Transmembrane proteins affect vital cellular functions and diseases, and are a focus of drug design. It is difficult to obtain diffraction quality crystals to study transmembrane protein structure. Computational tools for transmembrane protein topology prediction fill in the gap between the abundance of transmembrane proteins and the scarcity of known membrane protein structures. Their prediction accuracy is still inadequate: TMHMM [2,7], the current state-of-the-art method, has less than 52% accuracy on the prediction of transmembrane proteins collected by Moller et al. [1, 4]. Based on the assumption that there are functional domains that occur preferentially internal or external to the membrane, we have extended the model of TMHMM, incorporatingfunctional domain information into it, using an approach originally used in gene finding [8]. Results show that our Augmented HMM, or AHMM, is better than TMHMM on both helix and sidedness prediction. This improvement is verified by both statistical tests as well as sensitivity and specificity studies. As prediction of functional domain improves, our system's prediction accuracy will likely improve as well.
展开▼
