Today we announced our collaboration with Santen, a world leader in the development of innovative ophthalmology treatments. Scientists at twoXAR will use our proprietary computational drug discovery platform to discover, screen and prioritize novel drug candidates with potential application in glaucoma. Santen will then develop and commercialize drug candidates arising from the collaboration. This collaboration is an exciting example of how artificial intelligence-driven approaches can move beyond supporting existing hypotheses and lead the discovery of new drugs. Combining twoXAR’s unique capabilities with Santen’s experience in ophthalmic product development and commercialization…
The short-list for the annual Arthur C. Clarke Award was recently announced and it reminded me of a post we did last fall on augmentation vs. automation. Clarke is a British science fiction writer who is famous for being the co-screenplay writer (with Stanley Kubrick) of the 1968 film 2001: A Space Odyssey. He is also known for the so-called Clarke’s Laws, which are three ideas intended to guide consideration of future scientific developments.
- When a distinguished but elderly scientist states that something is possible, he is almost certainly right. When he states that something is impossible, he is very probably wrong.
- The only way of discovering the limits of the possible is to venture a little way past them into the impossible.
- Any sufficiently advanced technology is indistinguishable from magic.
These laws resonate here at twoXAR where every week we meet with biopharma research executives who tell us — usually right after we say something like, “using our platform you can evaluate tens of thousands of drug candidates and identify their possible MOAs, evaluate chemical similarity, and screen for clinical evidence in minutes” — that’s “impossible” or “magic”!
In the 25-plus years since the modern Internet was launched we have seen virtually every industry evolve by leveraging the connected, global computing infrastructure we can now tap into any time, from anywhere. Today, advanced software programming tools like machine learning, massive data sets and cloud-based compute are making it easier than ever to rapidly launch and globally scale software-driven services without the capital expense that was once required.
The debate about whether or not software will eat drug discovery is not a new one and remains a topic that can raise voices. As a formally educated computer scientist and cofounder of a company focused on software-driven drug discovery, I come to the discussion with my own biases.
There is no shortage of software in today’s biopharma R&D organization. Cloud-based electronic data capture (EDC), laboratory information management systems (LIMS), process automation, and chemical informatics are just a few of the well-established tools that support R&D and have a meaningful impact. While software has become a …
Guest post by Marina Sirota, PhD, twoXAR Advisor and Assistant Professor, UCSF Institute for Computational Health Sciences
Earlier this month, Andrew A. Radin and I had the opportunity to attend acommunity outreach meeting at UC Irvine hosted by the NIH Libraries of Cellular Signatures (LINCS) consortium. It was a great and diverse community gathering of drug discovery researchers from academia, biopharma, startups, consulting companies and government funding agencies. For anyone interested in listening to the talks, some of them have been posted on YouTube.
The focus of day one was…
“Any sufficiently advanced technology is indistinguishable from magic.”
Science writer and futurist Arthur C. Clarke’s poignant “third law” only becomes more relevant as technological innovation accelerates and disciplines like computer science, data science and life science converge.
As we have been out in the field demonstrating the power of our technology platform to our collaborators, it has been interesting to hear their reactions when we tell them how it can
evaluate tens of thousands of drug candidates and identify their possible MOAs, evaluate chemical similarity, and screen for clinical evidence in minutes. These responses cover the gamut from, “Wow, this is going to revolutionize drug discovery!” to “this is magic, I don’t believe computers can do this…”
However, whether we are talking to the converted or the skeptical, as we get deeper into conversations about how our technology works, we come into agreement that using advanced data science techniques to analyze data about drug candidates is not magic. In fact, we’re doing what scientific researchers have always done – analyze data that arises from experiments. What’s different is that advances in statistical methods, our proprietary algorithms, and secure cloud computing enable us to do this orders of magnitude faster than by hand or with the naked eye.
The speed of our technology combined with the massive quantities of data that it processes, is simply enhancing the work that our collaborators have been doing in the lab for years. We believe that the most interesting and powerful new discoveries will arise at the intersection of open-minded life scientists combining their deep expertise with unbiased software.
Technologies like ours are meant to augment* the work of life scientists and help them accelerate drug discovery and fill clinical pipelines while leading society to a more robust and streamlined scientific process. Although DUMA might sound futuristic, today it is enabling therapeutic researchers to better leverage the value of their data and do it more rapidly than ever before.
Don’t believe the magic? Contact me and we’ll get a trial started to show you the science.
