In a recent publication in Nature Reviews Drug Discovery, the Boston Consulting Group assessed the performance of pharma companies that take an AI-centric approach.
One of their key conclusions was that AI-enabled drug discovery helps in the acceleration of discovery timelines - in particular rapid target identification and validation or fewer and faster cycles of molecule design and optimization.
These findings confirm Euretos' 10-year experience in data-driven target discovery & assessment and indication selection. We have helped many pharma and biotech companies to lower risks and time frames by providing ready-to-use applications and predictive models that reflect the combined experiences of our 30+ client engagements.
The impact of AI-driven drug discovery on pipeline performance
Over the last few years, AI-enabled drug discovery has surged through technological progress, such as using neural networks to design molecules and applying knowledge graphs to understand target biology. Many AI-native drug discovery companies have progressed molecules into clinical trials, in some cases reporting greatly accelerated timelines and reduced costs. In addition, many established pharmaceutical companies have formed discovery partnerships with AI companies like Euretos to explore technology.
Boston consulting shared their analysis of the impact of AI on creating significant value in drug discovery, including greater productivity (faster speed and lower cost), broader molecular diversity, and improved chances of clinical success.
The above analysis shows that AI drug discovery companies had rapid pipeline growth during the mentioned time, with an average annual growth rate of around 36%. This is driven mainly by assets and programs at the discovery and preclinical stage. Fig.1 a) reflects the early-stage nature of AI-native companies, and Fig.1 b) shows that AI companies appear to have a combined pipeline equivalent to 50% of the in-house discovery and preclinical output of the ‘big pharma.’
Taking a data-driven approach to target discovery and assessment
Euretos has created AI-driven computational disease models that have been tried and tested with many leading pharma and biotech companies. The disease models predict novel target-indication combinations by assessing whether a target’s biological interactors are linked to known disease associations. Domain experts can then review these predictions independently in the Euretos AI Platform and draw evidence-based conclusions.
We take a unique approach that focuses on productizing AI and making it ready-to-use for researchers. Our computational disease models predict novel drug target candidates by applying state-of-the-art data-driven methods that create unique insights into molecular disease mechanisms. We then empower researchers to assess which of these predicted targets should move forward to in-vitro and in-vivo testing by giving access to the largest AI-integrated biomolecular knowledge platform.
“ AI-enabled drug discovery could prove a game-changer for pharmaceutical R&D, especially for small-molecule drug discovery, potentially allowing it to catch-up with other modalities that typically have faster discovery timelines. This will impact how research and organizations should be organized and governed to unlock AI’s full potential.”
- Boston Consulting Group
An AI-enabled wave with the potential to transform drug discovery
Drug discovery is a multi-dimensional, multi-step search and optimization problem. AI- with its powerful new tools for solving complex problems- has the potential to play an essential role in drastically improving this process. The analysis of Boston Consulting Group depicts early signs of a fast-approaching, AI-enabled wave with the potential to transform drug discovery radically.
If you are interested in learning how you can apply AI to take a data-driven approach to target discovery & assessment and indication selection, then contact us today!
Reference: https://www.bcg.com/publications/2022/ai-in-drug-discovery-impact
.svg)
