Predicting antigenic variants of H1N1 influenza virus based on epidemics and pandemics using a stacking model

Abstract

H1N1 is the earliest emerging subtype of influenza A viruses with available genomic sequences, has caused several pandemics and seasonal epidemics, resulting in millions of deaths and enormous economic losses. Timely determination of new antigenic variants is crucial for the vaccine selection and flu prevention. In this study, we chronologically divided the H1N1 strains into several periods in terms of the epidemics and pandemics. Computational models have been constructed to predict antigenic variants based on epidemic and pandemic periods. By sequence analysis, we demonstrated the diverse mutation patterns of HA1 protein on different periods and that an individual model built upon each period can not represent the variations of H1N1 virus. A stacking model was established for the prediction of antigenic variants, combining all the variation patterns across periods, which would help assess a new influenza strain's antigenicity. Three different feature extraction methods, i.e. residue-based, regional band-based and epitope region-based, were applied on the stacking model to verify its feasibility and robustness. The results showed the capability of determining antigenic variants prediction with accuracy as high as 0.908 which performed better than any of the single models. The prediction performance using the stacking model indicates clear distinctions of mutation patterns and antigenicity between epidemic and pandemic strains. It would also facilitate rapid determination of antigenic variants and influenza surveillance.

Fig 1. The workflow of stacking model for the antigenic variants prediction based on pandemics and epidemics.

Fig 2. Position-dependent entropy.

Moving average position information entropy was calculated with a window size of 11 for HA1 protein if influenza A virus in each period, that is period 2 (black), period 3 (yellow), period 4 (red), period 5 (green) and period 6 (blue). The amino acid position are in H1 numbering system [37].

Fig 3. Performance comparison of residue-based, regional band-based and epitope-based computational models trained and tested across different types.

“acc”: accuracy; “sen”: sensitivity; “spe”: specificity.

Fig 4. The performance of stacking model with imbalanced and balanced datasets based on three feature generation methods.

“acc”: accuracy; “sen”: sensitivity; “spe”: specificity. (a) The performance of residue-based stacking model (b) The performance of ten regional-based stacking model (c) The performance of five epitope-based stacking model.

Fig 5. The Receiver Operating Characteristic (ROC) curve of the stacking model predicting the antigenic variants of influenza A H1N1 virus.