scholarly journals A Deep Learning Approach for Predicting Antigenic Variation of Influenza A H3N2

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Yuan-Ling Xia ◽  
Weihua Li ◽  
Yongping Li ◽  
Xing-Lai Ji ◽  
Yun-Xin Fu ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Amino Acid ◽  
Antigenic Variation ◽  
Amino Acid Sequences ◽  
Validation Dataset ◽  
Sequence Information ◽  
Learning Approach ◽  
Long Distance ◽  
Flu Virus

Modeling antigenic variation in influenza (flu) virus A H3N2 using amino acid sequences is a promising approach for improving the prediction accuracy of immune efficacy of vaccines and increasing the efficiency of vaccine screening. Antigenic drift and antigenic jump/shift, which arise from the accumulation of mutations with small or moderate effects and from a major, abrupt change with large effects on the surface antigen hemagglutinin (HA), respectively, are two types of antigenic variation that facilitate immune evasion of flu virus A and make it challenging to predict the antigenic properties of new viral strains. Despite considerable progress in modeling antigenic variation based on the amino acid sequences, few studies focus on the deep learning framework which could be most suitable to be applied to this task. Here, we propose a novel deep learning approach that incorporates a convolutional neural network (CNN) and bidirectional long-short-term memory (BLSTM) neural network to predict antigenic variation. In this approach, CNN extracts the complex local contexts of amino acids while the BLSTM neural network captures the long-distance sequence information. When compared to the existing methods, our deep learning approach achieves the overall highest prediction performance on the validation dataset, and more encouragingly, it achieves prediction agreements of 99.20% and 96.46% for the strains in the forthcoming year and in the next two years included in an existing set of chronological amino acid sequences, respectively. These results indicate that our deep learning approach is promising to be applied to antigenic variation prediction of flu virus A H3N2.

scholarly journals Identification of Enzymes-specific Protein Domain Based on DDE, and Convolutional Neural Network

2021 ◽  
Vol 12 ◽  
Author(s):  
Rahu Sikander ◽  
Yuping Wang ◽  
Ali Ghulam ◽  
Xianjuan Wu
Keyword(s):  
Neural Network ◽  
Amino Acid ◽  
Convolutional Neural Network ◽  
Cross Validation ◽  
Amino Acid Sequences ◽  
Protein Domain ◽  
Biological Information ◽  
Sequence Information ◽  
Accuracy Score ◽  
Feature Maps

Predicting the protein sequence information of enzymes and non-enzymes is an important but a very challenging task. Existing methods use protein geometric structures only or protein sequences alone to predict enzymatic functions. Thus, their prediction results are unsatisfactory. In this paper, we propose a novel approach for predicting the amino acid sequences of enzymes and non-enzymes via Convolutional Neural Network (CNN). In CNN, the roles of enzymes are predicted from multiple sides of biological information, including information on sequences and structures. We propose the use of two-dimensional data via 2DCNN to predict the proteins of enzymes and non-enzymes by using the same fivefold cross-validation function. We also use an independent dataset to test the performance of our model, and the results demonstrate that we are able to solve the overfitting problem. We used the CNN model proposed herein to demonstrate the superiority of our model for classifying an entire set of filters, such as 32, 64, and 128 parameters, with the fivefold validation test set as the independent classification. Via the Dipeptide Deviation from Expected Mean (DDE) matrix, mutation information is extracted from amino acid sequences and structural information with the distance and angle of amino acids is conveyed. The derived feature maps are then encoded in DDE exploitation. The independent datasets are then compared with other two methods, namely, GRU and XGBOOST. All analyses were conducted using 32, 64 and 128 filters on our proposed CNN method. The cross-validation datasets achieved an accuracy score of 0.8762%, whereas the accuracy of independent datasets was 0.7621%. Additional variables were derived on the basis of ROC AUC with fivefold cross-validation was achieved score is 0.95%. The performance of our model and that of other models in terms of sensitivity (0.9028%) and specificity (0.8497%) was compared. The overall accuracy of our model was 0.9133% compared with 0.8310% for the other model.

scholarly journals Combining statistical and neural network approaches to derive energy functions for completely flexible protein backbone design

2019 ◽  
Author(s):  
Bin Huang ◽  
Yang Xu ◽  
Haiyan Liu
Keyword(s):  
Neural Network ◽  
Amino Acid ◽  
Protein Structures ◽  
Amino Acid Sequences ◽  
Conformational Space ◽  
Sequence Information ◽  
Protein Backbone ◽  
Energy Functions ◽  
Non Local ◽  
Energy Surfaces

