Exact Protein Structure Classification Using the Maximum Contact Map Overlap Metric

Abstract : In this work we propose a new distance measure for compar-ing two protein structures based on their contact map representations. We show that our novel measure, which we refer to as the maximum con-tact map overlap (max-CMO) metric, satisfies all properties of a metric on the space of protein representations. Having a metric in that space allows to avoid pairwise comparisons on the entire database and thus to significantly accelerate exploring the protein space compared to non-metric spaces. We show on a gold-standard classification benchmark set of 6, 759 and 67, 609 proteins, resp., that our exact k-nearest neighbor scheme classifies up to 95% and 99% of queries correctly. Our k-NN classification thus provides a promising approach for the automatic clas-sification of protein structures based on contact map overlap.
Type de document :
Communication dans un congrès
1st International Conference on Algorithms for Computational Biology, AlCoB 2014, Jul 2014, Tarragona, Spain. pp.262 - 273, 2014, 〈10.1007/978-3-319-07953-0_21〉
Liste complète des métadonnées

Littérature citée [19 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01093803
Contributeur : Mathilde Le Boudic-Jamin <>
Soumis le : jeudi 11 décembre 2014 - 10:50:05
Dernière modification le : mercredi 11 avril 2018 - 01:51:31
Document(s) archivé(s) le : jeudi 12 mars 2015 - 10:20:51

Fichier

dominance_k_NN_final.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Inken Wohlers, Mathilde Le Boudic-Jamin, Hristo Djidjev, Gunnar W. Klau, Rumen Andonov. Exact Protein Structure Classification Using the Maximum Contact Map Overlap Metric. 1st International Conference on Algorithms for Computational Biology, AlCoB 2014, Jul 2014, Tarragona, Spain. pp.262 - 273, 2014, 〈10.1007/978-3-319-07953-0_21〉. 〈hal-01093803〉

Partager

Métriques

Consultations de la notice

426

Téléchargements de fichiers

171