📊Bloomberg Technology•Freshcollected in 2m
Roche and Recursion Hunt New Brain Disease Targets
💡See how Roche is applying AI to reduce failure risk in brain-disease drug discovery.
⚡ 30-Second TL;DR
What Changed
Roche is applying Recursion AI to discover new brain disease targets.
Why It Matters
Successful AI-enabled target discovery could shorten the time and cost required to identify viable drug candidates. It may also strengthen partnerships between pharmaceutical companies and specialized AI drug-discovery firms.
What To Do Next
Evaluate Recursion’s AI-enabled target-discovery platform for a pilot focused on ranking disease-relevant biological targets.
Who should care:Researchers & Academics
Key Points
- •Roche is applying Recursion AI to discover new brain disease targets.
- •The initiative focuses on improving early-stage drug discovery.
- •AI drug discovery companies aim to reduce failed clinical trials.
🧠 Deep Insight
AI-generated analysis for this event.
🔑 Enhanced Key Takeaways
- •The collaboration utilizes Recursion’s proprietary 'Recursion OS,' a massive biological and chemical dataset combined with high-throughput automated experimentation.
- •This partnership specifically leverages Recursion’s Phenom-1 foundation model, which analyzes cellular images to predict drug-target interactions without prior biological assumptions.
- •The deal structure includes significant upfront payments and potential milestone payments reaching hundreds of millions of dollars, contingent on successful target validation.
- •Recursion’s infrastructure integrates wet-lab automation with dry-lab AI, allowing for the iterative testing of hypotheses generated by their machine learning models.
- •The focus on neuroscience is part of a strategic pivot by Roche to address the high attrition rates in CNS (Central Nervous System) drug development, where traditional target identification has historically struggled.
📊 Competitor Analysis▸ Show
| Feature | Recursion Pharmaceuticals | Exscientia | Insilico Medicine |
|---|---|---|---|
| Core Platform | Phenomics/Image-based AI | Structure-based Drug Design | Generative Biology/Chemistry |
| Lab Integration | Fully integrated wet-lab | Hybrid/Partnered labs | Partnered/CRO network |
| Primary Focus | Target discovery & Phenomics | Small molecule optimization | De novo target/molecule design |
🛠️ Technical Deep Dive
- Recursion utilizes a proprietary 'Map of Biology' which consists of petabytes of biological data generated from high-throughput microscopy.
- The Phenom-1 model is a transformer-based architecture trained on millions of cellular images to learn representations of biological states.
- The platform employs automated liquid handling and robotic systems to perform thousands of experiments in parallel, feeding real-time data back into the AI models to refine predictions.
- The system uses deep learning to identify 'phenotypic fingerprints,' allowing researchers to observe how potential drug candidates alter cellular morphology in disease states.
🔮 Future ImplicationsAI analysis grounded in cited sources
AI-driven target discovery will reduce CNS clinical trial failure rates by at least 15% within five years.
Improved target validation through phenotypic screening reduces the likelihood of selecting biologically irrelevant targets that fail during Phase II trials.
Major pharmaceutical companies will shift more than 40% of their early-stage R&D budget to AI-native biotech partners by 2030.
The high cost of traditional discovery and the proven scalability of AI platforms are forcing a structural change in pharmaceutical R&D capital allocation.
⏳ Timeline
2021-09
Recursion Pharmaceuticals announces a major multi-year collaboration with Roche and Genentech.
2023-07
Recursion acquires Valence Labs and Cyclica to bolster its generative AI and chemistry capabilities.
2023-12
Recursion releases the first open-source foundation model for biology, Phenom-Beta.
2024-05
Recursion announces the expansion of its partnership with Roche to include additional therapeutic areas.
📰
Weekly AI Recap
Read this week's curated digest of top AI events →
👉Related Updates
AI-curated news aggregator. All content rights belong to original publishers.
Original source: Bloomberg Technology ↗