Harnessing the Power of Big Data to Drive Clinical Discovery

Translational medicine encompasses multiple areas of applied research, which work in concert to help us quickly analyze and interpret data from the lab, implement new insights in clinical trials and accelerate the pipeline to identify the right treatments, for the right patients, at the right time. One of the most critical pieces of this puzzle is our ability to generate, integrate, analyze and synthesize complex data sets to develop actionable insights and testable hypotheses that help drive discovery and clinical development. 

One example of this is in immuno-oncology, where our Translational Bioinformatics team is using cutting-edge algorithms to sift through massive raw genomics data. Whole Exome Sequencing (WES) generates data on tumor and blood samples from clinical trials, which we can use to identify mutations present in the tumor and inherited variants present in normal tissues. This allows us to identify correlations between patterns of genes or mutations and responses to certain therapies, which can in turn guide treatment decisions for patients. With more than three billion letters in the human genome, this may seem like an impossible effort, but thanks to a number of new experimental and in silico technologies, we are able to generate and analyze unprecedented amounts 

Before the analysis stage, the role of technology platforms can’t be ignored when it comes to our ability to generate enormous volumes of data. Advances in imaging and analytical sciences have enabled us to generate more precise and higher volumes of data than ever before. Traditional platforms, such as flow cytometry, quantitative PCR and pathology, are being augmented by next generation sequencing, high level multiplexing, quantitative digital pathology and machine learning, which are allowing us to not only generate data faster, but in many cases access raw information that wasn’t available before.