A predictor of transmembrane alpha-helix domains of proteins based on neural networks

Back-propagation, feed-forward neural networks are used to predict alpha-helical transmembrane segments of proteins. The networks are trained on the few membrane proteins whose transmembrane alpha-helix domains are known to atomic or nearly atomic resolution. When testing is performed with a jackknife procedure on the proteins of the training set, the fraction of total correct assignments is as high as 0.87, with an average length for the transmembrane segments of 20 residues. The method correctly fails to predict any transmembrane domain for porin, whose transmembrane segments are beta-sheets. When tested on globular proteins, lower and upper limits of 1.6 and 3.5% for a total of 26826 residues are determined for the mispredicted cases, indicating that the predictor is highly specific for alpha-helical domains of membrane proteins. The predictor is also tested on 37 membrane proteins whose transmembrane topology is partially known. The overall accuracy is 0.90, two percentage points higher than that obtained with statistical methods. The reliability of the prediction is 100% for 60% of the total 18242 predicted residues of membrane proteins. Our results show that the local directional information automatically extracted by the neural networks during the training phase plays a key role in determining the accuracy of the prediction.