Research progress of artificial intelligence in high-throughput drug screening

Area of Science:

• Drug Discovery and Development
• Computational Chemistry
• Bioinformatics

Background:

• High-throughput screening (HTS) is crucial for identifying active compounds in drug discovery.
• Current HTS methods face challenges in screening efficiency and accuracy.
• Integrating artificial intelligence (AI) offers a promising solution to these limitations.

Purpose of the Study:

• To review the recent advancements in applying AI to HTS.
• To discuss the implementation of machine learning (ML) and deep learning (DL) models in HTS workflows.
• To highlight AI's role in accelerating innovative drug development.

Main Methods:

• Review of current research on AI applications in HTS.
• Discussion of ML and DL model integration in virtual screening, combination drug screening, and image analysis.
• Analysis of AI's contribution to post-screening data interpretation and hit identification.

Main Results:

• AI significantly optimizes various stages of the HTS workflow.
• AI enhances structure-based and ligand-based virtual screening processes.
• AI improves image recognition and hit identification from complex screening data.

Conclusions:

• AI integration is transforming drug discovery by boosting HTS efficiency and accuracy.
• AI-driven approaches are key to accelerating the identification of novel drug candidates.
• The continued development and application of AI in HTS promise to expedite the creation of innovative therapeutics.