Contrastive Learning-Enhanced Drug Metabolite Prediction Drives the Discovery of an Orally Bioavailable RSK4 Inhibitor for Esophageal Cancer
Authors:
Preprint
Abstract
Drug metabolism liabilities are a major bottleneck in drug development, necessitating accurate metabolite prediction tools. While AI-driven methods have advanced, challenges remain in achieving high-precision, robustness, broad reaction coverage and seamless integration into the drug development workflow. To address this, we first constructed the most comprehensive human-specific drug metabolism database to date, encompassing 11,665 human metabolic reactions and 2,497 high-quality rules. Leveraging this resource, we developed ConMeter ( Con trastive learning and feature interaction based Met abolic R eaction prediction), a novel model integrating chemical feature interaction and contrastive learning. ConMeter demonstrates significant improvements, achieving ∼80% accuracy in identifying at least one metabolite within the top 5 predictions and showing an average 25% relative enhancement in ranking true positives compared to state-of-the-art methods. The comprehensive database also expands the range of predictable metabolic reactions. To demonstrate the utility of ConMeter, we integrated it into a metabolite prediction-guided drug design strategy aimed at addressing the low oral bioavailability of a metabolically vulnerable RSK4 lead compound — a pervasive issue among known RSK inhibitors. This strategy successfully yielded R636, a novel RSK4 inhibitor exhibiting remarkably improved bioavailability (a 63-fold increase, reaching 63% absolute bioavailability) while maintaining its potent activity. Notably, R636 showed favorable safety profile and significant anti-tumor efficacy against esophageal squamous cell carcinoma (ESCC) in vitro and in two distinct patient-derived xenograft (PDX) mouse models. This work introduces ConMeter as a powerful and practical tool for high-accuracy metabolite prediction, demonstrating its potential to accelerate lead optimization, exemplified by the discovery of R636 as a promising orally bioavailable candidate for ESCC.Keywords
Funding Information
- the national key Research and Development Program of China (2022YFC3400504, 2022YFC3400501)
This publication has 53 references indexed in Scilit:
- Comparative genomic analysis of esophageal squamous cell carcinoma and adenocarcinoma: New opportunities towards molecularly targeted therapyActa Pharmaceutica Sinica B, 2021
- Discovery, Optimization, and Structure–Activity Relationship Study of Novel and Potent RSK4 Inhibitors as Promising Agents for the Treatment of Esophageal Squamous Cell CarcinomaJournal of Medicinal Chemistry, 2021
- How Much Does It Cost to Research and Develop a New Drug? A Systematic Review and AssessmentPharmacoEconomics, 2021
- Substituted pteridinones as p90 ribosomal S6 protein kinase (RSK) inhibitors: A structure-activity studyBioorganic & Medicinal Chemistry, 2020
- Current trends in drug metabolism and pharmacokineticsActa Pharmaceutica Sinica B, 2019
- Prediction of Organic Reaction Outcomes Using Machine LearningACS Central Science, 2017
- In vitro and in vivo conjugation of dietary hydroxycinnamic acids by UDP-glucuronosyltransferases and sulfotransferases in humansThe Journal of Nutritional Biochemistry, 2010
- Extended-Connectivity FingerprintsJournal of Chemical Information and Modeling, 2010
- Constructing virtual combinatorial fragment libraries based upon MDL Drug Data Report databaseScience in China Series B: Chemistry, 2007
- ErG: 2D Pharmacophore Descriptions for Scaffold HoppingJournal of Chemical Information and Modeling, 2005