From Data to Drug Discovery
Machine learning (ML) has become a cornerstone of the drug discovery process, offering new tools
that enhance the effectiveness of pharmaceutical research. Today, many companies are taking these
developments a step further using the transformative power of generative AI (Gen AI) to search for
molecules under specific constraints, such as solubility, therapeutic success and patent status. In
doing so, Gen AI is poised to enhance the efficiency, speed and creativity of the new drug discovery
process in profound ways.
Yet despite their potential to revolutionize the way scientists explore molecular spaces, ML and Gen AI
depend on the quality of the data that feeds them. The reality is, however, many companies neglect
the critical data engineering steps in the rush to deploy ML and Gen AI technologies, undermining
their efficacy as research tools.
Successful implementation of ML and Gen AI in drug discovery therefore requires an optimized
approach to research informatics — merging data science practices into drug discovery pipelines to
accelerate innovation.
PDF