This interview is part of our new AI in Healthcare series, where we interview the world's top thought leaders on the front lines of the intersections between AI and healthcare.
In this interview, we speak with Sergii Shelpuk, CEO of DeepTrait, to understand how his company is using AI to transform healthcare, and what the future of the healthcare industry holds.
1. What’s the story behind DeepTrait? Why and how did you begin?
SS: DeepTrait happened largely due to the ability to make complex things simple. Both co-founders have starkly different backgrounds: Ruslana (Radchuk) is a seasoned scientist and researcher in biology while I had a career in engineering and engineering management. We've known each other for ten years and are good friends. However, it took us two years of discussion to figure out that there is an incredibly important biological problem which could be addressed with artificial intelligence.
We only assume how and why life arose on our planet, but we know for sure that it is based on the principle of coding genetic information in a nucleic acid molecule and the mechanism of its copying. An organism — its appearance, development, and behavior — are the product of the unfolding of the genome under environmental conditions.
The search for genes, regulatory elements, and their relationship to the features of the organism for which these areas are responsible is the Holy Grail of biology. The solution to this problem is key to plant breeding, healthcare, food supply, mitigation of global warming and even supplying extraterrestrial colonies of humanity in the future.
2. Please describe your use case and how DeepTrait uses artificial intelligence:
SS: We work on developing self-learning AI capable of working with full genomes on the nucleotide level. Our goal is to change the way we analyze, develop, engineer, and breed new organisms such as crops and medical plants, as two examples. DeepTrait technology connects traits with their genetic origins, thus helping to analyze and design new lines with desired phenotypes.The genome is an enormously complex world still very much unfamiliar for us. The search for a connection between genome elements and traits is based on a carefully planned experiment, a large sample, control of environmental conditions and, last but not least, luck. There is a number of discoveries which demonstrate a correlation, but not a causal link between a section of the genome and a feature of the organism.
At DeepTrait, we develop artificial intelligence technology aimed to decipher genetic information from large sets of raw genomic data. The new method reduces the role of human intuition and qualifications, as well as luck and chance. Moreover, our technology is designed to figure out the exact cause of the trait, not just associated markers.
3. Could you share a specific customer/user that benefits from what you offer? What has your service done for them?
SS: Our technology is still in the testing phase. We have successfully verified that it finds the genes responsible for various antibiotic resistances of E. coli, a gut bacteria which infected thousands of people in Europe and the US in 2011 and killed 53. DeepTrait technology figured out what part of the E. coli genome gives the bacteria antibiotic resistance, and the analysis time is less than 24 hours.Right now, we are testing our approach on plant genomes.
Applications for our AI technology for healthcare are countless, starting with analyzing resistances to different conditions, through producing better drugs in plants such as medical cannabis and more nutritious health non-allergenic food, up to figuring out the genetic causes of human medical conditions.
We believe that the 21st century will be dominated by genetic engineering and artificial intelligence and are happy to work on the cutting edge of the intersection of these technologies.
Share your feedback and we'll consider adding it to the piece!
Have expert insights to add to this article?
Share your feedback and we'll consider adding it to the piece!ADD YOUR INSIGHTS