Quantum-assisted fragment-based automated structure generator (QFASG) for small molecule design: an in vitro study

Area of Science:

• Computational chemistry
• Drug discovery
• Artificial intelligence in medicine

Background:

• Automated drug design using virtual generative models is increasingly important.
• AI-driven generative chemistry platforms have shown limited success in producing valuable structures.
• Virtual fragment-based drug design is gaining traction due to advancements in chemoinformatics and computing power.

Purpose of the Study:

• To develop and evaluate a novel automated algorithm for generating drug-like molecules.
• To design new inhibitors for the CAMKK2 and ATM proteins using the developed algorithm.

Main Methods:

• Development of the Quantum-assisted Fragment-based Automated Structure Generator (QFASG) algorithm.
• Utilizing a library of molecular fragments to construct ligands for target proteins.
• Application of QFASG for generating novel CAMKK2 and ATM inhibitors.

Main Results:

• Successful design of new low-micromolar inhibitors for CAMKK2.
• Successful design of new low-micromolar inhibitors for ATM.
• Demonstration of QFASG's capability in generating potent drug candidates.

Conclusions:

• The QFASG algorithm shows significant potential for designing initial hit compounds in drug discovery.
• QFASG represents an effective tool for AI-assisted virtual fragment-based drug design.
• The developed method can accelerate the identification of novel therapeutic agents.