Building Portfolios for the Protein Structure Prediction Problem

6 pages•Published: May 15, 2012

Alejandro Arbelaez, Youssef Hamadi and Michèle Sebag

Abstract

This paper, concerned with the protein structure prediction problem, aims at automatically selecting the Constraint Satisfaction algorithm best suited to the problem instance at hand. The contribution is twofold. Firstly, the selection criterion is the quality (minimal cost) in expectation of the solution found after a fixed amount of time, as opposed to the expected runtime. Secondly, the presented approach, based on supervised Machine Learning algorithms, considers the original description of the protein structure problem, as opposed to the features related to the SAT or CSP encoding of the problem.

Keyphrases: algorithm selection, constraint programming, machine learning, protein structure prediction problem

In: Agostino Dovier, Alessandro Dal Palù and Sebastian Will (editors). WCB10. Workshop on Constraint Based Methods for Bioinformatics, vol 4, pages 2-7.

Links:	https://easychair.org/publications/paper/fbP
	https://doi.org/10.29007/dnbk

BibTeX entry

@inproceedings{WCB10:Building_Portfolios_Protein_Structure,
  author    = {Alejandro Arbelaez and Youssef Hamadi and Michèle Sebag},
  title     = {Building Portfolios for the Protein Structure Prediction Problem},
  booktitle = {WCB10. Workshop on Constraint Based Methods for Bioinformatics},
  editor    = {Agostino Dovier and Alessandro Dal Palù and Sebastian Will},
  series    = {EPiC Series in Computing},
  volume    = {4},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {/publications/paper/fbP},
  doi       = {10.29007/dnbk},
  pages     = {2-7},
  year      = {2012}}

Download PDF Open PDF in browser