Improving protein secondary-structure prediction by predicting ends of secondary-structure segments

Uros Midic, A. Dunker, Zoran Obradovic

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

4 Citations (Scopus)

Abstract

Motivated by known preferences for certain amino acids in positions around a-helices, we developed neural network-based predictors of both N and C a-helix ends, which achieved about 88% accuracy. We applied a similar approach for predicting the ends of three types of secondary structure segments. The predictors for the ends of H, E and C segments were then used to create input for protein secondary-structure prediction. By incorporating this new type of input, we significantly improved the basic one-stage predictor of protein secondary structure in terms of both per-residue (Q3) accuracy (+0.8%) and segment overlap (SOV3) measure (+1.4).

Original languageEnglish
Title of host publicationProceedings of the 2005 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB '05
Volume2005
StatePublished - 2005
Event2005 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB '05 - La Jolla, CA, United States
Duration: Nov 14 2005Nov 15 2005

Other

Other2005 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB '05
CountryUnited States
CityLa Jolla, CA
Period11/14/0511/15/05

Fingerprint

Proteins
Amino acids
Neural networks

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Midic, U., Dunker, A., & Obradovic, Z. (2005). Improving protein secondary-structure prediction by predicting ends of secondary-structure segments. In Proceedings of the 2005 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB '05 (Vol. 2005). [1594959]

Improving protein secondary-structure prediction by predicting ends of secondary-structure segments. / Midic, Uros; Dunker, A.; Obradovic, Zoran.

Proceedings of the 2005 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB '05. Vol. 2005 2005. 1594959.

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

Midic, U, Dunker, A & Obradovic, Z 2005, Improving protein secondary-structure prediction by predicting ends of secondary-structure segments. in Proceedings of the 2005 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB '05. vol. 2005, 1594959, 2005 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB '05, La Jolla, CA, United States, 11/14/05.
Midic U, Dunker A, Obradovic Z. Improving protein secondary-structure prediction by predicting ends of secondary-structure segments. In Proceedings of the 2005 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB '05. Vol. 2005. 2005. 1594959
Midic, Uros ; Dunker, A. ; Obradovic, Zoran. / Improving protein secondary-structure prediction by predicting ends of secondary-structure segments. Proceedings of the 2005 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB '05. Vol. 2005 2005.
@inproceedings{ad2392448f2f48259a1c538d4b9859df,
title = "Improving protein secondary-structure prediction by predicting ends of secondary-structure segments",
abstract = "Motivated by known preferences for certain amino acids in positions around a-helices, we developed neural network-based predictors of both N and C a-helix ends, which achieved about 88{\%} accuracy. We applied a similar approach for predicting the ends of three types of secondary structure segments. The predictors for the ends of H, E and C segments were then used to create input for protein secondary-structure prediction. By incorporating this new type of input, we significantly improved the basic one-stage predictor of protein secondary structure in terms of both per-residue (Q3) accuracy (+0.8{\%}) and segment overlap (SOV3) measure (+1.4).",
author = "Uros Midic and A. Dunker and Zoran Obradovic",
year = "2005",
language = "English",
isbn = "0780393872",
volume = "2005",
booktitle = "Proceedings of the 2005 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB '05",

}

TY - GEN

T1 - Improving protein secondary-structure prediction by predicting ends of secondary-structure segments

AU - Midic, Uros

AU - Dunker, A.

AU - Obradovic, Zoran

PY - 2005

Y1 - 2005

N2 - Motivated by known preferences for certain amino acids in positions around a-helices, we developed neural network-based predictors of both N and C a-helix ends, which achieved about 88% accuracy. We applied a similar approach for predicting the ends of three types of secondary structure segments. The predictors for the ends of H, E and C segments were then used to create input for protein secondary-structure prediction. By incorporating this new type of input, we significantly improved the basic one-stage predictor of protein secondary structure in terms of both per-residue (Q3) accuracy (+0.8%) and segment overlap (SOV3) measure (+1.4).

AB - Motivated by known preferences for certain amino acids in positions around a-helices, we developed neural network-based predictors of both N and C a-helix ends, which achieved about 88% accuracy. We applied a similar approach for predicting the ends of three types of secondary structure segments. The predictors for the ends of H, E and C segments were then used to create input for protein secondary-structure prediction. By incorporating this new type of input, we significantly improved the basic one-stage predictor of protein secondary structure in terms of both per-residue (Q3) accuracy (+0.8%) and segment overlap (SOV3) measure (+1.4).

UR - http://www.scopus.com/inward/record.url?scp=33847024256&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847024256&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33847024256

SN - 0780393872

SN - 9780780393875

VL - 2005

BT - Proceedings of the 2005 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB '05

ER -