Prediction of pandemic risk for animal-origin coronavirus using a deep learning method

Abstract

Background Coronaviruses can be isolated from bats, civets, pangolins, birds and other wild animals. As an animal-origin pathogen, coronavirus can cross species barrier and cause pandemic in humans. In this study, a deep learning model for early prediction of pandemic risk was proposed based on the sequences of viral genomes. Methods A total of 3257 genomes were downloaded from the Coronavirus Genome Resource Library. We present a deep learning model of cross-species coronavirus infection that combines a bidirectional gated recurrent unit network with a one-dimensional convolution. The genome sequence of animal-origin coronavirus was directly input to extract features and predict pandemic risk. The best performances were explored with the use of pre-trained DNA vector and attention mechanism. The area under the receiver operating characteristic curve (AUROC) and the area under precision-recall curve (AUPR) were used to evaluate the predictive models. Results The six specific models achieved good performances for the corresponding virus groups (1 for AUROC and 1 for AUPR). The general model with pre-training vector and attention mechanism provided excellent predictions for all virus groups (1 for AUROC and 1 for AUPR) while those without pre-training vector or attention mechanism had obviously reduction of performance (about 5–25%). Re-training experiments showed that the general model has good capabilities of transfer learning (average for six groups: 0.968 for AUROC and 0.942 for AUPR) and should give reasonable prediction for potential pathogen of next pandemic. The artificial negative data with the replacement of the coding region of the spike protein were also predicted correctly (100% accuracy). With the application of the Python programming language, an easy-to-use tool was created to implements our predictor. Conclusions Robust deep learning model with pre-training vector and attention mechanism mastered the features from the whole genomes of animal-origin coronaviruses and could predict the risk of cross-species infection for early warning of next pandemic. Graphical Abstract

Using amino acid features to identify the pathogenicity of influenza B virus

“…Although features from signature positions were used to construct the model, whole genomes and full-length proteins should be considered to increase the performance of the prediction model [ 26 ]. A mathematical algorithm should be designed for complex data of various models to identify pathogenicity [ 18 , 42 ].…”

“…The area under the ROC curve (AUC) was used to evaluate the predictive performance. A larger AUC value suggests that the model achieves a better performance [ 26 ].…”

“…A model with good performance evaluates the pathogenicity of IBV and predicts the ability of transmission. With the increase of genome data in the public database, machine learning methods are ideal tools for phenotype identification of IBVs [ 26 ].…”

Efficient Cavity Searching for Gene Network of Influenza A Virus

“…The genome of the influenza A virus is composed of eight segments of single-strand negative RNA. With the classification of HA and NA, the influenza A virus has 16 subtypes HA and nine subtypes NA [8][9] [10]. Following fast mutation of the viral genome, antigen escaping, drug-resistance, and virulence enhancing will occur [8][9] [10].…”

“…With the classification of HA and NA, the influenza A virus has 16 subtypes HA and nine subtypes NA [8][9] [10]. Following fast mutation of the viral genome, antigen escaping, drug-resistance, and virulence enhancing will occur [8][9] [10]. In order to understand the evolution of the influenza virus, scientists tried to search high order structures by using 0-1 programming.…”