The technological innovations in high-parameter discovery have brought with them the notable challenge of analyzing the exponentially larger volume of raw data. To date, no professional guidelines or industry standards have been adopted tostandardize the computational workflows and algorithms used in high-parameter data analysis. Numerous open-source (Cytofkit, HistoCAT, etc) and commercially available (Cytobank, Gemstone, etc) computational tools are available to corral the the raw data into biologically meaningful insight. The one consensus that appears to have emerged among computational biologists is that the most appropriate tools generally depends on the research objective. (Baharlou H, Front. Immunol., 2019)

At Intersect, we discover with precision. That means that our data analysis workflows are optimized and validated not only for each unique research question being asked but also for every tissue type under investigation.  We do this by optimizing machine learning algorithms within coding toolkits that themselves have been developed by programming experts at established, commercial firms exclusively dedicated to high-parameter data and image analytics. This provides our biotech and biopharma partners two key assurances: first – as with everything we do – analytics are optimized to the specifications of the research and development objective. Secondly, we don’t do it alone; rather we collaborate with industry experts who provide continuous support for our analytics pipelines.

Cell clustering, auto-phenotyping, dimensionality reduction… t-SNE, UMAP, SPADE, Random Forest…. the data science landscape can seem like the Wild West. Let Intersect Diagnostics help you make sense of it all by contacting us at info@IntersectDx.com