Chai Discovery, which is developing AI models for drug discovery and design, raised $70 million in a series A on Wednesday. The startup will use the funding to expand on the functionality of its Chai platform, particularly in regards to targets that have been historically difficult to drug. Menlo Ventures led the round, which saw participation from other new investors Yosemite, DST Global Partners, SV Angel, Avenir and DCVC. Several existing backers also contributed, including Thrive Capital, OpenAI and Dimension— which led Chai's $30-million seed round last year — along with Lachy Groom and Fred Ehrsam.The financing comes a little over a month after Chai pulled back the curtain on its latest model, Chai‑2, which was able to design antibodies, fully from scratch, with a near-20% hit rate. According to the company, this far exceeds the 0.1% rate seen with some computational models, which often have to screen millions to billions of antibodies to find hits."Before Chai-2, the process was not unlike searching a giant bunch of keys for the right fit for a lock — but there are millions of keys," said Matthew McPartlon, Chai co-founder. "Now, it’s like having a master locksmith design exactly the right shape key, based only on your description of the lock."Chai said that even when only the target antigen and epitope are input to Chai-2, the model can generate accurate binder hits across a multitude of targets. In regards to drug development, the company predicts that Chai-2 will be able to design de novo antibodies that can precisely target a disease-causing protein. In conjunction with the financing, Greg Yap, a partner at Menlo Ventures, and Mikael Dolsten, Pfizer's former chief scientist, will join Chai's board. "Chai-2 demonstrates amazing progress in antibody design, and we have seen a meaningful fraction of the biotech industry already apply for Chai-2 access," Yap said. "We believe Chai can help create better medicines faster."