Valency lexicon of Czech verbs has been intensively worked on for more than a year, and now we have at our disposal a detailed description of valency frames of several hundreds verbs. Presently, the challenge naturally arises, to use the existing lexicon for capturing valency of other word classes. In this paper, we focus on valency of nouns derived from verbs. We propose an algorithm for automatic prediction of valency frames of these nouns, and we test it on a sample of data.