Czarnecki, Jan Michael (2015) The fully automated construction of metabolic pathways using text mining and knowledge-based constraints. PhD thesis, Birkbeck, University of London.
|
PDF
Fullversion-2015CzarneckiJMphdBBK.pdf - Full Version Download (2MB) | Preview |
Abstract
Understanding metabolic pathways is one of the most important fields in bioscience in the post-genomic era, but curating metabolic pathways requires considerable man-power. As such there is a lack of reliable experimentally verified metabolic pathways in databases and databases are forced to predict all but the most immediately useful pathways by inheriting annotations from other organisms where the pathway has been curated. Due to the lack of curated data there has been no large scale study to assess the accuracy of current methods for inheriting metabolic pathway annotations. In this thesis I describe the development of the Literature Metabolic Pathway Extraction Tool (LiMPET), a text-mining tool designed for the automated extraction of metabolic pathways from article abstracts and full-text open-access articles. I propose the use of LiMPET by metabolic pathway curators to increase the rate of curation and by individual researchers interested in a particular pathway. The mining of metabolic pathways from the literature has been largely neglected by the textmining community. The work described in this thesis shows the tractability of the problem, however, and it is my hope that it attracts more research into the area.
Metadata
| Item Type: | Thesis |
|---|---|
| Copyright Holders: | The copyright of this thesis rests with the author, who asserts his/her right to be known as such according to the Copyright Designs and Patents Act 1988. No dealing with the thesis contrary to the copyright or moral rights of the author is permitted. |
| Depositing User: | Acquisitions And Metadata |
| Date Deposited: | 02 Jul 2015 12:01 |
| Last Modified: | 01 Nov 2023 12:28 |
| URI: | https://eprints.bbk.ac.uk/id/eprint/40135 |
| DOI: | https://doi.org/10.18743/PUB.00040135 |
Statistics
Additional statistics are available via IRStats2.
Archive Staff Only (login required)
