PreTP-2L: identification of therapeutic peptides and their types using two-layer ensemble learning framework
Related Experiment Video
Updated: Aug 4, 2025
Peptide-based Identification of Functional Motifs and their Binding Partners
Published on: June 30, 2013
Ke Yan1, Yichen Guo1, Bin Liu1,2
1School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China.
Motivation:
Therapeutic peptides play an important role in immune regulation. Recently various therapeutic peptides have been used in the field of medical research, and have great potential in the design of therapeutic schedules. Therefore, it is essential to utilize the computational methods to predict the therapeutic peptides. However, the therapeutic peptides cannot be accurately predicted by the existing predictors. Furthermore, chaotic datasets are also an important obstacle of the development of this important field. Therefore, it is still challenging to develop a multi-classification model for identification of therapeutic peptides and their types.
Results:
In this work, we constructed a general therapeutic peptide dataset. An ensemble-learning method named PreTP-2L was developed for predicting various therapeutic peptide types. PreTP-2L consists of two layers. The first layer predicts whether a peptide sequence belongs to therapeutic peptide, and the second layer predicts if a therapeutic peptide belongs to a particular species.
Availability And Implementation:
A user-friendly webserver PreTP-2L can be accessed at http://bliulab.net/PreTP-2L.
