A fundamental and hard question in biology is identification of organisms. This proposal focuses on identification of nematodes, which are particularly difficult to identify, with the average identification requiring significant time and high level of expertise. Nematodes have direct and significant effect on humans, other animals, and agriculture. Four species of nematode parasites infect over 2 billion people worldwide, and one type of nematode causes one-third of the total estimated worldwide annual yield losses to all soybean pathogens. The current limiting factors for identification are the lack of tools and automation, the need for image comparison off-line and a need for significant expertise. To enable seasoned researchers as well as students to use resources, the team will build on image searching work, using a set of images that will make nematode identification a simple process of point and click. In addition to enabling research by harnessing data and experience of experts, the work may make biology more accessible. The team will build a computer-assisted interactive navigator that will intelligently assist and learn from the user. The work can be extended to many other biological data sets. The research challenges include extraction of features and similarity functions, and the mining, clustering, and anomaly detection for image and non-image data. Graduate students are engaged in the research and outreach involving high school students is also planned.
