A context-free encoding scheme of protein sequences for predicting antigenicity of diverse influenza A viruses

Abstract

BackgroundThe evolution of influenza A viruses leads to the antigenic changes. Serological diagnosis of the antigenicity is usually labor-intensive, time-consuming and not suitable for early-stage detection. Computational prediction of the antigenic relationship between emerging and old strains of influenza viruses using viral sequences can facilitate large-scale antigenic characterization, especially for those viruses requiring high biosafety facilities, such as H5 and H7 influenza A viruses. However, most computational models require carefully designed subtype-specific features, thereby being restricted to only one subtype.MethodsIn this paper, we propose a Context-FreeEncoding Scheme (CFreeEnS) for pairs of protein sequences, which encodes a protein sequence dataset into a numeric matrix and then feeds the matrix into a downstream machine learning model. CFreeEnS is not only free from subtype-specific selected features but also able to improve the accuracy of predicting the antigenicity of influenza. Since CFreeEnS is subtype-free, it is applicable to predicting the antigenicity of diverse influenza subtypes, hopefully saving the biologists from conducting serological assays for highly pathogenic strains.ResultsThe accuracy of prediction on each subtype tested (A/H1N1, A/H3N2, A/H5N1, A/H9N2) is over 85%, and can be as high as 91.5%. This outperforms existing methods that use carefully designed subtype-specific features. Furthermore, we tested the CFreeEnS on the combined dataset of the four subtypes. The accuracy reaches 84.6%, much higher than the best performance 75.1% reported by other subtype-free models, i.e. regional band-based model and residue-based model, for predicting the antigenicity of influenza. Also, we investigate the performance of CFreeEnS when the model is trained and tested on different subtypes (i.e. transfer learning). The prediction accuracy using CFreeEnS is 84.3% when the model is trained on the A/H1N1 dataset and tested on the A/H5N1, better than the 75.2% using a regional band-based model.ConclusionsThe CFreeEnS not only improves the prediction of antigenicity on datasets with only one subtype but also outperforms existing methods when tested on a combined dataset with four subtypes of influenza viruses.Electronic supplementary materialThe online version of this article (doi:10.1186/s12864-018-5282-9) contains supplementary material, which is available to authorized users.

An Encoding Scheme Capturing Generic Priors and Properties of Amino Acids Improves Protein Classification

“…Herein, we improved our proposed method in [21] so that the encoding scheme can be applied to both protein sequences with varying lengths and protein sequence pairs, which covers the most situation of sequence analyses in bioinformatics. The method, CFreeEnS, is based on the AAindex database [22], which is the collection of amino acid indexes and mutation matrices from published work, representing physiochemic and biochemical properties related to the specificity and diversity of protein structures and functions.…”

“…Our previous work has demonstrated that CFreeEnS is effective in predicting the antigenic similarity between the hemagglutinin protein of influenza viral strains [21], indicating that CFreeEnS for protein sequence pairs can distinguish subtle differences between proteins within the same family.…”

“…Previously, we proposed an encoding scheme for protein sequence pairs, named CFreeEnS, to predict the antigenic similarity between the hemagglutinin proteins of influenza viruses, which was effective across multiple subtypes of influenza [21]. We hypothesized that the method captured intrinsic distinctions between amino acid pairs and was promising to be applied to other problems with aligned protein sequence pairs as the input.…”

“…1) Section II describes how CFreeEnS encodes the protein sequences and protein sequences pairs. The module dealing with protein sequence pairs has been presented in our previous work [21] so that we would only briefly introduce the framework. 2) Section III presents the applications of CFreeEnS.…”

Predicting Antigenicity of Influenza A Viruses Using biophysical ideas

“…Zhou et al . 24 proposed a Context-Free Encoding Scheme (CFreeEnS) prediction method that allows to be integrated with a large number of different substitution matrices for protein sequences.…”