*Sidenote: I have been particularly interested in this interaction between humans and machines, which led me to a class at MIT called The [Technological] Singularity and Related Topics. One of those major topics was whether or not machines (including software) will replace aspects of society. One of my professors Erik Brynjolfsson, author of The Second Machine Age: stated that “We are racing with machines – let’s augment, not automate.”And we definitely share that view here at twoXAR.
In 1993, I decided that I wanted to launch a biotech company.* Since then, my friends and I have brainstormed biotech-driven solutions in toothpaste, paint, energy, and medicine.
22 years later I have realized this dream. The path was by no means direct. But despite my sometimes seemingly random education and career path, I have found myself at the nucleolus of bioinnovation: the intersection of data science and biomedicine. Fortunately, my timing was impeccable. Technology is rapidly changing the rules for the life sciences and, like the many industries that it has already touched, software is finally enabling business models in the life sciences to scale to new heights.
I have posted previously about how biopharmas are shifting the burden of innovation to venture investors and startups and how, even at the POTUS-level, that data science is being recognized as the future of life science and healthcare.
More and more, we are seeing exciting examples of how biopharma companies are embracing big data, or at least confirming to the world that they need it, and how investors and startups are diving in to fill the gap.
Big pharma buys into big data
We were recently invited to speak at an internal Sanofi symposium called Convergence of Science, Technology, & Data Sciences – Impact on Pharma. We presented alongside leaders in the space including: Isaac Kohane (Co-Director of Harvard Medical School’s Biomedical Informatics Department), Vikram Bajaj (Chief Scientist, Google Life Sciences), and Avi Ma’ayan (Professor, Pharmacology and Systems Therapeutics at Mount Sinai).
Frankly, I was pleasantly surprised to experience how open to innovation large pharma companies like Sanofi are; I was also excited by how enthusiastically they embraced the opportunity to explore how data science-driven approaches can augment the drug development process from discovery to clinical trials.
As #databio nerds, we were stoked by the interesting approaches others in the computational biology space were taking; from the business side, we were equally pleased to hear a very clear message best summarized by a quote from the former NIH Director and Sanofi President of R&D, Elias Zerhouni: “Big Data and the way we approach it is going to be determinant for the long-term success as an R&D Organization.”
And this sentiment is being echoed throughout the industry:
“We have to build a data-analytics capability that we don’t have today. We’re also going to have to create partnerships and think about different types of people that we need to bring into our company so that we can take full advantage of that part of healthcare.” – Joe Jimenez, CEO, Novartis
“Data will also help more efficiently develop medicines and better define which patients will most benefit.” – Geno Germano, Group President, Global Innovative Pharma Business, Pfizer
“The [combined] role of health care and technology is going to be critical” – Alex Gorsky, CEO, Johnson & Johnson
An example of pharma action in this space recently is the doubling down on genomics. A number of large biopharma companies have publically announced their efforts to utilize big genomic data in both companion diagnostic and new drug development.
“Dramatic breakthroughs in understanding how the human genome functions are still in their infancy in terms of how they can be applied to drug discovery, but we can see their potential to transform the process. This is not an incremental change. We are aiming for transformative outcomes that could improve our ability to bring innovative and more effective new medicines to patients.” – Lon Cardon, Senior Vice President of Alternative Discovery and Development at GSK
“The acquisition of Bina is a significant step for Roche to enable the promise of personalized healthcare by delivering the highest quality genomic data possible.” – Dan Zabrowski, Head of Roche Sequencing
Where there’s scale, there is VC…
a16z’s recent podcast, When Bio Meets Computer Science, discusses “how everything changes when software eats biology” and captures why life science businesses can now scale.
“These new startups have potential to have the kind of economics profile and the kind of financing needs of a software startup as compared to a pharma startup?
These new startups remind me a lot of software startups in 2005 when we see cloud computing start to realize. That’s sort of what we are starting to see now and because they have software at their heart, either literally or in terms of how they think about things, that they are organizing themselves in a cloud-like biology way, this would be very much on the Moore’s Law curve of things. And in a sense you could use this differentiate traditional biotech from this new crop of companies. That traditional biotech is governed by Eroom’s Law and these are governed much more by Moore’s Law”
Life science investors have questioned the value of platform companies in the recent past but the venture community is starting to warm up to them. VC’s recognize that the life science investment model of betting the farm on a potential billion dollar drug (unicorn drugs, anyone?) with a binary outcome is dying. Computation-driven platform companies coupled with the established CRO industry enable life science companies to look and act much more like software companies yielding stepwise, milestone-driven returns and valuations, with much smaller investments and shorter runways.
