Chai-1 is a multimodal foundational model for drug discovery that predicts the molecular structures of proteins, small molecules, DNA, RNA, and covalent modifications. It achieved a 77% success rate in the PoseBusters benchmark tests, comparable to AlphaFold3. Chai-1 operates without requiring multiple sequence alignments while maintaining most of its performance and can accurately fold polymeric structures. Additionally, Chai-1 can enhance predictive performance by incorporating laboratory data. This model aims to transform biology from a science into an engineering discipline, promoting the application of AI in biological research.