Dataset Information

Antigenicity prediction and vaccine recommendation of human influenza virus A (H3N2) using convolutional neural networks.

ABSTRACT: The rapid evolution of influenza A viruses poses a great challenge to vaccine development. Analytical and machine learning models have been applied to facilitate the process of antigenicity determination. In this study, we designed deep convolutional neural networks (CNNs) to predict Influenza antigenicity. Our model is the first that systematically analyzed 566 amino acid properties and 141 amino acid substitution matrices for their predictability. We then optimized the structure of the CNNs using particle swarm optimization. The optimal neural networks outperform other predictive models with a blind validation accuracy of 95.8%. Further, we applied our model to vaccine recommendations in the period 1997 to 2011 and contrasted the performance of previous vaccine recommendations using traditional experimental approaches. The results show that our model outperforms the WHO recommendation and other existing models and could potentially improve the vaccine recommendation process. Our results show that WHO often selects virus strains with small variation from year to year and learns slowly and recovers once coverage dips very low. In contrast, the influenza strains selected via our CNN model can differ quite drastically from year to year and exhibit consistently good coverage. In summary, we have designed a comprehensive computational pipeline for optimizing a CNN in the modeling of Influenza A antigenicity and vaccine recommendation. It is more cost and time-effective when compared to traditional hemagglutination inhibition assay analysis. The modeling framework is flexible and can be adopted to study other type of viruses.

SUBMITTER: Lee EK

PROVIDER: S-EPMC7734114 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:The prediction of breeding values and phenotypes is of central importance for both livestock and crop breeding. In this study, we analyze the use of artificial neural networks (ANN) and, in particular, local convolutional neural networks (LCNN) for genomic prediction, as a region-specific filter corresponds much better with our prior genetic knowledge on the genetic architecture of traits than traditional convolutional neural networks. Model performances are evaluated on a simulated maize data panel (n = 10,000; p = 34,595) and real Arabidopsis data (n = 2,039; p = 180,000) for a variety of traits based on their predictive ability. The baseline LCNN, containing one local convolutional layer (kernel size: 10) and two fully connected layers with 64 nodes each, is outperforming commonly proposed ANNs (multi layer perceptrons and convolutional neural networks) for basically all considered traits. For traits with high heritability and large training population as present in the simulated data, LCNN are even outperforming state-of-the-art methods like genomic best linear unbiased prediction (GBLUP), Bayesian models and extended GBLUP, indicated by an increase in predictive ability of up to 24%. However, for small training populations, these state-of-the-art methods outperform all considered ANNs. Nevertheless, the LCNN still outperforms all other considered ANNs by around 10%. Minor improvements to the tested baseline network architecture of the LCNN were obtained by increasing the kernel size and of reducing the stride, whereas the number of subsequent fully connected layers and their node sizes had neglectable impact. Although gains in predictive ability were obtained for large scale data sets by using LCNNs, the practical use of ANNs comes with additional problems, such as the need of genotyping all considered individuals, the lack of estimation of heritability and reliability. Furthermore, breeding values are additive by design, whereas ANN-based estimates are not. However, ANNs also comes with new opportunities, as networks can easily be extended to account for additional inputs (omics, weather etc.) and outputs (multi-trait models), and computing time increases linearly with the number of individuals. With advances in high-throughput phenotyping and cheaper genotyping, ANNs can become a valid alternative for genomic prediction.

Project description:Human influenza A viruses are rapidly evolving pathogens that cause substantial morbidity and mortality in seasonal epidemics around the globe. To ensure continued protection, the strains used for the production of the seasonal influenza vaccine have to be regularly updated, which involves data collection and analysis by numerous experts worldwide. Computer-guided analysis is becoming increasingly important in this problem due to the vast amounts of generated data. We here describe a computational method for selecting a suitable strain for production of the human influenza A virus vaccine. It interprets available antigenic and genomic sequence data based on measures of antigenic novelty and rate of propagation of the viral strains throughout the population. For viral isolates sampled between 2002 and 2007, we used this method to predict the antigenic evolution of the H3N2 viruses in retrospective testing scenarios. When seasons were scored as true or false predictions, our method returned six true positives, three false negatives, eight true negatives, and one false positive, or 78% accuracy overall. In comparison to the recommendations by the WHO, we identified the correct antigenic variant once at the same time and twice one season ahead. Even though it cannot be ruled out that practical reasons such as lack of a sufficiently well-growing candidate strain may in some cases have prevented recommendation of the best-matching strain by the WHO, our computational decision procedure allows quantitative interpretation of the growing amounts of data and may help to match the vaccine better to predominating strains in seasonal influenza epidemics. Importance: Human influenza A viruses continuously change antigenically to circumvent the immune protection evoked by vaccination or previously circulating viral strains. To maintain vaccine protection and thereby reduce the mortality and morbidity caused by infections, regular updates of the vaccine strains are required. We have developed a data-driven framework for vaccine strain prediction which facilitates the computational analysis of genetic and antigenic data and does not rely on explicit evolutionary models. Our computational decision procedure generated good matches of the vaccine strain to the circulating predominant strain for most seasons and could be used to support the expert-guided prediction made by the WHO; it thus may allow an increase in vaccine efficacy.

Dataset Information

Antigenicity prediction and vaccine recommendation of human influenza virus A (H3N2) using convolutional neural networks.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets