Genetically modified autistic model monkeys make new achievements

The Center for Excellence and Innovation in Brain Science and Intelligent Technology of the Chinese Academy of Sciences, the Shanghai Brain Science and Brain Research Center, the Wang Zheng Research Team of the National Key Laboratory of Neuroscience, and the Research Team of the Institute of Automation of the Chinese Academy of Sciences have designed the monkey-human cross-species machine learning and analysis process for the first time in the world, using genetically modified The characteristics of macaque model, the construction of classifier model for patients with clinical mental illness, and the further analysis of the neural loop mechanism of human autism and obsessive-compulsive disorder provide new evidence for the accurate diagnosis of mental illness imaging, and open up a new way to use non-human primate model to serve the clinical application needs of mental illness. The findings were published online June 17 in the American Journal of Psychiatry.
Non-human primate model animals and humans are relatively close in brain structure and function, genetically modified primate models can show similar symptoms to human clinical patients esoteric, such as MECP2 over-expression of macaques show repeated stereotypes, social behavior disorders and other autism symptoms.
"We are the original innovation work based on the early work, which in a sense is an extension of the achievements of genetically modified autistic model macaques, " Wang said. "We hope to build a bridge with genetically modified autism model macaques and explore new ideas for clinical diagnosis of autism-related diseases through magnetic resonance imaging."
to explore possible evolutionary conservative characteristics among primate species, the team boldly hypothesized that based on conservative brain region functions, the team constructed a model for the classification and prediction of mental illness that could migrate across species, Wang said.
Researchers first used "sparse learning" to screen brain regions from brain function maps from five genetically modified macaques and 11 wild macaques to identify nine core brain regions, then mapped each of these brain regions to the human brain and used functional connections in brain regions to form a collection of features to build a sparse logical regression classifier for the diagnosis and classification of people with autism, obsessive compulsive disorder and attention deficit ADHD. AbIDE-I, ABIDE-II, OCD and ADHD-200 were collected from a total of 4 clinical patient imaging databases.
By integrating primate models and functional magnetic resonance imaging data from patients with clinical mental illness, the researchers found that the classification model based on the characteristics of genetically modified macaques had an 82.14 percent accuracy of distinguishing between autistic and normal people in ABIDE-I data set, and 75.17 percent accuracy of human subjects in the ABIDE-II database, significantly higher than the performance of classifiers based on the characteristics of patients with autism and obsessive-compulsive disorder. When the same nine brain regions were extended to obsessive compulsive disorder image data, it was found that the classification model of macaque characteristics was still 78.36 percent accurate, significantly higher than the classifier performance based on the characteristics of autistic patients. These characteristics, based on macaque model learning, have not significantly improved the classification accuracy of ADHD patients.
"Autism clinical manifestations are diverse, some anxiety, some social disorders, some language disorders ... The genes behind various symptoms are changing, which is also an important reason for the low accuracy of clinical diagnosis. We hope that this research, based on primate models with a single disease genetic background, will provide a more accurate and objective basis for clinical imaging diagnosis. Wang Zheng said. (Source: He Jing, China Science Journal)
related paper information: