We believe that machine learning is the future of biology—that it can unlock breakthroughs at unprecedented speed. But exabytes of biological data worldwide are unusable because of poor documentation. So, we are building infrastructure to transform these data into the clean, standardized resources that machine learning requires. But machine learning isn’t the only goal—by automating data extraction, metadata standardization, and curation, we aim to eliminate countless hours wasted by millions of researchers worldwide searching for and cleaning biological data, enabling these scientists to spend more time discovering new treatments and cures.

Covalent.Bio

Org chart

Teams

Offices