![](images/icon_discovery.svg)
- Drug Discovery
The development of new drug molecules involves a huge number of experiments, predictive models, and expertise.
AI and machine learning technologies are adopted to many stages of the drug discovery processes to transform this
time-consuming and labor-intensive process.
HelloGene provides multiple tools that span all stages in the drug discovery process.
Along with the high-throughput compound screening, fragment screening, and computational modeling, our platform includes tools for ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) prediction and drug response
prediction based on AI-powered data analysis.
![](images/img_discovery_n.png)
![](images/img_discovery_01_n.png)
- ADMET prediction
-
ADMET refers to drug absorption, distribution, metabolism, excretion, and toxicity. Prediction of ADMET is an important process in drug design and drug screening, but the current experimental methods for ADMET test are cost- and time-consuming. ADMET prediction can be shortened in evaluation period and enhanced in accuracy by applying AI based on big data, machine learning, and deep learning technologies.
- SAR analysis
-
Structure-activity relationships (SARs) and quantitative
structure–activity relationships (QSARs) are basic and
theoretical models in drug research and development, which can be used to predict the physicochemical, biological, and other properties of chemicals and guide compound optimization. The computer-based modeling methods, as well as AI-driven approaches relating chemical structure to qualitative biological activity and quantitative biological potency, have been widely applied in diverse problem settings. AI-powered methods are also applied to model nonlinear SARs and predict novel active compounds.