We hypothesize

that understanding and harnessing biochemistry is the key to medical advancements and solutions to climate change

We believe

that enabling researchers with affordable computational products and publishing findings is the best way to build capital for research and support science

We are

pioneering cutting-edge protein annotation and design systems to turn biochemistry into a programming language

Bridging the Gap Between Computation and Wet Lab

While wet lab experiments are invaluable, they are often constrained by high costs and lengthy timelines. The immense combinatorial space in drug discovery and industrial biocatalysis is too vast to explore on the bench alone. We are addressing this challenge by building reliable computational resources to narrow down possibilities, making experimental workloads more manageable.

Our techniques harness the latest advancements in artificial intelligence, informed by deep expertise in molecular biology. By utilizing new unsupervised learning methods, we bridge gaps in sparsely labeled biochemical data and integrate information across multiple modalities.

Our frameworks currently support a wide range of inputs, including protein annotations, amino acids, nucleotide sequences, and crystal structures. With state-of-the-art generative models and scoring functions we are building products to bootstrap resources. We're currently securing funding for new foundational models, wet lab validation, and to integrate more modalities.