A multi-institutional $1.2M grant from the National Science Foundation will accelerate discovery and exploration of the synthetic biology design space. Professor and Associate Dean for Research J. Stephen Downie serves as a principal investigator on the project, "Synthetic Biology Knowledge Systems," which brings together researchers from the University of Illinois; University of Utah; University of California, San Diego; Virginia Commonwealth University; Worcester Polytechnic Institute; and the non-partisan and objective research organization NORC at the University of Chicago.
During the course of the two-year project, a multidisciplinary team of biological engineers, machine learning experts, data scientists, library scientists, and social scientists will build a knowledge system integrating disparate data and publication repositories. The goal will be to deliver effective and efficient information access to researchers who are currently using a trial-and-error approach because reliable information about prior experiments does not exist.
According to Postdoctoral Research Associate Jacob Jett, a lead researcher on the project, machine learning methods like named entity recognition, topic modeling, and word embeddings will be used to mine information from the existing synthetic biology literature.
"The results of these machine learning processes will be reconciled and grounded using existing knowledge representations of real-world entities like organisms, genes, proteins, and cell parts through ontologies and controlled vocabularies like the Gene Ontology, the Sequence Ontology, and the National Center for Biotechnology Information's organism taxonomy, among other vocabulary resources," Jett said.
The Illinois team will help build an information retrieval recommender system for the scientists and advise on the ontologies and metadata.
"Synthetic biology has a transformative potential in applications from energy, agriculture, materials, and health. Our participation in this important project illustrates how the iSchool can make unique contributions to harnessing the data revolution," Downie said.
Downie is codirector of the HathiTrust Research Center (HTRC), a collaboration between the University of Illinois, Indiana University, and the HathiTrust to enable advanced computational access to text found in the HathiTrust Digital Library. His research areas include the design and evaluation of information retrieval systems, including multimedia music information retrieval; the political economy of internetworked communication systems; database design; and Web-based technologies. He holds a bachelor’s degree in music theory and composition, along with master's and doctoral degrees in library and information science, all from the University of Western Ontario.
Jett's research is primarily focused on information modeling issues with a special focus on ontology, controlled vocabulary, and schema development for Semantic Web infrastructure. He uses a combination of formal conceptual analysis approaches to analyze and organize digital information systems such as databases, repositories, and digital libraries. Jett earned his PhD in library and information science from the iSchool at Illinois, where he also completed his master's and Certificate of Advanced Study work.