The drug discovery landscape has rapidly changed over the past 10 years due to technological advancements such as AI and Machine Learning. Back in December, we posted a whitepaper that detailed some predictions for the life sciences industry in 2021, with this being a key highlight.
Now that we are coming to the end of H1, we wanted to revisit some of the predictions that were made, and comment on how AI has changed the drug discovery landscape so far.
In our whitepaper, we highlighted that AI and ML were propelled into the spotlight at the height of the Covid-19 pandemic, as it helped to pave the way for the industry to learn about the virus quickly without sacrificing accuracy and quality.
The World Economic Forum had already evidenced this in May 2020, explaining that “in the fight against Covid-19, organisations have been quick to apply their machine learning expertise in several areas: scaling customer communications, understanding how Covid-19 spreads, and speeding up research and treatment”.
We spoke to a number of life science professionals whilst researching this element of our whitepaper, and many agreed that without the Covid-19 pandemic, we may not have seen such a vast appetite for AI and ML to be used not only during the drug discovery process, but throughout the whole lifecycle of drug development.
It’s clear that Covid-19 showcased what AI and ML can achieve, and although the last eighteen months have been incredibly tough economically, mentally, and physically, the life sciences industry was at the forefront of ensuring we could achieve “normality” as quickly as possible.
One of the main benefits and security that AI and ML provide, is the speed of being able to gather and analyse data, conduct research, or create logical workflows and methodologies.
Although there is enough resource and knowledge for this to be conducted by a person instead of a piece of technology, something that is unmatchable is the speed in which specific tasks can be completed.
In an article posted by Labiotech, this was discussed, stating, “last year, London-based firm BenevolentAI successfully applied AI to quickly find a potential Covid-19 treatment in repurposing the rheumatology drug baricitinib. BenevolentAI’s Scientific Advisor, Jackie Hunter, remarks that they progressed an idea to an actionable research finding in as little as 48 hours.”
This is one of many examples showcasing the speed of which AI and ML can operate to.
Although speed is incredibly important, there is no room for error when using AL and ML in the drug discovery process. Human error happens more often than when using AL and ML.
Whilst using AI and ML effectively still requires human knowledge and infrastructure, it’s a reliable way to guarantee perfect results (for the majority of the time).
In the same article published by Labiotech, it was highlighted that “AI offers a high level of precision to the complicated and time-consuming discovery phase in drug development. That precision leads to faster development timelines and a lower failure risk down the road.”
A key factor in the drug discovery and development process is data. Whether this is collecting data with speed and precision, comparing data sets, or even organising and cleaning data, AI is a master of this. This allows for better analysis and accurate comparisons.
The precision offered by AI and ML technology elevates drug discovery and development as the process of taking a drug to market can be sped up by a number of years, the most notable example being the Covid-19 vaccine which took less than a year to develop.
In summary, it’s clear that although there are still scepticisms around AI and ML, the consensus is that it’s only going to grow and develop over the coming years. We have worked with several AI Drug Discovery companies in the last 12 months, and it’s fascinating to see that they can quicken the drug discovery process by over 6 years.
This is a game-changer when it comes to getting new medicines from bench to bed side. We’re excited to see how things will continue to evolve, and how AI and ML will continue to change the drug discovery landscape.