DEL, AI, and ML: The Digital Future of Research Tools

Digital: AI and ML

IPT talks to Noor Shaker at X-Chem about the adoption of AI and ML into life sciences and how pre-trained algorithms can aid research

IPT: What assistance can AI-based DNA-Encoded Library (DEL) provide in life sciences research?

Noor Shaker: DEL technology offers one of the most powerful approaches to hit discovery available today. It provides access to enormous libraries that can be screened for hit identification with unparalleled speed and efficiency. The fact that these libraries are so huge means that each screen produces a wealth of high-quality labelled data.

Such data are ideal for machine learning (ML), which can be used to discover hidden patterns in chemical libraries; differentiating between compounds that can potentially hit a certain target and those that won’t. By using a combination of DEL data and AI, we have shown that we can increase the efficiency of hit identification – finding more hits from a more diverse chemical space – and also speed up the process by finding hits that are commercially available. These can therefore be directly tested, as opposed to hits that require weeks for synthesis.

What are the biggest changes that the adoption of AI and ML have caused in areas such as protein-protein interactions (PPI) and G protein-coupled receptors (GPCR)?

The use of a special class of AI methods, called generative models, has opened new possibilities for the design and identification of novel chemistries. Generative models can design novel chemotypes for certain therapeutic targets that might not be intuitive for humans. By training these models on known chemistry, we gain the ability to explore, in an unbiased way, larger, more novel, and diverse chemical spaces that form more interesting starting points for virtual screening. This has proven useful for the discovery of hits for challenging targets such as PPIs and GPCRs.

What is the biggest challenge in integrating AL and ML into life sciences research?

One of the biggest challenges that has hindered adoption is the lack of access to diverse, high-quality data. Drug discovery is a long and expensive process that requires finding the right starting chemical compounds and optimising them for human efficacy. This means evaluating hundreds of different properties that are necessary for safe and efficacious drugs. Data for many of these endpoints do not exist or are very expensive to acquire, so training ML for drug discovery is a particularly challenging task.

How can the prediction of chemical properties be improved by using pre-trained ML models?

When data sets are unavailable, very small, or not diverse, we have what we call a cold-start problem. One way to approach this challenge is to start from a ML model pre-trained on the data available. This model can then either be gradually improved as new batches of data become available, or it can be fine-tuned by accessing a company’s specific, or proprietary data, catalogues.

In principle, the pre-trained model forms the starting points for model refinement and improvement. Other classes of ML methods, such as active learning, can be combined with this approach to ensure that useful information is collected with each new data batch.

Where do you see AI and ML taking life science research in the future?

The past few years have been transformative for AI in life science, and this trend will continue in the future. AI will become an integrated part of every step of the drug discovery process, from target identification, to selecting the right patients for trials, to marketing the drugs to the most responsive patient population. We’ve seen bits and pieces of this already happening, and we will witness more advances and better integration of these components within the overall healthcare system.

Noor Shaker, Senior Vice President and General Manager at X-Chem, is a biotech entrepreneur and recognised healthcare innovator. Prior to Glamorous AI (acquired by X-Chem in October 2021), she was an assistant professor at Aalborg University, Denmark.

Noor is passionate about data and AI and is on a mission to cure disease by pushing the boundaries for what is possible with AI. She has a record of achievements in AI, including numerous papers published in the field and its application to drug discovery, as well as holding a number of AI patents.

She sits on AI and diversity advisory boards for prestigious organisations and universities and is a recognised healthcare leader – she was one of the 2018 winners of Innovators Under 35 Europe from MIT Technology Review and named one of BBC’s 100 Women of 2019.

Future Life Sciences’ Regulation and Processes Will Be Data Driven: Who Will Steer That Future?

Industry experts joined in a live video discussion about the critical next steps as life sciences embrace a future that is data rather than document driven in its management of information, knowledge and essential business processes. Ultimately, whose responsibility should it be to look after the quality and consistency of the data, and how will they do this?

Accelerating Life Sciences Research and Delivery with Knowledge Graphs

Advanced data handling techniques may point the way to a potential new innovation-rich future, which two use studies are already proving

Technological and Scientific Advances Bring New Hope for Therapeutic Cancer Vaccines

Advances in immunotherapy and other areas have delivered new tools for the treatment of cancer. Cancer vaccine research is now showing greater promise, offering new hope for patients

Turning an Ocean of Data Into Actionable Wisdom To Support Optimal Site Identification

Advancements in AI can help the pharmaceutical industry identify the best sites for their clinical trials through the harnessing of Big Data

The Burden of Proof – Implementing Blockchain in Life Sciences

Blockchain technology is fast becoming a mainstay in pharma companies. What is the draw for these companies to use it, and how can it help improve data collection and protection in the future?

Human-Centred Design: From Inception to Integration

IPT sat down with Dr Chris Vincent at PDD, to understand more about the digital innovations that are leading design and whether technologies like Extended Reality (XR) can be beneficial to the process

Digital · Dec 14, 2022

The Importance of Temperature Control in Pharmaceutical Analysis

As technology within the analysis sphere continues to evolve, temperature control is becoming increasingly important for drug discovery and research

Digital · Dec 14, 2022

Providing Support Throughout the Patient Journey

Concierge services are critical to helping patients navigate technology and other logistics in a decentralised clinical trial. How best can they be implemented?

Digital · Dec 14, 2022

Future Life Sciences’ Regulation and Processes Will Be Data Driven: Who Will Steer That Future?

Accelerating Life Sciences Research and Delivery with Knowledge Graphs

Technological and Scientific Advances Bring New Hope for Therapeutic Cancer Vaccines

Turning an Ocean of Data Into Actionable Wisdom To Support Optimal Site Identification

The Burden of Proof – Implementing Blockchain in Life Sciences

Human-Centred Design: From Inception to Integration

The Importance of Temperature Control in Pharmaceutical Analysis

Providing Support Throughout the Patient Journey

Innovations in Pharmaceutical Technology (IPT)

Categories

Social Footprints