Research of protein 3D structures plays a key role in molecular biology, cell biology, biomedicine, and drug design. The protein fold type reflects the topological pattern of the structure's core. Fold recognition is an important method in protein sequence-structure research. On the 53 fold types which have more than 10 samples in LIFCA were selected. The functional domain composition is introduced to predict the fold types of a protein or a domain. After testing 9 211 proteins with less than 95% sequence identity from the Astral 1.65 database, the average sensitivity, specificity and Matthew's correlation coefficient (MCC) of the 53 fold types were found to be 96.42%, 99.91% and 0.91, respectively. The result indicates that using the functional domain composition to represent a protein is very promising for protein fold recognition. And though based on simple classification rules, LIFCA can concentrate the functional features of proteins, reflecting the corresponding relation between structure and function.