Mouse model systems of autism spectrum disorder: Replicability and informatics signature

• Published in: Genes, brain and behavior brain and behavior, 2020-09, Vol.19 (7), p.e12676-n/a
• Main Authors: Kabitzke, Patricia, Morales, Diana, He, Dansha, Cox, Kimberly, Sutphen, Jane, Thiede, Lucinda, Sabath, Emily, Hanania, Taleen, Biemans, Barbara, Brunner, Daniela
• Format: Article
• Language: English
• Subjects: 16p11.2; Animal models; Autism; behavior; Cacna1c; Cntnap2; Cognitive ability; Housing; Informatics; Laboratories; mouse model systems; Original; Pathophysiology; Phenotypes; Phenotyping; preclinical; replication; Shank3; Social behavior
• ISSN: 1601-1848; 1601-183X
• DOI: 10.1111/gbb.12676

Phenotyping mouse model systems of human disease has proven to be a difficult task, with frequent poor inter‐ and intra‐laboratory replicability, particularly in behavioral domains such as social and cognitive function. However, establishing robust animal model systems with strong construct validity is of fundamental importance as they are central tools for understanding disease pathophysiology and developing therapeutics. To complete our studies of mouse model systems relevant to autism spectrum disorder (ASD), we present a replication of the main findings from our two published studies of five genetic mouse model systems of ASD. To assess the intra‐laboratory robustness of previous results, we chose the two model systems that showed the greatest phenotypic differences, the Shank3/F and Cntnap2, and repeated assessments of general health, activity and social behavior. We additionally explored all five model systems in the same framework, comparing all results obtained in this three‐yearlong effort using informatics techniques to assess commonalities and differences. Our results showed high intra‐laboratory replicability of results, even for those with effect sizes that were not particularly large, suggesting that discrepancies in the literature may be dependent on subtle but pivotal differences in testing conditions, housing enrichment, or background strains and less so on the variability of the behavioral phenotypes. The overall informatics analysis suggests that in our behavioral assays we can separate the set of tested mouse model system into two main classes that in some aspects lie on opposite ends of the behavioral spectrum, supporting the view that autism is not a unitary concept. Despite many of our findings not replicating with results published in the literature, we found overall excellent replication of most of the results from our previous publications, using the same protocols and animal models and often after consultation with the originating laboratories. In the present collection of studies, wild type controls' data were robust and consistent, although there were exceptions. The direction of the genotype effects, and often the effect size, was also very comparable. We argue that the problem in the lack of replicability of results resides more in the differences between labs, protocols, husbandry, data handling and statistical analysis, that lead to different outcomes, than in the variability of the animal models themselves.