Welcome to ToxIBTL server

Peptides have emerged as a promising class of pharmaceuticals for various diseases treatment poised between traditional small molecule drugs and therapeutic proteins. However, one of the key bottlenecks preventing them from therapeutic peptides is their toxicity toward human cells, and few available algorithms for predicting toxicity are specially designed for short-length peptides. Therefore, there is a need to develop a more accurate method for peptide toxicity prediction to reduce a large number of false positives and thus improve the confidence of the predicted toxic peptides, which can reduce the cycle of the peptide-based drugs developing.

In this study, we proposed ToxIBTL, we present ToxIBTL, a novel deep learning framework by exploiting the information bottleneck principle and transfer learning to predict the toxicity of peptides as well as proteins. Specifically, we use evolutionary information and physicochemical properties of peptide sequences and integrate the information bottleneck principle into a feature representation learning scheme to retain relevant information while minimizing the amount of other excess information in the obtained features. Moreover, transfer learning is introduced to transfer the knowledge contained in proteins to peptides, which aims to improve the feature representation capability. Extensive experimental results demonstrate that ToxIBTL not only achieves a higher prediction performance than state-of-the-art methods on the peptide dataset but also has a competitive performance on the protein dataset.

ToxIBTL: prediction of peptide toxicity based on information bottleneck and transfer learning

October, 20th, 2021: the first version of ToxIBTL server was established.