Profluent and Lilly: the next gene editor will be designed by AI

2025-10-09 · Source: Air Street Press · Field: Science & Research — Life Sciences & Biology, Health & Medical Research, Mathematics & Computational Sciences · Depth: Intermediate, medium

Summary

Profluent, an Air Street Capital portfolio company, announced a multi-program strategic partnership with Eli Lilly, potentially valued at over \$2.25 billion, to develop AI-designed recombinases for genetic medicine. This collaboration aims to tackle kilobase-scale DNA editing, a long-unsolved problem in genetic medicine that involves inserting healthy gene copies into specific genomic locations. Unlike CRISPR, which primarily makes small changes, this approach targets heterogeneous genetic diseases by replacing large DNA segments. Historically, recombinases, enzymes capable of large-scale DNA cutting and pasting, were difficult to retarget due to their specificity being built into the protein structure. Profluent's core thesis is that protein design, specifically for novel recombinases, is a frontier AI problem, not a traditional biology problem, enabling the generation of non-naturally occurring enzymes. Lilly's investment reflects its aggressive strategy in genetic medicine, assembling the necessary components to industrialize the field.

Key takeaway

For AI Scientists and Research Scientists developing genetic therapies, Profluent's partnership with Lilly signals a critical shift: AI-driven protein design is now central to overcoming complex gene editing challenges. You should explore generative AI models for designing novel enzymes, particularly for kilobase-scale DNA insertions, to address heterogeneous genetic diseases. This approach moves beyond traditional discovery, enabling the precise engineering of therapeutic tools.

Key insights

AI-designed recombinases offer a credible path to kilobase-scale DNA editing for complex genetic diseases.

Principles

• Protein design is a frontier AI problem.
• Recombinase specificity is protein-encoded.
• Generative models can design novel enzymes.

Method

Profluent trains large frontier AI models on extensive protein datasets, including recombinases, to generate novel enzymes for specific genomic targets.

In practice

• Design editors for specific genomic addresses.
• Target heterogeneous monogenic diseases.
• Enable large-payload gene corrections.

Topics

• AI-designed Proteins
• Genetic Medicine
• Recombinase Engineering
• Kilobase DNA Editing
• Eli Lilly
• Profluent

Best for: Investor, AI Scientist, Research Scientist, Director of AI/ML

Related on AIssential

• All life runs on 20 amino acids. These cells run key machinery on just 19 — Bacteria were reengineered to operate with 19 amino acids, leveraging AI for protein design.
• Unlocking the Future of Gene Therapy — AI is revolutionizing gene therapy by enabling precise cellular targeting and accelerating discovery-to-clinic pathways.
• Identification and engineering of highly functional potyviral proteases in cells using co-evolutionary models — Co-evolutionary models can accurately predict and engineer superior potyviral proteases for precise cellular control.
• Imperagen raises £5M seed round to accelerate AI-driven enzyme engineering — Imperagen's closed-loop AI platform integrates quantum simulation and automated wet lab feedback to rapidly engineer enzymes, significantly boosting productivity.
• 🔬Beyond AlphaFold: How Boltz is Open-Sourcing the Future of Drug Discovery — AlphaFold's legacy drives open-source tools for democratizing advanced molecular structure prediction and generative design.
• Programmable RNA translation through deep learning-driven IRES discovery and de novo generation — An AI framework unifies IRES identification, optimization, and de novo generation for programmable RNA translation.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Air Street Press.