1简介

方法中可用的功能a4Classif包中。

此包包含用于分类的Affymetrix微阵列数据,存储在一个ExpressionSet.该软件包集成在自动Affymetrix阵列分析软件包套件中。

##加载所需的包:a4Core
##加载所需的包:a4Preproc
## ## a4Classif版本1.44.0
##加载所需的包:Biobase
##加载所需的包:BiocGenerics
## ##附加包:“BiocGenerics”
以下对象从'package:stats'中屏蔽:## ## IQR, mad, sd, var, xtabs
##以下对象从'package:base'中屏蔽:## ## Filter, Find, Map, Position, Reduce, anyduplication, append, ## as.data.frame, basename, cbind, colnames, dirname, do。调用,## duplicate eval evalq get grep grepl, intersect, is。Unsorted, ## lapply, mapply, match, mget, order, paste, pmax, pmax.int, pmin, ## pmin.int, rank, rbind, rownames, sapply, setdiff, sort, table, ## tapply, union, unique, unsplit,其中。马克斯,which.min
##欢迎访问Bioconductor ## ##小插图包含介绍性材料;查看## 'browseVignettes()'。要引用Bioconductor,请参见##“citation(“Biobase”)”,以及软件包的“citation(“pkgname”)”。

为了演示包的功能,使用所有使用数据集。基因被注释多亏了addGeneInfo的效用函数a4Preproc包中。

data(ALL, package = "ALL") ALL <- addGeneInfo(ALL)
##加载所需包:hgu95av2.db
##加载所需的包:AnnotationDbi
##加载所需的包:stats4
##加载所需的包:IRanges
##加载所需的包:S4Vectors
## ##附加包:“S4Vectors”
以下对象从'package:base'中屏蔽:## ## I,展开。网格,unname
##加载所需的包:org.Hs.eg.db
# #
# #
ALL$BTtype <- as.factor(substr(ALL$BT,0,1))

2分类微阵列数据

2.1套索回归

resultLasso <- lassoClass(object = ALL, groups = "BTtype") plot(resultLasso, label = TRUE, main = "Lasso系数与惩罚程度的关系。")

topTable(resultLasso, n = 15)
套索选择了16个基因。前15个基因是:## ##基因因数38319_at CD3D 0.95966733 ## 35016_at CD74 -0.60928095 ## 37563_at SH2D1A 0.49240967 ## 35792_at MGLL 0.46856925 ## 37563_at SRGAP3 0.266489240 ## 38917_at YME1L1 0.251000775 ## 40278_at GGA2 -0.25017550 ## 41164_at IGHM -0.12387272 ## 41409_at THEMIS2 -0.10581122 ## 38242_at BLNK -0.10309606 ## 35523_at HPGDS 0.10169706 ## 38949_at PRKCQ 0.07832802 ## 33316_at TOX 0.06963509 ## 33839_at ITPR2 0.05801832 ## 40570_at FOXO1 -0.04858863

2.2PAM回归

resultPam <- pamClass(object = ALL, groups = "BTtype") plot(resultPam, main = "Pam错误分类错误与基因数量。")

topTable(resultPam, n = 15)
帕姆选择了1个基因。排名前15位的基因为:## ## GeneSymbol B.score T.score av.rank.in.CV prop. selective .in. cv ## 38319_at CD3D -0.1693 0.4875 1 1
confusionMatrix (resultPam)
##预测##真实B T ## B 95 0 ## T 1 32

2.3随机森林

#由于计算时间原因,只选择数据的一个子集all子集<- ALL[sample.int(n = nrow(ALL), size = 100, replace = FALSE),] resultRf <- rfClass(object = all子集,groups = "BTtype") plot(resultRf)

topTable(resultRf, n = 15)
##随机森林选择7个基因。排名前15位的基因是:## ## GeneSymbol ## 32236_at UBE2G2 ## 33453_at PTPN18 ## 35663_at NPTX2 ## 38802_at PGRMC1 ## 39317_at CMAHP ## 39721_at EFNB1 ## 914_g_at ERG

2.4ROC曲线

ROCcurve(gene = "ABL1", object = ALL, groups = "BTtype")
## ROCcurve(gene = "ABL1", object = ALL, groups = "BTtype"):基因ABL1对应6个探针集;图上只显示了第一个探针集(1635_at)。

3.附录

3.1会话信息

## R版本4.2.0 RC (2022-04-19 r82224) ##平台:x86_64-pc-linux-gnu(64位)##运行在Ubuntu 20.04.4 LTS ## ##矩阵产品:默认## BLAS: /home/biocbuild/bbs-3.15-bioc/R/lib/libRblas。/home/biocbuild/bbs-3.15-bioc/R/lib/libRlapack。所以## ## locale: ## [1] LC_CTYPE=en_US。UTF-8 LC_NUMERIC=C LC_TIME=en_GB LC_COLLATE=C LC_MONETARY=en_US。utf - 8 LC_MESSAGES = en_US。utf - 8 LC_PAPER = en_US。UTF-8 LC_NAME=C LC_ADDRESS=C LC_TELEPHONE=C LC_MEASUREMENT=en_US。UTF-8 LC_IDENTIFICATION=C ## ##附加的基础包:## [1]stats4 stats graphics grDevices utils datasets methods base ## ##其他附加包:## [1]hgu95av2.db_3.13.0 org. hs . gg .db_3.15.0 AnnotationDbi_1.58.0 IRanges_2.30.0 S4Vectors_0.34.0 ALL_1.37.0 Biobase_2.56.0 BiocGenerics_0.42.0 a4Classif_1.44.0 a4Preproc_1.44.0 a4Core_1.44.0 ## ##通过命名空间加载(且未附加):## [1] Rcpp_1.0.8.3 lattice_0.20-45 png_0.1-7 Biostrings_2.64.0 glmnet_4.1-4 digest_0.6.29 foreach_1.5.2 R6_2.5.1 GenomeInfoDb_1.32.0 RSQLite_2.2.12 evaluate_0.15 httr_1.4.2 highr_0.9 zlibbioc_1.42.0 rlang_1.0.2 jquerylib_0.1.4 blob_1.2.3 Matrix_1.4-1 rmarkdown_2.14 splines_4.2.0 string_1 .4.0 ## [22] RCurl_1.98-1.6 bit_4.0.4 compiler_4.2.0 xfun_0.30 pkgconfig_2.0.3 shape_1.4.6 htmltools_0.5.2 KEGGREST_1.36.0 GenomeInfoDbData_1.2.8 varSelRF_0.7-8 codetools_0.2-18 randomforest_4 .1 crayon_1.5.1bitops_1.0-7 grid_4.2.0 jsonlite_1.8.0 DBI_1.1.2 magrittr_2.0.3 cli_3.3.0 stringi_1.7.6 cachem_1.0.6 ## [43] XVector_0.36.0 rocr_1 . 11 bslib_0.3.1 vctrs_0.4.1 iterators_1.0.14 tools_4.2.0 bit64_4.0.5 pamr_1.5.1 parallel_4.2.0 fastmap_1.1.0 survivval_3 .3 yaml_2.3.5 cluster_2.1.3 memoise_2.0.1 knitr_1.38 sass_0.4.1