Introducing DeepRNAi: A transcriptome-wide model for preventing siRNA drug failure. Albi Celaj October 6, 2026 By Albi Celaj, Director, Machine Learning/AI Lab Previously, Brendan Frey set out a vision for an integrated AI stack for genetic medicine and Greg Hoffman outlined what it means for drug developers. Today, I want to build upon this with something concrete. I'm excited to share its latest-and-greatest results building DeepRNAi and what it could mean for the development of siRNA drugs. This will be the culmination of work Deep Genomics has been doing for over a year at Deep Genomics and I am very proud about what the team here was able to accomplish in this time. This is an important unsolved problem in the field and I think it could really change the siRNA drug design process. Targeting a gene for silencing with siRNA often triggers off-target effects across the transcriptome, adding risk and delays to the drug development process. Predicting siRNA off-target effects has remained elusive because an accurate model of induced hybridization-mediated knockdown is difficult to develop. The RNA-induced silencing complex (RISC) does not appear to follow straightforward sequencing-matching rules, making it impractical to exclude off-target effects using, e.g. string matching methods or following heuristics based on thermodynamics. To accelerate the development of potent siRNA drugs with fewer off-target liabilities, Deep Genomics introduce DeepRNAi, a deep learning model to accurately predict transcriptome-wide RISC-mediated knockdown from siRNA drug treatment DeepRNAi predicts the knockdown of any siRNA-transcript pair, regardless of sequence complementarity, including intended on-targets, near-perfect matches (NPMs), and canonical seed matches. Overall, when Deep Genomics measure the performance of DeepRNAi on pairs of siRNAs screened in two common preclinical in vitro cell lines, its correlation for NPMs and seed matches is approaching the reproducibility of RNAseq measurements themselves. This made Deep Genomics think that DeepRNAi is accurate enough to reduce (or largely replace) the need for RNAseq in siRNA drug development. In addition to each off-target effect adding liability to the drug development process (and reportable to the FDA!), an excess of overall off-target effects has also been linked by Janas et al to heptatoxicity in a rat animal model. When comparing its RNAseq data for hepatotoxic compounds from the Janas study ("Bad Actors") to five FDA-approved siRNA drugs ("Good Actors"), Deep Genomics saw a difference in the overall off-target burden that could distinguish these two classes. This separation in off-target burden was well-predicted by DeepRNAi, and can be minimized during the drug development process. Because DeepRNAi has learned the conserved "rules" of RISC-mediated knockdown, it can even generalise to different species used in the preclinical development. When Deep Genomics applied DeepRNAi to two experiments of rats treated with siRNA, it continued to perform with the high accuracy Deep Genomics observed in its test set in predicting seeds and NPMs. For these two siRNAs, it even did as well as in vitro rat hepatocyte experiments at predicting which NPMs would be down-regulated in an in vivo rat study! This suggests that DeepRNAi can also minimize effects in preclinical animals to avoid off-target-based animal safety signals and potentially lead to fewer animals being used. Deep Genomics also take these results to support that DeepRNAi may have similar potential for in vivo translation in humans. Finally, Deep Genomics evaluated how well DeepRNAi ranks Inclisiran, a cholesterol-lowering drug which targets PCSK9. Without having seen any previous siRNAs targeting PCSK9, DeepRNAi scored 3,599 fully complementary siRNAs. Amongst these candidates, the model predicted exceptionally strong knockdown and minimal off-target liabilities for Inclisiran, ranking it to be the most potent compound with low off-target burden. Taken together, these results support using DeepRNAi to prioritize potent siRNAs with fewer predicted off-target liabilities. Deep Genomics is excited to announce this capability to siRNA drug developers. Creating a highly-accurate "virtual screening" model like this was a challenge that required fit-for-purpose data, biological foundation models that encode the appropriate genomic context, and a learning strategy focused on RISC-mediated knockdown. In future posts, Deep Genomics will go into more depth about the secret sauce that really made DeepRNAi work. For example, in his next post, Scott Findlay will explain how Deep Genomics generated 15 million measurements of potential siRNA-mRNA interactions that allowed Deep Genomics to build a "fit for purpose" dataset that allows Deep Genomics specifically to learn which interactions cause silencing. To follow along and read its previous pieces, visit the Deep Genomics blog here.

