| Title: | Biomarker Optimal Segmentation System |
| Version: | 1.0.4 |
| Description: | The Biomarker Optimal Segmentation System R package, 'bossR', is designed for precision medicine, helping to identify individual traits using biomarkers. It focuses on determining the most effective cutoff value for a continuous biomarker, which is crucial for categorizing patients into two groups with distinctly different clinical outcomes. The package simultaneously finds the optimal cutoff from given candidate values and tests its significance. Simulation studies demonstrate that 'bossR' offers statistical power and false positive control non-inferior to the permutation approach (considered the gold standard in this field), while being hundreds of times faster. |
| License: | GPL-3 |
| Encoding: | UTF-8 |
| RoxygenNote: | 7.2.3 |
| Imports: | mvtnorm,survival,stats |
| Depends: | R (≥ 2.10), |
| LazyData: | true |
| NeedsCompilation: | no |
| Packaged: | 2024-01-12 19:24:16 UTC; xzhang |
| Author: | Liuyi Lan [aut],
Xing Li  [aut],
Xuanjin Cheng [aut],
Xuekui Zhang
[aut, cre] |
| Maintainer: | Xuekui Zhang <ubcxzhang@gmail.com> |
| Repository: | CRAN |
| Date/Publication: | 2024-01-15 16:00:02 UTC |
Select Optimal cutoff for a biomarker
Description
Given a set of data including survival time ,censor status and Biomarker values, return the Optimal cutoff for the biomarker.
Usage
getOC(data, cutoff, type = 2)
Arguments
data |
A data frame which contains 3 columns for cox regression : survival time, censor status, Biomarker values. 2 columns for linear regression : Y, X. |
cutoff |
Numeric vector of candidate cutoffs. |
type |
A number; if =1, will perform linear regression;if =2(default) will perform cox regerssion. |
Value
Optimal cutoff for the biomarker, the FWER of the model
References
BOSS - Biomarker Optimal Segmentation System
Examples
cutoff=c(56,112,167,223,278,334,389,445)
data(myGene)
getOC(data=myGene,cutoff)
Get regression coefficient
Description
Computes the regression coefficient of certain regression based on certain cutoff.
Usage
getbeta(data, point, type = 2)
Arguments
data |
A data frame which contains 3 columns for cox regression : survival time, censor status, Biomarker values. 2 columns for linear regression : Y, X. |
point |
A number to cut biomarker or X. |
type |
A number; if =1, will perform linear regression; if =2(default) will perform cox regression. |
Value
An object with 3 class: Coefficient beta, number of samples of which the biomarker is greater than the point, standard error of coefficient estimation.
Computes the distribution function of the multivariate normal distribution
Description
Computes the distribution function of the multivariate normal distribution.
Usage
getpvalue(threshold, mu, n, Sigma)
Arguments
threshold |
A number. |
mu |
The mean vector of length n. |
n |
A number indicates dimension. |
Sigma |
The correlation matrix of dimension n. |
Value
The evaluated distribution function
clinical dataset
Description
This data set gives the expression levels of gene data, overall survival time, and censoring status from 500 lung adenocarcinoma cases.
Usage
myGeneFormat
A dataframe containing 500 observations of 3 variables.
Source
raw survival data come from https://tau.cmmt.ubc.ca/cSurvival/project_data/TCGA-LUAD/df_survival_o.csv and raw gene expression data come from https://tau.cmmt.ubc.ca/cSurvival/project_data/TCGA-LUAD/df_gene.csv
References
Xuanjin Cheng, Yongxing Liu, Jiahe Wang, Yujie Chen, Andrew Gordon Robertson, Xuekui Zhang, Steven J M Jones, and Stefan Taubert. (2022) cSurvival: a web resource for biomarker interactions in cancer outcomes and in cell lines. Briefings in Bioinformatics.