Drug design and development is expensive, often insufficient, and laced with the tendency for failure. Traditionally, it’s a hit-and-miss process that can stretch over a decade and consume around $2.3 billion — figures that have only climbed higher recently; with a 15% increase in costs among top global biopharmaceutical firms last year alone. However, despite misconceptions about its use, artificial intelligence (AI), through modalities such as machine learning models, is poised to enable companies to expedite the drug design process.
Designing future therapies with future technologies
The chemical universe spans over 1060 molecules that can be linked to potential drugs – a number far too large for human beings to explore in one lifetime. Current practices involve selecting, designing, and prioritizing molecular structures based on a host of different factors ranging from desired biological activity to retrosynthetic analysis. However, this process involves solving complex, multidimensional optimization problems that can take a considerable amount of time.
Unlocking Transparency in PBM Pricing
The TSX Venture Exchange has a strong history of helping early-stage health and life sciences companies raise patient capital for research and development.
Thankfully, AI is revolutionizing the way in which we explore this chemical space by speeding up the identification of promising compounds. Machine learning and data analysis technologies can quickly pinpoint hit and lead compounds, accelerate the validation of drug targets, and optimize drug structure designs, thereby cutting down the time required to develop drugs while significantly reducing costs. Consequently, it’s becoming more possible to experiment with a wider range of potential therapies.
One of the greatest barriers to drug design is finding the right protein involved in a disease so that the drug molecule can be made accurately. With AI tools such as AlphaFold and MATLAB, scientists can predict the 3D structures of target proteins, including never-see-before molecules, entirely from scratch. This allows for more precise and effective drug formulations at a fraction of the time and cost. These modern machine learning AI models work by predicting protein structure through four models:
- An input module that gathers amino acid sequences from various proteins
- A neural network that uses pattern-recognition software to convert amino acid sequences into spatial information
- An output model which translates the spatial information into a 3D structure
- A refinement process that fine-tunes the structure into a drug molecule
As we get into a more automated drug design model in the not-too-distant future, the value of these machine-learning technologies becomes more immense. Studies suggest that AI has the potential to not only develop drugs but also to do so in the most optimal dosage form in consistent batches.
At ViVE 2024, Panelists Share Prior Authorization Progress and Frustration in Payer Insights Program
At the Payer Insights sessions on Day 1 of ViVE 2024, a panel on prior authorization offered compelling insights from speakers who shared the positive developments in this area after years of mounting frustration. Speakers also shared challenges as they work with providers to figure out how policy developments and technology will work in practice.
AI-designed drugs in clinical trials
AI-designed drugs have been entered into trials, with preliminary read-outs holding great promise. In June 2022, an AI-designed drug molecule by Exscientia successfully entered phase 1b/2 trials for certain cancer patients. Likewise, in the beginning of 2023, New Zealand-based company, Insilico Medicine, demonstrated the capabilities of its Pharma.AI platform to target and design drug molecules with a high level of integration with human biology.
Nonetheless, it’s still early days for AI-designed drugs, with many innovative companies out there making claims they’re yet to live up to. It may take years for the first fully AI-designed drugs to hit the market, but it is clear that this technology has certainly shaken up the pharma industry for the better.
Application of AI in medical practice
Alongside its use in drug design and development, AI has been incorporated into physical medical practices to expedite processes and streamline workflows. For instance, local infusion centers, which like the rest of the healthcare industry, face significant challenges such as staffing shortages and operational inefficiencies, have been shown to significantly benefit from AI. A survey conducted by LeanTaaS involving 100 leaders from U.S. cancer centers demonstrated that AI can reduce patient wait times by 30%, decrease staff overtime by 50%, and handle a 15% increase in patient volumes.
When local infusion centers are able to utilize these technologies, they’re inadvertently enhancing patient experiences and creating a more seamless journey for those who have once struggled to find a streamlined path to managing their disease. While yes, there is the added stress attributed to enhancing technological competency within staff, this technology can, in the long run, empower healthcare workers to better allocate their resources and ensure their patients receive the care they deserve.
Over the next few years, AI will likely integrate larger and more diverse data sets, including real-world patient data, further enhancing the precision of drug design and discovery and allowing for new products to be developed at record-breaking speeds. However, as past technologies have once raised hopes for revolutionizing drug discovery and failed to live up to expectations, it’s important to look beyond the hype and take each step as it comes.
Editor’s note: The author and his employer have no financial relationship with any of the companies or tools mentioned in this article.
Photo: metamorworks, Getty Images
As Chief Executive Officer of TwelveStone Health Partners, Shane Reeves leads all aspects of the business, including product, marketing, sales, finance, and delivery strategy. Shane’s career began with the organization in 1994 when he joined the family business and worked his way up through every function in the company. Under Shane’s leadership, moving forward as TwelveStone, the organization has grown into a broad medical service company with a long list of clients across the entire care continuum.
This post appears through the MedCity Influencers program. Anyone can publish their perspective on business and innovation in healthcare on MedCity News through MedCity Influencers. Click here to find out how.
