Abstract
A structure generator is an algorithm that creates new molecular structures according to the initial conditions toward de novo drug design. We introduce two major types of structure generators: building block-based structure generator and deep learning-based structure generator. Recently, omics-based drug discovery has received much attention from the pharmaceutical industry and academia. We propose a novel computational method for omics-based de novo drug design via the integration of transcriptome data analysis and molecular generative models, which we call TRIOMPHE（transcriptome-based inference and generation of Molecules with desired phenotypes）.