AbstractA designable protein backbone is one for which amino acid sequences that stably fold into it exist. To design such backbones, a general method is much needed for continuous sampling and optimization in the backbone conformational space without specific amino acid sequence information. The energy functions driving such sampling and optimization must faithfully recapitulate the characteristically coupled distributions of multiplexes of local and non-local conformational variables in designable backbones. It is also desired that the energy surfaces are continuous and smooth, with easily computable gradients. We combine statistical and neural network (NN) approaches to derive a model named SCUBA, standing for Side-Chain-Unspecialized-Backbone-Arrangement. In this approach, high-dimensional statistical energy surfaces learned from known protein structures are analytically represented as NNs. SCUBA is composed as a sum of NN terms describing local and non-local conformational energies, each NN term derived by first estimating the statistical energies in the corresponding multi-variable space via neighbor-counting (NC) with adaptive cutoffs, and then training the NN with the NC-estimated energies. To determine the relative weights of different energy terms, SCUBA-driven stochastic dynamics (SD) simulations of natural proteins are considered. As initial computational tests of SCUBA, we apply SD simulated annealing to automatically optimize artificially constructed polypeptide backbones of different fold classes. For a majority of the resulting backbones, structurally matching native backbones can be found with Dali Z-scores above 6 and less than 2 Å displacements of main chain atoms in aligned secondary structures. The results suggest that SCUBA-driven sampling and optimization can be a general tool for protein backbone design with complete conformational flexibility. In addition, the NC-NN approach can be generally applied to develop continuous, noise-filtered multi-variable statistical models from structural data.Linux executables to setup and run SCUBA SD simulations are publicly available (http://biocomp.ustc.edu.cn/servers/download_scuba.php). Interested readers may contact the authors for source code availability.

scholarly journals Deep Learning for Caries Detection and Classification

Diagnostics ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. 1672
Author(s):  
Luya Lian ◽  
Tianer Zhu ◽  
Fudong Zhu ◽  
Haihua Zhu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Disease Diagnosis ◽  
Validation Dataset ◽  
Reference Dataset ◽  
Dice Coefficient ◽  
Learning Methods ◽  
Test Dataset ◽  
The Impact ◽  
Caries Lesions

Objectives: Deep learning methods have achieved impressive diagnostic performance in the field of radiology. The current study aimed to use deep learning methods to detect caries lesions, classify different radiographic extensions on panoramic films, and compare the classification results with those of expert dentists. Methods: A total of 1160 dental panoramic films were evaluated by three expert dentists. All caries lesions in the films were marked with circles, whose combination was defined as the reference dataset. A training and validation dataset (1071) and a test dataset (89) were then established from the reference dataset. A convolutional neural network, called nnU-Net, was applied to detect caries lesions, and DenseNet121 was applied to classify the lesions according to their depths (dentin lesions in the outer, middle, or inner third D1/2/3 of dentin). The performance of the test dataset in the trained nnU-Net and DenseNet121 models was compared with the results of six expert dentists in terms of the intersection over union (IoU), Dice coefficient, accuracy, precision, recall, negative predictive value (NPV), and F1-score metrics. Results: nnU-Net yielded caries lesion segmentation IoU and Dice coefficient values of 0.785 and 0.663, respectively, and the accuracy and recall rate of nnU-Net were 0.986 and 0.821, respectively. The results of the expert dentists and the neural network were shown to be no different in terms of accuracy, precision, recall, NPV, and F1-score. For caries depth classification, DenseNet121 showed an overall accuracy of 0.957 for D1 lesions, 0.832 for D2 lesions, and 0.863 for D3 lesions. The recall results of the D1/D2/D3 lesions were 0.765, 0.652, and 0.918, respectively. All metric values, including accuracy, precision, recall, NPV, and F1-score values, were proven to be no different from those of the experienced dentists. Conclusion: In detecting and classifying caries lesions on dental panoramic radiographs, the performance of deep learning methods was similar to that of expert dentists. The impact of applying these well-trained neural networks for disease diagnosis and treatment decision making should be explored.

Sars-Cov-2 Spike protein function prediction using a convolutional neural network ensemble

2021 ◽  
pp. 7831-7845
Author(s):  
Raghad Monther Eid, Eman K. Elsayed, Fatma T. Ghanam
Keyword(s):  
Neural Network ◽  
Amino Acid ◽  
Protein Function ◽  
Protein Function Prediction ◽  
Small Error ◽  
Amino Acid Sequences ◽  
Spike Protein ◽  
Neural Network Ensemble ◽  
Classification Problems ◽  
Past Experiences

Introduction: SARS-CoV-2 has become a worldwide pandemic that affects all aspects of life; therefore, numerous organizations and open exploration foundations focus their efforts on research for viable therapeutics. Given past experiences and involvement in SARS, the essential focus has been the Spike protein, considered as the perfect objective for COVID-19 immunotherapies. Most of the vaccines being developed target the spike proteins because this protein covers the virus and helps it invade human cells. Methods: Applications of deep neural network is a quickly expanding field now reaching many areas including proteomics. Results: To be precise, convolutional neural networks have been used for identifying the functional role of amino acid sequences, because of its ability to give nearly accurate results for multi-label classification problems. Here we present a modified convolutional deep learning model that can  identify if a given amino acid sequence is a spike protein or not based on the length of the sequence and the function of the protein, that will be done  with a short execution time and a relatively small error rate. Conclusion: CNN is an efficient tool at supervised multilabel classification problems

Sign in / Sign up

Export Citation Format

Share Document