Machine Learning Using Template-Based-Predicted Structure of Haemagglutinin Predicts Pathogenicity of Avian Influenza
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Deep learning presents a promising approach to complex biological classifications, contingent upon the availability of well-curated datasets. This study addresses the challenge of analyzing threedimensional protein structures by introducing a novel pipeline that utilizes open-source tools to convert protein structures into a format amenable to computational analysis. Applying a twodimensional convolutional neural network (CNN) to a dataset of 12,143 avian influenza virus genomes from 64 countries, encompassing 119 hemagglutinin (HA) and neuraminidase (NA) types, we achieved significant classification accuracy. The pathogenicity was determined based on the presence of H5 or H7 subtypes, and our models, ranging from zero to six mid-layers, indicated that a four-layer model most effectively identified highly pathogenic strains, with accuracies over 0.9. To enhance our approach, we incorporated Principal Component Analysis (PCA) for dimensionality reduction and one-class SVM for abnormality detection, improving model robustness through bootstrapping. Furthermore, the K-nearest neighbor (K-NN) algorithm was fine-tuned via hyperparameter optimization to corroborate the findings. The PCA identified distinct clustering for pathogenic HA, yielding an AUC of up to 0.85. The optimized K-NN model demonstrated an impressive accuracy between 0.96 and 0.97. These combined methodologies underscore our deep learning framework's capacity for rapid and precise identification of pathogenic avian influenza strains, thus providing a critical tool for managing global avian influenza threats.
Abstract
Deep learning presents a promising approach to complex biological classifications, contingent upon the availability of well-curated datasets. This study addresses the challenge of analyzing threedimensional protein structures by introducing a novel pipeline that utilizes open-source tools to convert protein structures into a format amenable to computational analysis. Applying a twodimensional convolutional neural network (CNN) to a dataset of 12,143 avian influenza virus genomes from 64 countries, encompassing 119 hemagglutinin (HA) and neuraminidase (NA) types, we achieved significant classification accuracy. The pathogenicity was determined based on the presence of H5 or H7 subtypes, and our models, ranging from zero to six mid-layers, indicated that a four-layer model most effectively identified highly pathogenic strains, with accuracies over 0.9. To enhance our approach, we incorporated Principal Component Analysis (PCA) for dimensionality reduction and one-class SVM for abnormality detection, improving model robustness through bootstrapping. Furthermore, the K-nearest neighbor (K-NN) algorithm was fine-tuned via hyperparameter optimization to corroborate the findings. The PCA identified distinct clustering for pathogenic HA, yielding an AUC of up to 0.85. The optimized K-NN model demonstrated an impressive accuracy between 0.96 and 0.97. These combined methodologies underscore our deep learning framework's capacity for rapid and precise identification of pathogenic avian influenza strains, thus providing a critical tool for managing global avian influenza threats.
참고문헌 (20)
- Bouvier NM, "The biology of influenza viruses", Vaccine 26 Suppl, 4, pp.D49~D53 (2008)
- Krammer F, "Influenza", Nat. Rev. Dis. Primers, 4, pp.3~ (2018)
- Long JS, "Host and viral determinants of influenza A virus species specificity", Nat. Rev. Microbiol, 17, pp.67~81 (2019)
- Blagodatski A, "Avian influenza in wild birds and poultry : dissemination pathways, monitoring methods, and virus ecology", Pathogens, 10, pp.630~ (2021)
- Taubenberger JK, "1918 Influenza : the mother of all pandemics", Emerg. Infect. Dis, 12, pp.15~22 (2006)
- Seltzer ML, "The data deluge : challenges and opportunities of unlimited data in statistical signal processing", Proc. IEEE Int. Conf. Acoust. Speech Signal Process, 2009, pp.3701~3704 (2009)
- LeCun Y, "Deep learning", Nature, 521, pp.436~444 (2015)
- AlQuraishi M, "ProteinNet : a standardized data set for machine learning of protein structure", BMC Bioinformatics, 20, pp.311~ (2019)
- Wang S, "VIGOR, an annotation program for small viral genomes", BMC Bioinformatics, 11, pp.451~ (2010)
- Fiser A, "Modeller : generation and refinement of homology-based protein structure models", Methods Enzymol, 374, pp.461~491 (2003)
- Lin T, "The hemagglutinin structure of an avian H1N1 influenza A virus", Virology, 392, pp.73~81 (2009)
- Kazutaka Katoh, "MAFFT : a novel method for rapid multiple sequence alignment based on fast Fourier transform", Nucleic Acids Res, 30, pp.3059~3066 (2002)
- Lawrence S, "Overfitting and neural networks: conjugate gradient and backpropagation", Proc IEEE-INNS-ENNS Int Joint Conf Neural Netw, IJCNN 2000, Neural Computing: New Challenges and Perspectives for the New Millennium, pp.114~119 (2000)
- Visa S, "CEUR Workshop Proc, Vol. 710", pp.120~127 (2011)
- Trappenberg TP, "Fundamentals of Machine Learning", pp.38~65 (2019), Oxford Univ Press
- Hunter JD, "Matplotlib : A 2D Graphics Environment", Comput Sci Eng, 9, pp.90~95 (2007)
- Claas EC, "Human influenza A H5N1 virus related to a highly pathogenic avian influenza virus", Lancet, 351, pp.472~477 (1998)
- Fouchier RA, "Avian influenza A virus(H7N7)associated with human conjunctivitis and a fatal case of acute respiratory distress syndrome", Proc. Natl. Acad. Sci. USA, 101, pp.1356~1361 (2004)
- Ramazi P, "Predicting insect outbreaks using machine learning : a mountain pine beetle case study", Ecol Evol, 11, pp.13014~13028 (2021)
- Chapelle O, "Semi-Supervised Learning", pp.57~72 (2006), MIT Press