Vials in equipment

The COVID-19 pandemic has highlighted the importance of bringing drugs to market quickly. However, the process of discovering and developing a new drug can take years and comes with a price tag of hundreds of millions—or even billions—of dollars.

Though technological advances have helped speed up the timeline, the progress has been incremental. To transform the time-consuming and labor-intensive process of developing a drug for market, pharma companies should look to artificial intelligence (AI).

Delivering Targeted Data

The drug discovery process is a lesson in managing Big Data. Pharmaceutical company databases house millions of compounds and molecular designs that sort, filter and analyze information, but the effort is time-consuming—even with machine automation and robotic support.

Why AI: AI tools can sort and cross-reference data to deliver targeted results, which can speed up discovery. For example, one team in Germany created a tool that queries and cross-checks millions of organic chemical reactions. The tool helped plan a detailed, multistep chemical synthesis, a process that can take human researchers hours or even days.

Other companies use AI to mine and query historical information to predict clinical design pitfalls and target drugs for specific disease categories. For example, Microsoft and Eagle Genomics are developing an enterprise research platform that processes large amounts of data on how the body’s bacteria, fungi and viruses play a role in disease.

Reduce Development Costs

Process workflows, prioritization and pipeline management also present a data challenge. That’s because pharma companies typically work on many potential new drugs at once. These efforts use multiple complex workflows, including sequencing and molecular engineering, validation, mapping and inventory management integration.

Why AI: AI can help standardize and streamline data, and—most importantly—integrate that data with workflow management across disparate processes. This improves speed and efficiency, which ultimately reduces drug pipeline management costs.

Challenges to Adoption

Though AI presents the possibility of a smarter, faster and less expensive drug development process, it also presents challenges, including:

  • Data standardization: Data processes vary from company to company and even within organizations. Industrywide platforms and unified protocols are needed before AI can be widely adopted. Efforts are already underway. For example, Merck, Accenture and Amazon Web Services are developing a cloud-based research platform to share and standardize data.
  • Employee training and development: Chemists are not always up to date on technological advancements and applications. Organizations will need to invest in training and development for their employees to make the most of AI and machine learning technologies.

The bottom line: Even with challenges to adoption, AI presents exciting opportunities to improve the drug development process by lowering costs and reducing time to market.