MONSTROUS: a web-based chemical-transporter interaction profiler

Mohamed Diwan M AbdulHameed ^1,2* Souvik Dey ^1,2 Zhen Xu ^1,2 Ben Clancy ^1,2 Valmik Desai ^1,2 Anders Wallqvist ^1*

• ¹ Biotechnology HPC Software Applications Institute (BHSAI), Frederick, United States
• ² Henry M Jackson Foundation for the Advancement of Military Medicine (HJF), Bethesda, Maryland, United States

Transporters are membrane proteins that are critical for normal cellular function and mediate the transport of endogenous and exogenous chemicals. Chemical interactions with these transporters have the potential to affect the pharmacokinetic properties of drugs. Inhibition of transporters can cause adverse drug-drug interactions and toxicity, whereas if a drug is a substrate of a transporter, it could lead to reduced therapeutic effects. The importance of transporters in drug efficacy and toxicity has led regulatory agencies, such as the U.S. Food and Drug Administration and the European Medicines Agency, to recommend screening of new molecular entities for potential transporter interactions. To aid in the rapid screening and prioritization of drug candidates without transporter liability, we developed a publicly available, web-based transporter profiler, MOlecular traNSporT inhibitoR and substrate predictOr Utility Server (MONSTROUS), that predicts the potential of a chemical to interact with transporters recommended for testing by regulatory agencies. We utilized publicly available data and developed machine learning or similarity-based classification models to predict inhibitors and substrates for 12 transporters. We used graph convolutional neural networks (GCNNs) to develop predictive models for transporters with sufficient bioactivity data, and we implemented two-dimensional similarity-based approach for those without sufficient data. The GCNN inhibitor models have an average five-fold cross-validated receiver operating characteristic area under the curve (ROC-AUC) of 0.85 ±0.07, and the GCNN substrate models have an average ROC-AUC of 0.79 ± 0.08. We implemented the models along with applicability domain calculations in an easy-to-use web interface and made it publicly available at https://monstrous.bhsai.org/.