Stucture Prediction of Membrane Proteins: is it possible?

Author: R. Casadio
Submitted: Thursday 10th of December 2009 04:21:50 PM
Submitted by: egf
Language: English
Content type: Learning resource
Educational levels: qc2, qc3


In the “omic era” Bioinformatics tools may be used to address the basic problem of genome annotation, when sequences are not identical to other sequences of known structure and/or function in the data bases. Our group ( has implemented machine learning based predictors capable of performing with some success in different tasks, including predictions of the secondary structure of globular and membrane proteins, of the topology of membrane proteins and porins, of stable alpha helical segments suited for protein design. All our predictors take advantage of evolution information derived from the structural alignments of homologous proteins and derived from the sequence and structure databases. A hybrid system based on neural networks and hidden Markov models seems particularly successful in predicting the bonding state of cysteines in proteins scoring as high as 88% and well predicting 84% of the proteins of the testing set. Recently our predictors have been integrated in a package (HUNTER) capable of performing genome-wide analysis of protein sequences and annotating them on the basis of characteristic structural features. Its variant MANHUNTER is specifically implemented to predict signal peptides and discriminate globular from membrane proteins in the human genome. Furthermore, membrane proteins can be classified as inner membrane (all-alpha) and outer membrane (of the beta barrel type) membrane proteins. This work addresses the specific question of estimating the membrane protein content of each chromosome and defining the structural class of proteins annotated hypothetical in the last release.


Similar resources

Loading ...


Original version - English

abstract Casadio_1617.pdf

IMS Metadata


R. Casadio. Stucture Prediction of Membrane Proteins: is it possible?. EUROGENE portal. December 2009. online:



Terms of use

This work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 3.0 Unported License. Read more.