Deep Learning Method For Prediction Research Articles

DensePPI: A Novel Image-Based Deep Learning Method for Prediction of Protein-Protein Interactions.

Protein-protein interactions (PPI) are crucial for understanding the behaviour of living organisms and identifying disease associations. This paper proposes DensePPI, a novel deep convolution strategy applied to the 2D image map generated from the interacting protein pairs for PPI prediction. A colour encoding scheme has been introduced to embed the bigram interaction possibilities of Amino Acids into RGB colour space to enhance the learning and prediction task. The DensePPI model is trained on 5.5 million sub-images of size 128×128 generated from nearly 36,000 interacting and 36,000 non-interacting benchmark protein pairs. The performance is evaluated on independent datasets from five different organisms; Caenorhabditis elegans, Escherichia coli, Helicobacter Pylori, Homo sapiens and Mus Musculus. The proposed model achieves an average prediction accuracy score of 99.95% on these datasets, considering inter-species and intra-species interactions. The performance of DensePPI is compared with the state-of-the-art methods and outperforms those approaches in different evaluation metrics. Improved performance of DensePPI indicates the efficiency of the image-based encoding strategy of sequence information with the deep learning architecture in PPI prediction. The enhanced performance on diverse test sets shows that the DensePPI is significant for intra-species interaction prediction and cross-species interactions. The dataset, supplementary file, and the developed models are available at https://github.com/Aanzil/DensePPI for academic use only.

DeepCIP: A multimodal deep learning method for the prediction of internal ribosome entry sites of circRNAs

Circular RNAs (circRNAs) have been found to have the ability to encode proteins through internal ribosome entry sites (IRESs), which are essential RNA regulatory elements for cap-independent translation. Identification of IRES elements in circRNA is crucial for understanding its function. Previous studies have presented IRES predictors based on machine learning techniques, but they were mainly designed for linear RNA IRES. In this study, we proposed DeepCIP (Deep learning method for CircRNA IRES Prediction), a multimodal deep learning approach that employs both sequence and structural information for circRNA IRES prediction. Our results demonstrate the effectiveness of the sequence and structure models used by DeepCIP in feature extraction and suggest that integrating sequence and structural information efficiently improves the accuracy of prediction. The comparison studies indicate that DeepCIP outperforms other comparative methods on the test set and real circRNA IRES dataset. Furthermore, through the integration of an interpretable analysis mechanism, we elucidate the sequence patterns learned by our model, which align with the previous discovery of motifs that facilitate circRNA translation. Thus, DeepCIP has the potential to enhance the study of the coding potential of circRNAs and contribute to the design of circRNA-based drugs. DeepCIP as a standalone program is freely available at https://github.org/zjupgx/DeepCIP.

COVID-19 prediction based on hybrid Inception V3 with VGG16 using chest X-ray images.

The CoronaVirus was first started in the Wuhan city, China in December of 2019. It belongs to the Coronaviridae family, which can infect both animals and humans. The diagnosis of coronavirus disease-2019 (COVID-19) is typically detected by Serology, Genetic Real-Time reverse transcription-Polymerase Chain Reaction (RT-PCR), and Antigen testing. These testing methods have limitations like limited sensitivity, high cost, and long turn-around time. It is necessary to develop an automatic detection system for COVID-19 prediction. Chest X-ray is a lower-cost process in comparison to chest Computed tomography(CT). Deep learning is the best fruitful technique of machine learning, which provides useful investigation for learning and screening a large amount of chest X-ray images with COVID-19 and normal. There are many deep learning methods for prediction, but these methods have a few limitations like overfitting, misclassification, and false predictions for poor-quality chest X-rays. In order to overcome these limitations, the novel hybrid model called "Inception V3 with VGG16 (Visual Geometry Group)" is proposed for the prediction of COVID-19 using chest X-rays. It is a combination of two deep learning models, Inception V3 and VGG16 (IV3-VGG). To build the hybrid model, collected 243 images from the COVID-19 Radiography Database. Out of 243 X-rays, 121 are COVID-19 positive and 122 are normal images. The hybrid model is divided into two modules namely pre-processing and the IV3-VGG. In the dataset, some of the images with different sizes and different color intensities are identified and pre-processed. The second module i.e., IV3-VGG consists of four blocks.The first block is considered for VGG-16 and blocks 2 and 3 are considered for Inception V3 networks and final block 4 consists of four layers namely Avg pooling, dropout, fully connected, and Softmax layers. The experimental results show that the IV3-VGG model achieves the highest accuracy of 98% compared to the existing five prominent deep learning models such as Inception V3, VGG16, ResNet50, DenseNet121, and MobileNet.

