Using machine learning to predict success of biofuels

Engineers have been working to create fuel alternatives using synthetic biology for years. An engineer at Washington University in St. Louis plans to apply machine learning to guide synthetic biology applications.

Energy metabolism provides ATP to power carbon fluxes to biomass growth and product synthesis. Image by Yinjie Tang.

Yinjie Tang, associate professor of energy, environmental & chemical engineering in the School of Engineering & Applied Science, has received a three-year, $245,474 collaborative grant from the National Science Foundation (NSF) to better predict the productivity of microbes by analyzing big data, or the results of previously published results in this area. With his collaborator, Forrest Sheng Bao of the Electrical and Computer Engineering Department at the University of Akron, they plan to develop a new model to provide rational genetic engineering strategies. Bao received $232,523 from the NSF, bringing the total funding amount to $477,977.

“Biology is very complicated, and biological systems are too unpredictable,” Tang said. “The current mechanistic models always over-predict host performances, so we have to find an alternative approach.”

Through extracting information from thousands of papers in the PubMed academic database, the team plans to use data mining and machine learning to predict the success probability of future synthetic biology projects.

As part of the research, Tang will actively involve local high school students from groups underrepresented in the biosciences. He plans to employ several students from Hazelwood East High School in north St. Louis County to help with the data collection, as well as hold summer workshops for students from Hazelwood East to expose them to biotechnology and engineering.

The School of Engineering & Applied Science at Washington University in St. Louis focuses intellectual efforts through a new convergence paradigm and builds on strengths, particularly as applied to medicine and health, energy and environment, entrepreneurship and security. With 90 tenured/tenure-track and 40 additional full-time faculty, 1,300 undergraduate students, more than 900 graduate students and more than 23,000 alumni, we are working to leverage our partnerships with academic and industry partners — across disciplines and across the world — to contribute to solving the greatest global challenges of the 21st century.