sota.bio is an open-source effort to characterize the biotechnology industry itself, in particular, the frontier of our industry, the state-of-the-art (SOTA). We identify the core problems across biotech, and track the current best-in-class solutions, with a focus on areas under active industry development. We’re like a community-run, real-time leaderboard, but for technology.

What are the best-performing computational biology models, and which benchmarks should we use? Which company achieves the highest probability of success in developing cancer therapeutics? What’s the price per base of the cheapest DNA, and who sells it? Which characterization methods generate the most information per unit time, or per dollar spent? Who has the biggest genomics dataset? The most autonomous lab? … and how are the values changing over time?

We’ve all seen the plot of falling DNA sequencing costs over time by now, and while it's great, we hope to give you more.

Our strategy is to choose the right metrics to describe technologies, where if a new technology surpasses the existing value, it really feels like we’ve moved the needle. Choosing these parameters well is essential. In many cases it can be subjective and far from trivial. To get this right, we lean heavily on domain-specific expert input. We’re a community of researchers, engineers, and other curious minds, from students of bio to our thought leaders. We boil down this expert knowledge to characterize our industry’s SOTA technologies by the numbers, in a simple, interpretable way.

Be a part of our community .