X

 

 

How to Efficiently Discover Drugs
Episode

Ron Alfa, Senior Vice President, Translational Discovery at Recursion Pharmaceuticals

How to Efficiently Discover Drugs

Merging machine learning and AI for experimental biology at an unprecedented scale

How to Efficiently Discover Drugs

Thanks to Our Podcast Sponsor, Noveta Health

Save 25-30% on Your Health Benefit Spend

Recommended Book:

The Structure of Scientific Revolution By Thomas Kuhn

Best Way to Contact Ron:

ron@recursionpharma.com

Mentioned Links:

Company Website

How to Efficiently Discover Drugs with Ron Alfa, Senior Vice President, Translational Discovery at Recursion Pharmaceuticals (transcribed by Sonix)

Saul Marquez: Hey Outcomes Rocket listeners thanks for tuning into the podcast again. Tired of your businesses healthcare costs unpredictably increasing every year? Healthcare costs are typically a business’s second or third line item expense. And if you’re like most employers, it’s an expense that’s growing faster than your revenue. Luckily for employers Noveta Health has the solution. Noveta Health is a full service healthcare consulting firm with proven strategies to lower your healthcare costs by up to 30% or more. They operate on a fee for service model and never mark up any of their medical or pharmaceutical claims. None of your employees have to leave their doctor or pharmacist either. Their health captive and pharmacy benefit manager are the most cost effective and transparent solutions in the whole country. What they do is not magic. It’s just honest. So if you’re tired of over spending on health insurance and want to learn more visit outcomesrocket.health/save for a free spend analysis to see how you too could save by switching to Noveta Health. That’s outcomesrocket.health/save for your free spend analysis outcomesrocket.health/save.

Saul Marquez: Welcome back to the podcast. Saul Marquez here and I have the privilege of introducing you to Dr. Ron Alfa. He is the Senior Vice President of Translational Discovery at Recursion Pharmaceuticals. Ron is a physician scientist with training in metabolism, neuro degeneration, and genetics, committed to the discovery of breakthrough treatments for patients. He’s working alongside a brilliant and inspired team of biologists, engineers, and data scientists at Recursion Pharmaceuticals to build an incredible organization that leverages computation to revolutionize pharmaceutical development. I had the privilege of meeting Ron at the TED MED 2018 meeting, also heard his speech up on a stage and I couldn’t help but be inspired. Ron holds an M.D. and a Ph.D in neuroscientists from Stanford University and an M.A from University College of London. Over the course of his education he has developed molecular therapeutics for Alzheimer’s disease, discovered hormones of metabolism, and puzzled over the basics of the placebo effect. He’s a California native. He traded the valley for the slopes to follow his passion for accelerating therapeutic discovery with recursion in Salt Lake City. When he’s not working, Ron enjoys taking on various projects which some might construe as questionably different from working. So Ron, it’s a pleasure to have you on the podcast and a pleasure to connect with you again.

Ron Alfa: Thanks Saul, it’s great to be here. And one might argue that this is an activity that is quite similar to working I might do when and I’m not working.

Saul Marquez: I love it man you’re you’re so passionate I love your your way of doing things. What is it that got you into the medical sector to begin with?

Ron Alfa: Yeah yeah great question. So you know I initially decided I want to go into medicine. Then in particular medical research because you know over the course of all of our lives we have the sort of experiences where you know people get sick and we kind of interact with the medical system in some way shape or form and without telling my own kind of illness story if you will or how many illness stories of the people I’ve met or people in my family. Overall for me, was just this sort of idea that we’re spending so much of our effort and trying to understand medicine, trying to understand human physiology, science biology, and yet are so far away from having treatments for so many diseases. And as I was going through college of course undergrad and began graduate school that was always a point that just struck me as almost surprising but more troublesome that you know we are putting a huge amount of effort into science and we can why can’t we treat some of these diseases better. And actually it reminds me of a quote that George in couple of general just actually mentioned at a conference I’m at this weekend where he said “inventing a new medicine to treat disease maybe was the hardest thing humanity has ever done.” And I think that it’s inspirational because first of all it certainly is this incredibly hard problem on one hand but then there’s also very much feels like something that through science and we should be able to make an impact on.