RiRPSSP: A unified deep learning method for prediction of regular and irregular protein secondary structures

Protein secondary structure prediction (PSSP) is an important and challenging task in protein bioinformatics. Protein secondary structures (SSs) are categorized in regular and irregular structure classes. Regular SSs, representing nearly 50% of amino acids consist of helices and sheets, whereas the remaining amino acids represent irregular SSs. [Formula: see text]-turns and [Formula: see text]-turns are the most abundant irregular SSs present in proteins. Existing methods are well developed for separate prediction of regular and irregular SSs. However, for more comprehensive PSSP, it is essential to develop a uniform model to predict all types of SSs simultaneously. In this work, using a novel dataset comprising dictionary of secondary structure of protein (DSSP)-based SSs and PROMOTIF-based [Formula: see text]-turns and [Formula: see text]-turns, we propose a unified deep learning model consisting of convolutional neural networks (CNNs) and long short-term memory networks (LSTMs) for simultaneous prediction of regular and irregular SSs. To the best of our knowledge, this is the first study in PSSP covering both regular and irregular structures. The protein sequences in our constructed datasets, RiR6069 and RiR513, have been borrowed from benchmark CB6133 and CB513 datasets, respectively. The results are indicative of increased PSSP accuracy.

A Modified RNN-Based Deep Learning Method for Prediction of Atmospheric Visibility

Accurate atmospheric visibility prediction is of great significance to public transport safety. However, since it is affected by multiple factors, there still remains difficulties in predicting its heterogenous spatial distribution and rapid temporal variation. In this paper, a recursive neural network (RNN) prediction model modified with the frame-hopping transmission gate (FHTG), feature fusion module (FFM) and reverse scheduled sampling (RSS), named SwiftRNN, is developed. The new FHTG is used to accelerate training, the FFM is used for extraction and fusion of global and local features, and the RSS is employed to learn spatial details and improve prediction accuracy. Based on the ground-based monitoring data of atmospheric visibility from the China Meteorological Information Center during 1 January 2018 to 31 December 2020, the SwiftRNN model and two traditional ConvLSTM and PredRNN models are performed to predict hourly atmospheric visibility in central and eastern China at a lead of 12 h. The results show that the SwiftRNN model has better performance in the skill scores of visibility prediction than those of the ConvLSTM and PredRNN model. The averaged structural similarity (SSIM) of predictions at a lead up to 12 h is 0.444, 0.425 and 0.399 for the SwiftRNN, PredRNN and ConvLSTM model, respectively, and the averaged image perception similarity (LPIPS) is 0.289, 0.315 and 0.328, respectively. The averaged critical success index (CSI) of predictions over 1000 m fog area is 0.221, 0.205 and 0.194, respectively. Moreover, the training speed of the SwiftRNN model is 14.3% faster than the PredRNN model. It is also found that the prediction effect of the SwiftRNN model over 1000 m medium grade fog area is significantly improved along with lead times compared with the ConvLSTM and PredRNN model. All above results demonstrate the SwiftRNN model is a powerful tool in predicting atmospheric visibility.

LSTM-Based Deep Learning Methods for Prediction of Earthquakes Using Ionospheric Data

The ionosphere may play an essential role in the atmosphere and earth. Solar flares due to coronal mass ejection, seismic movements, and geomagnetic activity cause deviations in the ionosphere. The main parameter for investigating the structure of the ionosphere is Total Electron Content (TEC). TEC values obtained from GPS stations are a powerful technique for analyzing the ionospheric response to earthquakes and solar storms. This article analyzes the relations between earthquakes and TEC data to detect earthquakes. Our goal is to propose a prediction model to detect earthquakes in previous days. The ionospheric variability during moderate and severe earthquake events of varying strengths for 2012-2019 is discussed in this paper. The proposed models use LSTM-based (Long Short-Term Memory) deep learning models to classify earthquake days by analyzing TEC values of the last days. The LSTM-Based prediction models are compared against the SVM (Support Vector Machine), LDA (Linear Discriminant Analysis) classifier and Random Forest classifier to evaluate the proposed models based on earthquake prediction. The results reveal that the proposed models improve in detecting the earthquakes at an accuracy rate of about 0.82 and can be used as a successful tool for detecting earthquakes based on the previous days.

