Comparative analysis of binary logistic regression to artificial neural networks in predicting precursor sequence cleavage

Allison Tegge, Sandra Luisa Rodriguez-Zas, Jonathan V Sweedler, Bruce Southey

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

Abstract

Bioinformatic predictions of neuropeptides resulting from enzymatic cleavages of precursors enable a range of follow-up studies that are aided by accurate predictions. A comparative study of the performance of complementary cleavage prediction models has been undertaken. Binary logistic and artificial neural network (ANN) models were created using various strategies and trained and tested on bovine and rat precursors with experimental cleavage information. Multiple criteria were used to compare 4 logistic regression models with varying properties and 8 ANN with varying structures. All models had high specificity (>90%) and sensitivity ranged from 68% to 100%. ANN based on well-represented amino acid locations performed similarly or slightly worse than networks based on all amino acid locations. Logistic parameter estimates aided in the identification of amino acids associated with cleavage. No model was superior across data sets and thus, prediction of neuropeptides should rely on multiple model specifications and comprehensive training data sets.

Original languageEnglish (US)
Title of host publicationProceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW
Pages101-108
Number of pages8
DOIs
StatePublished - 2007
Event2007 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW - San Jose, CA, United States
Duration: Nov 2 2007Nov 4 2007

Other

Other2007 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW
CountryUnited States
CitySan Jose, CA
Period11/2/0711/4/07

Fingerprint

Logistics
Neural networks
Amino acids
Bioinformatics
Rats
Identification (control systems)
Specifications
Neuropeptides

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Tegge, A., Rodriguez-Zas, S. L., Sweedler, J. V., & Southey, B. (2007). Comparative analysis of binary logistic regression to artificial neural networks in predicting precursor sequence cleavage. In Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW (pp. 101-108). [4425407] https://doi.org/10.1109/BIBMW.2007.4425407

Comparative analysis of binary logistic regression to artificial neural networks in predicting precursor sequence cleavage. / Tegge, Allison; Rodriguez-Zas, Sandra Luisa; Sweedler, Jonathan V; Southey, Bruce.

Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW. 2007. p. 101-108 4425407.

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

Tegge, A, Rodriguez-Zas, SL, Sweedler, JV & Southey, B 2007, Comparative analysis of binary logistic regression to artificial neural networks in predicting precursor sequence cleavage. in Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW., 4425407, pp. 101-108, 2007 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW, San Jose, CA, United States, 11/2/07. https://doi.org/10.1109/BIBMW.2007.4425407
Tegge A, Rodriguez-Zas SL, Sweedler JV, Southey B. Comparative analysis of binary logistic regression to artificial neural networks in predicting precursor sequence cleavage. In Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW. 2007. p. 101-108. 4425407 https://doi.org/10.1109/BIBMW.2007.4425407
Tegge, Allison ; Rodriguez-Zas, Sandra Luisa ; Sweedler, Jonathan V ; Southey, Bruce. / Comparative analysis of binary logistic regression to artificial neural networks in predicting precursor sequence cleavage. Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW. 2007. pp. 101-108
@inproceedings{7969bdb678e449b7989c11bf2f559233,
title = "Comparative analysis of binary logistic regression to artificial neural networks in predicting precursor sequence cleavage",
abstract = "Bioinformatic predictions of neuropeptides resulting from enzymatic cleavages of precursors enable a range of follow-up studies that are aided by accurate predictions. A comparative study of the performance of complementary cleavage prediction models has been undertaken. Binary logistic and artificial neural network (ANN) models were created using various strategies and trained and tested on bovine and rat precursors with experimental cleavage information. Multiple criteria were used to compare 4 logistic regression models with varying properties and 8 ANN with varying structures. All models had high specificity (>90{\%}) and sensitivity ranged from 68{\%} to 100{\%}. ANN based on well-represented amino acid locations performed similarly or slightly worse than networks based on all amino acid locations. Logistic parameter estimates aided in the identification of amino acids associated with cleavage. No model was superior across data sets and thus, prediction of neuropeptides should rely on multiple model specifications and comprehensive training data sets.",
author = "Allison Tegge and Rodriguez-Zas, {Sandra Luisa} and Sweedler, {Jonathan V} and Bruce Southey",
year = "2007",
doi = "10.1109/BIBMW.2007.4425407",
language = "English (US)",
isbn = "9781424416042",
pages = "101--108",
booktitle = "Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW",

}

TY - GEN

T1 - Comparative analysis of binary logistic regression to artificial neural networks in predicting precursor sequence cleavage

AU - Tegge, Allison

AU - Rodriguez-Zas, Sandra Luisa

AU - Sweedler, Jonathan V

AU - Southey, Bruce

PY - 2007

Y1 - 2007

N2 - Bioinformatic predictions of neuropeptides resulting from enzymatic cleavages of precursors enable a range of follow-up studies that are aided by accurate predictions. A comparative study of the performance of complementary cleavage prediction models has been undertaken. Binary logistic and artificial neural network (ANN) models were created using various strategies and trained and tested on bovine and rat precursors with experimental cleavage information. Multiple criteria were used to compare 4 logistic regression models with varying properties and 8 ANN with varying structures. All models had high specificity (>90%) and sensitivity ranged from 68% to 100%. ANN based on well-represented amino acid locations performed similarly or slightly worse than networks based on all amino acid locations. Logistic parameter estimates aided in the identification of amino acids associated with cleavage. No model was superior across data sets and thus, prediction of neuropeptides should rely on multiple model specifications and comprehensive training data sets.

AB - Bioinformatic predictions of neuropeptides resulting from enzymatic cleavages of precursors enable a range of follow-up studies that are aided by accurate predictions. A comparative study of the performance of complementary cleavage prediction models has been undertaken. Binary logistic and artificial neural network (ANN) models were created using various strategies and trained and tested on bovine and rat precursors with experimental cleavage information. Multiple criteria were used to compare 4 logistic regression models with varying properties and 8 ANN with varying structures. All models had high specificity (>90%) and sensitivity ranged from 68% to 100%. ANN based on well-represented amino acid locations performed similarly or slightly worse than networks based on all amino acid locations. Logistic parameter estimates aided in the identification of amino acids associated with cleavage. No model was superior across data sets and thus, prediction of neuropeptides should rely on multiple model specifications and comprehensive training data sets.

UR - http://www.scopus.com/inward/record.url?scp=44949250821&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44949250821&partnerID=8YFLogxK

U2 - 10.1109/BIBMW.2007.4425407

DO - 10.1109/BIBMW.2007.4425407

M3 - Conference contribution

AN - SCOPUS:44949250821

SN - 9781424416042

SP - 101

EP - 108

BT - Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW

ER -