Saul Marquez: Yeah. You know Ron I think it’s true and I think we don’t give proper credit to the people, companies, that have come up with the drugs that already exist and work effectively the life sciences, lifecycle from the beginning to a drug that actually work as long it’s expensive and oftentimes it doesn’t work. I love to hear from you what you believe a hot topic needs to be made as agenda as it relates to this and how are you guys approaching it?

Ron Alfa: Yeah that’s exactly right. And so you know everyone recognizes the challenges in discovering a new medicine you know early on doing the science on and identifying either the target or the first compound that could be potential new medicine and taking that all the way through the many many stages to clinical development and there are numbers that folks throw around so to me that can cost two billion dollars for a compound per new medicine if you count the entire cost of RNB. And so a hot topic in this space right now and you see I’m sure you’ve heard a lot about this is machine learning and computational tools, machine learning, artificial intelligence, lots of terms that don’t necessarily mean the same things that oftentimes are used interchangeably in the media are generally in a position where people sort of think that these types of approaches using software and advanced machine learning techniques are going to revolutionize just about any industry. So why aren’t they making an impact on drug discovery. So that’s the one question. But from a controversial standpoint, I think a lot of folks are saying how biology is just too hard and there’s a lot of disbelief in many ways that machine learning techniques are actually going to be impactful. So people often reference sort of the hype cycle and suggest that you know there’s a lot of companies in this space are talking about, how machine learning tools can be built to accelerate drug discovery but there isn’t a lot to show from it.

Saul Marquez: Yeah so totally totally get it. The hype cycle really are people just using these terms to get press. Maybe you could give us an example Ron of how year companies making a difference in creating results by using these techniques.

Ron Alfa: Yeah great point. So one of the things that we as a company want to emphasize is you know I think the only way to sort of get past the hype is to actually get to results and you know as a company it’s only been around for five years. Three years ago we really couldn’t point to any results. Today we can point to a compounded and new potential therapeutic that’s just finishing off the first of the Phase 1 study. So it’s actually been inhuman. And we can point to another compound that we’ve discovered that we’ve license that the clinical stage compound. So those are tangible results where we can say look we’ve applied machine learning to drive this area and in a relatively short amount of time. Now as short as we would hope for but in a relatively short round time we’ve made an impact because I was also going to add that I think from from the perspective of recursion of the company what we are trying to do in this space is think about what kind of data set do we need in order to build a suite of tools if you will that will help us to move our candidate faster through the pipeline from the early discovery phase to the clinical development phase and increasingly building those datasets and those tools using software.

Saul Marquez: Dan definitely another sort of logistical issue there and one that deserves attention. So I think it’s fascinating work that you’re up to Ron and intriguing to me. I mean in the typical life cycle from discovery to market five years is nothing. So in the context of what we’re talking about yeah I mean it’s free. Fabulous work. However in the context of startups and everything. Five years is a long time. You know folks you gotta listen to these results and put them in the context I would say because it is big progress that these folks are making. With the good things come setbacks and I’d like to hear from you Ron maybe a time when you guys had a setback and what you learned from that that has made you guys better.

