The scientific literature as a resource for biological prediction and data validation

Thursday, September 28, 2017, 11:00 am - 12:00 pm PDTiCal
11th floor large conference room
This event is open to the public.
AI Seminar
Karin Verspoor
Video Recording:

The biomedical literature captures the most current biomedical knowledge and is a tremendously rich resource for research with over 26 million publications currently indexed in the US National Library of Medicine’s PubMed repository. Large-scale processing of the literature enables direct biomedical knowledge discovery. In this presentation, I will introduce the use of text mining techniques for applications in protein function and phenotype prediction. I will also explore a novel alternative use of the literature to support curation of biological database records by cross-checking their content with associated literature; this work further broadens the value of the literature in bioinformatics applications.

Karin is a Professor in the School of Computing and Information Systems and Deputy Director of the Health and Biomedical Informatics Centre at the University of Melbourne. Her research focuses on text analytics and machine learning for biomedical applications, to enable knowledge extraction from unstructured data as well as to provide clinical decision support. A current active project is related to enabling precision medicine with machine learning.

Karin was previously the Scientific Director for Health and Life Sciences at NICTA. Prior to arriving in Australia from the United States she held research roles at the University of Colorado School of Medicine and Los Alamos National Laboratory and spent 5 years developing language technology software in two start-up companies.



« Return to Upcoming Events