Predicting the short-term success of human influenza virus variants with machine learning

Abstract

Seasonal influenza viruses are constantly changing and produce a different set of circulating strains each season. Small genetic changes can accumulate over time and result in antigenically different viruses; this may prevent the body’s immune system from recognizing those viruses. Due to rapid mutations, in particular, in the haemagglutinin (HA) gene, seasonal influenza vaccines must be updated frequently. This requires choosing strains to include in the updates to maximize the vaccines’ benefits, according to estimates of which strains will be circulating in upcoming seasons. This is a challenging prediction task. In this paper, we use longitudinally sampled phylogenetic trees based on HA sequences from human influenza viruses, together with counts of epitope site polymorphisms in HA, to predict which influenza virus strains are likely to be successful. We extract small groups of taxa (subtrees) and use a suite of features of these subtrees as key inputs to the machine learning tools. Using a range of training and testing strategies, including training on H3N2 and testing on H1N1, we find that successful prediction of future expansion of small subtrees is possible from these data, with accuracies of 0.71–0.85 and a classifier ‘area under the curve’ 0.75–0.9.

Deep clustering of bacterial tree images

“…We also compared tree shape statistics and our clustering patterns. For this purpose, we computed a set of tree shape statistics [ 37 , 38 ] for the trees on each cluster. We computed both unnormalized (electronic supplementary material, figure S2) as well as normalized versions ( figure 9 ) of each statistic, with the exception of those that are intrinsically normalized.…”

Towards evolutionary predictions: current promises and challenges

“…We argue that predicting and trying to influence evolution is more common than you may think, but it is not always easy to recognize because the jargon used in different fields is varied. For example, in the influenza virus literature, there are many articles on predicting evolution and these predictions are used to design vaccines for the next influenza season (Łuksza & Lässig 2014, Morris et al 2018, Barrat-Charlaix et al 2020, Hayati et al 2020. On the other hand, in the literature on the evolution of drug resistance in HIV, the words "evolution" and "prediction" are not used often.…”

“…The model could predict around one third of the mutational targets in a new but similar evolve and resequence experiment. Machine learning methods have also been used to predict the somatic evolution of cancer (Caravagna et al 2018, Gerhauser et al 2018) and success of influenza virus variants (Hayati et al 2020). A particularly promising future direction is the ability for machine learning methods to combine increasingly complex cancer genomic data with data on transcriptome, epigenome and advanced imaging to guide precision medicine (Gerstung et al 2020).…”

Utility of Artificial Intelligence Amidst the COVID 19 Pandemic: A Review

“…Machine learning has also been used in the past to predict the strains of influenza virus that are more likely to cause infection in a population in an upcoming year, and in turn, should constitute the year’s seasonal influenza vaccine. Successful prediction of the future expansion of small subtrees of hemagglutinins (HA) part of the viral antigenic set was possible from training H3N2 and testing on H1N1, using reconstructed timed phylogenetic tree [ 37 ]. Machine learning can also be used to predict the hosts of newly discovered viruses based on analysis of nucleoprotein gene sequences and spike gene sequences, and can be a useful additional tool for tracing back viral origins, especially when the data set is large and comparative analysis is difficult or time-consuming [ 38 ].…”