Limits...
Predictions of hot spot residues at protein-protein interfaces using support vector machines.

Lise S, Buchan D, Pontil M, Jones DT - PLoS ONE (2011)

Bottom Line: These are the amino acid types on which the original model did not perform well.We have therefore developed two additional SVM classifiers, specifically optimised for these cases.HSPred reaches an overall precision and recall respectively of 61% and 69%, which roughly corresponds to a 10% improvement.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Science, University College London, London, United Kingdom.

ABSTRACT
Protein-protein interactions are critically dependent on just a few 'hot spot' residues at the interface. Hot spots make a dominant contribution to the free energy of binding and they can disrupt the interaction if mutated to alanine. Here, we present HSPred, a support vector machine(SVM)-based method to predict hot spot residues, given the structure of a complex. HSPred represents an improvement over a previously described approach (Lise et al, BMC Bioinformatics 2009, 10:365). It achieves higher accuracy by treating separately predictions involving either an arginine or a glutamic acid residue. These are the amino acid types on which the original model did not perform well. We have therefore developed two additional SVM classifiers, specifically optimised for these cases. HSPred reaches an overall precision and recall respectively of 61% and 69%, which roughly corresponds to a 10% improvement. An implementation of the described method is available as a web server at http://bioinf.cs.ucl.ac.uk/hspred. It is free to non-commercial users.

Show MeSH

Related in: MedlinePlus

Schematic overview of protein structural regions which define the different energy contributions.The red filled area, (a), corresponds to side-chain atoms of the mutated residue; the red and blue striped regions, (b) and (c) respectively, correspond to atoms within  of the  of the mutated residue. We distinguish  types of interactions: side-chain inter-molecular between (a) and (c), environment inter-molecular between (b) and (c), side-chain intra-molecular between (a) and (b).
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC3046169&req=5

pone-0016774-g001: Schematic overview of protein structural regions which define the different energy contributions.The red filled area, (a), corresponds to side-chain atoms of the mutated residue; the red and blue striped regions, (b) and (c) respectively, correspond to atoms within of the of the mutated residue. We distinguish types of interactions: side-chain inter-molecular between (a) and (c), environment inter-molecular between (b) and (c), side-chain intra-molecular between (a) and (b).

Mentions: The problem we have investigated is the prediction of hot spot residues at a protein-protein interface using a machine learning approach. As input variables, we have considered basic energy terms (van der Waals, hydrogen bond, electrostatic and desolvation potentials) calculated from the complex structure. We have distinguished contributions from different structural regions in the complex, leading to distinct types of interactions: side-chain inter-molecular, environment inter-molecular and side-chain intra-molecular (see Figure 1). To each of them, we have associated input features, corresponding to the energy terms above. In total therefore there are input features but some of them have not been included in our models because scarcely informative (see Materials and Methods for more details). Support Vector Machines (SVMs) have then be used to learn from a training set to classify residues as hot spots or non hot spots .


Predictions of hot spot residues at protein-protein interfaces using support vector machines.

Lise S, Buchan D, Pontil M, Jones DT - PLoS ONE (2011)

Schematic overview of protein structural regions which define the different energy contributions.The red filled area, (a), corresponds to side-chain atoms of the mutated residue; the red and blue striped regions, (b) and (c) respectively, correspond to atoms within  of the  of the mutated residue. We distinguish  types of interactions: side-chain inter-molecular between (a) and (c), environment inter-molecular between (b) and (c), side-chain intra-molecular between (a) and (b).
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC3046169&req=5

pone-0016774-g001: Schematic overview of protein structural regions which define the different energy contributions.The red filled area, (a), corresponds to side-chain atoms of the mutated residue; the red and blue striped regions, (b) and (c) respectively, correspond to atoms within of the of the mutated residue. We distinguish types of interactions: side-chain inter-molecular between (a) and (c), environment inter-molecular between (b) and (c), side-chain intra-molecular between (a) and (b).
Mentions: The problem we have investigated is the prediction of hot spot residues at a protein-protein interface using a machine learning approach. As input variables, we have considered basic energy terms (van der Waals, hydrogen bond, electrostatic and desolvation potentials) calculated from the complex structure. We have distinguished contributions from different structural regions in the complex, leading to distinct types of interactions: side-chain inter-molecular, environment inter-molecular and side-chain intra-molecular (see Figure 1). To each of them, we have associated input features, corresponding to the energy terms above. In total therefore there are input features but some of them have not been included in our models because scarcely informative (see Materials and Methods for more details). Support Vector Machines (SVMs) have then be used to learn from a training set to classify residues as hot spots or non hot spots .

Bottom Line: These are the amino acid types on which the original model did not perform well.We have therefore developed two additional SVM classifiers, specifically optimised for these cases.HSPred reaches an overall precision and recall respectively of 61% and 69%, which roughly corresponds to a 10% improvement.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Science, University College London, London, United Kingdom.

ABSTRACT
Protein-protein interactions are critically dependent on just a few 'hot spot' residues at the interface. Hot spots make a dominant contribution to the free energy of binding and they can disrupt the interaction if mutated to alanine. Here, we present HSPred, a support vector machine(SVM)-based method to predict hot spot residues, given the structure of a complex. HSPred represents an improvement over a previously described approach (Lise et al, BMC Bioinformatics 2009, 10:365). It achieves higher accuracy by treating separately predictions involving either an arginine or a glutamic acid residue. These are the amino acid types on which the original model did not perform well. We have therefore developed two additional SVM classifiers, specifically optimised for these cases. HSPred reaches an overall precision and recall respectively of 61% and 69%, which roughly corresponds to a 10% improvement. An implementation of the described method is available as a web server at http://bioinf.cs.ucl.ac.uk/hspred. It is free to non-commercial users.

Show MeSH
Related in: MedlinePlus