D Video-audio stimuli. Around 66 subjects were involved during data acquisition using 32 channel Enobio device. FIR filter is used to preprocess the acquired raw EEG signals. The desired frequency bands like alpha, delta, beta and theta are extracted using 8-level DWT. The statistical features, Hurst exponential, entropy, power, energy, differential entropy of each bands are computed. Artificial Neural network is implemented using Sequential Keras model and applied on the extracted features to classify in to four classes (HVLA, HVHA, LVHA and LVLA) and eight discrete emotion states like clam, relax, happy, joy, sad, fear, tensed and bored. The performance of ANN classifier found to perform better for 4- classes than 8-classes with a classification rate of 90.835% and 74.0446% respectively. The proposed model achieved better performance rate in detecting discrete emotion states. This model can be used to build applications on health like stress / depression detection and on entertainment to build emotional DJ.

scholarly journals Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation

2020 ◽  
Vol 34 (05) ◽  
pp. 7797-7804
Author(s):  
Goran Glavašš ◽  
Swapna Somasundaran
Keyword(s):  
State Of The Art ◽  
Language Transfer ◽  
Text Segmentation ◽  
Word Embeddings ◽  
Neural Architecture ◽  
Text Coherence ◽  
Sentence Level ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Cross Lingual

Breaking down the structure of long texts into semantically coherent segments makes the texts more readable and supports downstream applications like summarization and retrieval. Starting from an apparent link between text coherence and segmentation, we introduce a novel supervised model for text segmentation with simple but explicit coherence modeling. Our model – a neural architecture consisting of two hierarchically connected Transformer networks – is a multi-task learning model that couples the sentence-level segmentation objective with the coherence objective that differentiates correct sequences of sentences from corrupt ones. The proposed model, dubbed Coherence-Aware Text Segmentation (CATS), yields state-of-the-art segmentation performance on a collection of benchmark datasets. Furthermore, by coupling CATS with cross-lingual word embeddings, we demonstrate its effectiveness in zero-shot language transfer: it can successfully segment texts in languages unseen in training.

scholarly journals Gated Recurrent Unit Networks and Discrete Wavelet Transforms Applied to Forecasting and Trading in the Stock Market

2020 ◽  
Author(s):  
Victor Biazon ◽  
Reinaldo Bianchi
Keyword(s):  
Stock Market ◽  
Wavelet Transforms ◽  
Stock Price ◽  
Discrete Wavelet ◽  
Discrete Wavelet Transforms ◽  
Time Step ◽  
Proposed Model ◽  
Gated Recurrent Unit ◽  
Novel Model ◽  
Unit Network

Trading in the stock market always comes with the challenge of deciding the best action to take on each time step. The problem is intensified by the theory that it is not possible to predict stock market time series as all information related to the stock price is already contained in it. In this work we propose a novel model called Discrete Wavelet Transform Gated Recurrent Unit Network (DWT-GRU). The model learns from the data to choose between buying, holding and selling, and when to execute them. The proposed model was compared to other recurrent neural networks, with and without wavelets preprocessing, and the buy and hold strategy. The results shown that the DWT-GRU outperformed all the set baselines in the analysed stocks of the Brazilian stock market.

Sign in / Sign up

Export Citation Format

Share Document