Year
Month
(Peer-Reviewed) Prediction of pandemic risk for animal-origin coronavirus using a deep learning method
Zheng Kou 寇铮 ¹, Yi-Fan Huang ¹, Ao Shen ¹, Saeed Kosari ¹, Xiang-Rong Liu 刘向荣 ², Xiao-Li Qiang 强小利 ¹
¹ Institute of Computing Science and Technology, Guangzhou University, Guangzhou, 510006, China
中国 广州 广州大学计算科技研究院
² Department of Computer Science, Xiamen University, Xiamen, 361005, China
中国 厦门 厦门大学计算机科学系
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.
Prediction of pandemic risk for animal-origin coronavirus using a deep learning method_1
Prediction of pandemic risk for animal-origin coronavirus using a deep learning method_2
Prediction of pandemic risk for animal-origin coronavirus using a deep learning method_3
Prediction of pandemic risk for animal-origin coronavirus using a deep learning method_4
  • Preplanned Studies: Disease Burden of Pancreatic Cancer — China, 1990−2019
  • Yuan He, Xiaolong Zhou, Xueqi Fan, Bin Zhang, Li Ma, Jing Wu, Xudong Li
  • China CDC Weekly
  • 2022-03-23
  • Effects of low molecular weight organic acids on aggregation behavior of biochar colloids at acid and neutral conditions
  • Yang Wang, Changxi Wang, Jiayi Xiong, Qianru Zhang, Jianying Shang
  • Biochar
  • 2022-03-23
  • A universal spray printing strategy to prepare gradient hybrid architectures
  • Lingyu Du, Songshan Bi, Yang Hu, Rui Wang, Jiacai Zhu, Minghui Zhang, Zhiqiang Niu
  • Carbon Energy
  • 2022-03-21
  • Terahertz metasurface zone plates with arbitrary polarizations to a fixed polarization conversion
  • Zhen Yue, Jitao Li 李继涛, Jie Li, Chenglong Zheng, Jingyu Liu, Guocui Wang, Hang Xu, Mingyang Chen, Yating Zhang, Yan Zhang, Jianquan Yao
  • Opto-Electronic Science
  • 2022-03-18
  • Single-shot mid-infrared incoherent holography using Lucy-Richardson-Rosen algorithm
  • Vijayakumar Anand, Molong Han, Jovan Maksimovic, Soon Hock Ng, Tomas Katkus, Annaleise Klein, Keith Bambery, Mark J. Tobin, Jitraporn Vongsvivut, Saulius Juodkazis
  • Opto-Electronic Science
  • 2022-03-18
  • A virus-derived small RNA targets the rice transcription factor ROC1 to induce disease-like symptom
  • Xiuqin Huang, Feifei Li, Xishan Zhang, Jiahao Chen, Junkai Wang, Jing Wei, Xin Yang, Guohui Zhou, Tong Zhang
  • Phytopathology Research
  • 2022-03-17
  • Effects of β-carotene on glucose metabolism dysfunction in human subjects and type 2 diabetic rats
  • Jianjun Wu, Yinan Zhou, Hanqing Hu, Dawei Yang, Fan Yang
  • Deep Science
  • 2022-03-17
  • Advances in phase-sensitive optical time-domain reflectometry
  • Shuaiqi Liu, Feihong Yu, Rui Hong, Weijie Xu, Liyang Shao, Feng Wang
  • Opto-Electronic Advances
  • 2022-03-15
  • Second harmonic generation of laser beams in transverse mode locking states
  • Zilong Zhang, Yuan Gao, Xiangjia Li, Xin Wang, Suyi Zhao, Qiang Liu, Changming Zhao
  • Advanced Photonics
  • 2022-03-14
  • A combined multiscale modeling and experimental study on surface modification of high-volume micro-nanoparticles with atomic accuracy
  • Zoushuang Li, Junren Xiang, Xiao Liu, Xiaobo Li, Lijie Li, Bin Shan, Rong Chen
  • International Journal of Extreme Manufacturing
  • 2022-03-09
  • Tailoring a novel hierarchical cheese-like porous biochar from algae residue to boost sulfathiazole removal
  • Ke Wang, Yue Wang, Shiyu Zhang, Yi-di Chen, Rupeng Wang, Shih-Hsin Ho
  • Environmental Science & Ecotechnology
  • 2022-03-09
  • Giant magneto field effect in up-conversion amplified spontaneous emission via spatially extended states in organic-inorganic hybrid perovskites
  • Tangyao Shen, Jiajun Qin, Yujie Bai, Jia Zhang, Lei Shi, Xiaoyuan Hou, Jian Zi, Bin Hu
  • Opto-Electronic Advances
  • 2022-02-28



  • GLP-1 mimetics as a potential therapy for nonalcoholic steatohepatitis                                Epigenetic integrity of paternal imprints enhances the developmental potential of androgenetic haploid embryonic stem cells
    About
    |
    Contact
    |
    Copyright © PubCard