Pepmol

PepMol: A Comprehensive Platform for Peptide and Small Molecule Function Prediction Understanding the functional properties of peptides and the pharmacokinetic characteristics of small molecules is essential for drug discovery and development. PepMol is a cutting-edge computational platform designed to address these challenges by leveraging advanced machine learning and quantum chemistry-based models.

肽结构
Peptide structures

PepUniBERT

PepUniBERT is a general-purpose large language model for peptide function and property prediction, which can easily and efficiently predict the function of 20 peptides and the subcellular localization of peptides.

View details

MolFFNN

For the prediction of blood-brain barrier permeability for small molecules, we have integrated multiple descriptors to achieve optimal predictive performance. These descriptors include information extracted from the Simplified Molecular-Input Line-Entry System (SMILES), molecular graph data, molecular fingerprints, and quantum chemical properties of the molecules.

View details
Molecule structure 1