BMC Bioinformatics is calling for submissions to our Collection on ''Artificial intelligence for drug design''.
Drug discovery is a time-consuming and expensive process, taking an average of more than 10 years and one billion US dollars to deliver a new drug into patients’ hands. Among the steps in drug discovery, drug design is a critical part in developing novel molecules that can bind the target(s) of interest. From the computational perspective, the chemical space is too vast for the identification of promising drug candidates through the enumeration of each molecular structure. Furthermore, drug design can be modeled as a many-objective optimization process, as not only must a candidate interact with the target, but it also has to be synthesizable and fulfill ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties. Many drug development projects declare failure in later stages due to severe side effects caused by the drug candidates under investigation. The rise of artificial intelligence (AI) techniques and the accumulation of extensive molecular datasets provide us with a great opportunity to revolutionize this field by innovative representation, prediction, and generative approaches. This collection welcomes submissions about the development and/or improvement of AI approaches including, but not limited to, deep learning models, (deep) generative models, reinforcement learning, computational intelligence, and foundation/generalist models, to address challenges in the following (but not exclusive to) tasks:
• Drug target interaction prediction
• Drug combination prediction
• Drug response prediction
• Molecular representation learning
• Small-molecule drug design
• Lead optimization
• Protein and antibody design
• Aptamer design
• Protein-ligand docking
• Active site prediction
• Protein tertiary structure prediction
• Drug repurposing
• ADMET property prediction
• Side-effect prediction
Image credit: Grycaj / stock.adobe.com
