CPPLocPred identifies Cell-Penetrating Peptides and predicts their subcellular destination – Cytoplasm, Mitochondria, Nucleus, Endo_lysosome and Others – using Machine Learning models trained on experimentally validated sequences.
Identify whether a peptide sequence has cell-penetrating activity using ExtraTree (ET)-based ML model trained on curated experimental data.
Predict the intracellular destination of CPPs - Cytoplasm, Mitochondria, Nucleus, Endo_lysosome and Others.
Scan full-length protein sequences to discover embedded CPP motifs and map localization-determining sequence patterns.
Cell-penetrating peptides (CPPs) are short peptides, typically 5–30 amino acids, capable of crossing lipid bilayer membranes. They are widely studied as vectors for intracellular drug delivery, gene therapy, and molecular imaging agents.
Understanding not only whether a peptide is cell-penetrating, but where it localizes inside the cell, is critical for rational design of targeted therapeutics. CPPLocPred provides a comprehensive in silico platform addressing both questions in a single submission.
The server is built on a curated dataset of experimentally validated CPP sequences with confirmed subcellular localization, enabling high-confidence predictions for novel peptide sequences submitted by users.
General cytosolic distribution following membrane translocation.
Nuclear-targeted CPPs bearing NLS-like recognition sequences.
Mitochondria-penetrating peptides with MTS targeting signals.
Vesicular or endoplasmic reticulum targeting motif patterns.
Targeting other subcelluar locations.
