Date of Award

Spring 2017

Document Type

Poster Session

Department

Biological Sciences

First Advisor

Lisa R. Moore

Second Advisor

Marcia Ackerman

Abstract

Millions of species reside in the Tree of Life, making the task of resolving the evolutionary origin of many organisms difficult. Biologists draw on genetic and phenotypic information to sort the Tree of Life, but the study can be slow and complex. Phenomic data (such as cell shape, metabolism and ecology), particularly for microorganisms, is often found in scientific publications and has little digital presence outside of being scanned into an online database. This has been aided by a new text mining computer program, MicroPIE (Microbial Phenomics Information Extractor), that sifts through relevant phenomic data and creates a matrix of key phenomic characters taken from the published descriptions. MicroPIE utilizes multiple natural language processing tools to extract data, along with the knowledge of microbiologists to help with developing and verifying the tools. One major challenge to building such a tool is the time it takes to collect and edit phenomic data for tens of thousands of sentences needed to develop a functioning program. We have helped to further the development of MicroPIE to identify new characteristics by providing sentences from published microbial descriptions. We also are creating a “Gold Standard” matrix (GSM) of phenomic information for 100 different bacteria that can then be compared to the MicroPIE output in order to test that MicroPIE has correctly identified and extracted phenomic information. So far MicroPIE has shown potential to aid in resolution of the microbial Tree of Life.

Included in

Biology Commons

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.