DeepFam: Deep learning based alignment-free method for protein family modeling and prediction

Abstract

Recently, there are a large number of newly sequenced proteins by the next- generation sequencing technologies. However, biological experiments are too expensive to characterize such a large number of protein sequences, thus protein function prediction is primarily done by computational mod- eling methods, such as profile hidden Markov model (pHMM) and k-mer based methods. Nevertheless, existing methods have some limitations

k- mer based methods are not accurate enough to assign protein functions and pHMM is not fast enough to handle large number of protein sequences from numerous genome projects. Therefore, a more accurate and faster protein function prediction method is needed. In this paper, we introduce DeepFam, an alignment-free method that can extract functional information directly from sequences without the need of multiple sequence alignments. Through extensive experiments using the Clusters of Orthologous Groups (COGs) and G protein-coupled receptor (GPCR) dataset, DeepFam showed higher performance in predicting func- tions of proteins compared to the state- of-the-art methods, both alignment- free and alignment-based methods. Additionally, we showed that DeepFam has a power of capturing conserved regions to model protein families. In fact, DeepFam was able to detect conserved regions documented in the Prosite database while predicting functions of proteins. Our deep learn- ing method will be useful in characterizing functions of the ever increasing protein sequences. Implementation of algorithm is available at https://bhi- kimlab.github.io/DeepFam.