Scientists increasingly use workflows to represent and share their computational experiments. Because of their declarative nature, focus on pre-existing component composition and the availability of visual editors, workflows provide a valuable start for creating user-friendly environments for end user scientists. However, there is still work to be done to create even more user-friendly environments. In this paper, we aim to identify key constructs that intelligent workflow systems could support to allow for more natural workflow representations. These constructs are identified through a comparison of bioinformatics workflows and their associated natural language descriptions obtained from the virtual research environment myExperiment.