PANDA: prioritization of autism-genes using network-based deep-learning approach

Abstract

Autism is a neuropsychiatric disorder characterized by impairments in reciprocal social interaction and communication, and the presence of restricted and repetitive behaviours. Autism is predominantly heritable, but the underlying genetic associations are still largely unknown. Understanding the genetic background of complex diseases, such as autism, plays an essential role in the promising precision medicine. The evaluation of candidate genes, however, requires time-consuming and expensive experiments given the large number of possibilities. Thus, computational methods have seen increasing applications in predicting gene-disease associations. In this thesis, we proposed a bioinformatics framework, Prioritization of Autism-genes using Network-based Deep-learning Approach (PANDA). Our approach aims to identify autism-genes across the human genome based on patterns of gene-gene interactions and topological similarity of genes in the interaction network. PANDA trains a graph deep learning classifier using the input of the human molecular interaction network (HMIN) and predicts and ranks the probability of autism association of every node (gene) in the network. PANDA was able to achieve a high classification accuracy of 89%, outperforming three other commonly used machine learning algorithms. Moreover, the gene prioritization ranking list produced by PANDA was evaluated and validated using a large-scale independent exome-sequencing study. The top decile (top 10%) of PANDA ranked genes were found significantly enriched for autism association.