We plan to work on inverse-designing the hydrophobic patches on DNA origami for mesoscale assembly of superlattices. This problem is important as understanding the complex assembly rules of patchy DNA origami will create avenues for functioning mesoscale materials with practical applications, such as therapeutics, drug delivery, or metamaterials. The current challenge in DNA nanotechnology is to extend DNA origami, a type of material with molecular precision, from the nanoscale to the mesoscale. A novel experimental method exploits the hydrophobic attraction to organize nanoscale cubic DNA origami on the mesoscale. Although it bears the potential to fabricate functioning superlattices, the underlying relationship between the assembled structure and the design of DNA origami building blocks is expensive to be explored and exploited. Inferring potential design with desired properties through artificial intelligence, an inverse design approach, would be well suited for this task. Neural-adjoint is a recently refined technique for general deep inverse modeling that has to show its promise in material design-related tasks for problems with high one-to-manyness. We believe it would be a good stepping stone toward designing new DNA origami material.