@article {bioinflmu-555,
	title = {{Confidence measures for protein fold recognition}},
	journal = {Bioinformatics},
	volume = {18},
	number = {6},
	year = {2002},
	pages = {802-812},
	abstract = {MOTIVATION: We present an extensive evaluation of different methods

and criteria to detect remote homologs of a given protein sequence. We

investigate two associated problems: first, to develop a sensitive searching

method to identify possible candidates and, second, to assign a confidence to the

putative candidates in order to select the best one. For searching methods where

the score distributions are known, p-values are used as confidence measure with

great success. For the cases where such theoretical backing is absent, we propose

empirical approximations to p-values for searching procedures. RESULTS: As a

baseline, we review the performances of different methods for detecting remote

protein folds (sequence alignment and threading, with and without sequence

profiles, global and local). The analysis is performed on a large representative

set of protein structures. For fold recognition, we find that methods using

sequence profiles generally perform better than methods using plain sequences,

and that threading methods perform better than sequence alignment methods. In

order to assess the quality of the predictions made, we establish and compare

several confidence measures, including raw scores, z-scores, raw score gaps,

z-score gaps, and different methods of p-value estimation. We work our way from

the theoretically well backed local scores towards more explorative global and

threading scores. The methods for assessing the statistical significance of

predictions are compared using specificity--sensitivity plots. For local

alignment techniques we find that p-value methods work best, albeit

computationally cheaper methods such as those based on score gaps achieve similar

performance. For global methods where no theory is available methods based on

score gaps work best. By using the score gap functions as the measure of

confidence we improve the more powerful fold recognition methods for which

p-values are unavailable. AVAILABILITY: The benchmark set is available upon

request.},
	doi = {10.1093/bioinformatics/18.6.802},
	author = {Ingolf Sommer and Alexander Zien and Niklas Von {\"O}hsen and Ralf Zimmer and Thomas Lengauer}
}