Technology Networks Features Sapient’s DynamiQ™ Insights Engine

“Disease processes aren’t static, and that’s why DynamiQ is our differentiator,” said Dr. Jonathan Usuka, Chief Executive Officer at Sapient. “We’re focused on the deep characterization of dynamic molecular processes which are read out by proteins and metabolites that modulate, or are modulated by, disease and exposures. We have these multi-omic measures from samples collected in the same patients at different timepoints, and when we combine those with inputs from their clinical data, we can better decipher multifactorial diseases in the context of the patient’s real-world experience – how disease subtypes manifest, how lifestyle factors contribute, and how drug exposure and drug adherence impact biological mechanisms and clinical outcomes. This becomes extremely powerful to understand how a therapy will actually work in a patient, to better predict response and stratify patients that are most likely to benefit from a given therapy.”

DynamiQ enables rapid curation of Sapient’s unique datasets comprising thousands of protein, metabolite, lipid, and cytokine measures per sample alongside matched genomic and RWD including electronic health records (EHR), lab measures, and clinical outcomes. This data has been collected and integrated for more than 56,000 samples from diverse individuals across multiple timepoints, making DynamiQ among the most deeply phenotyped datasets available for longitudinal analysis and drug discovery intelligence.

“With DynamiQ’s next-generation functionality and harmonized datasets, we increase the depth and breadth of analyses we can perform for biomarker discovery, target identification, and clinical insight delivery,” said Dr. Tao Long, Co-Founder and Head of Data Science at Sapient. “We can readily analyze molecular interactions across omics layers, rapidly build cohorts from standardized patient data, and validate discoveries from client studies in these independent populations. Importantly, because our multi-omics datasets are nontargeted they are ideal for AI and machine learning-based analysis to uncover new subgroups, novel biomarkers, and targets.”