505b2 Drug Repurposing: From AI Targets Prediction to Clinical Drug Formulation

Advancements both in AI and database curation have dramatically improved drug discovery, facilitating more efficient identification of 505b2 drug's new indication which save time in drug discovery. The success of a 505b2 drug's application relies not only on early-stage drug repurposing prediction, but also the PK/PD simulation prior to clinical study, underscoring the importance of accurate predictive models. Several essential databases, like Protein Data Bank (PDB), OpenTarget, PubChem, SEA and ChemBL etc., have made 505b2 drug research easier with the use of fast AI drug-target interactions computation, streamlining the drug repurposing process. In drug dosage design, the oral formulation is still the most commonly needed due to its convenience in administration. Recently oral dosage simulation have shown that PBPK modeling may lead to better prediction of ADME. In addition, an alternative method using FDA-approved PK database and PAMPA dissolution also contributed to the improvement of repurposing oral formulation, providing complementary approaches for formulation optimization. Hence, a better prediction of repurposing drug from AI to clinical drug formulation could be conducted to enhance the success rate of oral formulation development.