When preparing an IND application, it is necessary to provide extensive information on preclinical studies, manufacturing processes, proposed clinical trial plans, and any data available from previous human use. This data will then be submitted to the regulatory authority, the US FDA.


USA has a regulatory pathway called 505(b)(2) that permits the approval of drugs based on data from studies conducted by others. This pathway enables the submission of an IND application referencing existing data, such as data from a previously approved drug, to establish the safety and efficacy of the new drug. By potentially streamlining the development process and lowering costs, this regulatory pathway is worth considering.

End to End drug discovery using AI/ML

The process of discovering and developing a new drug involves identifying and validating a biological target or pathway that is relevant to a specific disease. With the help of high-throughput technology, a candidate molecule is identified, and then lead optimization is carried out to improve its potency, safety, and pharmacokinetics. In preclinical development, both in vitro and in vivo studies are conducted to assess the safety, efficacy, and PK of the lead compounds or biologics.

Drug discovery involves various stages ranging from target identification to clinical trials. Artificial intelligence and machine learning have the potential to expedite and enhance these stages by analyzing large datasets, predicting drug-target interactions, optimizing drug candidates, and supporting decision-making. The use of these technologies can greatly improve the efficiency and effectiveness of the drug discovery process.