Computer-aided drug design in acute myeloid leukemia: a comprehensive review of advances, challenges, and future prospect.

Blood diseases, such as leukemia, and particularly acute myeloid leukemia (AML), bring a severe burden on patients, while conventional therapies are often limited by poor target specificity, toxicity and drug resistance. This underscores the urgent need for innovative strategies in drug discovery. Computer-aided drug design (CADD) integrates computational biology, quantum chemistry, and systems pharmacology, has potential to meet this need. CADD employs advanced computational techniques such as molecular docking, molecular dynamics and virtual screening to accelerate drug design and screening through the more accurate prediction of ligands-targets binding affinities and high-throughput screening. The integrate of artificial intelligence (AI) with CADD has further improve the efficiency, speed and accuracy of drug design and screening through improved drugs-targets binding prediction, better structures optimization, and faster screening in AML drug development. This review delineates the mechanistic principles underlying major CADD methods and highlights their latest applications for AML-targeted therapeutics such as developing the next generation highly selective FMS-like tyrosine kinase 3 (FLT3) inhibitors, de novo design of inhibitors for novel targets like methyltransferase-like 3 (METTL3), and overcoming acquired drug resistance. Finally, we propose a future direction of personalized precision treatment assisted by CADD and AI driven models for drug response prediction and drugs combination recommendation. This review aims to serve as a key reference and inspiration for scientists working at the intersection of AI, CADD and AML drug discovery.