Machine Learning for the Identification of Viral Attachment Machinery from Respiratory Virus Sequences

At the outset of an emergent viral respiratory pandemic, sequence data is among the first molecular information available. As viral attachment machinery is a key target for therapeutic and prophylactic interventions, rapid identification of viral "spike" proteins from sequence can significantly accelerate the development of medical countermeasures. For five families of respiratory viruses, covering the vast majority of airborne and droplet-transmitted diseases, host cell entry is mediated by the binding of viral surface glycoproteins that interact with a host cell receptor. In this report it is shown that sequence data for an unknown virus belonging to one of the five families above provides sufficient information to identify the protein(s) responsible for viral attachment and to permit an assignment of viral family. Random forest models that take as input a set of respiratory viral sequences can classify the protein as "spike" vs. non-spike based on predicted secondary structure elements alone (with 97.8 % correctly classified) or in combination with N-glycosylation related features (with 98.1 % correctly classified). In addition, a Random Forest model developed using the same dataset and only secondary structural elements was able to predict the respiratory virus family of each protein sequence correctly 89.0 % of the time. Models were validated through 10-fold cross-validation as well as bootstrapping. Surprisingly, we showed that secondary structural element and N-glycosylation features were sufficient for model generation. The ability to rapidly identify viral attachment machinery directly from sequence data holds the potential to accelerate the design of medical countermeasures for future pandemics.