Three innovations driving growth in healthcare

Agustin Mohedas: Today, I’m going to be speaking to you about healthcare, and then more specifically about biotechnology.

ADCs: Revolutionizing cancer treatment

Now, I want to spend a little bit of time focused on something called antibody-drug conjugates because I think it’s a pretty revolutionary new technology that I think you’re going to be hearing a lot more about and it’s really changing the way we practice medicine in the field of oncology, or cancer treatments.

Just to do a little bit of Biology 101. Our body creates antibodies against bacteria and viruses to help neutralize and destroy those viruses and prevent infection, and so this is part of our natural immunity.

Biotechnology companies over the last many years, actually, have figured how to harness this part of our immune system to create therapies. And so, what we can do is actually create an antibody that binds to a specific part of a cell or a protein.

Now, cancers express on their cell surface specific markers that we can use to identify them over healthy tissue. So, we can design antibodies specifically against those markers. Not only that, we can attach what’s called a payload, and in this case a payload is basically chemotherapy; super potent chemotherapy that we attach to the antibody. So, basically what we’ve created is a trojan horse, essentially, that can bind to the cancer cell, enter, deliver the payload (or the cytotoxic drug or the chemotherapy), and then kill the cancer cell while any sparing any healthy tissue.

GLP-1s: Reducing health risks

Now, we’ll talk a little bit about obesity. So, I think the GLP-1s have gotten a lot of attention in the media, of course, and the reason I brought this up today is because I think what’s lost on a lot of people or what the media hasn’t focused too much on are the fact that these drugs actually improve survival. They not only help people lose weight, but they actually improve the downstream consequences of that, which are heart disease, stroke, and I think, eventually – now, this hasn’t been proven – but I think ultimately, cancer as well.

So, I wanted to highlight these GLP-1s because obesity is a major worldwide problem, and we expect the GLP-1 class of medicines or these obesity medicines to probably become a $100 billion to $200 billion worldwide market, which will be the largest pharmaceutical market we’ve ever seen. So, it’s pretty exciting from an investment point of view to try to figure out, okay, who are the winners going to be and what’s coming next.

AI: Speeding drug discovery

I want to talk a little bit about AI [artificial intelligence], something that’s also gotten a lot of attention recently, and how that might benefit the drug discovery and development process. Now, there’s a lot of hype around AI, so, I think it’s really important from an investment point of view to not get sucked into the hype of AI. However, I’d be remiss to not mention this because I do believe these technologies are going to materially improve the way we do drug discovery and development.

So, drug development takes anywhere from seven to 10 years to get a drug onto the market. From the initiation of a phase 1 clinical study all the way through phase 3 studies and finally, FDA [Food and Drug Administration] approval. That’s a seven to 10 year process. And actually, that seven to 10 year estimate is actually an underestimate because there’s a whole other part of the process called the preclinical development. This is where we’re doing the basic science to discover our drug target, where we are modifying molecules in the lab, like what I used to do during my Ph.D. days, pipetting and injecting mice and all that stuff. All that can take another three to five years.

Where I think AI is going to have the biggest impact for now is in this early stage of drug development. For example, when I was in my Ph.D., I worked with a chemist, and we probably synthesized maybe 200 to 500 molecules that then I tested in cells and in mice. Now, that was a very manual process; now, I was free labor, so it was fine. But ideally, this process would be done in a more robust way.

So, what AI is really helping us do is we can now model how these proteins behave in silico, or in a computer. We can actually model how a protein target – here on the left you see a protein – and then, what we can do is use the computer to basically guess how a drug might bind to that protein. And then instead of me synthesizing 200 to 500 molecules in the lab over the course of five years to do a Ph.D., we can have the computer synthesize a billion or a trillion molecules and test them all at once over the course of a week on a supercomputer and figure out, okay, we’ve tested a trillion molecules in the computer, here are the best ones. Here are the 100 best binders that we found, now make those.

This is really where AI is going to really revolutionize drug development. It’s in this early stage where we can model everything in the computer, have the computer run the experiments for us using these large models and adaptive machine learning technology, take all that big data, spit it out, and then all of a sudden turbocharge the productivity of scientists in the lab so they’re not wasting their time making things that aren’t going to work and are focused on the areas that are the highest yield.