GPT-5 lowers the cost of cell-free protein synthesis

2026-02-05 · Source: OpenAI News · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems, Life Sciences & Biology · Depth: Advanced, medium

Summary

OpenAI, in collaboration with Ginkgo Bioworks, developed an AI-driven autonomous lab utilizing GPT-5 to optimize cell-free protein synthesis (CFPS). This system achieved a 40% reduction in protein production cost, including a 57% improvement in reagent cost, by identifying novel reaction compositions. Over six rounds of closed-loop experimentation, the system tested more than 36,000 unique CFPS reaction compositions across 580 automated plates. GPT-5, provided with a computer, web browser, and access to relevant papers, established a new state of the art in low-cost CFPS within three rounds. The improvements stemmed from discovering combinations robust to high-throughput automation conditions, such as low oxygenation, and optimizing parameters like buffering, energy regeneration, and polyamines, which have an outsized impact on cost.

Key takeaway

For AI Researchers developing biological applications, this work demonstrates that integrating large language models like GPT-5 with autonomous wet labs can dramatically accelerate optimization and reduce costs in complex biological processes. You should consider closed-loop experimentation as a core strategy for tackling bottlenecks in iteration, particularly where high-throughput testing can uncover non-obvious solutions and improve robustness under automated conditions. This approach has implications for biosecurity that require careful assessment and mitigation.

Key insights

GPT-5 connected to a robotic lab significantly reduced cell-free protein synthesis costs through autonomous closed-loop optimization.

Principles

• High-throughput iteration reveals optimal biological conditions.
• Cost structures dictate optimization priorities.
• Automated labs enable discovery of non-intuitive solutions.

Method

GPT-5 designed experiments, which a cloud lab executed. Results fed back to GPT-5, which analyzed data, generated hypotheses, and designed subsequent rounds in a closed-loop system.

In practice

• Integrate frontier models with lab automation.
• Focus on yield to reduce dominant input costs.
• Validate AI-designed experiments programmatically.

Topics

• GPT-5
• Cell-Free Protein Synthesis
• Autonomous Labs
• Closed-Loop Experimentation
• Biotechnology Optimization

Best for: AI Researcher, AI Scientist, Research Scientist

Related on AIssential

• 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.
• A Self-Evolving Agentic System for Automated Generation and Execution of Biological Protocols — ProtoPilot demonstrates a verifiable route to autonomous wet-lab experimentation through a self-evolving multi-agent system.
• AI can design and run thousands of lab experiments without human hands. Humanity isn’t ready for the new risks this brings to biology — AI is rapidly automating biological experimentation, accelerating discovery but also creating significant dual-use biosecurity risks.
• Functional protein design and enhancement with ontology reinforcement iteration — ORI integrates ontology-conditioned decoding with reinforcement learning for controllable, interpretable, and experimentally validated protein design.
• ChemT Biotechnology Raises US$5 Million in 18 months to bring AI to Biomanufacturing — AI-driven virtual cell platforms can precisely guide cell behavior to enhance biomanufacturing efficiency and scalability.
• Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization — Unsupervised reward optimization using task-agnostic rewards enables steerable protein generation, outperforming baselines without ground-truth labels.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by OpenAI News.