Sometimes, studying the evolution and genomes of other mammals can provide insight into human evolution despite vast differences in evolutionary paths. Scientists at Carnegie Mellon University and the University of California, Berkeley used the U.S. National Science Foundation’s ACCESS program to help study something called regulatory DNA to compare gene expression across species. Their goal was to better understand vocalizations and how the ability to vocalize evolved.

With the help of Pittsburgh Supercomputing Center’s (PSC) Bridges-2, researchers used a machine-learning approach called TACIT (Tissue-Aware Conservation Inference Toolkit) to identify 50 gene regulatory elements from the brains of a variety of mammals looking for those that have a stronger relationship to vocalization. In the past, studying regulatory elements, which are important to understanding behavior evolution, has been difficult. With supercomputing and machine learning widely available at no cost through ACCESS, scientists working toward evolutionary discoveries are finding new avenues for their research.

“New artificial intelligence methods were needed to help find evolutionary signals in regulatory elements across hundreds of genomes,” said Pfenning, an Associate Professor in the Ray and Stephanie Lane Computational Biology Department at CMU and a corresponding author in the new study. “We’re entering an exciting era where AI is improving our ability to trace human evolutionary history.”

If you’d like to learn more about this fascinating study, including how this work might one day assist researchers studying autism, you can find the original story here: Non-Gene Regulatory DNA Identified via Artificial Intelligence also Associated with Autism in Humans

Project Details

Resource Provider Institution(s): Pittsburgh Supercomputing Center (PSC)
Affiliations: Carnegie Mellon University, University of California, Berkeley
Funding Agency: NSF
Grant or Allocation Number(s): BIO200055

The science story featured here was enabled by the U.S. National Science Foundation’s ACCESS program, which is supported by National Science Foundation grants #2138259, #2138286, #2138307, #2137603, and #2138296.