Limits...
Structure-based predictive models for allosteric hot spots.

Demerdash ON, Daily MD, Mitchell JC - PLoS Comput. Biol. (2009)

Bottom Line: Each residue had an associated set of calculated features.We combined the features from each set that produced models with optimal predictive performance.The top 10 models using this hybrid feature set had R = 73-81% and P = 64-71%, the best overall performance of any of the sets of models.

View Article: PubMed Central - PubMed

Affiliation: Biophysics Program, University of Wisconsin-Madison, Madison, Wisconsin, United States of America.

ABSTRACT
In allostery, a binding event at one site in a protein modulates the behavior of a distant site. Identifying residues that relay the signal between sites remains a challenge. We have developed predictive models using support-vector machines, a widely used machine-learning method. The training data set consisted of residues classified as either hotspots or non-hotspots based on experimental characterization of point mutations from a diverse set of allosteric proteins. Each residue had an associated set of calculated features. Two sets of features were used, one consisting of dynamical, structural, network, and informatic measures, and another of structural measures defined by Daily and Gray. The resulting models performed well on an independent data set consisting of hotspots and non-hotspots from five allosteric proteins. For the independent data set, our top 10 models using Feature Set 1 recalled 68-81% of known hotspots, and among total hotspot predictions, 58-67% were actual hotspots. Hence, these models have precision P = 58-67% and recall R = 68-81%. The corresponding models for Feature Set 2 had P = 55-59% and R = 81-92%. We combined the features from each set that produced models with optimal predictive performance. The top 10 models using this hybrid feature set had R = 73-81% and P = 64-71%, the best overall performance of any of the sets of models. Our methods identified hotspots in structural regions of known allosteric significance. Moreover, our predicted hotspots form a network of contiguous residues in the interior of the structures, in agreement with previous work. In conclusion, we have developed models that discriminate between known allosteric hotspots and non-hotspots with high accuracy and sensitivity. Moreover, the pattern of predicted hotspots corresponds to known functional motifs implicated in allostery, and is consistent with previous work describing sparse networks of allosterically important residues.

Show MeSH

Related in: MedlinePlus

Hotspot predictions mapped to the inactive state structure of myosin II.Predictions made by the top 9 highest-precision Hybrid Feature Set models according to the voting scheme for myosin II motor domain mapped onto the inactive state structure (1vom). Refer to Figure 4 above for an explanation of the coloring. Residues that met our criteria for classification as hotspot and included in the independent data set are rendered in van der Waals spheres. Switch-II (a region with high homology to the switch region of G-proteins that couples GTP hydrolysis to effector-domain conformation) residues (454–459) are depicted in van der Waals spheres as well, and colored according to the heat map.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC2748687&req=5

pcbi-1000531-g005: Hotspot predictions mapped to the inactive state structure of myosin II.Predictions made by the top 9 highest-precision Hybrid Feature Set models according to the voting scheme for myosin II motor domain mapped onto the inactive state structure (1vom). Refer to Figure 4 above for an explanation of the coloring. Residues that met our criteria for classification as hotspot and included in the independent data set are rendered in van der Waals spheres. Switch-II (a region with high homology to the switch region of G-proteins that couples GTP hydrolysis to effector-domain conformation) residues (454–459) are depicted in van der Waals spheres as well, and colored according to the heat map.

Mentions: The top-precision Hybrid Feature Set models predicted many residues with known functional significance to be hotspots in the myosin II motor domain (Figure 5; Table S3). The models predicted hotspots in regions implicated in the coupling of ATP hydrolysis with movement along actin filaments, in particular, a large portion of the relay helix proximal to the ATP binding site and the entirety of Switch II. Specifically, the models identified in the relay helix Ile 499 as an intermediate hotspot, and Thr 474, Glu 476, and Phe 506 as strong hotspots, consistent with experimental data showing that mutations at these sites uncouple ATPase activity and motor function [66]–[68]. In addition, Cys 678 in the SH2 helix, which, along with the SH1 and relay helix, holds the converter domain in place, was identified as a hotspot. Mutations at this residue have been found to reduce the velocity of movement of myosin along actin [69]. The fact that the top-precision models predicted all of Switch II residues (454–459) to be hotspots is also noteworthy, for this region, which is close to the nucleotide-binding site, couples ATP hydrolysis with motor activity and is also homologous to the Switch II loop of G-proteins, which connects the GTPase site to the effector binding region, putatively playing a key role in coupling nucleotide hydrolysis to effector affinity and activity [70],[71].


