Saved in:
| Main Author: | |
|---|---|
| Format: | Artículo científico |
| Language: | en |
| Published: |
Universidad del Valle
2015
|
| Subjects: | |
| Online Access: | https://www.redalyc.org/articulo.oa?id=291339265006 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- Remote homology detection of proteins using 3D models enriched with physicochemical properties Oscar F. Bedoya Irene Tischer Ingeniería SCOP family Classification 3D structural models remote homology detection physicochemical properties In this paper, a new method for remote protein homology detection called remote-3DP, is presented. The remote-3DPmethod is based on both predicted 3D information and physiochemical properties of amino acids. The remote-3DPmethod considers only 10 structural models to represent a protein and to distinguish between remote homologuesand non-remote homologues in 54 SCOP families. The low dimensionality of the protein representation allows us touse different classification techniques and discover which one works better for each SCOP family. In this paper, weshow that including a physicochemical property along with predicted 3D information into a local structural element,actually improves the accuracy in remote homology detection. The highest ROC score for a set of models thatincludes 3D information and the Hydropathy index reaches 0.953 on the SCOP 1.53 dataset. In addition, a modelthat ensembles the outputs of 10 physicochemical properties is built to make a consensus decision. The consensusstrategy reaches a ROC score of 0.963 on the SCOP 1.53 dataset, surpassing the current methods based on sequencecomposition which accuracy range from 0.87 to 0.92. 2015 artículo científico 0123-3033 https://www.redalyc.org/articulo.oa?id=291339265006 en http://www.redalyc.org/revista.oa?id=2913 Ingeniería y Competitividad application/pdf Universidad del Valle Ingeniería y Competitividad (Colombia) Num.1 Vol.17