DeepRTCP: Predicting ATP-Binding Cassette Transporters Based on 1-Dimensional Convolutional Network

摘要

ATP-binding cassette(ABC) transporters can promote cells to absorb nutrients and excrete harmful substances. It plays a vital role in the transmembrane transport of macromolecules.Therefore, the identification of ABC transporters is of great significance for the biological research.This paper will introduce a novel method called DeepRTCP for predicting ABC transporters. DeepRTCP uses the deep convolutional neural network and a feature combined of reduced amino acid alphabet based tripeptide composition and PSSM to predict ABC transporters.We constructed a dataset named ABC 2020. It contains the latest ABC transporters downloaded from the Uniprot.We performed 10-fold cross-validation on DeepRTCP. The average accuracy of DeepRTCP is 95.96%. We compared DeepRTCP with the previous method for predicting ABC transporters. The experimental result shows that DeepRTCP improved the accuracy by 9.29%. It is anticipated that DeepRTCP can be used as an effective ABC transporter classifier which provides a reliable guidance for the research of ABC transporters.