Good environmental governance: Predicting PM2.5 by using Spatiotemporal Matrix Factorization generative adversarial network

In the context of low-carbon globalization, green development has become the common pursuit of all countries and the theme of China’s development in the new era. Fine particulate matter (PM2.5) is one of the main challenges affecting air quality, and how to accurately predict PM2.5 plays a pivotal role in environmental governance. However, traditional data-driven approaches and deep learning methods for prediction rarely consider spatiotemporal features. Furthermore, different regions always have various implicit or hidden states, which have rarely been considered in the off-the-shelf model. To solve these problems, this study proposed a novel Spatial-Temporal Matrix Factorization Generative Adversarial Network (ST MFGAN) to capture spatiotemporal correlations and overcome the regional diversity problem at the same time. Specifically, Generative Adversarial Network (GAN) composed of graph Convolutional Network (GCN) and Long-Short-Term Memory (LSTM) network is used to generate a large amount of reliable spatiotemporal data, and matrix factorization network is used to decompose the vector output by GAN into multiple sub-networks. PM2.5 are finally combined and jointly predicted by the fusion layer. Extensive experiments show the superiority of the newly designed method.

Predicting the Sequence Specificities of DNA-Binding Proteins by DNA Fine-Tuned Language Model With Decaying Learning Rates.

DNA-binding proteins (DBPs) play vital roles in the regulation of biological systems. Although there are already many deep learning methods for predicting the sequence specificities of DBPs, they face two challenges as follows. Classic deep learning methods for DBPs prediction usually fail to capture the dependencies between genomic sequences since their commonly used one-hot codes are mutually orthogonal. Besides, these methods usually perform poorly when samples are inadequate. To address these two challenges, we developed a novel language model for mining DBPs using human genomic data and ChIP-seq datasets with decaying learning rates, named DNA Fine-tuned Language Model (DFLM). It can capture the dependencies between genome sequences based on the context of human genomic data and then fine-tune the features of DBPs tasks using different ChIP-seq datasets. First, we compared DFLM with the existing widely used methods on 69 datasets and we achieved excellent performance. Moreover, we conducted comparative experiments on complex DBPs and small datasets. The results show that DFLM still achieved a significant improvement. Finally, through visualization analysis of one-hot encoding and DFLM, we found that one-hot encoding completely cut off the dependencies of DNA sequences themselves, while DFLM using language models can well represent the dependency of DNA sequences. Source code are available at: https://github.com/Deep-Bioinfo/DFLM.

Deep learning method for prediction of patient-specific dose distribution in breast cancer

BackgroundPatient-specific dose prediction improves the efficiency and quality of radiation treatment planning and reduces the time required to find the optimal plan. In this study, a patient-specific dose prediction model was developed for a left-sided breast clinical case using deep learning, and its performance was compared with that of conventional knowledge-based planning using RapidPlan™.MethodsPatient-specific dose prediction was performed using a contour image of the planning target volume (PTV) and organs at risk (OARs) with a U-net-based modified dose prediction neural network. A database of 50 volumetric modulated arc therapy (VMAT) plans for left-sided breast cancer patients was utilized to produce training and validation datasets. The dose prediction deep neural network (DpNet) feature weights of the previously learned convolution layers were applied to the test on a cohort of 10 test sets. With the same patient data set, dose prediction was performed for the 10 test sets after training in RapidPlan. The 3D dose distribution, absolute dose difference error, dose-volume histogram, 2D gamma index, and iso-dose dice similarity coefficient were used for quantitative evaluation of the dose prediction.ResultsThe mean absolute error (MAE) and one standard deviation (SD) between the clinical and deep learning dose prediction models were 0.02 ± 0.04%, 0.01 ± 0.83%, 0.16 ± 0.82%, 0.52 ± 0.97, − 0.88 ± 1.83%, − 1.16 ± 2.58%, and − 0.97 ± 1.73% for D95%, Dmean in the PTV, and the OARs of the body, left breast, heart, left lung, and right lung, respectively, and those measured between the clinical and RapidPlan dose prediction models were 0.02 ± 0.14%, 0.87 ± 0.63%, − 0.29 ± 0.98%, 1.30 ± 0.86%, − 0.32 ± 1.10%, 0.12 ± 2.13%, and − 1.74 ± 1.79, respectively.ConclusionsIn this study, a deep learning method for dose prediction was developed and was demonstrated to accurately predict patient-specific doses for left-sided breast cancer. Using the deep learning framework, the efficiency and accuracy of the dose prediction were compared to those of RapidPlan. The doses predicted by deep learning were superior to the results of the RapidPlan-generated VMAT plan.

