
Deep Genomics
Precision Medicine & Genomics
Deep Genomics is an AI therapeutics company that uses its BioFM Model Platform to discover novel targets and design life-changing genetic medicines for patients.
About Deep Genomics
Deep Genomics uses AI to discover and develop genetic medicines, identifying disease-causing genetic variants and designing therapies to correct them.
Leadership Team
Key executives and founders sourced from public LinkedIn profiles.
Brendan led the launch of Deep Genomics in 2015, to address the need for a new data- and AI-driven approach to genetic medicine. He is responsible for ensuring that our machine learning platform rapidly identifies the best drug candidates, and that those candidates move forward for IND-enabling work. Over the past 15 years, he has co-authored over 200 papers on machine learning and genome biology, including over a dozen that appeared in Nature, Science and Cell. His inventions include one of the first deep learning algorithms (1995), factor graphs (1997), a coding method that is used in most telecommunications devices (1999), affinity propagation (2007), and deep learning models of splicing (2015, 2018), protein-DNA/RNA interaction (2015) and polyadenylation (2017). Brendan holds numerous distinctions and is a Professor of Engineering and Medicine at the University of Toronto, a Co-Founder of the Vector Institute for Artificial Intelligence and a Senior Fellow of the Canadian Institute for Advanced Research.
Jason is a Humanist who believes that the Singularity is nearer than we think and that positive futures must be thoughtfully created. He has 7 YoE building models and solutions across the entire ML lifecycle. As a results-driven engineer, Jason has a long track record of identifying and deeply understanding problems, delivering value, and iterating rapidly on lean, fast-moving teams operating in challenging domains. He has spearheaded scientific contributions of his own from ideation to deployment, while also supporting and mentoring ML Scientists with data & platform engineering along the way. Most notably, Jason trained, deployed, and presented a Multi-Agent Reinforcement Learned (MARL) model for autonomous stem cell colony control. The MARL agents, trained in a parallelized In Silico simulation which Jason also built, were successfully deployed Sim2Real to Cellino's biomanufacturing system and are estimated to have doubled production capacity. Additional career highlights also include the training of a ViT decoder from SAM2 Foundation Model embeddings to regressively model cell culture densities, co-inventing a variety of morphological management techniques for stem cell colonies, prototyping a Few-Shot In-Context Learning (ICL) Pluripotency classifier with the GPT-4o Vision Language Model (VLM), designing and building a graph-based cell culture tracking and visualization system, scaling RL systems for billions of products at Wayfair, and founding an Augmented Reality Metaverse startup. Jason is currently seeking another opportunity to build autonomy zero to one on an ambitious team with an incredible vision and strong technical leadership.
David Johnston, CFO, brings over thirty years of senior financial leadership experience. Currently, David Johnston is principal of dbj consulting LLC, providing fractional CFO services as well as financial and strategic advice to emerging life science companies. He was recently Chief Financial Officer for ImmunoGen, Inc., oncology-focused biotech based in Waltham, MA. During his tenure at ImmunoGen, he led several public offerings and a creative, non-dilutive royalty financing. Before ImmunoGen, David Johnston served as CFO for Aveo Oncology and Genzyme Biosurgery. He led both their initial public offerings and led several strategic initiatives, both on the buy-side and the sell-side. Mr. Johnston earned a B.S. at Washington and Lee University and an MBA at the University of Michigan. David Johnston sat on the board of directors of RAW Art Works, a nonprofit youth arts organization, and Tissue Banks International, one of the most significant eyes and tissue bank nonprofits in the United States.
Mission & Approach
Mission
“Building, running and improving the world's best Biological Foundation Models in an effort to transform the field of drug discovery - finding molecules and targets others would miss, and accelerating their development into life changing medicines for patients”
AI Approach
Deep learning foundation models, RNA biology prediction, sequence-based prediction, transformer architectures, fine-tuning for specific applications, embeddings generation for molecular design and target discovery
Founding Story
Founded in 2015 by Brendan Frey, Ph.D., an internationally acclaimed entrepreneur, engineer and scientist who made fundamental contributions in deep learning and genomic medicine. His pioneering work on AI systems that could accurately predict normal and pathological cell and genome biology led to the founding of Deep Genomics and the development of the first AI system for predicting pathogenic mutations and identifying therapeutic targets.
Products & Solutions
REPRESS
modelDeep learning model predicting cell-type-specific microRNA binding and mRNA degradation from RNA sequence
A deep learning foundation model that predicts cell-type-specific microRNA (miRNA) binding and mRNA degradation directly from RNA sequence. It reveals biology missed by other state-of-the-art methods, including identifying repressive non-canonical miRNA target sites and decoding regulatory effects of sequence context and miRNA binding site multiplicity. Outperforms other advanced methods on orthogonal tasks including identifying genetic variants affecting miRNA binding.
DeepADAR
modelAI model for designing guide RNAs to induce ADAR-mediated editing across trinucleotide contexts
A model that designs guide RNAs (gRNAs) to induce ADAR-mediated editing across various trinucleotide contexts. The base model predicts endogenous ADAR editing based on local sequence and structure around candidate editing sites, trained on 16 million target sites. Fine-tuned using screening data from synthetic gRNAs to predict gRNA-driven editing based on sequence and structural features created by gRNAs.
BigRNA
FlagshipmodelProprietary foundation model trained on over a trillion signals from RNA sequencing datasets
A powerful Biological Foundation Model trained on over a trillion signals derived from high-throughput sequencing datasets that has distilled core principles of RNA biology. It predicts effects of genetic variants, on- and off-target effects of genetic medicines, and generates rich sequence embeddings for target biology discovery and molecular design. Enhanced with 1-bp prediction resolution and integration of disease-relevant training datasets.
BioFM Platform
FlagshipplatformAI-driven genetic medicines platform with lab-in-the-loop workflows for drug discovery
A comprehensive Biological Foundation Model platform that generates differentiated predictions for molecular design and target biology discovery. The platform integrates lab-in-the-loop workflows, AI model development, fit-for-purpose training datasets, screening technologies, and software systems to accelerate drug discovery and find molecules and targets others would miss.
Hiring Activity
View Open Roles →Notable roles:
Product & Market
Product Stage
growthPrimary Market
pharmaCompany Details
- Founded
- 2015
- Headquarters
- Toronto, Canada
- Employees
- 125
- Stage
- series c
- Profile last updated
- June 22, 2026
Category
Precision Medicine & GenomicsOfficial Sources
Work here?
Claim this listing to update company information and connect with our audience.
Claim This ListingSocial & Media
Follow on
Data Accuracy Notice: Company information on HealthAI Central is compiled from public sources and updated regularly. While we strive for accuracy, details such as employee counts and product offerings may change. We recommend verifying critical information directly with the company before making business decisions.