Variational AI introduces Enki™ 4: an improved algorithm and architecture designed to scale, expanding the pre-trained target coverage from 592 to 760 and now applicable to proximity-based therapeutics and novel payloads for antibody drug conjugates
VANCOUVER, British Columbia — Variational AI today announced the release of Enki™ 4, a major update to its generative AI platform for small-molecule drug discovery. The release of the fourth generation of Enki™ delivers significant improvements in algorithmic performance and target coverage through platform architecture design, as well as extending its application to degraders, PROTACs, glues, and novel payload design for antibody drug conjugates (ADCs) and related modalities.
“Enki 4 is a massive step forward for our platform,” said Ali Saberali, Co-Founder & Head of Platform at Variational AI.
“We’ve re-architected Enki and improved the underlying algorithms to expand target and modality coverage, while operating faster to deliver even better performance for our partners.”
Enki 4 now supports the rapid generation of novel, potent, selective, and synthesizable lead-like structures pre-trained on 760 drug targets, a 28% increase over the previous Enki version’s 592 targets, with more to be released soon. The update delivers enhanced performance across more than 12 target classes, including: GPCRs, kinases, ion channels, proteases, oxidoreductases, hydrolases, and others.
“This Enki release continues our process of continuous model innovation” added Handol Kim, Co-Founder & CEO.
“Enki 4 enables our biotech partners to start with novel leads they would not have discovered using traditional methods. Our goal is to eliminate hit ID and hit-to-lead, generating molecules ready to go directly into lead optimization.”
For more information about Enki 4 and to access the full list of 760 targets, visit variational.ai/enki or contact bd@variational.ai.
About Variational AI
Variational AI is a generative AI drug discovery company based in Vancouver, Canada. Founded by machine learning researchers from MIT, Caltech, Google Research, Microsoft Research, and D-Wave Quantum, its proprietary Enki™ platform uses state-of-the-art generative AI models to design novel, optimized small molecules with improved probability of success for biopharmaceutical partners. variational.ai