Limits...
Function prediction from networks of local evolutionary similarity in protein structure.

Erdin S, Venner E, Lisewski AM, Lichtarge O - BMC Bioinformatics (2013)

Bottom Line: One proven computational strategy has been to group a few key functional amino acids into templates and search for these templates in other protein structures, so as to transfer function when a match is found.To this end, we previously developed Evolutionary Trace Annotation (ETA) and showed that diffusing known annotations over a network of template matches on a structural genomic scale improved predictions of function.We improve the accuracy and sensitivity of predictions by using multiple templates per protein structure when constructing networks of ETA matches and diffusing annotations.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Molecular and Human Genetics, Baylor College of Medicine, One Baylor Plaza, Houston, Texas 77030, USA.

ABSTRACT

Background: Annotating protein function with both high accuracy and sensitivity remains a major challenge in structural genomics. One proven computational strategy has been to group a few key functional amino acids into templates and search for these templates in other protein structures, so as to transfer function when a match is found. To this end, we previously developed Evolutionary Trace Annotation (ETA) and showed that diffusing known annotations over a network of template matches on a structural genomic scale improved predictions of function. In order to further increase sensitivity, we now let each protein contribute multiple templates rather than just one, and also let the template size vary.

Results: Retrospective benchmarks in 605 Structural Genomics enzymes showed that multiple templates increased sensitivity by up to 14% when combined with single template predictions even as they maintained the accuracy over 91%. Diffusing function globally on networks of single and multiple template matches marginally increased the area under the ROC curve over 0.97, but in a subset of proteins that could not be annotated by ETA, the network approach recovered annotations for the most confident 20-23 of 91 cases with 100% accuracy.

Conclusions: We improve the accuracy and sensitivity of predictions by using multiple templates per protein structure when constructing networks of ETA matches and diffusing annotations.

Show MeSH
View of a sub-network around 2b83A (center, dark border). Red links are direct matches based multiple six-residue ETA and grey links are secondary connections. Proteins are represented by circles of different colors that denote the enzymatic function (red: EC 1.1.1.1, pink: EC 1.1.1.2, orange: EC 1.1.1.95, brown: EC 1.1.1.47, yellow: EC 1.1.1.103, lavender: EC 1.1.1.90). The network diffusion model is able to make a correct prediction in this case due to the weight of the edges and proximity of correct functional labels in the network to 2b83A.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3584919&req=5

Figure 6: View of a sub-network around 2b83A (center, dark border). Red links are direct matches based multiple six-residue ETA and grey links are secondary connections. Proteins are represented by circles of different colors that denote the enzymatic function (red: EC 1.1.1.1, pink: EC 1.1.1.2, orange: EC 1.1.1.95, brown: EC 1.1.1.47, yellow: EC 1.1.1.103, lavender: EC 1.1.1.90). The network diffusion model is able to make a correct prediction in this case due to the weight of the edges and proximity of correct functional labels in the network to 2b83A.

Mentions: The gene ahd from the bacterium clostridium beijerinckii (PDB 2b83; chain A) [32]highlights the benefit of ETA networks. ETA makes no prediction because of a four apiece tie between matches to NAD-dependent alcohol dehydrogenase activity (EC 1.1.1.1) and to NADP-dependent alcohol dehydrogenase activity (EC 1.1.1.2.). But, when edge weights are taken into account by the network, the stronger connectivity to nodes labelled with EC 1.1.1.2 break the tie and give the edge, correctly, to this annotation. The confidence score is moderate (0.5), reflecting the difficulty of disentangling this dense cluster of matches (Figure 6).


Function prediction from networks of local evolutionary similarity in protein structure.

Erdin S, Venner E, Lisewski AM, Lichtarge O - BMC Bioinformatics (2013)

View of a sub-network around 2b83A (center, dark border). Red links are direct matches based multiple six-residue ETA and grey links are secondary connections. Proteins are represented by circles of different colors that denote the enzymatic function (red: EC 1.1.1.1, pink: EC 1.1.1.2, orange: EC 1.1.1.95, brown: EC 1.1.1.47, yellow: EC 1.1.1.103, lavender: EC 1.1.1.90). The network diffusion model is able to make a correct prediction in this case due to the weight of the edges and proximity of correct functional labels in the network to 2b83A.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3584919&req=5

Figure 6: View of a sub-network around 2b83A (center, dark border). Red links are direct matches based multiple six-residue ETA and grey links are secondary connections. Proteins are represented by circles of different colors that denote the enzymatic function (red: EC 1.1.1.1, pink: EC 1.1.1.2, orange: EC 1.1.1.95, brown: EC 1.1.1.47, yellow: EC 1.1.1.103, lavender: EC 1.1.1.90). The network diffusion model is able to make a correct prediction in this case due to the weight of the edges and proximity of correct functional labels in the network to 2b83A.
Mentions: The gene ahd from the bacterium clostridium beijerinckii (PDB 2b83; chain A) [32]highlights the benefit of ETA networks. ETA makes no prediction because of a four apiece tie between matches to NAD-dependent alcohol dehydrogenase activity (EC 1.1.1.1) and to NADP-dependent alcohol dehydrogenase activity (EC 1.1.1.2.). But, when edge weights are taken into account by the network, the stronger connectivity to nodes labelled with EC 1.1.1.2 break the tie and give the edge, correctly, to this annotation. The confidence score is moderate (0.5), reflecting the difficulty of disentangling this dense cluster of matches (Figure 6).

Bottom Line: One proven computational strategy has been to group a few key functional amino acids into templates and search for these templates in other protein structures, so as to transfer function when a match is found.To this end, we previously developed Evolutionary Trace Annotation (ETA) and showed that diffusing known annotations over a network of template matches on a structural genomic scale improved predictions of function.We improve the accuracy and sensitivity of predictions by using multiple templates per protein structure when constructing networks of ETA matches and diffusing annotations.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Molecular and Human Genetics, Baylor College of Medicine, One Baylor Plaza, Houston, Texas 77030, USA.

ABSTRACT

Background: Annotating protein function with both high accuracy and sensitivity remains a major challenge in structural genomics. One proven computational strategy has been to group a few key functional amino acids into templates and search for these templates in other protein structures, so as to transfer function when a match is found. To this end, we previously developed Evolutionary Trace Annotation (ETA) and showed that diffusing known annotations over a network of template matches on a structural genomic scale improved predictions of function. In order to further increase sensitivity, we now let each protein contribute multiple templates rather than just one, and also let the template size vary.

Results: Retrospective benchmarks in 605 Structural Genomics enzymes showed that multiple templates increased sensitivity by up to 14% when combined with single template predictions even as they maintained the accuracy over 91%. Diffusing function globally on networks of single and multiple template matches marginally increased the area under the ROC curve over 0.97, but in a subset of proteins that could not be annotated by ETA, the network approach recovered annotations for the most confident 20-23 of 91 cases with 100% accuracy.

Conclusions: We improve the accuracy and sensitivity of predictions by using multiple templates per protein structure when constructing networks of ETA matches and diffusing annotations.

Show MeSH