MAIP: An Open-Source Tool to Enrich High-Throughput Screening Output and Identify Novel, Druglike Molecules with...

Area of Science:

• Medicinal Chemistry
• Computational Chemistry
• Parasitology

Background:

• Malaria remains a significant global health threat, affecting half the world's population.
• Emerging parasite resistance necessitates novel antimalarial chemotypes with proven efficacy and safety.
• Existing drug discovery pipelines require enhanced methods for identifying promising drug candidates.

Purpose of the Study:

• To experimentally validate the Malaria Artificial Intelligence Platform (MAIP) for predicting antimalarial compound activity.
• To demonstrate the utility of MAIP in a drug discovery workflow, including compound selection and high-throughput screening (HTS).
• To identify novel antimalarial compounds with high potency and favorable absorption, distribution, metabolism, and excretion (ADME) properties.

Main Methods:

• Development and training of a machine-learning model (MAIP) on diverse compound collections to predict antimalarial activity.
• Integration of MAIP with a compound selection strategy and a high-throughput screening (HTS) cascade.
• Experimental screening of compounds selected using MAIP against malaria parasites.

Main Results:

• The MAIP platform demonstrated significant predictive power for antimalarial activity.
• Compounds selected using MAIP showed a 12-fold enrichment in activity compared to random selection.
• Eight validated hits exhibited promising antimalarial potency and suitable ADME profiles.

Conclusions:

• MAIP is a valuable tool for prioritizing molecules in virtual screening and hit-to-lead optimization for antimalarial drug discovery.
• The combined approach of MAIP, strategic compound selection, and HTS accelerates the identification of potential new antimalarial therapies.
• Experimental validation confirms MAIP's effectiveness in identifying promising drug leads for malaria treatment.