Our client performs and analyzes large-scale assays that yield results with many proteins identified as significant. Their scientists are charged with determining the biological relevance of those proteins to the disease or phenotype being studied. They then need to be able to explore the literature about these proteins and the pathways they have in common. This process needs to be quick but thorough, to understand how the experimental results fit into the broader biomedical picture, including potential connections to drugs, diseases, or other biomedical entities.
Our team leveraged our ERGO platform and designed an interface to perform enrichment analyses on sets of significant proteins, and take the results directly into our ERGO biological knowledge graph. Based on the design, the users can then explore the surrounding network to visualize connections.
Using natural language processing (NLP) and named entity recognition (NER), scientists will be able to layer on information distilled from complex biological literature, and find the relevant research articles they need to efficiently understand their results.