Assessing a novel approach for predicting local 3D protein structures from sequence

Abstract

We developed a novel approach for predicting local protein structure from sequence. It relies on the Hybrid Protein Model (HPM), an unsupervised clustering method we previously developed. This model learns 3D protein fragments encoded into a structural alphabet of 16 Protein Blocks (PBs). Here, we focused on 11-residue fragments encoded as series of 7 PBs and used HPM to cluster them according to their local similarities. We thus built a library of 120 overlapping prototypes (mean fragments from each cluster), with good 3D local approximation, i.e., a mean accuracy of 1.61 Å C rmsd.Our prediction method is intended to optimize the exploitation of the sequence-structure relations deduced from this library of long protein fragments. This was achieved by setting up a system of 120 experts, each defined by logistic regression to optimize the discrimination from sequence of a given prototype relative to the others. For a target sequence window, the experts computed probabilities of sequence-structure compatibility for the prototypes and ranked them, proposing the top scorers as structural candidates. Predictions were defined as successful when a prototype less than 2.5 Å from the true local structure was found among those proposed. Our strategy yielded a prediction rate of 51.2% for an average of 4.2 candidates per sequence window. We also proposed a confidence index to estimate prediction quality.Our approach predicts from sequence alone and will thus provide valuable information for proteins without structural homologues. Candidates will also contribute to global structure prediction by fragment assembly.Local Protein Structure Prediction 3

Local Protein Structures

“…This was achieved by setting up a system of experts, each defined by logistic regression and best able to discriminate from sequence a given local structure prototype relative to the others. The experts then computed probabilities for each prototype for a target sequence window, and the top scorers become structural candidates [409]. Recent use of Support Vector Machines coupled with evolutionary data has greatly improved the prediction rates (Bornot et al, in preparation).…”

Analysis of protein contacts into Protein Units

“…In the same way, analysis of PUs in terms of secondary structures did not show any significant tendency in comparison to the entire databank. The Protein Blocks [56,75,85,88,99,[101][102][103][104][105][106][107][108] give a finer description than secondary structures [109], they so give more precise description of protein contacts and even some insights in signature of specific regions of protein loops in the PUs (e.g., PBs h and i).…”

A short survey on protein blocks

“…This innovative approach made it possible to create longer prototypes comprising 10 to 13 residues. (Benros, et al, 2006; Benros, et al, 2003; Benros, et al, 2009; Benros, et al, 2002; de Brevern and Hazout, 2001; de Brevern and Hazout, 2003). This resulted in higher structural variability for the longer fragments through a significant increase in the number of prototypes, e.g ., 100 to 130 prototypes (Benros, et al, 2006; Benros, et al, 2009; de Brevern and Hazout, 2001; de Brevern and Hazout, 2003).…”

“…Our earlier work on PBs have shown that PBs are effective in describing and predicting conformations of long fragments (Benros, et al, 2006; Benros, et al, 2009; Bornot, et al, 2009; de Brevern, et al, 2007; de Brevern and Hazout, 2001; de Brevern and Hazout, 2003; de Brevern, et al, 2002) and short loops (Fourrier, et al, 2004; Tyagi, et al, 2009; Tyagi, et al, 2009), analyzing protein contacts (Faure, et al, 2008), in building a transmembrane protein (de Brevern, 2005; de Brevern, et al, 2009), and in defining a reduced amino acid alphabet to aid design of mutations (Etchebest, et al, 2007). This reduced amino acid alphabet was recently proved suitable for predicting protein families or sub-families and secretory proteins of P. falciparum (Zuo and Li, 2009; Zuo and Li, 2009).…”