I recently authored an article for MedCity News discussing the hype surrounding AI, especially as it relates to fighting COVID-19. Since the very beginning of this pandemic, researchers and pharmaceutical companies have been working around the clock to find treatments and, more importantly, develop a vaccine. And, as usual, there has been a plethora of media articles and peer-reviewed journal publications discussing how AI can support these efforts. A lot of that is driven by AI companies themselves, or companies that apply AI to discover treatments.
When this virus became a serious public threat at the beginning of this year, multiple AI companies shifted their focus to using AI to fight coronavirus and their approaches are varied, ranging from drug repurposing to finding novel molecules. But, as I have stated in my article, what we need is the wide availability of safe and effective vaccines. AI is not the key to achieving this goal.
When companies shift their focus as dramatically as many have, there are unintended consequences because progress against other diseases where AI can be better applied may be halted or stifled. We specifically chose not to refocus here at twoXAR, and I want to explain why.
The primary reason is that the scientific community knows how to create vaccines, test them and distribute them widely. What it boils down to is that the solution, and the path to that solution, is fairly certain. When it comes to using AI for drug discovery, uncertainty is where AI works best. AI has more meaningful applications where analytical insight is required to make decisions under uncertainty.
And that is where we focus at twoXAR. We focus on diseases that are complicated and riddled with so much uncertainty that the underlying biology of a therapeutic approach is not well understood. The global scientific community knows a lot about the underlying biology of most viruses and how to prevent and treat them.
We use AI in early-stage drug development as a tool to improve hit predictions, giving us a better understanding of whether a set of compounds being tested will have a desired clinical effect. For us, understanding what data is available is key because we’ll begin a discovery program in a disease only when we have confidence, based on the available data, in our ability to make high-quality hit predictions.
We know AI’s potential for helping uncover new potential treatments. We also know that complex diseases require a team of drug discovery and development experts working in collaboration to discover breakthroughs. There’s no replacement for that.
We will continue to progress our novel pipeline forward amidst this pandemic because people living with lupus, NASH, cancer and other complex diseases need new therapies. Given our history of positive preclinical results we are confident that our approach will ultimately create new medicines to improve lives.
We are equally confident that the global scientific community will develop a safe and effective COVID-19 vaccine using the approaches that we know work. There has been tremendous progress in a matter of months. We now have 11 vaccines in large-scale phase 3 trials and six approved for early or limited use. We also have an FDA-approved treatment for the virus.
The progress in fighting COVID-19 has been remarkable, but to say that AI has been a key part of these advances is far from accurate.