Identification of compounds that repress DUX4 expression in facioscapulohumeral muscular dystrophy

Facioscapulohumeral muscular dystrophy (FSHD) is caused by epigenetic dysregulation of the disease locus, leading to pathogenic misexpression of <i>DUX4</i> in skeletal muscle. Thus, most FSHD therapeutic approaches target <i>DUX4</i> . Our previous study identified the chromatin remodeling factor BAZ1A (bromodomain adjacent to zinc finger domain protein 1A) as a promising target for therapeutic development. Here we used an artificial intelligence-based screening pipeline to identify molecules predicted to bind the BAZ1A bromodomain, and validated hit compounds using FSHD-specific assays in FSHD myocytes. One compound, termed C06, emerged as a potent and specific repressor of <i>DUX4</i> and DUX4 target gene expression. Interestingly, while C06 exhibited binding to BAZ1A in vitro, it can also inhibit multiple kinases, including p38α, an upstream activator of <i>DUX4</i> . Despite this, at low doses C06 was an equally effective and more specific repressor of <i>DUX4</i> than losmapimod, which is a robust and specific p38 inhibitor. Thus, C06 is a useful tool for potent and specific <i>DUX4</i> suppression, and a viable candidate for further development. Our results highlight both the utility and limitations of AI for targeted drug discovery, and the importance of using an FSHD-specific functional screening strategy for selecting relevant candidates.