Novel approach for identification of influenza virus host range and zoonotic transmissible sequences by determination of host-related associative positions in viral genome segments

Abstract

BackgroundRecent (2013 and 2009) zoonotic transmission of avian or porcine influenza to humans highlights an increase in host range by evading species barriers. Gene reassortment or antigenic shift between viruses from two or more hosts can generate a new life-threatening virus when the new shuffled virus is no longer recognized by antibodies existing within human populations. There is no large scale study to help understand the underlying mechanisms of host transmission. Furthermore, there is no clear understanding of how different segments of the influenza genome contribute in the final determination of host range.MethodsTo obtain insight into the rules underpinning host range determination, various supervised machine learning algorithms were employed to mine reassortment changes in different viral segments in a range of hosts. Our multi-host dataset contained whole segments of 674 influenza strains organized into three host categories: avian, human, and swine. Some of the sequences were assigned to multiple hosts. In point of fact, the datasets are a form of multi-labeled dataset and we utilized a multi-label learning method to identify discriminative sequence sites. Then algorithms such as CBA, Ripper, and decision tree were applied to extract informative and descriptive association rules for each viral protein segment.ResultWe found informative rules in all segments that are common within the same host class but varied between different hosts. For example, for infection of an avian host, HA14V and NS1230S were the most important discriminative and combinatorial positions.ConclusionHost range identification is facilitated by high support combined rules in this study. Our major goal was to detect discriminative genomic positions that were able to identify multi host viruses, because such viruses are likely to cause pandemic or disastrous epidemics.Electronic supplementary materialThe online version of this article (doi:10.1186/s12864-016-3250-9) contains supplementary material, which is available to authorized users.

Identifying mutation positions in all segments of influenza genome enables better differentiation between pandemic and seasonal strains

“…The distinguished power of CBA algorithm to discover and combine the mutilations from different segments of influenza for distinguishing of pandemic sequences was remarkable in this study. In line with this finding, CBA has demonstrated high performance in identification of host range of influenza sequence (avian, human, and swine) by combination of mutation positions in all segments of influenza as host discriminative rules, leading to the establishment of a novel approach for identification of influenza virus host range and zoonotic transmissible sequences (Kargarfard et al, 2016). CBA is a high performance and robust classifier that integrates classification algorithm with association rule mining algorithm, the two key discriminative machine learning approaches techniques (Kargarfard et al, 2015).…”

“…The final aim of these data mining techniques is to extract knowledge (underlying rules) from a dataset and converting this knowledge into a perceptible format for further use (Jamali et al, 2016;Ebrahimie et al, 2018;Sharifi et al, 2018). The most popular method for discovering relations in a dataset is "association rule generation" (Ebrahimi et al, 2010;Kargarfard et al, 2015;Kargarfard et al, 2016). Human readable rules imply to data presented in a format which is readily interpreted by humans.…”

The First Implication of Image Processing Techniques on Influenza A Virus Sub-Typing Based on HA/NA Protein Sequences, using Convolutional Deep Neural Network

“…Influenza A pandemics of the last century (H1N1, H2N2, and H3N2), avian H5N1 and recent H7N9 have been infecting the human with high mortality rates [22]. Multiple gene reassortant of viruses from various sources (such as swine, avian and even human populations) have been blamed for the H1N1 pandemic in 2009 and novel reassortant of H7N9 in 2013; expecting more pandemics to happen in near future due to high reassortment capacity of the virus [23]. Therefore understanding the biological bases of influenza virus A evolution and subtype differentiation is critical.…”

The Central Role of Non-Structural Protein 1 (NS1) in Influenza Biology and Infection

“…Finally, the dataset was trained using different ML models, such as decision trees, and it was possible to pinpoint the most discriminative and combinatorial positions, regarding the host range. NS1 was one of the proteins associated with high human host range [165].…”