Deep Genomics CEO Brian O'Callaghan honored as gold stevie(r) Award winner in 2025 Stevie Awards for Technology Excellence. August 1, 2026 TORONTO, August 1, 2025 - Brian O'Callaghan, CEO of Deep Genomics, the AI-first TechBio organization pioneering a new path for genomic R&D, has been named Biotech Executive of the Year, winning gold in the second annual Stevie Awards for Technology Excellence. Since his appointment as CEO in September 2023, O'Callaghan has led Deep Genomics into a new era of innovation and growth, helping to transition the company from a single-model initiative to a fully integrated platform of AI foundation models for drug discovery. Deep Genomics has been a pioneer in the drug discovery space through its cohesive AI foundation model platform, which dramatically accelerates therapeutic discovery. The company's flagship AI foundation model, BigRNA, is reshaping the landscape of RNA research and development with 1.8 billion tunable parameters trained on over one trillion genomic signals. Under O'Callaghan's leadership, Deep Genomics launched additional proprietary AI foundation models that work alongside BigRNA, including DeepADAR for RNA editing and REPRESS, which accurately predicts microRNA (miRNA) binding and mRNA degradation directly from RNA sequences. O'Callaghan has also driven the strategic and structural expansion of Deep Genomics, opening a new lab and office in Cambridge, Massachusetts, expanding its Toronto headquarters, and appointing key leaders across science and business functions. "Winning a Stevie Award is a reflection of the extraordinary talent and mission-driven mindset at Deep Genomics," said O'Callaghan. "Our AI foundation model platform is unlocking AI-driven drug discovery in a way that was previously inconceivable, and I'm incredibly proud of our team for driving innovations that bring us closer to transforming care for patients." "We're proud to honor the 2025 Stevie Awards for Technology Excellence winners for their remarkable achievements," said Stevie Awards President Maggie Miller. "We look forward to celebrating their innovation and impact at the awards ceremony on September 16." The Stevie Awards for Technology Excellence recognize the remarkable achievements of individuals, teams, and organizations that are shaping the future of technology across all industry sectors. Winners of the awards, named the Stevies from the Greek word meaning "crowned," will be recognized during a gala awards event on Tuesday, September 16, at the Marriott Marquis Hotel in New York City. More than 160 professionals worldwide participated in the judging process to select this year's honorees. Details about the Stevie Awards for Technology Excellence and the list of 2025 Stevie winners are available at www.StevieAwards.com/Tech. About Deep Genomics Deep Genomics is an AI-first TechBio organization pioneering a new path for genomic R&D through its multidisciplinary team of AI and biology scientists and its Foundation Model Platform. Leveraging cutting-edge AI technologies and biological insights, Deep Genomics is at the forefront of revolutionizing drug discovery and development. Through its innovative approach and collaborative partnerships, Deep Genomics aims to accelerate the delivery of life-saving therapeutics to patients worldwide. Deep Genomics is located in Toronto, Ontario, and Cambridge, Massachusetts. For more information, visit www.deepgenomics.com and follow Deep Genomics on LinkedIn. About the Stevie Awards Stevie Awards are conferred in nine programs: the Asia-Pacific Stevie Awards, the German Stevie Awards, the Middle East & North Africa Stevie Awards, The American Business Awards(R), The International Business Awards(R), the Stevie Awards for Great Employers, the Stevie Awards for Women in Business, the Stevie Awards for Technology Excellence and the Stevie Awards for Sales & Customer Service. Stevie Awards competitions receive more than 12,000 entries each year from organizations in more than 70 nations and territories. Honoring organizations of all types and sizes and the people behind them, the Stevies recognize outstanding performance in the workplace worldwide. Learn more about the Stevie Awards at http://www.StevieAwards.com. Media Contact: [email protected]