Biotech research and development continues to advance new technologies that can help predict the onset of disease before it happens, thus enhancing the power of preventative medicine. One such advancement is a novel genetic computer network inference model developed at UT Arlington that could someday help clinicians predict if someone will develop mental illness.
The new technology is the result of a project led by Dr. Jean Gao, a computer science and engineering associate researcher at UT Arlington, and Dong-Chul Kim, Dr. Gao’s doctoral student graduate student, who recently earned his doctorate in computer science and engineering from UT Arlington.
The findings from the genetic computer network inference model were recently published in a paper entitled, “Inference of SNP-Gene Regulatory Networks by Integrating Gene Expressions and Genetic Perturbations,” which appeared in the June edition of Biomed Research International. Dr. Gao served as principal investigator along with Dong-Chul Kim, who also partnered with Jiao Wang of the Beijing Genomics Institute at Wuhan, China; and Chunyu Liu, visiting associate professor at the University of Illinois Department of Psychiatry. All in all, the team worked for four years compiling and analyzing the data.
Gao explained how the team went about discovering their findings: “We looked for the differences between our genetic computer network and the brain patterns of 130 patients from the University of Illinois,” she said, adding that, “This work could lead to earlier diagnosis in the future and treatment for those patients suffering from bipolar disorder or schizophrenia. Early diagnosis allows doctors to provide timely treatments that may speed up aid to help affected patients.”
For serious mental illness, patients are often treated with powerful drugs. Dr. Gao believes that being able to diagnose mental illness early could also give rise to a new subset of therapies designed to treat mental illness in its early stages. “Our work will allow doctors to analyze a patient’s genetic pattern and apply the appropriate levels of personalized therapy based on patient-specific data,” she said.
Khosrow Behbehani, the dean of the College of Engineering at UT Arlington, noted that the research and findings brings together computer science with engineering, psychology and genetics. “This research holds a lot of promise in the area of genetic expression,” he said. “If successful, it opens up the possibility of applying the method to other pathological conditions.”