The Biomedical Knowledge Miner (BiK>Mi) provides tools to access and validate knowledge encompassing all of the latest information pertaining to Alzheimer's Disease. This project aims to use a comprehensive computational model of biological mechanisms in the context of Alzheimer's Disease to determine currently used drugs that can effectively treat this disease. This drug repurposing workflow would significantly expedite development and research time as well as be applied to a variety of diseases.
The Fraunhofer Institute for Algorithms and Scientific Computing (Department of Bioinformatics) seeks to reshape scientific knowledge into a single, computable repository despite the fact that this knowledge is stored in a variety of formats, databases, and sources. Pathway databases store information on the underlying mechanisms that govern biological processes while databases such as UniProt contain detailed data on specific molecules. However, these databases only contain established information, in order to include the most up-to-date findings, knowledge needs to be extracted from current scientific publications. To ensure that our knowledge graph contains the latest findings, hundreds of publications were manually curated and their contents converted in Biological Expression Language (BEL) statements. These statements are then parsed and used to build an interactive knowledge graph by the in-house developed software package e(BE:L). The e(BE:L) software then enriches the knowledge graph with public available data and knowledge bases spanning multiple research fields including: drugs and their targets, protein properties, pathways, associated clinical trials, SNPs, and protein-protein interactions (PPIs) to create a comprehensive warehouse of information.