We are excited to share that we’ve successfully leveraged GPT‑4b micro to design novel and significantly enhanced variants of the Yamanaka factors, a set of proteins which led to a Nobel Prize for their role in generating induced pluripotent stem cells (iPSCs) and rejuvenating cells. They have also been used to develop therapeutics to combat blindness⁠(opens in a new window), reverse diabetes⁠(opens in a new window), treat infertility⁠(opens in a new window), and address organ shortages⁠(opens in a new window).

In vitro, these redesigned proteins achieved greater than a 50-fold higher expression of stem cell reprogramming markers than wild-type controls. They also demonstrated enhanced DNA damage repair capabilities, indicating higher rejuvenation potential compared to baseline. This finding, made in early 2025, has now been validated by replication across multiple donors, cell types, and delivery methods, with confirmation of full pluripotency and genomic stability in derived iPSC lines. To ensure the findings are discoverable and replicable to benefit the life sciences industry, we are now sharing insights into the research and development of GPT‑4b micro.

Figure 1: Left is initial conditions; center is standard proteins; right is using our novel proteins. The increase in round, white cells indicate an increase in reprogramming. More specifically: phase-contrast images of human fibroblasts before induction (left) and 10 days after transduction with wild‑type Yamanaka factors (middle), and our re-engineered variants (right). The engineered cocktail promotes the emergence of colonies with the compact, round morphology typically seen during progression toward an iPSC‑like state.

To test our belief that AI can be used to accelerate life sciences research, we designed and trained a custom model—GPT‑4b micro—to possess a broad base of knowledge and skills across biology, with a particular focus on steerability and flexibility to enable advanced use cases such as protein engineering. We initialized it from a scaled-down version of GPT‑4o to take advantage of GPT models’ existing knowledge, then further trained it on a dataset composed mostly of protein sequences, along with biological text and tokenized 3D structure data, elements most protein language models omit.