The development of drugs takes a long time from finding the right connection to the approval of the FDA could take more than a decade and cost a billion dollars, and the research team of the New York City University Graduate Centre has developed an artificial intelligence model that reduces the time and cost of the drug development process.
The model has been called CODE-AE and is testing new drug compounds to predict how they will affect people and their effectiveness. During the tests, scientists, though theoretically, have found personalized drugs for over 9,000 patients who better treat the disease of the subjects.
The accurate and reliable prediction of a patient ' s response to a new chemical compound is crucial for the discovery of safe and effective therapeutics and the choice of an existing drug for a particular patient; however, it is not possible to conduct early testing of the drug ' s effectiveness directly on the individual.
As analogs, scientists use cell or tissue models to assess the therapeutic effects of a drug molecule, but the effect of a drug on a model often does not correlate with the effectiveness and toxicity of a drug in human patients. This knowledge gap is a major factor in the high cost and low productivity of drug development.