Ginkgo Bioworks' Autonomous Laboratory Driven by OpenAI's GPT-5 Achieves 40% Improvement Over State-of-the-Art Scientific Benchmark

Ginkgo Bioworks (NYSE: DNA) and OpenAI report an autonomous laboratory using GPT-5 that cut cell-free protein synthesis reaction costs by 40% versus prior state of the art, producing sfGFP at $422 per gram versus $698 per gram.

Rhea-AI Summary

Ginkgo Bioworks (NYSE: DNA) and OpenAI report an autonomous laboratory using GPT-5 that cut cell-free protein synthesis reaction costs by 40% versus prior state of the art, producing sfGFP at $422 per gram versus $698 per gram. The system ran 36,000 reaction compositions across six iterative cycles and generated ~150,000 data points.

The collaborative workflow combined GPT-5 reasoning, Ginkgo's cloud laboratory infrastructure, validation via a Pydantic model, and limited human oversight; the AI-improved reagent mix is now commercially available.

Positive

• Reaction cost reduced by 40% to $422 per gram
• Executed 36,000 reaction compositions across six cycles
• Generated ~150,000 experimental data points
• Pydantic validation model to prevent invalid experiments
• AI-improved reagent mix now commercially available

Negative

• Human role still required for reagent preparation and oversight
• Results limited to stated experimental conditions and benchmark protein
• Commercialization scope and revenue impact not quantified

Argus Feb 5 session

+0.60% close to close Open Argus

Details

News Market Reaction – DNA

In the Feb 5 session, DNA gained 0.60%, reflecting a mild positive market reaction.

Data tracked by StockTitan Argus on the day of publication.

Market Context

This announcement highlights a GPT-5–powered autonomous lab that achieved a 40% reduction in cell-fr...

Analysis

This announcement highlights a GPT-5–powered autonomous lab that achieved a 40% reduction in cell-free protein synthesis costs, down to $422 per gram over 36,000 experiments and nearly 150,000 data points. It reinforces Ginkgo’s strategy of pairing AI with its cloud lab and RAC/Catalyst automation stack. In context with prior AI initiatives and existing ATM capacity, investors may watch how effectively this capability converts into recurring reagent sales and broader platform demand.

Key Figures

Cost reduction: 40% Experiments run: 36,000 Experiment cycles: 6 +5 more

Cost reduction

40%

Reduction in cell-free protein synthesis reaction costs vs state of the art

Experiments run

36,000

Experimental conditions across six iterative cycles in autonomous lab

Experiment cycles

6

Six rounds of experiments over six months

Production cost

$422 per gram

Total reaction component cost for sfGFP benchmark protein

Prior benchmark cost

$698 per gram

Previously reported state-of-the-art reaction cost for sfGFP

Plates run

580

More than 580 384-well plates executed by autonomous lab

Data points

150,000

Nearly 150,000 experimental data points generated

Benchmark improvement

40%

Improvement over state-of-the-art scientific benchmark cited in headline

Previous AI Reports

3 past events · Latest: Aug 20

Same Type 3 events

1. Aug 20

   AI lab partnership

   24h Move

   -2.9%

   Strategic AI-driven lab-in-the-loop workflow partnership for drug discovery.

2. Sep 18

   AI data platform launch

   24h Move

   +8.8%

   Launch of Ginkgo Datapoints to supply large biological datasets for AI training.

3. Apr 10

   AI grant award

   24h Move

   -3.5%

   Grant to develop AI-enabled forecasting tools for measles outbreaks.

24h Move is the share-price change in the day after each event; other market factors may also have contributed.

Key Terms

cell-free protein synthesis, reconfigurable automation carts, catalyst automation software, superfolder green fluorescent protein, +4 more

8 terms

cell-free protein synthesis medical

"reduced cell-free protein synthesis reaction costs by 40% relative to state of the art"

Cell-free protein synthesis is a method for making proteins using the molecular machinery taken out of cells, but without growing living cells — like running an assembly line without the factory building around it. Investors care because it can shorten development time, cut manufacturing costs, and enable rapid, on-demand production of vaccines, enzymes or diagnostics with lower contamination risk and greater flexibility than traditional cell-based processes.

reconfigurable automation carts technical

"infrastructure, built from its reconfigurable automation carts (RAC) technology and Catalyst"

