Drug discovery and bringing new medicine to market - the future of AI in pharma

By Liza Laws

- Last updated on GMT

© Getty Images
© Getty Images
Artificial intelligence (AI) is now infiltrating core industries and according to Forbes, the market is expected to reach a value of $22.6 billion dollars by next year (2025).

One area it is thriving is pharmaceuticals as it is being used to bring drugs to market faster than ever before. OSP sat down with Melanie Nelson, director of product management, solutions and integrations at Dotmatics​, a research and development (R&D) scientific software company to find out where they think AI will take the industry and what challenges could crop up along the way. 

How is Dotmatics using AI to accelerate the drug discovery process, and what advancements have been made in recent years?

Dotmatics partners with scientists globally to help them become AI-ready and power their own AI journey. Our software is used by over 2 million scientists, including those at top pharmaceutical companies like Bristol-Myers Squibb and Merck, and research institutions such as MIT and Oxford. In October 2023, we introduced Dotmatics Luma, a new scientific intelligence platform combining science data and data science for an AI-powered ‘Lab-in-a-Loop’. This platform helps centralize and analyze data, allowing for more efficient and informed drug discovery processes.

The Lab-in-a-Loop approach allows R&D and clinical data to be ingested and centralized, which helps create predictive models that inform the next set of experiments. For AI to be effective, companies must integrate their proprietary data to improve prediction models. Dotmatics’ software supports this by streamlining processes so companies can derive greater value from their experiments.

How does AI reduce the time and cost involved in bringing a new drug to market compared to traditional methods?

AI has enormous potential to drive down costs and time in drug development. The traditional drug discovery process is complex, taking up to 10 years and costing approximately $2.5 billion to bring one drug to market, with high failure rates. AI can identify potential failures earlier in the development process, saving significant time and money. Predictive modeling allows for the simulation of drug behavior in the human body, reducing the need for extensive physical testing and cutting the chances of late-stage failures. Additionally, AI helps refine clinical trial designs by linking phenotypic and genotypic data, making trials more efficient. This reduces the overall cost and accelerates the delivery of treatments to patients.

What are the key challenges in integrating AI into drug discovery, and how is Dotmatics addressing them?

One major challenge is ensuring data is “AI-ready.” Data silos, where different departments store their information separately, make it difficult to fully utilize AI. Regulatory requirements for data protection and ethical considerations around human subjects’ data also add complexity. Dotmatics addresses these challenges through the Luma platform, which unifies and analyzes vast amounts of multimodal data from R&D and clinical sources. By bringing data into one platform, scientists can access and use it more effectively for AI modeling.

Another challenge is embedding AI into existing research workflows. To maximize AI’s benefits, it must be an integral part of decision-making, not a separate project. Luma simplifies this by making it easy for scientists to access AI models within their daily workflows, removing the need for IT involvement with every new AI initiative.

How does AI improve the accuracy and efficiency of identifying potential drug candidates in the early stages of research?

AI is transforming early-stage research by analyzing large and diverse datasets to find patterns and correlations that human researchers might overlook. In target identification, AI can quickly sift through vast amounts of data, suggesting more promising experimental paths. In lead selection, AI can recommend approaches that scientists might not have considered, helping to design better experiments and reducing the time it takes to move from discovery to clinical trials. While the field is still evolving, the ability of AI to handle these complex datasets is already making drug discovery more efficient and accurate.

What role does AI play in managing and analyzing the vast amounts of data generated during the drug discovery process?

Drug discovery produces massive datasets that require advanced computational tools for analysis. AI plays a crucial role in managing this data volume and complexity. For example, researchers can use natural language queries across complex datasets to find relevant data, while AI algorithms can identify patterns that inform the next steps in the discovery process.

Dotmatics developed Luma Lab Connect to automate the flow of lab instrument data into the Luma platform, eliminating manual processes and improving data accuracy. This system makes data interoperable, helping scientists use it for AI modeling and analysis without needing advanced coding skills. This integration of AI into data management allows scientists to focus on research rather than data handling.

Can you provide examples of drug discoveries that have been accelerated or improved by Dotmatics' AI technologies?

One example is Addex Therapeutics, a biotech company based in Geneva. Addex focuses on developing small molecule drugs for neurological disorders such as Parkinson’s, epilepsy, and Alzheimer’s. Their R&D teams faced challenges managing complex workflows and vast amounts of data. By adopting Dotmatics’ solutions, they significantly improved efficiency, allowing their scientists to spend more time on research rather than data analysis. This has accelerated their drug discovery process.

What are the key challenges in integrating AI with traditional research workflows, and how does Dotmatics help scientists overcome these challenges?

One of the biggest challenges is embedding AI into existing workflows without disrupting them. Many organizations run AI initiatives as isolated projects, but to truly benefit, AI needs to be part of the everyday decision-making process. For this to happen, AI models must be accessible and user-friendly, enabling scientists to use them without extensive IT involvement. Dotmatics' Luma platform makes this possible by allowing scientists to integrate AI into their research processes with minimal disruption. The platform supports the ingestion, extraction, and analysis of data at scale, helping scientists incorporate AI into their workflows seamlessly.

How do you see AI evolving in the next 5-10 years, particularly in the context of drug discovery and development?

Over the next 5-10 years, AI will likely become a standard component of drug discovery projects. We expect generative AI to simplify the querying of diverse and complex datasets, enabling scientists to ask questions without needing specialized knowledge of the underlying data models. Predictive AI methods will also prove their value and become integral tools for accelerating drug discovery.

Dotmatics is focused on developing data management solutions that help scientists unlock the full potential of AI. By enabling better insights into biology and disease processes, AI will help bring cures to patients faster and more efficiently.

What impact do you believe AI-driven drug discovery will have on global health, particularly in addressing unmet medical needs or rare diseases?

If AI lives up to its promise, it will significantly impact global health by reducing the time and cost of drug discovery. This will allow companies to pursue more challenging unmet medical needs and rare diseases that have traditionally been too costly to address. The high cost of developing a drug often discourages companies from tackling rare diseases, but AI could change this by reducing the risk of failure and shortening development timelines.

Personalized medicine is another exciting area where AI can play a transformative role. Diseases like cancer are highly individualized, with treatments often depending on specific genetic mutations. AI can help tailor therapies to each patient, improving outcomes and reducing side effects. As AI continues to evolve, we’ll see more accurate predictions about patient responses, and real-world data will play a larger role in drug development.

How is Dotmatics positioning itself to lead the future of AI-driven drug discovery?

Dotmatics is committed to helping scientists use technology and data science to improve global health. Our mission is to provide digital tools that enable scientists to leverage AI for meaningful discoveries. We believe that the journey toward harnessing AI will be marked by many small victories, leading to significant transformations in drug discovery. We’re excited to be part of this journey and are working to build the platforms that will support the next generation of scientific breakthroughs.

Related news

Show more

Related products

show more

Solution for challenging antibodies – Planova™ S20N

Solution for challenging antibodies – Planova™ S20N

Content provided by Asahi Kasei Medical Co., Ltd. | 24-Sep-2024 | White Paper

Designed as a next generation cellulose-based virus removal filter, Planova™ S20N has demonstrated robust filtration performance for challenging molecules...

Saama accelerates data review processes

Saama accelerates data review processes

Content provided by Saama | 25-Mar-2024 | Infographic

In this new infographic, learn how Saama accelerates data review processes. Only Saama has AI/ML models trained for life sciences on over 300 million data...

Related suppliers

Follow us

Products

View more

Webinars