“RosettaDOM” was apparently something in Rosetta++ (the 2.x series) not 3.x. Glancing at the paper, I don’t think it’s been ported to 3. Have you read the ++ documentation? (Failing that, the answer is, “I don’t know” and you should try contacting authors for that paper.)
smlewis, thanks for your quick response. I looked through the ++ docs and source code and could not find any mention of domain prediction (just domain insertion), so I emailed Prof. Baker.