Idea2Data: Toward a New Paradigm for Drug Discovery.

Area of Science:

• Drug Discovery and Development
• Computational Chemistry
• Medicinal Chemistry

Background:

• Current drug discovery hit identification relies on screening limited physical compound libraries.
• This approach surveys only a small fraction of the vast chemical space, leading to inefficiencies.
• Hypothesis generation for hit identification often uses predictive models based on prior screening data.

Purpose of the Study:

• To introduce and describe the Idea2Data (I2D) process for enhanced drug discovery efficiency.
• To integrate vast virtual compound libraries with predictive computational models.
• To enable rapid hypothesis testing and accelerate the identification of novel drug candidates.

Main Methods:

• The Idea2Data (I2D) process connects virtual, synthesizable compound libraries with predictive computational models.
• It allows for the processing of billions of virtual molecules.
• Selected virtual compounds are synthesized using automated systems for biological testing.

Main Results:

• The I2D process has successfully identified novel chemical scaffolds and functionalized existing ones in portfolio efforts.
• It enables timely hypothesis testing by rapidly providing synthesized compounds for biological assays.
• The described application focuses on the discovery of new ULK inhibitors.

Conclusions:

• Idea2Data (I2D) represents a paradigm shift in hit identification, significantly improving efficiency and throughput.
• This integrated computational and experimental approach expands the exploration of chemical space for drug discovery.
• I2D facilitates the rapid identification and optimization of promising hit compounds for therapeutic development.