Peptide Resources

iQSP is a sequence-based predictor for quorum-sensing peptides analysis, integrating 18 physicochemical properties with support vector machine (SVM), accompanied by interpretable rules IR-QSP and a web service.

JenPep is a relational database supporting immunoinformatics research, containing quantitative binding data of peptides to Major Histocompatibility Complexes (MHCs) and Transmembrane Peptide Transporter (TAP), along with an annotated list of T-cell epitopes. It provides data support for epitope prediction tool development in cellular immunology and computational vaccinology research.

A two-stage computational framework for antiviral peptide (AVPs) identification, integrating contrastive learning and multi-feature fusion to enhance prediction performance and interpretability. The first stage screens AVPs from broad-spectrum peptide libraries, while the second stage accurately identifies AVPs targeting six viral families (Coronaviridae, Retroviridae, Herpesviridae, Paramyxoviridae, Orthomyxoviridae, Flaviviridae) and eight viruses (FIV, HCV, HIV, HPIV3, HSV1, INFVA, RSV, SARS-CoV).

ADPDeep is a deep learning-based tool for antidiabetic peptide (ADPs) prediction, enabling efficient screening via multi-channel neural network architectures and evolutionary feature preprocessing. The model comprises two core modules: ① single-channel convolutional neural network (CNN) and ② three-channel hybrid network (CNN+RNN+Bi-LSTM), modeling local sequence features and long-range dependencies respectively.

KELM-CPPpred is a kernel extreme learning machine (KELM)-based prediction model for cell-penetrating peptides, integrating amino acid composition, dipeptide composition, pseudo amino acid composition, and motif-based hybrid features.