Reconfigurable automation carts are mobile platforms with power, sensors and interchangeable robotic or tooling modules that can be swapped or reprogrammed to perform different tasks—such as moving parts, picking inventory, dispensing medication, or running tests—without buying new equipment. Investors care because they let businesses change workflows quickly and cheaply, reducing downtime and capital expense; think of them as a Swiss Army knife on wheels that keeps operations flexible and productive as needs evolve.

catalyst automation software technical

"RAC) technology and Catalyst automation software, to design, execute, and analyze"

Software that automates routine business tasks and workflows tied to company milestones or market-moving events—such as product launches, regulatory filings, sales campaigns, or manufacturing steps—so those catalysts happen faster, with fewer mistakes and more predictable timing. For investors, this matters because smoother, quicker execution can raise revenue, cut costs and reduce the chance that key events are delayed or fail, all of which influence a company’s short- and long-term value; think of it as an automated assembly line for business milestones.

superfolder green fluorescent protein medical

"production of a standard benchmark protein, superfolder green fluorescent protein (sfGFP), at"

An engineered version of green fluorescent protein that reliably folds into the correct shape and glows inside cells, acting like a tiny, built‑in light bulb researchers attach to proteins or cells to see where they go and how they behave. For investors, it matters because this reliability makes laboratory tests, diagnostic tools and biologic development faster and less failure‑prone, which can shorten timelines, cut costs and reduce technical risk in biotech projects.

sfGFP medical

"benchmark protein, superfolder green fluorescent protein (sfGFP), at $422 per gram"

sfgfp is a lab-engineered version of green fluorescent protein that reliably folds and emits a bright green glow when produced inside cells, acting like a tiny lightbulb attached to molecules or cells. Investors should note it as a common research tool: its use can make experiments clearer and faster to interpret, improving reproducibility and signaling more robust preclinical data that may affect development timelines and regulatory review.

384-well plates technical

"The autonomous lab executed more than 580 384-well plates, tested 36,000 reaction"

A 384-well plate is a flat laboratory tray with 384 tiny, regularly spaced containers (wells) used to run many small experiments or tests at once. Think of it as a muffin tin or egg carton for chemical or biological samples: it lets researchers process many samples quickly, consistently, and with less reagent per test. For investors, widespread use of these plates signals higher R&D throughput, lower per-test costs, and demand for automated lab equipment and supplies, which can affect revenues and development timelines.

pydantic model technical

"every design was validated against a Pydantic model before execution, including checking"

A Pydantic model is a software component used in Python programs to define the expected shape and rules for data, automatically checking and converting incoming values into the correct types. For investors, it matters because it acts like a quality checker on a data assembly line—helping ensure financial feeds, filings and reporting systems are consistent and error-free, which reduces false alerts, reporting delays and costly mistakes in decision-making.

large language model technical

"By pairing a frontier large language model with an autonomous lab, we found reaction"

A large language model is a computer system trained on vast amounts of text to understand and generate human-like writing, like a very well-read virtual assistant that can summarize, draft, translate, or answer questions. Investors care because it can change how businesses operate and compete—boosting productivity, cutting costs, or enabling new products—while also creating risks around accuracy, regulation, and security that can affect revenue and valuation.

AI-generated analysis. How Rhea-AI works. Not financial advice.

See more from StockTitan in Google Search and AI answers. Adds StockTitan as a preferred source · opens Google

Add on Google Not now

• Research conducted in collaboration with OpenAI using Ginkgo's cloud laboratory
• Preprint describes how GPT-5-driven autonomous lab significantly reduced reaction costs in cell-free protein synthesis
• GPT-5-driven autonomous lab executed over 36,000 experiments
• Ginkgo now selling the AI-improved reaction mix in its reagents store, showing commercial potential of AI-driven science

BOSTON, Feb. 5, 2026 /PRNewswire/ -- Ginkgo Bioworks (NYSE: DNA) today announced it has demonstrated, in collaboration with OpenAI, an AI system that autonomously designed, executed, and learned from biological experiments with minimal human involvement. In a new preprint, the company reports the system reduced cell-free protein synthesis reaction costs by 40% relative to state of the art, while running 36,000 experimental conditions across six iterative cycles.

