Open Access
- 13 August 2017
- conference paper
- Published by Association for Computing Machinery (ACM)
- Vol. 2017, 1633-1642
Abstract
Hypothesis generation is becoming a crucial time-saving technique which allows biomedical researchers to quickly discover implicit connections between important concepts. Typically, these systems operate on domain-specific fractions of public medical data. MOLIERE, in contrast, utilizes information from over 24.5 million documents and does not limit the document vocabulary. At the heart of our approach lies a multi-modal and multi-relational network of biomedical objects extracted from several heterogeneous datasets from the National Center for Biotechnology Information (NCBI). These objects include but are not limited to scientific papers, keywords, genes, proteins, diseases, and diagnoses. We model hypotheses using Latent Dirichlet Allocation applied on abstracts found near shortest paths discovered within this network. We demonstrate the effectiveness of MOLIERE by performing hypothesis generation on historical data. Our network, implementation, and resulting data are all publicly available for the broad scientific community.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- DDX3 modulates cell adhesion and motility and cancer cell metastasis via Rac1-mediated signaling pathwayOncogene, 2014
- Stem Cell-Based Therapies for Ischemic StrokeBioMed Research International, 2014
- RNA Helicase DDX3 Is a Regulatory Subunit of Casein Kinase 1 in Wnt–β-Catenin SignalingScience, 2013
- NCATS launches drug repurposing programNature Biotechnology, 2012
- Conflicting Biomedical Assumptions for Mathematical Modeling: The Case of Cancer MetastasisPLOS Computational Biology, 2011
- Advancing Science through Mining Libraries, Ontologies, and CommunitiesJournal of Biological Chemistry, 2011
- Literature mining, ontologies and information visualization for drug repurposingBriefings in Bioinformatics, 2011
- Network Properties of Complex Human Disease Genes Identified through Genome-Wide Association StudiesPLOS ONE, 2009
- The human disease networkProceedings of the National Academy of Sciences, 2007
- Finding scientific topicsProceedings of the National Academy of Sciences of the United States of America, 2004