Drug Discovery with AI – Targets, Designs, Selection

Targets, Molecule Design/Generation, Docking, ADMET, Candidate Prioritization

AI-driven methods are employed for target identification, molecule design, docking simulations, ADMET (absorption, distribution, metabolism, excretion, toxicity) prediction, and candidate prioritization. These techniques significantly reduce the cost of screening by up to 70%.

The cost of screening is reduced by as much as 70%.

Data? ELN/LIMS/Publications.

AI models require extensive and diverse datasets for training, including experimental data from electronic lab notebooks (ELNs) and laboratory information management systems (LIMS), as well as published literature. This data is crucial for the generation of accurate predictions and novel molecular designs.

Data sources include ELNs, LIMS, and publications.

From Target Identification and Compound Design to ADMET, Repositioning

The process begins with target identification based on omics data such as genomics, proteomics, and metabolomics. Once a promising target is identified, AI algorithms are used for designing new molecules that can interact effectively with the target. These designs undergo ADMET prediction to ensure they will be safe and effective in clinical use before moving to repositioning studies.

Target identification uses omics data.

Frequently asked questions