A hierarchical artificial neural network system for the classification of transmembrane proteins

This work presents a simple artificial neural network which classifies, from their sequences alone, proteins into classes: the membrane protein class and the non-membrane protein class. This is important in the functional assignment and analysis of Open Reading Frames (ORF) identified in complete genomes and, especially those ORF’s that correspond to proteins with unknown function. The network described here have a simple hierarchical feed-forward topology and a limited number of neurons which make it very fast. By using only information contained in 11 protein sequences, the method was able to identify with 100% accuracy all membrane proteins with reliable topologies collected from several papers in the literature. Applied to a test set of 995 soluble proteins, the neural network classifies falsely 23 of them in the membrane protein class (with considerable success of 97.7% of correct assignment). The method was also applied to the whole SWISS-PROT database and on ORF's of several complete genomes. The neural network developed was associated with the PRED-TMR algorithm (Pasquier et al., 1999) in a new application package called PRED-TMR2. A WWW server running the PRED-TMR2 software is available at http://o2.db.uoa.gr/PRED-TMR2