Augmenting Drug Discovery with Computer Science

by: Andrew M. Radin
Chief Business Officer, twoXAR

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.

  1. 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.
  2. The only way of discovering the limits of the possible is to venture a little way past them into the impossible.
  3. 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”!

At twoXAR we spent the first half of 2016 running preclinical studies to demonstrate that computational technology can discover novel drugs candidates (in minutes) that result in efficacy in standard in vivo models. In June, we announced results from our rheumatoid arthritis studies and will share preclinical results from studies in other diseases in time. With our partners we discuss the rationale behind our technology and review our in vivo case studies and we often come into agreement that using advanced data science techniques to analyze data about drug candidates is neither impossible nor 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 partners have been doing in the lab for years.

Anyone who says that computational drug discovery and development cannot be done in a vacuum is absolutely correct — the biopharmaceutical industry is an extremely complex environment. No biopharma company has a core competency in all aspects of the drug development process, and most rely on partnerships to be successful. As society moves further into the Second Machine Age, the industry will adapt to leverage that which is most efficient. The most interesting and powerful new discoveries will arise at the intersection of open-minded biomedical researchers combining their deep expertise with unbiased software. As Daphne Koller puts it in the July 2016 Anniversary Issue of Cell Systems, “Computing is not just a set of tools — it is a mode of thinking that can provide new ways of looking at the data and even suggest new questions that one could answer.”

Technologies like ours are meant to augment — not automate or replace — the work of R&D researchers and accelerate drug discovery. While our approach may sound futuristic, it is already enabling us and our partners to better leverage the value of large biomedical data in pursuit of new medicines, and does it faster than previously possible.