Ron Alfa: So the one thing that comes to mind. I’ll say two things regarding that back first I think very broadly speaking as a startup you fail every tech you need to be wrong a lot. So I think it’s important for all of us and especially in leadership positions and especially at startups to be very comfortable being wrong and being very comfortable taking feedback from other people putting ideas out there and letting people pressure test those ideas. One of our company mottos at Recursion is it’s actually asked why and that’s a very uncomfortable company model or company culture because it gives everyone free rein to say why do you think that way about that thing or why do you think that’s going to be effective. And really to pressure test you on just about everything. And so for folks that often started at Recursion they’re a little bit uncomfortable with it but pretty soon you get really used to it and you realize that you know this is incredibly important because we don’t all have all the answers. In fact we certainly do not have all the answers and this is the correct approach or the best approach as it were not the correct approach. But the best approach often is emergent from conversation with multiple different people and kind of and oftentimes conversation people just pressure testing. Yes. So I think for me I think that’s one of the important most important thing. In just a more practical response to your question however is and I sort of reference this I’m going to go the very beginning. I think we thought we were going to be able to build the tools, built the data set a lot more quickly than we could. And that’s not to say that but we haven’t. And just a short amount of time really made an impact on drug discovery by building machine learning tools. We certainly have made lots of fantastic progress. But I would say one of the big lessons that we’ve learned was that one of the most important aspects of being a data science company and using machine learning models is to have extraordinary first of all extraordinary data and have extraordinary control and understanding of that data. And I think it’s safe to say that it took us just a little bit longer than than than we had anticipated to fully understand every aspect of the data that we needed to control in order to fully understand the assumptions that we were making. And I think a lot of folks in this space that’s kind of a lesson that a lot of folks in the space that are generating data or that are that are using machine learning tools alongside large datasets will come to that conclusion as well.

Saul Marquez: Great findings Ron and appreciate you sharing those. There’s definitely a point where all of these these are lessons and successes culminate into great opportunity happening and things like that. I know you’ve got a lot a lot of really interesting things happening today. What would you say up to this point is one of your proudest leadership experiences with the company?

Ron Alfa: Yeah that is a great question and also a little bit of a difficult one I would say so I started at Recursion about three years ago. We were a very small team took around around 10 or 12 people and so on one hand I feel incredibly proud and incredibly privileged for how far we’ve come. And I think my contributions to building that team is an area that I certainly feel proud of. But I also have a very hard time sort of giving that response because on one hand you know I owe my ability to contribute this incredible rocket ship of a mission to the fantastic founders of Recursion that invites me to join the team and that has been incredibly passionate and incredibly hardworking throughout the journey of the company. I also have to recognize everyone that along the way all these incredible people that we’ve hired and you know being in Salt Lake City a lot of folks have had moved from you know I moved from San Francisco a lot of other folks have moved from different areas of the country. They hit the ground running and really really committed and inspired by the mission. So on one hand I feel very proud of how far we have gotten as a company and what we’ve got and what we have achieved. But I also feel very privileged to have worked with such a tremendous number of incredibly driven people that have contributed to that.

Saul Marquez: For sure. Now that’s a great call out you know and it’s definitely important to consider the people on your team as you as you think about your proud moments in the building of your company eventually kind of like the the question you left us with that at TED MED is “can we map all of all of human biology?” And if you guys keep up the work you’re up to I don’t know maybe the answer to that is yes. So what would you say today is an exciting project that you’re focused on/

Ron Alfa: Yes. So there there’s a lot of incredible work going on in Recursion. I already mentioned that you know we have our first compound that drug that’s been discovered using our machine learning tools in human clinical trials and phase one that we’re incredibly excited about that that compound is for a rare genetic disease called Eagle Cavernous Malformation that’s a very devastating hereditary stroke syndrome that affects thousands of patients. So we’re thrilled to be moving that compound into the clinic and looking forward to talking more about results as as we progressed. We also just licensed another compound that is again a clinical stage compound one that we discovered on our on our platform for a disease called nerve fiber the of type 2 and that’s another very severe case a rare tumor syndrome again a rare genetic disease that’s quite debilitating and so that’s another piece that we have close to our heart of recursion and are very excited to potentially impact the way in which our candidate. Then the last thing I’ll mention is the on that we have over the past year you know allows a lot of what we had done earlier in the company is built this very large dataset but over the past year we’ve begun to ask questions like Can we combine this core dataset that we have cellular images with other types of dataset and use the combination of those datasets with machine learning tools to build predictive models or other important aspects of drug discovery. So for example cardiac toxicity is an important, evaluating cardiac toxicity and an important step in any drug discovery campaign. So we’ve been asking can we actually predict cardiac toxicity from the original dataset without running additional studies. E by this one thing which is called Herb and we were able to very quickly generate this additional dataset that we can combine with the power core imaging dataset and we’re actually seeing great results in predicting our results for the FSA for compounds that have never been run out. And so we’ve been able to do that across multiple different FDA. So I think this is one area that’s really only been in development for about a year and out where we’re seeing incredibly rapid results which is incredibly exciting.

