Autism is a neurodevelopmental disorder that is diagnosed in early childhood. Timely diagnosis and early initiation of treatments such as behavioral therapy is so important in these children. One of the common ways to study this disorder and finding factors causing it, is to study gene expression data from patients and try to find biomarkers for it. This could be an initial step in recognition of autism, drug discovering and drug designing. In this presentation, we review several computational methods and propose a framework using networks of co-expression, protein-protein interaction, miRNA-mRNA to find genes and microRNAs involved in autism.