# sw.rob: Robustness Calculation for Smith-Waterman Algorithm In cgh: Microarray CGH analysis using the Smith-Waterman algorithm

## Description

Calculate robustness scores to evaluate how sensitive to the threshold value is the localisation of the highest-scoring island identified by the Smith-Waterman algorithm

## Usage

 ```1 2 3``` ``` sw.rob(x, lo.func = function(x) median(x), hi.func = function(x) median(x) + .4 * mad(x), prec = 100) ```

## Arguments

 `x` a vector of real values `lo.func` a function for the lowest threshold value `hi.func` a function for the highest threshold value `prec` the precision of the calculation.

## Details

This function performs a sensitivity analysis to determine the robustness the localisation of the highest-scoring island obtained by the Smith-Waterman algorithm to different values of the threshold. The Smith-Waterman algorithm is run repeatedly, each time using a different threshold value. The range of threshold values used is that obtained by dividing ( lo.func(x), hi.func(x) ) into ‘prec’ equal intervals. The robustness is calculated as the proportion of times that a particular chromosomal location falls within the highest-scoring island.

## Value

A vector of robustness values equal in length to the input vector.

T.S.Price

## References

Price TS, et al. SW-ARRAY: a dynamic programming solution for the identification of copy-number changes in genomic DNA using array comparative genome hybridization data. Nucl Acids Res. 2005;33(11):3455-3464.

`sw`
 ``` 1 2 3 4 5 6 7 8 9 10``` ```## simluate vector of logratios set.seed(3) logratio <- c(rnorm(20) - 1, rnorm(20)) ## invert sign of values and subtract threshold to ensure negative mean x <- sw.threshold(logratio, function(x) median(x) + .2 * mad(x), -1) ## calculate robustness values sw.rob(x) ```