Technologies for mapping dynamic patterns of neural activity over time and space have advanced our understanding of brain function in both health and disease. An important application of these technologies is the discovery of next-generation neurotherapeutics for neurological and psychiatric disorders lacking effective treatments. Here, we describe an in vivo drug screening strategy that combines high-throughput brain activity mapping (BAM) technology with bioinformatic analysis. This platform enables evaluation of a compound’s therapeutic potential based on information rich BAMs derived from drug-treated zebrafish larvae. From a screen of clinically used drugs, we found intrinsically coherent drug clusters that are significantly associated with known therapeutic categories. Using the BAM-based clusters as a functional classifier, we successfully predicted anti-epileptic candidate drugs from non-clinical compounds and implicate epigenetic mechanisms for the development of novel anti-epileptic drugs. Collectively, these BAMs linked to specific compounds provide an experimental framework to advance the field of systems neuropharmacology.