In a recent post on YC’s move in to the biotech realm, Atlas’ Bruce Booth commented:
“Although the math may be different, virtual biotechs doing drug discovery today are leveraging a similar trend: remove the heavy fixed costs of building out your own laboratory, purchasing expensive lab equipment, and then having to “feed” the system, and move to a lower cost virtual model of renting lab capabilities via a global network of CROs and collaborators. Others have already commented about the decreasing cost of DNA sequencing… but same holds for other aspects of drug discovery, like computer-aided drug design and structural biology. It’s easier to start a scientifically credible biotech today than ever before, and entrepreneurs can make real progress in validating a thesis on seed capital.”
Some examples of investments in the data science-driven drug development space today include Data Collective’s investments in Mousera and Atomwise and Atlas Venture Life Science’s investments in Nimbus Therapeutics and Numerate.
Software has enabled these dreams to become reality
I wish I was prescient enough in 1993 to have predicted the role of technology in transforming biopharma. Honestly, I was really just a kid eager to learn about biology and technology and explore the potential futuristic and off-the-wall applications. Applications that at the time seemed wacky, but today are becoming a reality.
At twoXAR, we use data science to accelerate the identification and validation of drug candidates for complex diseases. I hadn’t thought that this was possible until Andrew introduced me to the DUMA platform and demonstrated how, in minutes, we can identify new treatments for a disease. Since then we’ve translated our in silico results to the physical world and continue to do so through a growing list of exciting collaborations with commercial and academic discovery organizations.
Over the last 12 months, I have heard a variety of reactions to the speed and scalability that computational biology enables (and to the fact that both twoXAR founders are named Andrew Radin). But, it’s clear that as software continues to penetrate all industries it will also keep altering the landscape of drug discovery and the life sciences. And, it’s refreshing to see executives and investors acknowledge the power of computation-based approaches and how they speed up discovery and validation of therapies and enable a new era of software-like scalability in the biopharmaceutical industry.
*feel free to ask me why!
When independent scientific validation happens with new technologies it is an exciting time for both researcher and validator.
Some time ago we used our DUMA drug discovery platform to find new potential drug treatments for Parkinson’s disease. After processing over 25,000 drugs with our system, we identified a handful of promising candidates for further study. We noticed one of our highest ranked predictions was currently under study at an NIH Udall Center of Excellence in Parkinson’s Disease Research at Michigan State University.
We decided to be good citizens to the research community and provide our findings to the research team at Michigan State University. We prepared a 5-page PDF that summarized our computational prediction. When DUMA highly ranks a drug for efficacy it also provides the supporting evidence it used to make that prediction. This can include:
- Calculated proteins of significant interest in the disease state,
- How the drug interacts with those proteins or their binding neighbors,
- Drugs with similar molecular substructures that have similar effects, and
- Protective evidence found in clinical medical records.
We emailed our report to Dr. Tim Collier and figured that was the end of it. Much to our surprise we found ourselves on a phone call the next day with Tim and his colleague Dr. Katrina Paumier. Tim told us that we had independently validated work that had been going on for years.
As part of the review of the report, Tim and Katrina asked a number of questions on how we came up with the prediction we presented. We explained a bit about DUMA and how quickly it can be used to screen large databases of drugs and make predictions within a few minutes. They told us they had another promising drug under study and asked us to run it through DUMA. We returned the results on this new drug right away. It turned out this second candidate was highly predicted by DUMA to be effective in treating Parkinson’s disease. Once again our evidence matched their data, independently validating that they were on the right track with their second candidate.
Finally, Tim asked us to run one more drug through our system. He didn’t tell us much about this particular molecule, and we let DUMA process the data we collected on it. The prediction ranked this candidate relatively lower. We informed Tim that our system gave a low to moderate indication of efficacy, and supplied the evidence that DUMA had made to assign this ranking. This once again matched his own data about the compound.
Our work with Michigan State University continues today. We are working with Tim on providing new, novel compounds for further study. We have collaborated on combining the power of the DUMA drug discovery system with the expertise in Parkinson’s research labs.
We recently had an article written about us over at Medtech Boston, how fun! Click the link to learn more: https://medtechboston.medstro.com/twoxar/
From the White House to medical education data science is being recognized as the future of life science and healthcare.
President Obama recently appointed Dr. DJ Patil (fellow USCD Alum!) as U.S. Chief Data Scientist. In his memo: Unleashing the Power of Data to Serve the American People Dr. Patil states, “The vast majority of existing data has been generated in the past few years, and today’s explosive pace of data growth is set to continue. In this setting, data science — the ability to extract knowledge and insights from large and complex data sets — is fundamentally important.” One of Dr. Patil’s priority areas is the Precision Medicine Initiative President Obama announced in January, which is great to see that medical data is recognized as a strong national interest. But a focus on data science isn’t just seen at a national policy level, it continues to permeate in startups, medical school, and biopharma.
