Biological big data is being generated at an enormously mind-boggling rate. Over 90% of the data that exists today was generated in the last two years.¹ The last ten years have been about unleashing the power of this data to drive successful products and services in every sector. Consequently, large technology companies have emerged that have influenced, transformed and disrupted traditional industries, taking advantage of this data.²
However, the healthcare industry has lagged behind other industries in the use of this biological big data. Let’s take the case of an individual human being to understand the scale and potential of biological data. A single human being has over 20K genes and a single sequenced genome can generate up to 200 GB of data. The study of human genomes – Genomics, is still relatively static in its nature compared to metabolomics, glycan microarrays or transcriptomics.
For a moment, consider the thousands of molecules that exist in our body, that constantly respond to changes in the environment, affecting and defining our health. Through the last decade, the efforts of pharmaceutical companies and other organizations to digitize medical records, and of the government’s and federal organizations’ to make public data usable and searchable, have brought about the shift in this industry.³
Potential of this data to aid research in the pharmaceutical space has not been harnessed yet and companies are just beginning to derive insights from this data. Companies, including the likes of 23andMe, have only just begun to scratch the surface in the B2C space, with even fewer companies making a mark in the B2B space.
Biological big data (BBD) is the last frontier of human-generated data. It has been established that unlocking this data opportunity will create a world with numerous possibilities in the patient impact space leading to faster drugs to market and a suite of lifestyle products & services including but not limited to ‘personalized’ medicine, agriculture, beauty, diet & fitness.
Better tools to understand BBD are key to bridging the gap between data and analysis. Cloud analytics services built to support the nuances of BBD are a prerequisite. Elucidata is one such organization that works to enable organizations and institutions to harness the power of this data through its AI-enabled platform, Polly. Polly enables the utilization of this data to discover therapeutic assets. Elucidata integrates omics data to further the understanding of health and disease to aid the identification of potential drug targets.
Progress in the generation, analysis, and interpretation of this data is signaling a paradigm shift in drug development. One of the initial steps in drug development involves the identification of the links between molecular processes and disease pathology. Currently, this is established using a mix of intuition, hit-and-miss hypotheses, and a priori knowledge of disease context. With advances in data acquisition, analytics tools, and platforms, the process is shifting to a top-down pathology-based era of systems therapeutics. Systems therapeutics differ from current drugs by targeting biological systems and networks rather than single transduction pathways.
Another interesting industry that has witnessed a similar paradigm shift is the Semiconductor Industry, where a systemic top-down design was enabled by sophisticated simulation tools in conjunction with increasingly cost-effective compute power. We will talk more about the parallels between the two in the second part of this blog.
Get the latest insights on Biomolecular data and ML