Think of every patient as a unique garden: their genes are the soil, epigenetics is how the soil has been treated over time (fertilizer, pollution, stress), and the microbiome is the mix of plants and microbes living there. This work is about using data and models to understand how all three together affect health and how people respond to medicines, so treatments can be tailored to each person’s “garden” instead of using one-size-fits-all drugs.
Traditional drug development and treatment decisions largely ignore how individual genetic makeup, epigenetic changes, and microbiome composition jointly drive disease risk and drug response. This leads to variable efficacy, unexpected side effects, and failed clinical trials. Integrating these omics layers can identify better targets, stratify patients more precisely, and improve prediction of who will benefit from which therapy.
Proprietary longitudinal multi-omics datasets (genomics, epigenomics, microbiome) linked to high-quality phenotypes and clinical outcomes, plus in-house expertise and pipelines to integrate and interpret them at scale.
Early Adopters
Focus on the combined effects of genetics, epigenetics, and the microbiome—rather than genetics alone—enables richer patient stratification and more nuanced drug-response prediction, which can inform both drug development and precision therapeutic strategies.
This is like giving clinical trial teams a very smart assistant that can instantly read through trial documents, data tables, and reports, then summarize findings, highlight safety issues, and draft analysis text so humans don’t have to do all the slow, manual reading and writing themselves.
Think of these biotechs as ‘AI-powered discovery engines’ for new medicines: instead of scientists testing millions of molecules one by one in a lab, they use advanced algorithms to search, simulate, and shortlist the most promising drug candidates before expensive experiments begin.
Think of this as giving pharma companies a super-smart digital lab assistant and paperwork robot rolled into one. The assistant can sift through mountains of scientific data to suggest promising new drugs faster, and it can also take over a lot of the routine documentation and admin work that bogs down scientists and health‑care workers.