And this whole process from start to finish can be very expensive, cost billions of dollars and take, you know, up to a decade to do so. And in many cases, it still fails. As you know, there are countless diseases right now for which there is no vaccine, and no cure. And it’s not like people didn’t even try, it’s just a challenge.
And so we built the company thinking: How do we reduce those timelines? How can we target many, many things? And that’s how I kind of got into the company. As you know, my background is in software engineering and data science. I already have a PhD in the so-called information physics – which is closely related to data science.
And it started when the company was really small, maybe a hundred or 200 people at the time. And we were building the company’s early preclinical engine, which is, how do we target a bunch of different ideas at once, do some experiments, learn really fast and do it all over again. Let’s do a hundred experiments at a time and let’s 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 processing of mRNA, and we needed to integrate all of that. We needed systems to guide all those, uh, robots together. And as you know, as things evolve as you capture data in these systems, artificial intelligence begins to emerge. You know, instead of just capturing, you know, that’s what happened in the experiment, you’re now saying let’s use this data to make some predictions.
Let’s make a decision away from the scientists who don’t want to just stare and look at the data over and over again. But let’s use their insights. Let’s build models and algorithms to automate their analytics, and as you know, we do a much better and much faster job of predicting outcomes and improving the quality of our data.
So when Covid came up, it was really, uh, a powerful moment for us to take all that we’ve built and all we’ve learned, the research that we’ve done and really apply it to this really important scenario. Um, so when this sequence was first released by the Chinese authorities, we only had 42 days to go from taking this sequence, and identifying, you know, these are the mutations we want to make. This is the protein we want to target.
Forty-two days from that point to build, push, and ship clinical-grade, human-safe manufacturing to the clinic – totally unprecedented. I think a lot of people were surprised at how fast it went, but it’s really… It took us 10 years to get to this point. We’ve spent 10 years building this engine that allows us to move our search as fast as we can. But it didn’t stop there.
We thought, How can we use data science and artificial intelligence to inform the best way to get the best outcome for our clinical studies. And so one of the first big challenges we had was we had to do this big phase of the experiment to prove a large number of, you know, 30,000 people were in this study to prove that this works, right?