The benefit of intrinsic disorder information in neural network prediction of calmodulin binding targets

Timothy R. O'Connor, J. David Lawson, A. Dunker

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Calmodulin is an important calcium dependent signaling protein found in all eukaryotic cells. Binding calcium enables calmodulin to bind its targets: basic, amphipathic α-helices. Such binding regulates the activities of many proteins. Because calmodulin wraps completely around the target helix upon binding, it is hypothesized that disorder of a target helix is an important feature of this process. We have used several sequence derived features of calmodulin binding targets (CBT's), including intrinsic order/disorder predictions, to construct neural networks based on permutations of three or more of these features. The resulting networks demonstrate that the addition of intrinsic order/disorder information always increases the performance of a given neural network predictor. The best predictor generated has a performance of 87.8% true positive prediction and 87.2% true negative prediction.

Original languageEnglish (US)
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Pages296-299
Number of pages4
Volume1
StatePublished - 2002
Externally publishedYes
Event2002 International Joint Conference on Neural Networks (IJCNN '02) - Honolulu, HI, United States
Duration: May 12 2002May 17 2002

Other

Other2002 International Joint Conference on Neural Networks (IJCNN '02)
CountryUnited States
CityHonolulu, HI
Period5/12/025/17/02

Fingerprint

Calmodulin
Neural networks
Order disorder transitions
Calcium
Proteins

ASJC Scopus subject areas

  • Software

Cite this

O'Connor, T. R., Lawson, J. D., & Dunker, A. (2002). The benefit of intrinsic disorder information in neural network prediction of calmodulin binding targets. In Proceedings of the International Joint Conference on Neural Networks (Vol. 1, pp. 296-299)

The benefit of intrinsic disorder information in neural network prediction of calmodulin binding targets. / O'Connor, Timothy R.; Lawson, J. David; Dunker, A.

Proceedings of the International Joint Conference on Neural Networks. Vol. 1 2002. p. 296-299.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

O'Connor, TR, Lawson, JD & Dunker, A 2002, The benefit of intrinsic disorder information in neural network prediction of calmodulin binding targets. in Proceedings of the International Joint Conference on Neural Networks. vol. 1, pp. 296-299, 2002 International Joint Conference on Neural Networks (IJCNN '02), Honolulu, HI, United States, 5/12/02.
O'Connor TR, Lawson JD, Dunker A. The benefit of intrinsic disorder information in neural network prediction of calmodulin binding targets. In Proceedings of the International Joint Conference on Neural Networks. Vol. 1. 2002. p. 296-299
O'Connor, Timothy R. ; Lawson, J. David ; Dunker, A. / The benefit of intrinsic disorder information in neural network prediction of calmodulin binding targets. Proceedings of the International Joint Conference on Neural Networks. Vol. 1 2002. pp. 296-299
@inproceedings{5e656b118dd946549b1a1d00c7607149,
title = "The benefit of intrinsic disorder information in neural network prediction of calmodulin binding targets",
abstract = "Calmodulin is an important calcium dependent signaling protein found in all eukaryotic cells. Binding calcium enables calmodulin to bind its targets: basic, amphipathic α-helices. Such binding regulates the activities of many proteins. Because calmodulin wraps completely around the target helix upon binding, it is hypothesized that disorder of a target helix is an important feature of this process. We have used several sequence derived features of calmodulin binding targets (CBT's), including intrinsic order/disorder predictions, to construct neural networks based on permutations of three or more of these features. The resulting networks demonstrate that the addition of intrinsic order/disorder information always increases the performance of a given neural network predictor. The best predictor generated has a performance of 87.8{\%} true positive prediction and 87.2{\%} true negative prediction.",
author = "O'Connor, {Timothy R.} and Lawson, {J. David} and A. Dunker",
year = "2002",
language = "English (US)",
volume = "1",
pages = "296--299",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",

}

TY - GEN

T1 - The benefit of intrinsic disorder information in neural network prediction of calmodulin binding targets

AU - O'Connor, Timothy R.

AU - Lawson, J. David

AU - Dunker, A.

PY - 2002

Y1 - 2002

N2 - Calmodulin is an important calcium dependent signaling protein found in all eukaryotic cells. Binding calcium enables calmodulin to bind its targets: basic, amphipathic α-helices. Such binding regulates the activities of many proteins. Because calmodulin wraps completely around the target helix upon binding, it is hypothesized that disorder of a target helix is an important feature of this process. We have used several sequence derived features of calmodulin binding targets (CBT's), including intrinsic order/disorder predictions, to construct neural networks based on permutations of three or more of these features. The resulting networks demonstrate that the addition of intrinsic order/disorder information always increases the performance of a given neural network predictor. The best predictor generated has a performance of 87.8% true positive prediction and 87.2% true negative prediction.

AB - Calmodulin is an important calcium dependent signaling protein found in all eukaryotic cells. Binding calcium enables calmodulin to bind its targets: basic, amphipathic α-helices. Such binding regulates the activities of many proteins. Because calmodulin wraps completely around the target helix upon binding, it is hypothesized that disorder of a target helix is an important feature of this process. We have used several sequence derived features of calmodulin binding targets (CBT's), including intrinsic order/disorder predictions, to construct neural networks based on permutations of three or more of these features. The resulting networks demonstrate that the addition of intrinsic order/disorder information always increases the performance of a given neural network predictor. The best predictor generated has a performance of 87.8% true positive prediction and 87.2% true negative prediction.

UR - http://www.scopus.com/inward/record.url?scp=0036075368&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036075368&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0036075368

VL - 1

SP - 296

EP - 299

BT - Proceedings of the International Joint Conference on Neural Networks

ER -