The client’s scientists were using several screening assays and metrics to identify and prioritize potential new drug targets within a specific protein family. They were spending a large amount of time and effort manually cross-compiling insights from many diverse datasets, and finding the need to do extensive additional diligence via manual literature reviews. They wanted an application with a single interface to elegantly stitch together disparate data to increase processivity of ideas, and more efficiently filter the candidates in their pipeline down to the best leads.

In our Ergo platform, we combined a knowledge network extracted using NLP and entity recognition of biomedical abstracts with 3rd-party datasets spanning relationships between drugs, disease, and genes/proteins. We designed a UI/UX experience to utilize this biological network in their target prioritization workflow.
Our client found that some candidates that looked promising by many criteria had disqualifying problems hidden in the literature. Revealing these with Ergo would allow resources to be spent on more viable leads. In one example, Ergo ruled out a top-screened candidate for knockout therapy by highlighting its stabilizing interaction with TP53.