Saul Marquez: That is exciting Ron and kudos to you and your team for being creative in your approach and taking a look beyond the regular practices and how you could combine these datasets for four results. Getting close to the end here. Let’s pretend you and I are building a course on what it takes to be successful in the business of pharma on healthcare it’s the ABC’s of Dr. Ron Alfa. So I’ve got five questions lightning round style for you followed by a book that you recommend to the listeners. You ready?

Ron Alfa: Yeah. Okay.

Saul Marquez: All right. What’s the best way to improve healthcare outcomes?

Ron Alfa: One of the challenges that always comes up for healthcare is just probably innovation. And on one hand healthcare systems are always trying to innovate. But on the other hand physicians and others and both outside the States even are always sort of complaining that innovation is incredibly slow in healthcare and understandably so because health care is a very conservative state. Human lives and health at stake but at the same time I think there is opportunity to create sort of innovation and to innovate in ways that don’t put patients health at risk. And so I think we need to continue to think creatively about how can we innovate in health care and the physician hospitals the health care ecosystem needs to be open to in some cases outsiders coming in and thinking a little bit differently about how we can solve problems.

Saul Marquez: What’s the biggest mistake or pitfall to avoid/

Ron Alfa: I think one of the things that always comes to mind as a pitfall is sort of this assumption that the status quo how things are today are necessary or are so because they are the best or most optimal solution. I think you know my I have a degree in history as you mentioned in the bio and one of the things I studied was the history of science and medicine and as you look back in time you often realize that the way things are today are so because at some point in time someone made a discovery or some decisions were made or there’s some understanding of the world that gave rise to where we are today. And those initial understandings and observations may or may not apply to the world where we exist today. So I think we all want me to rethink the way we do things and ensure that the way we’re doing things they are applicable.

Saul Marquez: Love that Ron I always say don’t assume right. And so how do you stay relevant as an organization despite constant change?

Ron Alfa: Yeah I mean I think any organization and especially companies startups need to focus on creating value and focus on continuing to improve on the levers that better enable them to create value. So for us at Recursion while we are a company that is trying to use machine learning and computational tools to reimagine drug discovery at the top of our mind always discovering new medicine. So the thing that is incredibly important for us on the day basis is that we’re always thinking about how we are moving our therapeutic program from point A to Point B. And at the same time working on building the tools to do that more quickly.

Saul Marquez: What’s one area of focus that drives everything in your organization?

Ron Alfa: Yes I think that has I mentioned just now I think probably the best answer there is discovering new medicines. We have the company are absolutely focused on discovering medicines that are going to change lives to thousands of patients and doing that at a scale that’s been hasn’t been done before and that scale that some people might call crazy. And so we would like to continue to think of new ways to build new technologies that will enable us to more quickly to cover medicines for patients.

Saul Marquez: Love it. And the last one run is a two part question. What is your number one health habit and what is your number one success habit?

Ron Alfa: My number one health habit. Let’s see. I frequently like to like to go off and on Quito and you know the fun thing about Quito is that you feel really good when you’re doing it.

Saul Marquez: Yeah but you feel really bad when you’re well you’re not actually then you’re having this annoying very annoying eating so hence why go off and on the other thing I’d love to do it.

Ron Alfa: I do boxing classes at this incredible studio in Salt Lake called rebel house. And if you were there in Salt Lake you should definitely check out rebel house.

Saul Marquez: Love it. Shout out and check out the studio.

Ron Alfa: Shout out.

Saul Marquez: And how about the success have it. What would you say your number one success habit is?