Structure-based predictive models for allosteric hot spots.

Demerdash ON, Daily MD, Mitchell JC - PLoS Comput. Biol. (2009)

Hotspot predictions mapped to the inactive state structure of myosin II.Predictions made by the top 9 highest-precision Hybrid Feature Set models according to the voting scheme for myosin II motor domain mapped onto the inactive state structure (1vom). Refer to Figure 4 above for an explanation of the coloring. Residues that met our criteria for classification as hotspot and included in the independent data set are rendered in van der Waals spheres. Switch-II (a region with high homology to the switch region of G-proteins that couples GTP hydrolysis to effector-domain conformation) residues (454–459) are depicted in van der Waals spheres as well, and colored according to the heat map.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC2748687&req=5

pcbi-1000531-g005: Hotspot predictions mapped to the inactive state structure of myosin II.Predictions made by the top 9 highest-precision Hybrid Feature Set models according to the voting scheme for myosin II motor domain mapped onto the inactive state structure (1vom). Refer to Figure 4 above for an explanation of the coloring. Residues that met our criteria for classification as hotspot and included in the independent data set are rendered in van der Waals spheres. Switch-II (a region with high homology to the switch region of G-proteins that couples GTP hydrolysis to effector-domain conformation) residues (454–459) are depicted in van der Waals spheres as well, and colored according to the heat map.
Mentions: The top-precision Hybrid Feature Set models predicted many residues with known functional significance to be hotspots in the myosin II motor domain (Figure 5; Table S3). The models predicted hotspots in regions implicated in the coupling of ATP hydrolysis with movement along actin filaments, in particular, a large portion of the relay helix proximal to the ATP binding site and the entirety of Switch II. Specifically, the models identified in the relay helix Ile 499 as an intermediate hotspot, and Thr 474, Glu 476, and Phe 506 as strong hotspots, consistent with experimental data showing that mutations at these sites uncouple ATPase activity and motor function [66]–[68]. In addition, Cys 678 in the SH2 helix, which, along with the SH1 and relay helix, holds the converter domain in place, was identified as a hotspot. Mutations at this residue have been found to reduce the velocity of movement of myosin along actin [69]. The fact that the top-precision models predicted all of Switch II residues (454–459) to be hotspots is also noteworthy, for this region, which is close to the nucleotide-binding site, couples ATP hydrolysis with motor activity and is also homologous to the Switch II loop of G-proteins, which connects the GTPase site to the effector binding region, putatively playing a key role in coupling nucleotide hydrolysis to effector affinity and activity [70],[71].

Bottom Line: Each residue had an associated set of calculated features.We combined the features from each set that produced models with optimal predictive performance.The top 10 models using this hybrid feature set had R = 73-81% and P = 64-71%, the best overall performance of any of the sets of models.

View Article: PubMed Central - PubMed

Affiliation: Biophysics Program, University of Wisconsin-Madison, Madison, Wisconsin, United States of America.

ABSTRACT
In allostery, a binding event at one site in a protein modulates the behavior of a distant site. Identifying residues that relay the signal between sites remains a challenge. We have developed predictive models using support-vector machines, a widely used machine-learning method. The training data set consisted of residues classified as either hotspots or non-hotspots based on experimental characterization of point mutations from a diverse set of allosteric proteins. Each residue had an associated set of calculated features. Two sets of features were used, one consisting of dynamical, structural, network, and informatic measures, and another of structural measures defined by Daily and Gray. The resulting models performed well on an independent data set consisting of hotspots and non-hotspots from five allosteric proteins. For the independent data set, our top 10 models using Feature Set 1 recalled 68-81% of known hotspots, and among total hotspot predictions, 58-67% were actual hotspots. Hence, these models have precision P = 58-67% and recall R = 68-81%. The corresponding models for Feature Set 2 had P = 55-59% and R = 81-92%. We combined the features from each set that produced models with optimal predictive performance. The top 10 models using this hybrid feature set had R = 73-81% and P = 64-71%, the best overall performance of any of the sets of models. Our methods identified hotspots in structural regions of known allosteric significance. Moreover, our predicted hotspots form a network of contiguous residues in the interior of the structures, in agreement with previous work. In conclusion, we have developed models that discriminate between known allosteric hotspots and non-hotspots with high accuracy and sensitivity. Moreover, the pattern of predicted hotspots corresponds to known functional motifs implicated in allostery, and is consistent with previous work describing sparse networks of allosterically important residues.

Show MeSH
Related in: MedlinePlus