Researchers from the University of California, San Francisco (UCSF; CA, USA) have developed a novel tool for early stage drug discovery: utilizing computer vision in combination with genetically modified cancer cells. The cells are designed to change their appearance when treated with drugs targeting common disease pathways, and the team hopes to use them in combination with specially designed algorithms to rapidly organize the molecules in institutional compound libraries according to function.
The cells have been dubbed ORACLs (Optimized Reporter cell lines for Annotating Compound Libraries) and the researchers anticipate they will greatly assist the search for novel therapeutics. They predict that the field of drug discovery could become more like genomics, where large genomic databases have been annotated with more and more functions for individual genes. As a result, researchers can rapidly identify genes of interest and conduct more targeted investigations.
The team from UCSF believes that utilizing ORACLs to functionally annotate existing compound libraries could provide similar benefits, streamlining the way in which scientists use shared drug discovery facilities or cores.
Co-senior author, Lani Wu, explained, “Drug screening cores are very busy – they run continuously. The problem is that screening results generally cannot be reused. When you have a new biological target you want to hit with a drug, you have to go and screen the whole compound library again.”
Researchers often use reporter cells, specifically designed to change their behavior or appearance in response to successful treatment, to screen for effective drugs. The creation of ORACL, a single reporter capable of distinguishing between multiple drug classes, required a novel approach.
“We didn't know how to design such a versatile reporter cell based on our existing biological knowledge,” elaborated Chien-Hsiang Hsu, co-lead author on the study. “So we thought why not just randomly tag proteins and screen the cells with drugs to see which line could produce the response that fit our goal?"
The team hopes that ORACLs will be used to identify novel compounds where current therapies have dangerous side effects or miss certain patient populations. They could, theoretically, find compounds that affect pathways difficult to target or drugs whose effects are different from any known biological pathway.
Co-senior author Steven Altschuler concluded, “These are really early steps in drug discovery. We hope finding more high quality compounds will make all the later steps more efficient. Currently the process takes billions of dollars over many, many years. Wouldn't it be nice to make that easier?”
Kang, J., Hsu, C.-H., Wu, Q., et al. (2015). Improving drug discovery with high-content phenotypic screens by systematic selection of reporter cell lines. Nat Biotech, advance on. Retrieved from http://dx.doi.org/10.1038/nbt.3419