Sano Genetics & BenevolentAI: Combining machine learning with genetic and medical data in ulcerative colitis

What is the goal and current status of the research collaboration?

This research collaboration brings together BenevolentAI’s expertise in machine learning and IBD with Sano’s expertise in collecting and linking patient genetic and medical data. 

The goal of the project is to generate a linked genetic and medical record database that could be used in machine-learning applications to accelerate drug and biomarker discovery in UC. This aligns with BenevolentAI’s commitment to developing an oral, small-molecule treatment with disease-modifying efficacy, and improved safety for patients with UC who do not respond to the current standard of care options.

At the time of writing, we have enrolled 619 people into the database that forms the basis of this project. In the first phase, medical records were successfully retrieved for 399 participants. Of these 399, 68% completed a genetic test resulting in a linked dataset of 272 participants.*

The first phase of the study was conducted in the United States, where medical records are fragmented and often challenging to access. Despite this, we were still able to retrieve both electronic and paper medical records for more than 60% of participants. 

*These figures are correct at the time of writing and likely to increase. 

Exploring the study from the participant’s perspective

The study was conducted entirely using Sano Genetics’ HIPPA-compliant online platform, with participants providing:

• electronic consent
• detailed information about their symptoms 
• medical history
• permission for medical record linkage 

In parallel with the medical record linkage process, participants were sent a simple, at-home saliva sample collection kit. The saliva samples were then genotyped, and additional DNA was stored to enable whole exome sequencing or whole genome sequencing in the future.

Using machine learning for target discovery and patient stratification

BenevolentAI uses machine learning algorithms to integrate large volumes of scientific literature, along with patient-level data such as genetic and clinical data/medical records, to identify potential new drug targets and opportunities for precision medicine approaches such as patient stratification for a wide variety of diseases. By exploring large, well-annotated patient-level datasets in which clinical details are linked to genetic information, we can better understand the efficacy of different treatment regimens to try to identify those patients that are likely to respond (or not respond) to a given treatment for a given disease.

BenevolentAI has worked closely with Sano to guide the collection, formatting and ingestion of study data in a way that ensures it can be used efficiently in machine learning applications. As the database of enrolled patients grows, BenevolentAI plans to use this valuable resource to further explore precision medicine approaches, such as defining subgroups of UC patients who have experienced either effective or ineffective treatment regimens. 

Next steps

The successful completion of the first phase is a major milestone for Sano Genetics and BenevolentAI. By uniting genetics and clinical data through a patient-focused siteless study design, the project has created a powerful new tool for precision medicine and genomics research and a framework that can be applied to a range of diseases. And, by allowing participants to take part fully from home, this approach reduces barriers for participants and aligns with Sano’s and BenevolentAI’s commitments to developing more diverse and representative datasets.

The learnings from this phase are being applied to expand the programme, reach a greater number of participants, and explore testing for additional biomarkers that may provide insight into progression, treatment response, and novel drug targets for UC. 

References

¹ Jans, D and Cleynen, I. The genetics of non-monogenic IBD. Hum Genet. (2023) doi: 10.1007/s00439-023-02521-9. 

² The global, regional, and national burden of inflammatory bowel disease in 195 countries and territories, 1990–2017: a systematic analysis for the Global Burden of Disease Study 2017, Lancet Gastroenterol Hepatol. (2020) doi: 10.1016/S2468-1253(19)30333-4.