To demonstrate how exciting and varied data science is, here are a few examples of the research being conducted at Colorado School of Mines:
Hua Wang, associate professor of computer science and co-director of the Data Science Program, and Judith Klein-Seetharaman, associate professor of chemistry, are developing computational tools to synthesize the findings in published COVID-19 literature as well as on-the-ground medical data to make decisions related to the virus.
“It is becoming clear that many factors are at play in who develops complications and ultimately dies from the infection, including molecular, physiological, lifestyle, behavioral, demographic and socioeconomic ones. In particular, comorbidities such as diabetes and high blood pressure are known risk factors for COVID-19 complications and death, but are likely only the tip of the iceberg. Molecular data indicates that as many as 100 comorbidities exist,” Klein-Seetharaman said. “Integrating large numbers of risk factors through machine learning will allow us to build statistical models that take all of the evidence into account – and hopefully predict COVID-19 infections at the individual and population levels.”
In 2017, Wang received an NSF CAREER Award for a research project to create a new machine-learning model for mining various kinds of data that could lead to easier, earlier and less-costly detection of neurological diseases such as Alzheimer’s or Parkinson’s.
Wang developed algorithms aimed at revealing the relationships between people’s genetic information, how their brains appear in scans that measure volume and function and their performances in cognitive tests. “The algorithms can extract information from large amounts of data that cannot be directly analyzed by ourselves,” Wang said.
“How to fuse all this available information from different sources is a challenging mathematical problem,” Wang said. But the payoffs could be big.
Determining one person’s full genetic profile can cost several thousand dollars. If Wang’s project determines a link, for example, between a disease and a small section of that long genetic chain, testing one’s likelihood of developing the disease would be much cheaper. “I wouldn’t mind spending a few bucks to find that out,” Wang said. “For most people, that should not be a problem.”
The Alliance for the Development of Additive Processing Technologies is using machine learning techniques to create computer models to optimize the parameters for manufacturing a given part using a particular 3D metal printer. This data can be used by companies who are seeking consistency and quality in the pieces they produce themselves or outsource to others.
This collaboration between Citrine Informatics and Mines also includes the Mines Initiative for Data-Driven Materials Innovation, dedicated to educating students on the fundamentals of materials informatics.
Mines mathematicians and statisticians are collaborating with geologists to better analyze the subsurface, thus reducing the financial and environmental risk mining companies assume when they dig for materials that are increasingly harder to find.
The interdisciplinary push of the Center for Advanced Subsurface Earth Resources Models brings advanced mathematics and statistics to every step of mineral extraction, from exploration to drilling to environmental remediation. Through the collaborative effort, Mines faculty hope to develop machine-learning techniques that will allow geologists to better predict subsurface features and quantify uncertainty, taking some of the risk out of decision-making processes for the mining industry. They also plan to improve subsurface visualization tools and develop advanced analysis and interpretation methods for enhanced characterization of rock.
“The geosciences of the future are going to rely more and more heavily on these creative mathematical techniques,” said Stefanie Tompkins, vice president of research and technology transfer at Mines. “It gives us a great edge and changes how we explore and characterize the underground. The stakes are high, and you need sophisticated mathematical tools,” she said.