Ron Alfa: I would say probably my number one success habit is and has always been and maybe this is also not the health habit but just working excessively and working incredibly hard. I find that oftentimes especially you know in school oftentimes it’s sort of the to you that things just come naturally to people and at least for me I feel that the only way for me to really be at my peak in terms of understanding something, thinking creatively, is to work hard and to really sort of surround myself and whatever the topic is whatever I do. So I have historically not tried to sort of downplay how much work I put in the things I end up putting a lot of work into things and I think it’s important for all that to recognize that oftentimes things don’t come super easy.

Saul Marquez: Love it Ron. Love the candid message there. And what book would you recommend to the listeners?

Ron Alfa: So you know it’s a little point here. Giving a lot of where they end up reading as being at a startup or you know these business books and you know I really love the Hard Thing About Hard Things but I actually the book I wanted to recommend today it’s actually an old book by a guy named Thomas Kuhn that called The Structure of Scientific Revolution and so you actually can we can get really far by just reading the introduction and this book is incredibly important because it is the origin of the term paradigm or a paradigm shift that’s used in science less so these days kind of come out of fashion but that is the last couple of decades ago. But I think one of the main messages of the book is really analyzes a lot of different trends in scientific discoveries and he finds that it’s important to appreciate that I don’t want to say there’s no check in truth there’s certainly no objective observation but discoveries that happen at a certain point in time in the sense open up a new way of seeing the world that enable additional discoveries to be made. And prior to this discovery coming into existence that no one can really envision what might follow from this discovery. And so to take DNA for example, from the discovery of DNA we have been able to advance science in many different directions that had we not discovered DNA now sort of imagine and you can kind of understand many different threads using the same approach. And so I think for me it’s important scientifically it’s also important from kind of the innovation and sort of perspective because you almost have to appreciate that where we are today we sort of exist in a place where some avenues of discoveries have been opened up by others but others have not. And oftentimes something that seems totally impossible or totally crazy may not be so because you just haven’t sort of opened the door to that world.

Saul Marquez: Love that. Yeah. Yeah. So so it goes back to the assumptions right and making sure that you’re not making any assumptions. Something may be possible. You may have previously thought not. And that’s the door that opens to the sort of domino effect of the rest of them.

Ron Alfa: Yeah I mean that’s exactly true. I mean one thing we’re in a position right now where you know I’ve talked a lot about building machine learning tool to accelerate drug discovery. So today we can point to certain set where we can build tools to make predictions that might impact those steps. But we really can’t imagine how jump forward 10, 15 years, how the entire process of their discovery may look in a world where it’s not just biology and chemistry and how it’s biology chemistry and software and there are many different ways we might predict the failure of Angel therapeutics and humans that are very different from the ways that were invented 20 years ago.

Saul Marquez: Love it man you’re always thinking ahead. That’s why I enjoy chatting with you and folks fortunately you know these things I mean a decision early on in the podcast 30 minutes was the sweet spot. So maybe we’ll get you on for another round in about six to 12 months Ron to check you guys out see what you’re up to. But for now I love if you could just leave us with a closing thought and the best place for the listeners could follow your work or get in touch with you.

Ron Alfa: Sounds good Saul. Yeah I enjoyed speaking to you thoroughly and happy to be back on the on the podcast in the future if you’d like. And listeners can feel free to reach out to me at ron@recursionpharma.com.

Saul Marquez: Outstanding. Ron thanks again for spending time with us. I know you’re in the middle of your conference there so big thanks and looking forward to staying in touch.

Ron Alfa: Thanks Saul.

Thanks for listening to the Outcomes Rocket podcast. Be sure to visit us on the web at www.outcomesrocket.com for the show notes, resources, inspiration, and so much more.

Sonix is the best online audio transcription software in 2019.

The above audio transcript of “How to Efficiently Discover Drugs with Ron Alfa, Senior Vice President, Translational Discovery at Recursion Pharmaceuticals” was transcribed by the best audio transcription service called Sonix. If you have to convert audio to text in 2019, then you should try Sonix. Transcribing audio files is painful. Sonix makes it fast, easy, and affordable. I love using Sonix to transcribe my audio files.


Visit US HERE