An hierarchical artificial neural network system for the classification oftransmembrane proteins

This work presents a simple artificial neural network which classifies prot eins into two classes from their sequences alone: the membrane protein clas s and the non-membrane protein class. This may be important in the function al assignment and analysis of open reading frames (ORF's) identified in com plete genomes and, especially, those ORF's that correspond to proteins with unknown function. The network described here has a simple hierarchical fee dforward topology and a limited number of neurons which makes it very fast. By using only information contained in 11 protein sequences, the method wa s able to identify, with 100% accuracy, all membrane proteins with reliable topologies collected from several papers in the literature. Applied to a t est set of 995 globular, water-soluble proteins, the neural network classif ied falsely 23 of them in the membrane protein class (97.7% of correct assi gnment). The method was also applied to the complete SWISS-PROT database wi th considerable success and on ORF's of several complete genomes. The neura l network developed was associated with the PRED-TMR algorithm (Pasquier,C. , Promponas,V.J., Palaios,G.A., Hamodrakas,J.S. and Hamodrakas,S.J., 1999) in a new application package called PRED-TMR2, A WWW server running the PRE D-TMR2 software is available at http://o2.db.uoa.gr/PRED-TMR2.