close
close

AI and bioengineering are driving start-ups in drug research


Register free to listen to this article

Thank you very much. Listen to this article using the player above. ✖

Biotechnology and drug discovery are areas characterized by constant innovation. Some notable new technologies include bioengineering and of course artificial intelligence (AI) and machine learning. These tools are being used to advance scientific research and discovery in new and exciting ways, particularly by biotech startups.

At the Drug Discovery 2024 event of the European Laboratory Research and Innovation Group (ELRIG), Europe's largest drug discovery conference, Technology networks spoke to a group of start-up companies that are just starting to make a name for themselves in drug discovery. This dedicated section of the Breakthrough Zone exhibition floor showcased start-up biotech companies and offered them the opportunity to showcase their innovative technologies and platforms.

We reached out to these companies to learn more about AI and bioengineering and their applications as emerging trends in biotech and drug discovery – here's what they had to say.

Sarah Whelan (SW): How are AI and automation increasing the productivity and precision of biotech/drug discovery and what key trends do you think will shape this field in the future?

Luke CoxCEO at Impulsonics: The value of AI’s ability to synthesize massive amounts of information and transform it into actionable insights and life-saving medicine will depend entirely on the quality of the data fed into it. I think the critical next step to unlocking this is to automate the experiments to run the high quality datasets needed. Otherwise, we are simply feeding these models noise and using a lot of energy not to generate much useful information. Or to put it another way; Garbage in, garbage out.

Jeroen VerheyenCo-founder and CEO of Semarion: AI and automation are transforming biotechnology and drug discovery, increasing both productivity and precision by making research processes faster, more efficient and less prone to human error. Key trends in this space include AI-driven automation and the shift toward modular and flexible automation systems that allow labs to adapt to new tests or strategy changes without the need for large, customized setups. This flexibility not only reduces infrastructure costs, but also accelerates the response to new scientific challenges. However, many current systems still require robotics specialists, slowing adoption. In the future, more user-friendly platforms are expected to expand access to these powerful tools.

Félix Lavoie-PerusseCo-founder and CCO Saguaro Biosciences: Dataset quality will become the most important variable in deriving meaningful insights from machine learning models in drug discovery. It has been shown that larger data sets, better models, and high quality data sets lead to better model performance.1,2

However, it is becoming clear that data and more powerful models are turning into commodities. In fact, more and more public datasets are being generated (e.g. image datasets from composite screens by the JUMP Cell Painting Consortium or the Oasis Consortium initiative) and made freely available to be fed into AI models to hopefully produce meaningful predictions.

Furthermore, we are seeing more and more AI models becoming freely available to everyone. Although building and training models is expensive and only very well-funded companies like Meta can afford them, the competitive dynamics of the market force these well-funded companies to make these expensive models freely available to everyone. Meta's defensive move to open source its Llama 3 base model is already a good indication of this trend.

This increased access to data and AI models creates a level playing field. This means companies need to generate unique, high-quality data sets to differentiate and gain new insights from AI models. In the world of drug discovery, this means organizations must adopt more physiologically relevant yet robust technologies in vitro Models. They also need to use data-rich readouts and probes with limited impact on cell biology, because the more relevant and information-rich the biological models, the better the AI ​​models will perform.

SW: What do you think are some of the most exciting developments in synthetic biology/bioengineering right now, and how do you think these innovations will change the biotech/drug discovery landscape?

Helen FrancisChief of Staff at Constructive biography: Synthetic biology and bioengineering have enormous potential to transform drug discovery and the entire bioeconomy. What is particularly exciting is the possibility of redefining the possibilities of biology and expanding the chemical space from which we can develop new life-saving therapeutics and other biomaterials. In the coming years, this will transform the way we develop and produce biological medicines, with new and improved chemical properties and more sustainable large-scale bioproduction.

Ruizhi WangFounder and CEO Abselion: Recent advances in cell and gene therapy, based on many years of development in bioengineering, have shown that they can impact human health in ways we may never have imagined possible. Pioneers have found a way to identify, develop, manufacture and deliver therapies that can transform lives by providing potentially curative options.

Applying engineering principles to biological systems presents many challenges associated with the inherent variability of a living cell factory. The key to accelerating access to next-generation therapies and ultimately reducing costs lies in improving the consistency and scalability of viral vector production.

Optimizing the production process requires a multidisciplinary approach and this is an exciting time with a shared momentum in the industry to tackle this problem head on.

You may also like...