Abstract 2247: Accelerating cancer research using big data with BioKDE platform

Abstract

Large volumes of data have been generated in biomedical field every day and made publicly accessible. A significant portion of the data are highly under-analyzed. On the other hands, biomedical researchers having problems that can be solved by these data do not have the expertise to access and analyze the data. The BioKDE (Biomedical Knowledge Discovery Engine) platform aims to bridge this gap by accelerating biomedical discovery through integration and mining of large volumes of public genomic data. We have integrated a large volume of genomics data from TCGA (the Cancer Genome Atlas) and GEO (Gene Expression Omnibus) database, which are linked with patient clinical information. Powerful and versatile query functions were built for the integrated data. Basic and advanced analysis tools have been implemented with user-friendly interfaces. Pipelines can be built by chaining the query tools with analysis tools to perform sophisticated data acquisition and analysis tasks very conveniently. Pipelines can be saved and shared among researchers to quickly replicate certain analyses using the same dataset or different datasets. A large number of novel discoveries have been made, which can be used directly to write scientific research papers using these discoveries alone or by combining with additional experimental validation studies. We will present a few case studies published recently to illustrate the power of the BioKDE. We are looking for collaborators to write papers together for the discoveries we made. The platform can be accessed at http://www.insilicom.com. Citation Format: Xiaodong Pang, Mayassa J. Bou-Dargham, Yuhang Liu, Zihan Cui, Linlin Sha, Tingting Zhao, Jinfeng Zhang. Accelerating cancer research using big data with BioKDE platform [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2018; 2018 Apr 14-18; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2018;78(13 Suppl):Abstract nr 2247.

KG-Hub—building and exchanging biological knowledge graphs

“…Other KGs are built on relationships extracted from unstructured text or from computational inference. For example, EMMAA (Ecosystem of Machine-maintained Models with Automated Analysis) assembles disease-specific graphs from published statements describing drug, gene, protein, and disease associations (INDRALAB, https://emmaa.indra.bio/ ), while BioKDE ( Pang et al 2018 ) supports literature search by connecting related concepts. Edges may also be extracted directly from biomedical literature with rule-based or natural language processing (NLP) approaches.…”