Using AI technology to advance precision medicine

PrecisionLife, a member of the NVIDIA Startup Accelerator Program from the UK, uses AI-led data analysis to identify important disease biomarker combinations.

With much mystery still surrounding New Coronary Pneumonia, UK-based PrecisionLife has used AI and combinatorial analysis to discover new genes associated with severe illness and hospitalization.

The tech-bio company published this study in June 2020, identifying 68 new genes associated with patients with severe New Coronary Pneumonia. More than 70% of these target factors were later individually validated in the global scientific literature as genetic risk factors for triggering severe New Coronary Pneumonia.

With the help of AI, the startup could perform this accurate early analysis using the first small dataset of patients with New Coronary Pneumonia from the UK Biosample Repository trained on NVIDIA A40 GPUs and supported by CUDA software libraries. precisionLife's combinatorial analysis approach identifies genetic variants in patients and other clinical or epidemiological factors that interact.

PrecisionLife technology helps researchers better understand the complex biology of disease at both the population and individual levels. In addition to Neocoronary pneumonia, the PrecisionLife analytics platform is used to identify precision medicine targets for more than 30 chronic diseases, including type 2 diabetes and amyotrophic lateral sclerosis (ALS).

The company is a member of the NVIDIA Startup Acceleration Program, a free program that supports these startups that are revolutionizing the industry with cutting-edge technology.

Unique discoveries about diseases

PrecisionHealth considers an individual's genetics, environment, and lifestyle when selecting the treatments that may be most effective for that individual. PrecisionLife is dedicated to determining how these factors affect the chronic disease.

The PrecisionLife platform provides greater insight into the biological factors contributing to chronic disease in various subgroups of patients. It begins by obtaining genomic and clinical history data on patients from datasets provided by national biobanks, research consortia, patient charities, and others, and then uses combinatorial analysis to draw deeper insightful conclusions from them.

Due to the inherent heterogeneity of chronic diseases, patients diagnosed with the same disease do not necessarily have the same cause, trajectory, or treatment.

The PrecisionLife platform identifies subgroups within large patient populations with matching disease drivers, disease progression, and treatment response, helping researchers select the right drug discovery targets, choose the right treatment for individuals and select the right patients for clinical trials.

Chronic disease is a complex field," said Mark Strivens, Chief Technology Officer of PrecisionLife. Such diseases are triggered by multiple genetic and environmental factors and create multiple patient subpopulations. We are committed to solving problems that have not been addressed by previous technologies, and our unique discoveries about disease will yield a variety of effective individual treatment options."

PrecisionLife technology differs from traditional analysis methods such as genome-wide association studies. While the latter is best suited for situations where most disease risk arises from a single genetic variant, PrecisionLife offers a combinatorial analysis that can uncover significant combinations of multiple genetic and environmental factors.

The PrecisionLife platform running on NVIDIA A40 GPUs can analyze data from 100,000 patients in just a few hours, which was previously impossible, Strivens said.

In addition, as a member of the NVIDIA Startup Accelerator Program, the PrecisionLife team has access to technical resources, hardware discounts, and go-to-market support.

The NVIDIA Startup Accelerator Program provides technical expertise and connects us with other data-driven organizations in the NVIDIA biotech AI ecosystem. the training provided by the NVIDIA Deep Learning Training Center shortens the time it takes for our team members to learn specific programming subfields," said Strivens. "

As a member of the groundbreaking UK life sciences community, PrecisionLife has access to a wide range of medical innovations and expertise, Strivens said. The company plans to offer novel disease insights based on global combinatorial analysis.