The study represents a real-world scientific application of Ginkgo's autonomous lab. The collaborators combined OpenAI's GPT-5 reasoning model with Ginkgo's cloud laboratory infrastructure, built from its reconfigurable automation carts (RAC) technology and Catalyst automation software, to design, execute, and analyze experiments in an iterative, closed-loop workflow. GPT-5 was given internet access, a computer with data analysis packages, experimental (meta)data from prior iterations, and a preprint describing state of the art, and was able to operate like an experimental scientist – designing experiments, analyzing results, and refining its approach in response. In six rounds of experiments over the course of six months, it was able to design lower cost cell-free protein synthesis reaction compositions than had been shown in the scientific literature previously.

"By pairing a frontier large language model with an autonomous lab, we found reaction compositions that are notably cheaper than prior state of the art," said Reshma Shetty, co-founder of Ginkgo Bioworks and co-author of the study. "We expect more and more experiments to be run on autonomous labs where reagent and consumables costs dominate the cost of an experiment. Lower cost reagents for protein production enable more data generation and thus more scientific progress per dollar spent."

The autonomous lab achieved production of a standard benchmark protein, superfolder green fluorescent protein (sfGFP), at $422 per gram of protein in total reaction component costs, compared to a previously reported state of the art of $698 per gram, representing a 40% reduction under the experimental conditions described. Cell-free protein synthesis is widely used in biological research but has been limited by high material costs and complex optimization, making it an ideal stress test for autonomous experimentation.

"At OpenAI, this was the first time we were able to interface a frontier model with an autonomous lab to carry out experimentation at a very large scale," said Joy Jiao, life sciences research lead at OpenAI and co-corresponding author of the study. "This success points to how AI systems can augment the experimental workflow, contributing to hypothesis generation, testing, and refinement based on real-world data."

The autonomous lab executed more than 580 384-well plates, tested 36,000 reaction compositions, and generated nearly 150,000 experimental data points. Human involvement was primarily limited to reagent preparation, loading and unloading and system oversight, while experimental design, execution data interpretation, and hypothesis generation were handled by the GPT-5-driven autonomous lab. Notably, the model also proposed and prioritized new reagents to test, some of which independently anticipated findings from published research it had not been given access to.

To preclude the AI from proposing impractical, invalid, or hallucinatory experiments, every design was validated against a Pydantic model before execution, including checking plate layout, standards, controls, replication, reagent availability, and volume constraints. Only experiments that passed validation were eligible to run. Additional scoring prioritized scientific rigor and consideration of prior results. GPT-5 generated human-readable lab notebook entries documenting its analysis, observations, and rationale, providing transparency into its reasoning.

"This is AI doing real experimental science: designing experiments, running them, and learning from the results," said Jason Kelly, co-founder and CEO of Ginkgo Bioworks. "AI combined with autonomous labs is needed to keep the United States competitive in science worldwide – the recently announced Genesis Mission led by the U.S. Department of Energy to bring AI into science is leading the way here and I'm excited that our results with OpenAI show this approach is working."

The Pydantic model is being released open source and the AI-improved cell-free reaction mix can be ordered by the scientific community at https://reagents.ginkgo.bio/

About the Preprint
The findings are described in a scientific preprint that has not yet undergone peer review. The full manuscript, "Using a GPT-5-driven autonomous lab to optimize the cost and titer of cell-free protein synthesis," is available on OpenAI's website and will soon be available on bioRxiv.

About Ginkgo Bioworks
Ginkgo Bioworks builds the tools that make biology easier to engineer for everyone. The company offers autonomous laboratories that replace manual laboratory work with robotics in the lab, greatly improving the productivity of scientists. Ginkgo's in-house autonomous lab is also available as a "cloud lab" through our Datapoints and Solutions contract research services. For more information, visit ginkgobioworks.com and ginkgobiosecurity.com, read our blog, or follow us on social media channels such as X (@Ginkgo and @Ginkgo_Biosec), Instagram (@GinkgoBioworks), Threads (@GinkgoBioworks), or LinkedIn.

