Self-driving laboratories to autonomously navigate the protein fitness landscape | Nature Chemical Engineering
Protein engineering is a powerful tool to create new proteins with useful functions and behaviors, but it is slow, laborious and requires specialized knowledge, limiting its broad application. Here, the authors present a system that combines AI and experimental automation to autonomously engineer proteins without human intervention.
Main Human researchers engineer biological systems through the discovery-driven process of hypothesis generation, designing experiments to test hypotheses, performing these experiments in a wet laboratory, and interpreting the resulting data to refine understanding of the system. This process is iterated to converge on knowledge of biological mechanisms and design new systems with improved properties and behaviors. However, despite notable achievements in biological engineering and synthetic biology, this process remains highly inefficient, repetitive and laborious, requiring multiple…
saved by
related reading
- ‘Set it and forget it’: automated lab uses AI and robotics to improve proteinsnature.com
- Heuristics for lab robotics, and where its future may gosubstack.com
- Automated Weak-to-Strong Researcheralignment.anthropic.com
- Heuristics for lab robotics, and where its future may goowlposting.com
- Using Self-Correcting Search to Accelerate Materials Discoverygoodfire.ai
- Engineering Plastic-Degrading Enzymes and PCSK9 Binders with Protein AI Toolsblog.latch.bio
- De novo design of ligand binding and sensing with a physics based generative approachbiorxiv.org
- The Language of Biology: Computation to aid protein designcarlosaldrete.substack.com
- AlphaProteo generates novel proteins for biology and health researchdeepmind.google
- Multiply Labs | Robotic Biomanufacturing Infrastructuremultiplylabs.com
- How we built our lab in 30 days — Bindwellbindwell.com
- Proto: A programming language for generative biology | Arc Institutearcinstitute.org