Machine learning is changing our society, as exemplified by speech and image recognition applications. Also, the life sciences change rapidly through the use of artificial intelligence, and it is expected that fields like drug development can take advantage of machine learning. The main goal of the AIDD project is to train and prepare the next generation of scientists who need to have skills in both machine learning and drug discovery and will, after graduating, be able to help speed up the drug development process. The European Marie Skłodowska-Curie Innovative Training Network funds (grant number 956832) the AIDD project that brings together twelve academic and four industrial partners. The scientific goal of the project is to develop and implement a "One-Chemistry" model that can deal with multiple modalities in input and output. Different representations of molecular compounds combined with multitask fashioned training can distill the real "meaning" of the structure in terms of its chemistry, biology, physics, physiology; thus, opening a new way of designing new drugs and improving currently used medicines.