A Review on Deep Learning Techniques for Video Prediction

The ability to predict, anticipate and reason about future outcomes is a key component of intelligent decision-making systems. In light of the success of deep learning in computer vision, deep-learning-based video prediction emerged as a promising research direction. Defined as a self-supervised learning task, video prediction represents a suitable framework for representation learning, as it demonstrated potential capabilities for extracting meaningful representations of the underlying patterns in natural videos. Motivated by the increasing interest in this task, we provide a review on the deep learning methods for prediction in video sequences. We first define the video prediction fundamentals, as well as mandatory background concepts and the most used datasets. Next, we carefully analyze existing video prediction models organized according to a proposed taxonomy, highlighting their contributions and their significance in the field. The summary of the datasets and methods is accompanied with experimental results that facilitate the assessment of the state of the art on a quantitative basis. The paper is summarized by drawing some general conclusions, identifying open research challenges and by pointing out future research directions.

MU-PseUDeep: A deep learning method for prediction of pseudouridine sites

Pseudouridine synthase binds to uridine sites and catalyzes the conversion of uridine to pseudouridine (Ψ). This binding takes place in a specific context and in the conformation of nucleotides. Most machine-learning methods for Ψ site classification use nucleotide frequency as a feature, which may not fully depict the relevant conformation around a Ψ site. Using the power of deep learning and raw sequence, as well as secondary structure features, our tool MU-PseUDeep is designed to capture both the sequence and secondary structure context, which inputs the raw RNA sequence and the predicted secondary structure to two sets of convolutional neural networks. It has shown considerable improvement in Ψ site prediction over existing tools, XG-PseU, PseUI, and iRNA-PseU for both balanced and imbalanced datasets. To the best of our knowledge, this is the most accurate tool for Ψ site prediction. We also used MU-PseUDeep to scan the human transcriptome, which shows that the genes with predicted Ψ sites are enriched in nucleotide and protein binding, as well as in neurodegeneration pathways. The tool is open source, available at https://github.com/smk5g5/MU-PseUDeep.

PiPred \u2013 a deep-learning method for prediction of \u03c0-helices in protein sequences

Canonical π-helices are short, relatively unstable secondary structure elements found in proteins. They comprise seven or more residues and are present in 15% of all known protein structures, often in functionally important regions such as ligand- and ion-binding sites. Given their similarity to α-helices, the prediction of π-helices is a challenging task and none of the currently available secondary structure prediction methods tackle it. Here, we present PiPred, a neural network-based tool for predicting π-helices in protein sequences. By performing a rigorous benchmark we show that PiPred can detect π-helices with a per-residue precision of 48% and sensitivity of 46%. Interestingly, some of the α-helices mispredicted by PiPred as π-helices exhibit a geometry characteristic of π-helices. Also, despite being trained only with canonical π-helices, PiPred can identify 6-residue-long α/π-bulges. These observations suggest an even higher effective precision of the method and demonstrate that π-helices, α/π-bulges, and other helical deformations may impose similar constraints on sequences. PiPred is freely accessible at: https://toolkit.tuebingen.mpg.de/#/tools/quick2d. A standalone version is available for download at: https://github.com/labstructbioinf/PiPred, where we also provide the CB6133, CB513, CASP10, and CASP11 datasets, commonly used for training and validation of secondary structure prediction methods, with correctly annotated π-helices.

