Navigating large chemical spaces in early-phase drug discovery

Area of Science:

• Medicinal Chemistry
• Computational Chemistry
• Drug Discovery

Background:

• The landscape of accessible chemical matter for drug discovery is rapidly expanding due to novel computational and experimental methodologies.
• This expansion presents unprecedented opportunities for identifying new molecular entities in early-phase drug discovery.

Purpose of the Study:

• To provide a compact overview of the state-of-the-art in exploring and analyzing large chemical spaces.
• To highlight the impact of emerging technologies on drug discovery processes.

Main Methods:

• Leveraging generative machine learning models for synthesis prediction.
• Utilizing DNA-encoded libraries for hit structure discovery.
• Developing advanced cheminformatics approaches for efficient chemical space analysis.

Main Results:

• Exponential growth in the content of large, combinatorial chemical spaces with high synthetic success probability.
• Demonstration of novel technologies enabling broader and deeper searches for new chemical matter with reduced effort and cost.
• Emergence of first bioactive compounds from successful application of these novel technologies.

Conclusions:

• Transformational developments in computational and synthetic chemistry are revolutionizing drug discovery.
• New cheminformatics strategies are essential for managing and analyzing vast chemical spaces efficiently and with minimal resource consumption.
• These integrated approaches hold significant promise for future drug discovery programs.