R语言 CSAR包 getThreshold()函数中文帮助文档(中英文对照)

loveR

getThreshold(CSAR)
getThreshold()所属R语言包：CSAR

                                         Calculate the threshold value corresponding to control FDR at a desired level
                                         计算相应的阈值控制在理想水平的FDR

                                         译者：生物统计家园网 机器人LoveR

描述----------Description----------

Calculate the threshold value corresponding to control FDR at a desired level
计算相应的阈值控制在理想水平的FDR


用法----------Usage----------


getThreshold(winscores, permutatedScores, FDR)



参数----------Arguments----------

参数：winscores
Numeric vector with score values obtained from the sigWin function  
sigWin函数获得的得分值的数字向量


参数：permutatedScores
Numeric vector with the permutated read-enrichment score values
与permutated读富集得分值的数字向量


参数：FDR
Numeric value with the desired FDR control  
FDR控制所需的数值


Details

详情----------Details----------

This is a very simple function to obtain the threshold value of our test statistic controlling FDR at a desired level. Other functions implemented in R (eg: multtest) could be more sophisticated. Basically, for each possible threshold value, the proportion of error type I is calculated assuming that the permutated score distribution is a optimal estimation of the score distribution under the null hypothesis. This is, the proportion of permutated scores exceding the considered threshold value is used as an estimation of the error type I of our statisitic. FDR is obtained as the ratio of the proportion of error type I by the proportion of significant tests.
这是一个非常简单的函数来获取所需的水平在我们的测试控制FDR统计阈值。 R中实施的其他功能（如：multtest）可能更复杂。基本上，每一个可能的阈值，错误类型的比例我计算假设的permutated的得分分布是得分分布零假设下的最优估计。这是，permutated exceding认为阈值的分数比例被用来作为一个错误类型我们statisitic我估计。FDR获得的I型错误的重大试验的比例的比例的比例。


值----------Value----------

A table with the columns being:
被列表：


参数：threshold
The threshold value
阈值


参数：p-value
The p-value obtained from the permutated score ditribution
P-值从permutated得分ditribution获得的


参数：FDR
The FDR control obtained using threshold
FDR控制取得使用threshold


作者（S）----------Author(s)----------


Jose M Muino, <a href="mailto:jose.muino@wur.nl">jose.muino@wur.nl</a>



参考文献----------References----------

<h3>See Also</h3>

举例----------Examples----------


##For this example we will use the a subset of the SEP3 ChIP-seq data (Kaufmann, 2009)[＃在这个例子中，我们将使用的SEP3的ChIP-seq的数据的一个子集（考夫曼，2009）]
data("CSAR-dataset");
##We calculate the number of hits for each nucleotide posotion for the control and sample. We do that just for chromosome chr1, and for positions 1 to 10kb[＃我们计算每个核苷酸posotion为控制和样品的点击次数。我们只是做染色体chr1的职位1到10KB]
nhitsS<-mappedReads2Nhits(sampleSEP3_test,file="sampleSEP3_test",chr=c("CHR1v01212004"),chrL=c(10000))
nhitsC<-mappedReads2Nhits(controlSEP3_test,file="controlSEP3_test",chr=c("CHR1v01212004"),chrL=c(10000))


##We calculate a score for each nucleotide position[＃我们计算每个核苷酸的位置得分]
test<-ChIPseqScore(control=nhitsC,sample=nhitsS)

##We calculate the candidate read-enriched regions[我们计算候选人读富集区域的＃]
win<-sigWin(test)


##We calculate two sets of read-enrichment scores through permutation[＃我们计算通过置换两种套读富集分数]
permutatedWinScores(nn=1,sample=sampleSEP3_test,control=controlSEP3_test,fileOutput="test",chr=c("CHR1v01212004"),chrL=c(100000))
permutatedWinScores(nn=2,sample=sampleSEP3_test,control=controlSEP3_test,fileOutput="test",chr=c("CHR1v01212004"),chrL=c(100000))

###Next function will get all permutated score values generated by permutatedWinScores function. [＃下一步的功能将得到所有permutated得分由permutatedWinScores功能产生价值。]
##This represent the score distribution under the null hypotesis and therefore it can be use to control the error of our test.[＃这代表得分空hypotesis下的分布，因此可以用它来控制我们的测试错误。]
nulldist<-getPermutatedWinScores(file="test",nn=1:2)

##From this distribution, several cut-off values can be calculated to control the error of our test. [＃从这个分布，几个临界值，可以计算来控制我们的测试错误。]
##Several functions  in R can be used for this purpose.[＃R中的几个功能，可用于这一目的。]
##In this package we had implemented a simple method for the control of the error based on FDR"[＃在这个包中，我们已实施了FDR基于错误控制的简单方法“]
getThreshold(winscores=win$score,permutatedScores=nulldist,FDR=.01)

转载请注明:出自 生物统计家园网(http://www.biostatistic.net)。


注：
注1：为了方便大家学习，本文档为生物统计家园网机器人LoveR翻译而成，仅供个人R语言学习参考使用，生物统计家园保留版权。
注2：由于是机器人自动翻译，难免有不准确之处，使用时仔细对照中、英文内容进行反复理解，可以帮助R语言的学习。
注3：如遇到不准确之处，请在本贴的后面进行回帖，我们会逐渐进行修订。