And that whole end-to-end process can be extremely expensive, cost billions of dollars and take, you know, up to a decade to do. And in many cases it still fails. You know, right now there are countless diseases for which there is no vaccine, for which there is no treatment. And it’s not that people haven’t tried, it’s just, they are, they’re challenging.
And so we built the company thinking about: How can we reduce those timelines? How can we target many, many more things? And that’s how I got into the company somehow. You know, my background is in software engineering and data science. I actually have a PhD in what’s called information physics—which is very closely related to data science.
And I started when the company was very young, maybe a hundred, 200 people at the time. And we were building that early preclinical engine of the company, which is how we can target a bunch of different ideas at once, run some experiments, learn really fast, and iterate. Let’s run a hundred experiments at once and learn quickly, and then take that learning to the next stage.
So if you want to do a lot of experiments, you have to have a lot of mRNA. So we built this massively parallel robotic mRNA processing and we had to integrate it all. We needed systems to kind of run all that, uh, robotics together. And, you know, as things have evolved as you capture data in these systems, that’s where AI starts to come in. You know, instead of just recording, you know, here’s what happened in the experiment, now you’re saying let’s use that data to make some predictions.
Let’s take the decision-making away from, you know, scientists who don’t want to just stare and look at data over and over again. But let’s use their insights. Let’s build models and algorithms to automate their analysis and, you know, do a much better job and a much faster job of predicting outcomes and improving the quality of our, our data.
So when Covid came along, it was a really, uh, powerful moment for us to take everything that we’ve built and everything that we’ve learned and the research that we’ve done and really apply it to this really important scenario. Um, and so when the Chinese authorities first released this sequence, we only had 42 days to go from taking that sequence, identifying, you know, these are the mutations that we want to do. This is the protein we want to target.
Forty-two days from that point to actually building a clinical, human-safe production, batch, and shipment to the clinic—which is completely unprecedented. I think a lot of people were surprised at how fast it moved, but it’s really… We’ve spent 10 years getting to this point. We’ve spent 10 years building this engine that allows us to launch research as quickly as possible. But it didn’t stop there.
We were thinking, how can we use data science and AI to really inform, the best way to get the best result from our clinical studies. And so one of the first big challenges that we had was we had to do this big phase 3 trial to prove in a large number, you know, there were 30,000 subjects in this study to prove that this works, right?