IBM Introduces AI Platform to Accelerate Vaccine Design and Testing
Though the impact of COVID-19 has been arduous for many industries, some companies have met the challenge head on. Specifically, IBM introduced a new AI platform, RoboRXN, designed to support scientists in their efforts to discover and test new drugs. The platform is just one of the innovative tools for fighting the virus that have emerged in the past few months, but it could be a powerful one.
Introducing RoboRXN
The principle behind RoboRXN is as simple as it is innovative. Essentially, the tool acts as a virtual chemical laboratory that can be accessed by scientists at any time. The system runs completely in the cloud, and makes use of AI-driven machine learning models to predict how particular medicines and chemicals will interact.
This creates a number of key benefits for chemical researchers and those working on medicines, in particular. In order to gain licenses for new medicines, researchers must investigate how a new drug interacts with other chemicals and medicines. This can be an extremely long and costly process. IBM’s own research indicates that it takes, on average, 10 years for a new medicine to be discovered, tested and prepared for distribution.
In the context of COVID-19, waiting that long is far from ideal. This is where RoboRXN comes in. By allowing researchers to run thousands of interaction tests simultaneously, the platform promises to make vaccine development faster.
The AI model that underpins the system is also extremely accurate. This could mean that, within a few years, licensing decisions could be based on the predictions of such AI systems, rather than on the results of lengthy, costly drug trials.
Technology Against COVID-19
RoboRXN isn’t the only solution launched to help fight the virus. IBM launched its own Functional Genomics Platform to help scientists make predictions about how genetic factors influence drug interactions. In addition to this, IBM also introduced platforms called Micromedex and EBSCO DynaMed for making faster and more accurate inquiries on drugs and clinical disease information. These two platforms help medical professionals gain access to a wide range of content related to infectious diseases, including COVID-19.
In fact, the necessity to develop a vaccine for COVID-19, and the resources being made available to do so, means that the pandemic may have far-reaching effects on the way that medical research is organized.
Some of these catalysts are obvious. The track and trace apps that have been rolled out around the world point to a future in which infectious disease experts have access to real-time information on the spread, severity and potential dangers of individual viruses.
Other researchers are looking to improve other parts of our medical infrastructure. Blockchain technology holds the potential to solve modern healthcare issues with a focus on allowing medical information to be shared between researchers while maintaining the privacy of individual patients.
The AI Doctor
Perhaps the most exciting advances in medical technology, though, are those (like RoboRXN) that leverage the power of AI.
There are several key ways in which AI can help in medical research. One approach, which is currently being investigated by researchers at Stanford, is to use these models to help clinicians make decisions. For example, in one study, AI was able to classify images of skin lesions as benign lesions or malignant skin cancers with the same level of accuracy as board-certified dermatologists. AI can even bring clarity to areas that clinicians disagree on, such as identifying tuberculosis on chest radiographs.
Another approach is using AI to trawl through existing databases of drug research and offer intelligent predictions about the best course of treatment to offer to patients. At the Institute of Cancer Research, for example, researchers have developed a unique canSAR database that combines patients’ clinical and genetic data with independent chemistry, biology, patient and disease information. Not only can this system help clinicians recommend treatments, it also provides predictions on novel drugs for cancer.
Automating the Cure
The holy grail for medical researchers, however, remains a system that is able to look at the DNA sequence of a novel virus, and be able to design a vaccine for it automatically.
The caveat, however, is that medical research is one of the most sensitive forms of research, and mistakes could be costly. Uncertain times call for reliable computing, and so it is important to ensure that these tools are reliable before they are pressed into widespread use.