Our founding belief is that the future of medicine will rely on artificial intelligence, because biology is too complex for humans to understand.

Today, the molecular world of the cell can be experimentally interrogated like never before. The resulting datasets provide an unprecedented opportunity to build artificial intelligence systems that are biologically accurate and that support the detection of disease and the development of molecular interventions.

Deep Genomics is building a biologically accurate data- and AI-driven platform that supports geneticists, molecular biologists and chemists in the development of therapies. 

Over the next two years, Deep Genomics will use its platform to unlock new classes of antisense oligonucleotide therapies that were previously inaccessible or out of reach, and advance them for clinical evaluation. In project Saturn, the platform will be used to search across a vast space of over 69 billion molecules with the goal of generating a library of 1000 compounds that can be used to manipulate cell biology and design therapies.


Founded in 2015, Deep Genomics has over twenty team members with advanced degrees, including from Cambridge, MIT, Stanford, Toronto, UCSD, Washington and Waterloo. The team has published over a dozen papers in Nature, Science, Cell and Nature Biotechnology, has received numerous science and innovation awards, and has over 50 years of cumulative experience in building artificial intelligence systems that accurately incorporate genome biology.

The company is funded by top Bay Area investors. Advisors include leaders from major pharmaceutical companies and industrial artificial intelligence groups, individuals with decades of experience in building life science and pharmaceutical companies, and professors from Harvard, MIT, Stanford, Toronto and UCSD.

Deep Genomics is located in the heart of Toronto, the fastest growing tech hub in North America and one of the most livable cities in the world. It has facilities spanning experimental biology and computational analysis and it is located next to the university, four research hospitals, three medical research institutes, JLABS, and the AI research labs of Google, Uber and Vector.



Our scientists regularly publish in their fields' most influential peer-reviewed journals. Here is a selection of our contributions:

  • Efficient in vivo correction of a splicing defect using an HDR-independent mechanism. Kemaladewi et al. Nature Medicine, July 2017.
  • Inference of the human polyadenylation code. Leung et al. RECOMB, April 2017.
  • Genome-wide characteristics of de novo mutations in autism. Yuen et al. NPJ Genome Medicine, August 2016.
  • Machine learning in genomic medicine: a review of computational problems and data sets. Leung et al. Proceedings of the IEEE, January 2016.
  • Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning. Alipanahi et al. Nature Biotechnology, August 2015.
  • The human splicing code reveals new insights into the genetic determinants of disease. Xiong et al. Science, January 2015.
  • Deep learning of the tissue-regulated splicing code. Leung et al. Bioinformatics, June 2014.