Modeling the pharmacokinetics profiles of therapeutic peptides by chemoinformatics methods. PEPTIMOL.
Peptides have been hailed as the future drugs, thanks to their high specificity and activity, as well as their easy degradation. These factors imply that they generally have low toxicity and few side effects and are administered in small doses. Peptides have multiple therapeutic applications, including antivirals, antifungals, antibiotics, modulators of the immune, cardiovascular and nervous systems, etc. However, it has been shown that therapeutically relevant peptides generally exhibit limited ability to diffuse across bio-membranes, such as the human gastrointestinal epithelium, and have low stability. Furthermore, these peptides’ short plasma half-life and low stability are administered by injection, often several times daily. Therefore, it is essential to develop methods to model the bioactivity of peptides, predict their pharmacokinetic profiles, and ultimately allow the design of new peptide chains tailored to predetermined bioactivity profiles. These modeling systems will enable the design of peptides with favorable therapeutic efficacy and, above all, ensure their adequate bioavailability and administration (preferably oral). On this basis, the objectives of PeptiMOL are:
⦁ Define parameters (numerical molecular descriptors) to characterize peptides’ structural, compositional, and physicochemical properties and develop an easy-to-use Java-based tool for their calculation.
⦁ Build math to predict the PK properties of peptides using the most advanced statistical techniques and machine learning models.
⦁ Deploy the developed models on a Java-based cheminformatics platform that will allow end-users to screen peptide libraries or design new peptide structures with desirable physicochemical and PK profiles.
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 893810.