AI and Drug Discovery
There are three major problems in traditional drug discovery: long research cycle, high research cost, low efficiency. Hundreds of compounds need to be screened from tens thousands of them to conduct preclinical trails, several of which can pass the preclinical trails, and only a few of which can be approved by FDA.
Pharmaceutical research and Manufacturers of America
In most cases, only we understand the mechanism of disease occurrence and development, then find the key target, can we conduct the research of new drug accordingly. There are complexity and individual differences in biological system, and the study of pathomechanism involves gene, protein, metabolism and other external factors. The most important functions of AI are capturing and processing the complex data of human body fast, and screening a large amount of genetic, metabolic, clinical data, thus, revealing the truth of diseases under the mask of biological network. Big data analysis provides drug discovery with new targets of drugs and prediction results, which makes drug discovery more accurate and focused.
AI can be widely used in the whole process from target identification to clinical trial. In the preclinical trails, Through in-depth learning, AI can assist to screen and identify the targets, offer instructions for synthesis and screening of compounds, optimize the lead compounds. AI can also apply to the recruitment of patients for clinical trials and clinical trials optimization .
Compared with traditional drug discovery, our drug discovery platform based on AI can greatly reduce the cost and time of research . The screening of compounds and optimization of lead compounds are the significant steps in the preclinical trail of new drug. Using AI technology, we can conduct big-scale screenings of compounds at lower cost, and reduce the time of compounds screening and lead compounds optimization from years to weeks.