Enhancing Drug Discovery Efficiency: The Design-Make-Test-Learn (DMTL) Cycle in the Pharmaceutical Industry
Accelerating Drug Discovery Through Digitalization, Automation, and AI
Pascal Mieville1 and Anna Codina2
1 Executive director, EPFL Swiss Cat+ West Hub
2 Senior Director of Strategy and Business Development, SciY
The pharmaceutical industry faces significant challenges in drug discovery, including lengthy timelines and high costs. Conventional drug discovery methods can take up to 15 years and cost over 2 billion dollars, with an average failure rate of 90–96 percent (1; 2) because scientists hunt for specific drug candidates among a chemical space of substantial magnitude, some mention 1060 (3), of possible small molecules (1).
Within drug discovery, the Design-Make-Test-Learn (DMTL) cycle emerges as a promising candidate for automation (4; 5), given that it is time consuming and repeated several times with the aim to identify and optimize drug candidates that later on will go into the clinical stage.
This review explores how leveraging advanced technologies such as chemistry AI and robotics accelerate through automation and digitalization, the DMTL cycle. It highlights the impact on drug discovery, detailing its benefits, challenges, and future prospects.