PEGASUS: Unlocking Polarity in Cell-Permeable Cyclic Peptides Using AI Models Built on Massively Parallel Biological Assays
Authors:
- Cole BakerCBCole Baker
- Francis A. AcquahFAFrancis A. Acquah
- Lakshmi G. ChivukulaLCLakshmi G. Chivukula
- Liping WuLWLiping Wu
- Laurence Philippe-VenecLPLaurence Philippe-Venec
- Mostafa AbediMAMostafa Abedi
- Yujun TaoYTYujun Tao
- Daniel RamírezDRDaniel Ramírez
- Matthew D. McCoyMMMatthew D. McCoy
- Brandon MooreBMBrandon Moore
Open Access
- 22 December 2025
- journal article
- Published by American Chemical Society (ACS) in Journal of Medicinal Chemistry
- Vol. 69 (5) , 5175-5198
Abstract
Cyclic peptides are a promising class of therapeutics that have the potential for oral bioavailability but are hindered by cell membrane permeability and aqueous solubility. Artificial intelligence (AI) can address the challenging multiparameter optimization of cyclic peptides, but it relies on wet lab ground truth biological data that are scarce, sparse, and dominated by hydrophobic amino acids. Here, we introduce PEGASUS, a multimodal AI model that achieves state-of-the-art performance in predicting cell membrane permeability. PEGASUS integrates an innovative high-throughput proxy biological assay (1910 PPA), which generates billions of cyclic peptides separated by permeability-related characteristics with solvent-dependent computational simulations. PEGASUS informs rules for designing cell-permeable cyclic peptides with high aqueous solubility that resemble FDA-approved therapeutics based on polarity and charge. Combining these rules with a novel generative AI, we design the first published cyclic peptides with more than two polar or ionizable fragments to achieve in vitro cell membrane permeability.Keywords
This publication has 88 references indexed in Scilit:
- Scaffold Splits Overestimate Virtual Screening Performance2024
- Cyclic Peptides for Drug DevelopmentAngewandte Chemie International Edition, 2023
- A Selection of Macrocyclic Peptides That Bind STING From an mRNA‐Display Library With Split Degenerate CodonsAngewandte Chemie International Edition, 2021
- Robust Atomistic Modeling of Materials, Organometallic, and Biochemical SystemsAngewandte Chemie International Edition, 2020
- Evaluating the Role of Solubility in Oral Absorption of Poorly Water‐Soluble Drugs Using Physiologically‐Based Pharmacokinetic ModelingClinical Pharmacology & Therapeutics, 2019
- Cyclic peptide natural products chart the frontier of oral bioavailability in the pursuit of undruggable targetsCurrent Opinion in Chemical Biology, 2017
- On the Impact of Data Set Size in Transfer Learning Using Deep Neural Networks2016
- Acetonitrile, the polarity chameleonAnalytical and Bioanalytical Chemistry, 2010
- Physiochemical drug properties associated with in vivo toxicological outcomesBioorganic & Medicinal Chemistry Letters, 2008
- The Remarkable Transport Mechanism of P-Glycoprotein: A Multidrug TransporterJournal of Bioenergetics and Biomembranes, 2005