Ginkgo Bioworks Holdings (DNA) announced on Thursday that, in collaboration with Microsoft (MSFT)-backed OpenAI (OPENAI), it has designed an AI system that can lower costs in cell-free protein synthesis by 40%.
Unlike DNA-based protein synthesis, cell-free protein synthesis can rapidly produce proteins without the need for living cells, making it useful for scientists who require quick clinical results.
The findings detailed in a scientific preprint that has yet to undergo peer review suggest that the system conducted more than 36,000 CFPS reactions across 580 automated plates, generating nearly 150,000 experimental data points.
The cell platform company added that the partnership combined OpenAI’s (OPENAI) GPT-5 large language model with Ginkgo’s (DNA) cloud laboratory infrastructure.
“By pairing a frontier large language model with an autonomous lab, we found reaction compositions that are notably cheaper than the prior state of the art,” Ginkgo co-founder and co-author of the study, Reshma Shetty, said.
“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,” added Joy Jiao, the study’s co-corresponding author and life sciences research lead at OpenAI.