Introduction
Therapeutic peptide is an important ingredient in the treatment of various diseases and drug discovery. The toxicity of peptides is one of the major challenges in peptide drug therapy. With the abundance of therapeutic peptides generated in the post-genomics era, it is a challenge to promptly identify toxicity peptides using computational methods. Although several efforts have been made, few algorithms are designed to identify whether a query peptide exhibits toxicity. Considering the varied levels of biological activities, the toxicity peptides should be further classified into multi-functional peptides. This study introduces a two-level predictor, ToxPre-2L, developed using the multi-view tensor learning and latent semantic learning framework. The proposed method utilized multi-label learning with feature induced labels to avoid the redundancy of information from each view. Then the multi-view tensor learning was employed to establish the latent semantic information among different views, while the low-rank constraint learning utilized the correlations information among multiple labels. Finally, we constructed an update toxicity peptide benchmark dataset to assess the effectiveness of the proposed method. Experimental results demonstrated that ToxPre-2L achieves a better performance than alternative computational methods in the prediction of toxicity peptides and their multi-functional types.
Figure 1. The framework of ToxPre-2L contains four stages. (A) The toxicity peptide dataset construction phase. (B) The feature extraction phase. The peptides are embedded by four feature-encoded methods that rely on sequential and physicochemical information. (C) The first-level stage. The input peptide sequences are first predicted by ToxPre-2L as TXP or Non-TXP. (D) The second-level stage. The predicted TXP sequences are further identified by ToxPre-2L as multi-label functional types.