Marilou Nicolas

Meet Marilou Nicolas, Institutional Links Grant awardee.

Research topic: COnserving Philippine bIOdiversity by UnderStanding big data (COPIOUS): Integration and analysis of heterogeneous information on Philippine biodiversity

Host institution / UK university: University of Manchester - National Centre for Text Mining

Home institution: University of the Philippines Manila - Department of Physical Sciences and Mathematics

Year of Award: 2014

What is your proposed research topic/title of your collaboration?

The project is about producing an application interface to facilitate collection of information on Philippine biodiversity using a text-mining tool. From the Philippine side, our contribution is to 1) coordinate the collection of primary data from various Philippine biodiversity institutions through the Biodiversity Management Bureau (BMB) of the Department of Environment and Natural Resources using the Philippine Biodiversity Information System – a database and service program initiated at the University of the Philippines; 2) do the annotation work for publications on Philippine biodiversity containing medical applications/ case studies that will feed into the tool being constructed at UK.

What is the relevance of your research to the Philippines’ economic development and/or social welfare?

To support conservation policies on Philippine biodiversity, it is necessary to identify the various species found in the Philippines, its distribution and possible uses particularly its health and environmental applications.  UP Manila is the health science campus of the University of the Philippines.  It has undertaken studies of plants used as herbal medicine and has to date produced several herbal drugs such as “lagundi” and “sambong”.  Communities living around the few remaining rainforests do not appreciate the need to conserve the species unless they see benefits from it.  The communities use these plants as herbal drugs but greater benefit can be realized from the utilization of the genetic resources of the species to produce substances that would benefit human health and well-being. The first step however to claim benefits as stated in the Nagoya Protocol is to ensure that the species are properly documented as part of Philippine biodiversity.

How will your UK collaboration contribute to your home institution’s research goals?

Information about Philippine biodiversity is nil or sourced from many, non-communicating databases. Thus, in 2012, the University of the Philippines started the Philippine Biodiversity Information System (PhilBIS).  However, certain problems hampered the full development of PhilBIS.  The collaboration with NaCTeM will allow us to fast track the collection of primary data from various sources, as well as mine published information to create a comprehensive data on Philippine biodiversity, including its application to health and the environment. As a health science campus, the information will also help UP Manila in carrying out studies on certain species and its potential medical applications.

What about the UK influenced your decision to collaborate with your partner institution?

The collaboration will bring together experts in creating text-mining tools, and institutions that will be sources of biodiversity information and its application, primarily in health and the environment.  Although DENR and UP have partnered to facilitate collection of information on Philippine biodiversity, there are few experts on validating information from various sources.  Moreover, searching literature manually is quite slow. This partnership with the National Centre for Text Mining (NaCTeM) will greatly facilitate collection of information from published sources.  NaCTeM has the experts in text mining and processing of big data, and bioinformatics. It has a research group that are able to analyze and recognize associations between texts, names and other entities.  By partnering with NaCTeM, the project will be able to facilitate applications in Philippine biodiversity since it will be able to automate extraction of information from the literature into the repository.