loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Carsten Henneges ; Marc Röttig ; Oliver Kohlbacher and Andreas Zell

Affiliation: Eberhard Karls Universität Tübingen, Germany

Keyword(s): Graphlets, DataMining, Relative Neighbourhood Graph, Secondary Structure Elements, Decision Tree Model Selection.

Related Ontology Subjects/Areas/Topics: Applications ; Artificial Intelligence ; Biomedical Engineering ; Biomedical Signal Processing ; Biometrics ; Computational Intelligence ; Data Manipulation ; Health Engineering and Technology Applications ; Human-Computer Interaction ; Methodologies and Methods ; Neural Networks ; Neurocomputing ; Neuroinformatics and Bioinformatics ; Neurotechnology, Electronics and Informatics ; Pattern Recognition ; Physiological Computing Systems ; Sensor Networks ; Signal Processing ; Soft Computing ; Supervised and Unsupervised Learning ; Theory and Methods

Abstract: Interactions between secondary structure elements (SSEs) in the core of proteins are evolutionary conserved and define the overall fold of proteins. They can thus be used to classify protein families. Using a graph representation of SSE interactions and data mining techniques we identify overrepresented graphlets that can be used for protein classification. We find, in total, 627 significant graphlets within the ICGEB Protein Benchmark database (SCOP40mini) and the Super-Secondary Structure database (SSSDB). Based on graphlets, decision trees are able to predict the four SCOP levels and SSSDB (sub)motif classes with a mean Area Under Curve (AUC) better than 0.89 (5-fold CV). Regularized decision trees reveal that for each classification task about 20 graphlets suffice for reliable predictions. Graphlets composed of five secondary structure interactions are most informative. Finally, we find that graphlets can be predicted from secondary structure using decision trees (5-fold CV) with a Matthews Correlation Coefficient (MCC) reaching up to 0.7. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.236.81.4

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Henneges, C.; Röttig, M.; Kohlbacher, O. and Zell, A. (2010). GRAPHLET DATA MINING OF ENERGETICAL INTERACTION PATTERNS IN PROTEIN 3D STRUCTURES. In Proceedings of the International Conference on Fuzzy Computation and 2nd International Conference on Neural Computation (IJCCI 2010) - ICNC; ISBN 978-989-8425-32-4, SciTePress, pages 190-195. DOI: 10.5220/0003077501900195

@conference{icnc10,
author={Carsten Henneges. and Marc Röttig. and Oliver Kohlbacher. and Andreas Zell.},
title={GRAPHLET DATA MINING OF ENERGETICAL INTERACTION PATTERNS IN PROTEIN 3D STRUCTURES},
booktitle={Proceedings of the International Conference on Fuzzy Computation and 2nd International Conference on Neural Computation (IJCCI 2010) - ICNC},
year={2010},
pages={190-195},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003077501900195},
isbn={978-989-8425-32-4},
}

TY - CONF

JO - Proceedings of the International Conference on Fuzzy Computation and 2nd International Conference on Neural Computation (IJCCI 2010) - ICNC
TI - GRAPHLET DATA MINING OF ENERGETICAL INTERACTION PATTERNS IN PROTEIN 3D STRUCTURES
SN - 978-989-8425-32-4
AU - Henneges, C.
AU - Röttig, M.
AU - Kohlbacher, O.
AU - Zell, A.
PY - 2010
SP - 190
EP - 195
DO - 10.5220/0003077501900195
PB - SciTePress