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
Accuracy versus sensitivity graph of network diffusion method for four different ETA networks based on six-residue (6R), five-residue (5R), multiple six-residue (M6R) and multiple five-residue templates (M5R) for 91 Structural Genomics enzymes with no ETA prediction with any template methods. The numbers inside the parentheses show the area-under-curve for each curve.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Figure 5: Accuracy versus sensitivity graph of network diffusion method for four different ETA networks based on six-residue (6R), five-residue (5R), multiple six-residue (M6R) and multiple five-residue templates (M5R) for 91 Structural Genomics enzymes with no ETA prediction with any template methods. The numbers inside the parentheses show the area-under-curve for each curve.

Mentions: Direct comparisons with default ETA (see the triangles in Figure 4) illustrate that incorporating global information extends the accuracy and sensitivity of predictions over ETA alone. This can also be seen by focusing on the network predictions for the 91 protein structures for which ETA alone had none. As depicted in Figure 5, all of the ETA networks were able to make predictions for these 91 proteins with those based on multiple templates yielding the best performance with around 0.68 area-under-curve (AUC). However, all of the ETA networks' accuracy rose up to 100% at around 21-29% sensitivity, which accounted for 20-23 cases depending on the network (see Figure 5).


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

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

Accuracy versus sensitivity graph of network diffusion method for four different ETA networks based on six-residue (6R), five-residue (5R), multiple six-residue (M6R) and multiple five-residue templates (M5R) for 91 Structural Genomics enzymes with no ETA prediction with any template methods. The numbers inside the parentheses show the area-under-curve for each curve.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Figure 5: Accuracy versus sensitivity graph of network diffusion method for four different ETA networks based on six-residue (6R), five-residue (5R), multiple six-residue (M6R) and multiple five-residue templates (M5R) for 91 Structural Genomics enzymes with no ETA prediction with any template methods. The numbers inside the parentheses show the area-under-curve for each curve.
Mentions: Direct comparisons with default ETA (see the triangles in Figure 4) illustrate that incorporating global information extends the accuracy and sensitivity of predictions over ETA alone. This can also be seen by focusing on the network predictions for the 91 protein structures for which ETA alone had none. As depicted in Figure 5, all of the ETA networks were able to make predictions for these 91 proteins with those based on multiple templates yielding the best performance with around 0.68 area-under-curve (AUC). However, all of the ETA networks' accuracy rose up to 100% at around 21-29% sensitivity, which accounted for 20-23 cases depending on the network (see Figure 5).

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