PT  - JOURNAL ARTICLE
AU  - Benjamin Elsworth
AU  - Karen Dawe
AU  - Emma E Vincent
AU  - Ryan Langdon
AU  - Brigid M Lynch
AU  - Richard M Martin
AU  - Caroline Relton
AU  - Julian Higgins
AU  - Tom Gaunt
TI  - MELODI - Mining Enriched Literature Objects to Derive Intermediates
AID  - 10.1101/118513
DP  - 2017 Jan 01
TA  - bioRxiv
PG  - 118513
4099  - http://biorxiv.org/content/early/2017/03/20/118513.short
4100  - http://biorxiv.org/content/early/2017/03/20/118513.full
AB  - Motivation The scientific literature contains a wealth of information from different fields on potential disease mechanisms. However, prioritising mechanisms for further analytical evaluation presents enormous challenges in terms of the quantity and diversity of published research. The application of data mining approaches to the literature offers the potential to identify and prioritise mechanisms for more focused and detailed analysis.Results Here we present MELODI, a literature mining platform that can identify mechanistic pathways between any two biomedical concepts. Two case studies demonstrate the potential uses of MELODI and how it can generate hypotheses for further investigation. Firstly, an analysis of ERG and prostate cancer derives the intermediate transcription factor SP1, recently confirmed to be physically interacting with ERG. Secondly, examining the relationship between a new potential risk factor for pancreatic cancer identifies possible mechanistic insights which can be studied in vitro.Availability MELODI has been implemented as a Python/Django web application, and is freely available to use at www.melodi.biocompute.org.ukContact melodi{at}biocompute.org.uk