Deep Learning Method for Prediction of DDoS Attacks on Social Media

Recently, data collected from social media enable to analyze social events and make predictions about real events, based on the analysis of sentiments and opinions of users. Most cyber-attacks are carried out by hackers on the basis of discussions on social media. This paper proposes the method that predicts DDoS attacks occurrence by finding relevant texts in social media. To perform high-precision classification of texts to positive and negative classes, the CNN model with 13 layers and improved LSTM method are used. In order to predict the occurrence of the DDoS attacks in the next day, the negative and positive sentiments in social networking texts are used. To evaluate the efficiency of the proposed method experiments were conducted on Twitter data. The proposed method achieved a recall, precision, [Formula: see text]-measure, training loss, training accuracy, testing loss, and test accuracy of 0.85, 0.89, 0.87, 0.09, 0.78, 0.13, and 0.77, respectively.

MRCNN: a deep learning model for regression of genome-wide DNA methylation

BackgroundDetermination of genome-wide DNA methylation is significant for both basic research and drug development. As a key epigenetic modification, this biochemical process can modulate gene expression to influence the cell differentiation which can possibly lead to cancer. Due to the involuted biochemical mechanism of DNA methylation, obtaining a precise prediction is a considerably tough challenge. Existing approaches have yielded good predictions, but the methods either need to combine plenty of features and prerequisites or deal with only hypermethylation and hypomethylation.ResultsIn this paper, we propose a deep learning method for prediction of the genome-wide DNA methylation, in which the Methylation Regression is implemented by Convolutional Neural Networks (MRCNN). Through minimizing the continuous loss function, experiments show that our model is convergent and more precise than the state-of-art method (DeepCpG) according to results of the evaluation. MRCNN also achieves the discovery of de novo motifs by analysis of features from the training process.ConclusionsGenome-wide DNA methylation could be evaluated based on the corresponding local DNA sequences of target CpG loci. With the autonomous learning pattern of deep learning, MRCNN enables accurate predictions of genome-wide DNA methylation status without predefined features and discovers some de novo methylation-related motifs that match known motifs by extracting sequence patterns.

A deep learning method for prediction of three-dimensional dose distribution of helical tomotherapy.

To develop a deep learning method for prediction of three-dimensional (3D) voxel-by-voxel dose distributions of helical tomotherapy (HT). Using previously treated HT plans as training data, a deep learning model named U-ResNet-D was trained to predict a 3D dose distribution. First, the contoured structures and dose volumes were converted from plan database to 3D matrix with a program based on a developed visualization toolkit (VTK), then transferred to U-ResNet-D for correlating anatomical features and dose distributions at voxel-level. One hundred and ninety nasopharyngeal cancer (NPC) patients treated by HT with multiple planning target volumes (PTVs) in different prescription patterns were studied. The model was typically trained from scratch with weights randomly initialized rather than using transfer-learning method, and used to predict new patient's 3D dose distributions. The predictive accuracy was evaluated with three methods: (a) The dose difference at the position r, δ(r, r)=Dc (r) - Dp (r), was calculated for each voxel. The mean (μδ(r,r) ) and standard deviation (σδ(r,r) ) of δ(r, r) were calculated to assess the prediction bias and precision; (b) The mean absolute differences of dosimetric indexes (DIs) including maximum and mean dose, homogeneity index, conformity index, and dose spillage for PTVs and organ at risks (OARs) were calculated and statistically analyzed with the paired-samples t test; (c) Dice similarity coefficients (DSC) between predicted and clinical isodose volumes were calculated. The U-ResNet-D model predicted 3D dose distribution accurately. For twenty tested patients, the prediction bias ranged from -2.0% to 2.3% and prediction error varied from 1.5% to 4.5% (relative to prescription) for 3D dose differences. The mean absolute dose differences for PTVs and OARs are within 2.0% and 4.2%, and nearly all the DIs for PTVs and OARs had no significant differences. The averaged DSC ranged from 0.95 to 1 for different isodose volumes. The study developed a new deep learning method for 3D voxel-by-voxel dose prediction, and shown to be able to produce accurately dose predictions for nasopharyngeal patients treated by HT. The predicted 3D dose map can be useful for improving radiotherapy planning design, ensuring plan quality and consistency, making clinical technique comparison, and guiding automatic treatment planning.