Predicting ATP-Binding Cassette Transporters Using Rough Set and Random Forest Model

Abstract

In reality, all homosapiens species benefit greatly from the function of ATP-binding cassette (ABC) transporter proteins. Many studies have focused specifically on the drug transporter prediction because to the recent advancements in biology. Machine learning and soft computing with data mining methodologies have been used to identify valid motif sequences from biological datasets in general. In this work, the authors analysed the research on the ABC transporter with the prediction of cellular cholesterol. This research is focused on this new area, as ABC transporters are frequently employed as pharmacological targets. In this instance, the authors have focused on the ABC transporter's legitimate signature motif involving plasma membrane cholesterol. The authors used an unique hybrid model that is rough set with random forest for the prediction of motif structure that has clinical significance for predicting relevant motif sequences.