Accelerating Drug Discovery with an AI-Based Virtual Human System CODA
Doheon Lee · 2020
Formidable complexity of systemic human physiology often give rises of unintended effects of therapeutic compounds during the drug development processes or even after the drug approvals. Though the beneficial unintended effects could lead opportunities of repositioning drugs, the harmful effects might put critical hurdles against successful drug development. We have been developing a virtual human system, CODA, which can explore functional effects of therapeutic compounds in the systemic level. CODA integrates three types of physiological knowledge from public structured databases, literature, and in-house experiments into a unified format of physiological interactions. More than ten public databases including KEGG, GO, and CTD have been transformed; around 25 million PUBMED abstracts have been text-mined; and more than 5,000 in-house novel findings have been incorporated. We have also developed two types of analysis on the CODA knowledge repository. Given therapeutic compounds of interest, CODA can identify possible phenotypic effects in the systemic level. When therapeutic compounds and their observed functional effects are given, CODA can enumerate possible effect paths encompassing molecular, functional, and disease level interactions. We have been testing CODA by applying it to various tasks including drug repositioning, drug-drug interactions, and side effect prediction with known benchmark datasets. Though we are enriching CODA with more knowledge sources and more sophisticated analysis techniques, the current version is already providing unique analysis capabilities and one of the most comprehensive information for drug discovery.