The abundance of data created in science, engineering, business, and everyday human activity is simply staggering. This data is often complex and high-dimensional, taking the form of video or time-dependent sensor data. Machine learning methods allow us to understand such data, automatically identifying patterns and making important data-driven decisions without human intervention. Machine learning methods have found a wide variety of applications, including providing new scientific insights and the development of self-driving cars.

One machine learning method in particular, neural networks, has emerged as the preeminent tool for the supervised learning tasks of regression and classification. Loosely modeled after the human brain and the basis for deep learning, Neural Networks use composition to develop complex representations of data. In recent years, researchers using Neural Networks have made tremendous breakthroughs in topics as varied as image processing, natural language processing, and playing board games such as Go.

Undergraduate students participating in this SRI stream will be introduced to neural networks and learn how they're used. Students will learn about the mathematics that forms the basis for neural networks and the optimization methods used to train them. They'll learn how to program in python and use machine learning packages such as scikit-learn and TensorFlow to analyze data. Working in teams, students will use Neural networks to solve real-world classification problems like object recognition in images, detecting falsified financial transactions, and controlling for manufacturing defects. They'll also learn to effectively communicate and visualize results.

The basic driving forces of evolution, mutation and selection, are often difficult to observe and study in the laboratory because it requires large numbers of individuals and long time periods in order to observe the evolutionary changes.

During our research we found that the yeast knockout collection (~4200 strains each containing a deletion of a non-essential gene) is a treasure trove for evolutionary and cell biological studies. Genome sequencing of several of these mutant strains in my lab identified additional mutations in each mutant that help the strain cope with the initial gene deletion.

Undergraduate students in SRI biology labs.

These suppressor mutations most likely arose during the copying of the original knockout collection, during which strains with suppressor mutations had the opportunity to outcompete the original mutant strain. Knowledge of the suppressor mutations can give insights not only into evolutionary mechanisms but also into the interactions between different cell biological pathways (systems biology).

The goal of the project is to systematically analyze the genomes of yeast deletion strains propose a mechanism of phenotypic suppression and test the model. Furthermore, we will perform evolutionary experiments in the lab to identify the factors that are responsible for the rapid genetic adaptation of yeast.

>> BACK <<

Chemists and engineers strive to develop safe, efficient, and environmentally sustainable chemical synthesis for the production of high-value molecules, such as those used in medical applications. Advances by electrochemists have demonstrated remarkable new means for improving product selectivity under mild reaction conditions. Unexplored realms of chemical synthesis are now attainable using electrons at the primary reactant.

Supported by the National Science Foundation Center for Chemical Innovation, chemists at the University of Utah and across the country are embarking on a collaborative project to employ the extensive knowledge electrochemists, materials scientists, and physical chemists in using electrons to make new molecules.  The overarching goal is to deploy this exciting new knowledge to advance chemical synthesis.

Undergraduates participating in this SRI project will demonstrate how using electrons as reactants can make pharmaceutical synthesis greener, safer, and environmentally friendly. Students will work towards learning advanced electrochemical methods for carrying out chemical transformations.  Working as a team, they will participate in designing a research plan for developing a general electrochemical route for introducing chemical functionality into molecules, and then demonstrate the general application of their method in the chemical syntheses of a series of molecules.

Inside the Minteer Lab.

The project will provide students with a working knowledge of many aspects of organic preparatory chemistry, the physical chemistry of electron-transfer reactions, catalysis, materials chemistry, and quantitative analytical measurements, providing a foundation for future advance research in all areas of chemistry.  Biweekly meetings of the entire team with the project leaders (Profs. Minteer and White) will focus on discussion of individual student results and the overall progress of the team.

Communication skills and scientific writing will be emphasized as part of the project.  Undergraduates from all areas of science and engineering are encouraged to apply.