Analyzing Various Types of Data Can Accelerate Drug Discovery, Study Says

a new role in cellular systems explores the importance of using multiple types of data in drug discovery. The paper examines more than 1,000 drugs tested at six doses and demonstrates that gene expression and cell morphology provide different information for drug prioritization.

Led by biomedical data scientist Gregory Way, Ph.D., MS, the study shows that by using these two types of data simultaneously, scientists can measure fundamentally different aspects of drug biology.

“We think these two popular approaches can be used to our advantage in designing drugs that address the full complexity of biology,” said Way, an assistant professor of biomedical informatics at the University of Colorado Anschutz Medical Campus.

Way and a team of data scientists found that the two types of data provide a partially shared but also complementary view of drug mechanisms. They said that using both approaches can advance drug discovery, functional genomics and precision medicine in unique directions.

“While drug labeling by mechanism of action is incredibly powerful, the approach risks missing the bigger picture. Both types of data, collected through phenotypic drug screening, span the complexity of biology and can allow scientists to study and take advantage of the multifaceted effects that drugs can offer,” adds Way.

Their article shows how assays compare to each other on useful biological tasks (eg, prediction of mechanism of action) given all sources of variation/noise and current best practices in data processing. The phenotypic drug screening approach allows researchers to measure thousands of characteristics of thousands of different drugs in a single experiment.

“We hope that our analysis can guide investigators in experimental design and in understanding the limitations of their particular profiling modality to provide more consistent measurements and maximize the potential for drug discovery success,” said Way.

The paper, published today (Oct. 24), guides scientists in planning experiments that profile cells to reverse disease phenotypes, quantify cellular response to chemical or genetic perturbations, and query drug mechanisms.