Forward-Looking Statements of Ginkgo Bioworks
This press release contains certain forward-looking statements within the meaning of the federal securities laws, including statements regarding the capabilities and potential success of Ginkgo's autonomous laboratories. These forward-looking statements generally are identified by the words "believe," "can," "project," "potential," "expect," "anticipate," "estimate," "intend," "strategy," "future," "opportunity," "plan," "may," "should," "will," "would," "will be," "will continue," "will likely result," and similar expressions. Forward-looking statements are predictions, projections and other statements about future events that are based on current expectations and assumptions and, as a result, are subject to risks and uncertainties. Many factors could cause actual future events to differ materially from the forward-looking statements in this press release, including but not limited to: (i) our ability to realize near-term and long-term cost savings associated with our site consolidation plans, including the ability to terminate leases or find sub-lease tenants for unused facilities, (ii) volatility in the price of Ginkgo's securities due to a variety of factors, including changes in the competitive and highly regulated industries in which Ginkgo operates and plans to operate, variations in performance across competitors, and changes in laws and regulations affecting Ginkgo's business, (iii) the ability to implement business plans, forecasts, and other expectations, and to identify and realize additional business opportunities, including with respect to our solutions and tools offerings, (iv) the risk of downturns in demand for products using synthetic biology, (v) the uncertainty regarding the demand for passive monitoring programs and biosecurity services, (vi) changes to the biosecurity industry, including due to advancements in technology, emerging competition and evolution in industry demands, standards and regulations, (vii) the outcome of any pending or potential legal proceedings against Ginkgo, (viii) our ability to realize the expected benefits from and the success of our Foundry platform programs and Codebase assets, (ix) our ability to successfully develop engineered cells, bioprocesses, data packages or other deliverables, (x) the product development, production or manufacturing success of our customers, (xi) our exposure to the volatility and liquidity risks inherent in holding equity interests in other operating companies and other non-cash consideration we may receive for our services, (xii) the potential negative impact on our business of our restructuring or the failure to realize the anticipated savings associated therewith and (xiii) the uncertainty regarding government budgetary priorities and funding allocated to government agencies. The foregoing list of factors is not exhaustive. You should carefully consider the foregoing factors and the other risks and uncertainties described in the "Risk Factors" section of Ginkgo's annual report on Form 10-K filed with the U.S. Securities and Exchange Commission (the "SEC") on February 25, 2025 and other documents filed by Ginkgo from time to time with the SEC. These filings identify and address other important risks and uncertainties that could cause actual events and results to differ materially from those contained in the forward-looking statements. Forward-looking statements speak only as of the date they are made. Readers are cautioned not to put undue reliance on forward-looking statements, and Ginkgo assumes no obligation and does not intend to update or revise these forward-looking statements, whether as a result of new information, future events, or otherwise. Ginkgo does not give any assurance that it will achieve its expectations.

Contacts

Ginkgo Bioworks investor contact:
investors@ginkgobioworks.com

Ginkgo Bioworks media contact:
press@ginkgobioworks.com

View original content to download multimedia:https://www.prnewswire.com/news-releases/ginkgo-bioworks-autonomous-laboratory-driven-by-openais-gpt-5-achieves-40-improvement-over-state-of-the-art-scientific-benchmark-302680619.html

SOURCE Ginkgo Bioworks

FAQ

AI-generated questions and answers. How Rhea-AI works. Not financial advice.

What did Ginkgo (DNA) and OpenAI announce on February 5, 2026 about GPT-5 and autonomous labs?

They announced an autonomous lab using GPT-5 that autonomously designed and ran experiments, reducing reaction costs by 40%. According to the company, the system ran 36,000 reaction compositions across six cycles and produced ~150,000 data points under limited human oversight.

How much did the GPT-5-driven autonomous lab reduce cell-free protein synthesis costs for DNA?

The autonomous lab reduced reagent costs by 40%, to $422 per gram of sfGFP. According to the company, the prior reported state of the art cost was $698 per gram under the experimental conditions described in the study.

How extensive was the experimental scale used by Ginkgo and OpenAI in the DNA study?

The project executed more than 580 384-well plates and tested 36,000 compositions. According to the company, the runs spanned six iterative cycles over six months and generated nearly 150,000 experimental data points for analysis.

What safeguards did Ginkgo use to prevent invalid experiments in the GPT-5 autonomous workflow?

All designs were validated against a Pydantic model checking layout, controls, reagent availability, and volumes before execution. According to the company, only validated experiments passed to the lab, and additional scoring prioritized scientific rigor and prior results.

Can researchers buy the AI-improved reagent mix from Ginkgo (DNA) and where is it available?

Yes; the AI-improved cell-free reaction mix is commercially available for order through Ginkgo's reagents store. According to the company, the product is listed on Ginkgo's reagent storefront for the scientific community to purchase.