Pharmaceutical companies are under intense pressure. With patents expiring and cost pressures growing, the speed and productivity of drug discovery and manufacturing are under the microscope. It is timely, then, that a team of researchers recently shared promising findings on ‘Eve’ — an artificially-intelligent ‘robot scientist’ that can screen potential drugs with minimal human oversight. Eve discovered a compound that possesses anti-cancer properties, and which might also be useful in the fight against malaria. Is this a glimpse of what the drug discovery lab of the future might look like?
The laboratory is becoming more automated, as the relentless march of technology continues. While research teams move from paper-based processes to more secure, electronic storing and sharing of knowledge, pharma companies are also trying out cognitive technologies such as IBM’s artificially intelligent (AI) Watson system. These types of systems will increasingly use existing knowledge and data to discover new, unique links between otherwise seemingly unconnected observations. This could unearth a rich source of untapped opportunities, and is a significant step forward given that new breakthroughs are becoming become scarcer and costlier — we’re rapidly approaching the one billion US dollar mark for developing a brand-new drug.
ENTRIES OPEN: Establish your company as a technology leader. For 50 years, the R&D 100 Awards, widely recognized as the “Oscars of Invention,” have showcased products of technological significance. Learn more.
The move towards automation and robotics has been a long time coming. In the 1990s, many cited AI — or computational chemistry and molecular modeling — and total lab automation as the ‘next big thing’ in R&D. While some industries are seeing wholesale job displacement brought about by new technologies, the pharma sector doesn’t yet see that entire ‘replacement’ observation. Drug discovery labs, for example, will still need a human element for the foreseeable future.
The role these AI systems play lies in helping to explore fresh ideas, such as a new pathway or target for a drug — and coupling this with predictive analysis to supplement the work of scientists in the lab. These predictive analyses do have limitations — the scale of data and computing power needed to simulate the effects of a drug on the whole body are enormous, for example. But their empirical basis means they can now get close to simulating ‘nature’ if the system is well-defined and understood.
While that stage may still be some way off, our ability to manage and analyze more and more data has increased exponentially. When performing any kind of analysis, these new systems will have to feed back the derived information and integrate it with other new — and potentially unrelated — data. With that in mind, a gradual adoption of more intelligent lab technologies will make it even more important to be able to securely manage multiple streams of data from one central point of knowledge and IP.
We must also consider the commercial practicalities of a ‘robot scientist’ system. Historically, the need to connect a network of computers made it an expensive option, viable only for the larger pharma players. However, the advent of cloud elastic computer resources has lowered this barrier to adoption. It’s now about what makes sense to analyze and, more importantly, what questions do we want to ask? Putting all the data into a ‘data lake’ and allowing these AI tools to crawl over it is one thing — but having them do it in a directed and reasoned manner to answer specific questions is another.
Does the introduction of AI signal a new dawn for life sciences? Not quite. Eve is the latest iteration of this kind of technology, not a brand new concept. This is not a silver bullet but, as science evolves and the data availability changes around it, AI technology will play a role in the discovery and development of new drugs and disease understanding. As with all new technologies in sciences, it will help support the scientists — but it will not replace them.
Paul Denny-Gouldson is VP of Strategic Solutions at IDBS. He may be reached at editor@ScientificComputing.com.
