tetano
Editor, Senior Moderator
Gigascience
. 2025 Jan 6:14:giaf089.
doi: 10.1093/gigascience/giaf089. WaveSeekerNet: accurate prediction of influenza A virus subtypes and host source using attention-based deep learning
Hoang-Hai Nguyen[SUP] 1 2 [/SUP], Josip Rudar[SUP] 1 3 [/SUP], Nathaniel Lesperance[SUP] 3 [/SUP], Oksana Vernygora[SUP] 1 [/SUP], Graham W Taylor[SUP] 4 5 [/SUP], Chad Laing[SUP] 6 [/SUP], David Lapen[SUP] 7 [/SUP], Carson K Leung[SUP] 2 [/SUP], Oliver Lung[SUP] 1 8 [/SUP]
Affiliations
Background: Influenza A virus (IAV) poses a significant threat to animal health globally, with its ability to overcome species barriers and cause pandemics. Rapid and accurate IAV subtypes and host source prediction is crucial for effective surveillance and pandemic preparedness. Deep learning has emerged as a powerful tool for analyzing viral genomic sequences, offering new ways to uncover hidden patterns associated with viral characteristics and host adaptation.
Findings: We introduce WaveSeekerNet, a novel deep learning model for accurate and rapid prediction of IAV subtypes and host source. The model leverages attention-based mechanisms and efficient token mixing schemes, including the Fourier Transform and the Wavelet Transform, to capture intricate patterns within viral RNA and protein sequences. Extensive experiments on diverse datasets demonstrate WaveSeekerNet's superior performance to existing models that use the traditional self-attention mechanism. Notably, WaveSeekerNet rivals VADR (Viral Annotation DefineR) in subtype prediction using the high-quality RNA sequences, achieving the maximum score of 1.0 on metrics, including the Balanced Accuracy, F1-score (Macro Average), and Matthews Correlation Coefficient. Our approach to subtype and host source prediction also exceeds the pretrained ESM-2 (Evolutionary Scale Modeling) models with respect to generalization performance and computational cost. Furthermore, WaveSeekerNet exhibits remarkable accuracy in distinguishing between human, avian, and other mammalian hosts. The ability of WaveSeekerNet to flag potential cross-species transmission events underscores its significant value for real-time surveillance and proactive pandemic preparedness efforts.
Conclusions: WaveSeekerNet's superior performance, efficiency, and ability to flag potential cross-species transmission events highlight its potential for real-time surveillance and pandemic preparedness. This model represents a significant advancement in applying deep learning for IAV classification and holds promise for future epidemiological, veterinary studies, and public health interventions.
Keywords: Fourier Transform; Wavelet Transform; alternate attention mechanisms; antigenic types; chaos game representation; deep learning; influenza A virus; viral genomics; viral host source.
. 2025 Jan 6:14:giaf089.
doi: 10.1093/gigascience/giaf089. WaveSeekerNet: accurate prediction of influenza A virus subtypes and host source using attention-based deep learning
Hoang-Hai Nguyen[SUP] 1 2 [/SUP], Josip Rudar[SUP] 1 3 [/SUP], Nathaniel Lesperance[SUP] 3 [/SUP], Oksana Vernygora[SUP] 1 [/SUP], Graham W Taylor[SUP] 4 5 [/SUP], Chad Laing[SUP] 6 [/SUP], David Lapen[SUP] 7 [/SUP], Carson K Leung[SUP] 2 [/SUP], Oliver Lung[SUP] 1 8 [/SUP]
Affiliations
- PMID: 40880133
- DOI: 10.1093/gigascience/giaf089
Background: Influenza A virus (IAV) poses a significant threat to animal health globally, with its ability to overcome species barriers and cause pandemics. Rapid and accurate IAV subtypes and host source prediction is crucial for effective surveillance and pandemic preparedness. Deep learning has emerged as a powerful tool for analyzing viral genomic sequences, offering new ways to uncover hidden patterns associated with viral characteristics and host adaptation.
Findings: We introduce WaveSeekerNet, a novel deep learning model for accurate and rapid prediction of IAV subtypes and host source. The model leverages attention-based mechanisms and efficient token mixing schemes, including the Fourier Transform and the Wavelet Transform, to capture intricate patterns within viral RNA and protein sequences. Extensive experiments on diverse datasets demonstrate WaveSeekerNet's superior performance to existing models that use the traditional self-attention mechanism. Notably, WaveSeekerNet rivals VADR (Viral Annotation DefineR) in subtype prediction using the high-quality RNA sequences, achieving the maximum score of 1.0 on metrics, including the Balanced Accuracy, F1-score (Macro Average), and Matthews Correlation Coefficient. Our approach to subtype and host source prediction also exceeds the pretrained ESM-2 (Evolutionary Scale Modeling) models with respect to generalization performance and computational cost. Furthermore, WaveSeekerNet exhibits remarkable accuracy in distinguishing between human, avian, and other mammalian hosts. The ability of WaveSeekerNet to flag potential cross-species transmission events underscores its significant value for real-time surveillance and proactive pandemic preparedness efforts.
Conclusions: WaveSeekerNet's superior performance, efficiency, and ability to flag potential cross-species transmission events highlight its potential for real-time surveillance and pandemic preparedness. This model represents a significant advancement in applying deep learning for IAV classification and holds promise for future epidemiological, veterinary studies, and public health interventions.
Keywords: Fourier Transform; Wavelet Transform; alternate attention mechanisms; antigenic types; chaos game representation; deep learning; influenza A virus; viral genomics; viral host source.