Neurodevelopmental disorders often have clear genetic components but linking genotype to phenotype remains challenging. Recent advances in genome editing technology have enabled the rapid generation of animal models for cognitive genetic disorders. However, the differing methodologies used across laboratories to phenotype these models confounds efforts to make predictive links between cellular functions of the brain and behavioral outcomes. I propose harnessing Multiplex Intermixed CRISPR droplet (MIC-Drop) technologies to generate knockouts of all 61 transcriptional regulators present in zebrafish larvae that are associated with human cognitive disorders. I will characterize these mutants at the molecular and cellular level with a multiplexed single-cell RNA sequencing technique I have developed, termed MIC-Drop-seq, that allows the simultaneous characterization of many transcriptomes from hundreds of mutant embryos in a single experiment. I will characterize these mutants at the brain morphology and behavioral levels with a battery of high throughput quantitative microscopy assays. I will use these large-scale quantitative datasets to construct new predictive machine learning models that will uncover the links between genetics, molecular features, brain morphology, and behavioral outcomes in brain development. These models may yield new treatment strategies for many human cognitive disorders. To achieve the goals of my proposal, I will embark on an intensive training plan with my mentorship team that will enable me to transition from my previous background in experimental biology to become a leader in the field of functional genomics and data informatics. My mentorship team at the University of Utah are leaders in the fields of single- cell biology, data science, and developmental biology, and will dedicate time to foster my career development as I transition to lead my own independent research group.