Abstract
Receptor tyrosine kinases are essential proteins involved in cellular differentiation and proliferation in vivo and are heavily involved in allergic diseases, diabetes, and onset/proliferation of cancerous cells. Identifying the interacting partner of this protein, a growth factor ligand, will provide a deeper understanding of cellular proliferation/differentiation and other cell processes. In this study, we developed a method for predicting tyrosine kinase ligand-receptor pairs from their amino acid sequences. We collected tyrosine kinase ligand-receptor pairs from the Database of Interacting Proteins (DIP) and UniProtKB, filtered them by removing sequence redundancy, and used them as a dataset for machine learning and assessment of predictive performance. Our prediction method is based on support vector machines (SVMs), and we evaluated several input features suitable for tyrosine kinase for machine learning and compared and analyzed the results. Using sequence pattern information and domain information extracted from sequences as input features, we obtained 0.996 of the area under the receiver operating characteristic curve. This accuracy is higher than that obtained from general protein-protein interaction pair predictions.
Highlights
Tyrosine kinases are enzymes that phosphorylate, tyrosine residues, in proteins
We developed a new bioinformatics tool to predict the interacting pairs of a receptor tyrosine kinase from amino acid sequences using a machine learning approach based on support vector machine (SVM) [6]
This paper proposes two combination techniques: combining features of both sequence and domain information to be an input to SVM and combining prediction results obtained by sequence- and domain-based prediction models
Summary
Tyrosine kinases are enzymes that phosphorylate, tyrosine residues, in proteins. Upon binding of a ligand to the extracellular domain, the receptor tyrosine kinases dimerize and tyrosine kinase domains in the intracellular regions mutually phosphorylate certain tyrosine residues present on each other [3] This autophosphorylation activates tyrosine kinase and the enzyme gains the capacity to phosphorylate other protein substrates [3]. Identifying the interacting partner of this protein, a growth factor ligand, will improve our understanding of cellular proliferation/differentiation and other cell processes. It may allow predicting inhibitors of signal transduction, further leading to their practical application in drug design processes, such as the synthesis of an inhibitor that hinders cellular activity [5]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