Last Friday Andrew and I attended the MIT Sloan Bioinnovations Conference – He spoke on the Big Data, Policy, and Personalized Medicine panel with several other companies noted here and naturally, the conversation focused on the power of computation in this space and whether or not our vision of “Star Trek Medicine” (as one audience member put it) was soon to come. During the rest of the conference, topics ranged from Policy to Biomedical Research to Financial Engineering to Education and I was excited that a common theme that ran through each of the sessions was data science and how it’s changing the medical landscape.
One example includes Jaime Heywood’s ALS Therapy Development Institute/PatientsLikeMe who used mathematical algorithms to determine that ½ of the animal studies they were attempting to reproduce (n=50) of an ALS drug could not even possibly have been statistically significant prompting more rigorous studies. When describing how they initially approached this, Jaime stated very matter-of-factly, “This can be done with math.” The power of data science in the life science and healthcare space is also being recognized in medical education. Dr. Jeffrey Flier, dean of Harvard Medical School, states in a recent WSJ piece: “There is palpable excitement at the interface of biology, psychology, engineering, sensor technology, computation and therapeutics… …The opportunities are immense and consequential.”
I’ve heard similar sentiment from senior executives at biopharmaceutical companies that I have spoken to – that the future of drug discovery resides in the data (whether biological, chemical, clinical or otherwise) and the surrounding analytics that can reveal hidden insights. However, industry professionals also express that it’s not yet apparent how the data sciences will transform the industry – that is where startups have room to show them how.
The shift in the recognition of the importance of data science is clear and being seen across the spectrum of public and private sector in the medical space. At twoXAR, we are excited to be a part of enabling society to reach Star Trek heights in medicine faster, cheaper, and ultimately more accurate.
Long before my biomedical informatics studies at Stanford, I learned to recognize the difference between what is computable and what is not. In my past three startups this knowledge has been the key to engineering success.
Recently I made a trip to visit my alma mater, the Rochester Institute of Technology, where I earned my computer science degrees. For those not familiar with RIT, it has been ranked as one the top 10 of universities in the Northeastern United States. Recently, Linked-In ranked RIT in the top 25 for software development programs in the nation, and as #13 for software developers specifically for startups.
While on campus, I reconnected with my thesis advisor, Prof. Stanisław P. Radziszowski. Dr. Radziszowski is a highly-respected computer scientist and mathematician, and is best known for his work in Ramsey theory. He has published a number of works in Ramsey theory, block designs, number theory, and computational complexity. Since 1984, Dr. Radziszowski has mentored and trained thousands of students at RIT and I was not sure if would remember me and my work. I was pleasantly surprised that he not only remembered me, but had my thesis readily available on his bookshelf. He told me that he was very excited about my work in combinatorial mathematics, and in the years since has shown it to students to inspire them to work on similar problems in computability theory.
One of the most important things I learned while a student of Dr. Radziszowski was how to skirt the line between what is computable and what is not. It is easy to imagine scenarios that seem like they should be easily solved with a computer, however there are many problems that turn out to be unsolvable. For example, let’s say you want to build a chemical storage facility. To minimize construction costs, you want to find the minimum number of buildings to store chemicals in, but you have to make sure no chemicals that react with each other are in the same building. Sounds simple, right? Well, turns out that there is no known solution that can be calculated optimally without nearly infinite computational resources.
My thesis at RIT was about the mathematical problem described by the chemical storage problem above. My method struck a balance between computability and complexity, right in the fuzzy center of what can be computed and what cannot. It involved developing a new heuristic which approximated the optimal solution. While my heuristic was not guaranteed to always produce the best solution, it produced a result that was theoretically very close to optimal, and better than other known approximation methods at the time.
Heuristics like these are the way that computer scientists model extremely complex systems. Today, there is no way to model every small detail that make up the complex interactions between organisms, disease, and drug treatments. There are too many variables; and to compute every possibility of interaction is impossible. We have perfected a computational technique at twoXAR that represents complex biological reactions in such a way that accurately reflects reality, but is simple enough to perform fast computation on. This technique is what enables us to go from biological data sets to accurate drug-disease prediction within minutes.
It was a pleasure to circle back and talk about twoXAR with the mathematician who inspired in me the principals behind our methodology all those years ago. Students at RIT should be honored to learn from such a talented individual, and I know the next generation of great data scientists are attending Dr. Radziszowski’s lectures today.