1Instalation

if (!require("BiocManager")) install.packages("BiocManager") BiocManager::install("glmSparseNet")

2需要包

库(dplyr)库(Matrix)库(ggplot2)库(forcats)库(parallel)库(reshape2)库(survival)库(VennDiagram)库(futile.logger)库(curatedTCGAData)库(TCGAutils)库(glmSparseNet) # #. log调试包。值< - flog.layout(布局。格式(“[~ l] ~ m”)).Last。value <- glmSparseNet:::show.message(FALSE) #设置ggplot2默认主题为最小theme_set(ggplot2::theme_minimal())

3.概述

这个小插图使用STRING数据库(https://string-db.org/)的蛋白质-蛋白质相互作用作为基于网络的惩罚器在广义线性模型使用乳腺癌样本数据集。

度向量是手动计算的，以考虑到STRING数据库中不存在的基因，因为这些基因不会有任何相互作用，即边。

#没有在vignette中计算，因为下载和处理all.interaction .700 <- stringDBhomoSapiens(score_threshold = 700) string.network <- buildStringNetwork(all.interaction .700, use.names = 'external')

4构建网络矩阵

构建一个包含网络的稀疏矩阵对象。

string.network.undirected <- string.network + Matrix::t(string.network) string.network.undirected <- (string.network.undirected != 0) * 1

5网络统计信息

## [INFO]有向图(score_threshold = 700) ## [INFO] *总边数:225330 ## [INFO] *惟一蛋白:11033 ## [INFO] *每蛋白边数:20.423276 ## [INFO] ## [INFO]无向图(score_threshold = 700) ## [INFO] *总边数:225209 ## [INFO] *惟一蛋白:11033 ## [INFO] *每蛋白边数:20.412309

## [INFO]程度总结:## ##最小第1节，中值平均第3节，最大第3节。## 1.00 3.00 13.00 40.83 43.00 4175.00

Qplot (degree.network[degree.network <= quantile(degree.network, probs = .99999)]， geom = 'histogram'， fill = my.colors(2)， bins = 100) + theme(legend. network[degree.network <=。position = 'none') + xlab('度(直到99.999%分位数)')

6glmSparseNet

• 数据集从curatedTCGAdata

brca <- curatedTCGAData(disease ecode = " brca "， assays = "RNASeq2GeneNorm"， version = "1.1.38"， dry.run = FALSE)

从临床栏中建立生存数据。

• 只选择原发实体瘤样本
• 合并患者的生存时间，其中有不同的列，以防他们活着或死了。
• 构建两个适合数据的矩阵对象xdata而且ydata

#只保留实体肿瘤(代码:01)brca.primary.solid.tumor <- TCGAutils::TCGAsplitAssays(brca， '01') xdata。raw <- t(化验(brca.primary.solid.tumor[[1]])) #获取生存信息ydata。raw <- colData(brca.primary.solid.tumor) %>% as.data.frame %>% #将天数转换为整数dplyr::mutate(days .to.date.of. death = as.integer(days .to.date.of. death)， days .to. last . contact = as.integer(days .to.date.of. contact)) %>% #查找所有天数之间的最大时间(忽略遗漏)dplyr::rowwise() %>% dplyr::mutate(time = max(days_to_last_followup, days .to.date.of. death)死亡,Days.to.Last。接触,days_to_death na。rm = TRUE)) %>% #只保留生存变量和代码dplyr::select(patientID, status = vital_status, time) %>% #丢弃生存时间小于或等于0的个体dplyr::filter(!is.na(time) & time > 0) %>% as.data.frame() #设置索引为patientID行名(ydata.raw) <- ydata. name。只保留degree.network中标准偏差为>的有效特征。Features <- colnames(xdata.raw)[colnames(xdata.raw) %in% names(degree.network[degree.network > 0])] xdata. properties。raw <- xdata.raw[TCGAbarcode(rownames(xdata.raw)) %in% rownames(ydata.raw)，有效。] xdata特性。raw <- scale(xdata.raw) #将ydata排序为与测定ydata相同。raw <- ydata.raw[TCGAbarcode(rownames(xdata.raw)))，] #只使用先前选择的基因子集来保持这个简短的示例。set.seed (params种子美元)小。< - c子集(‘AAK1’,‘ADRB1’,‘AK7’,“筛选”,“APOBEC3F”,“ARID1B”,“小鹿斑比”,‘BRAF’,‘BTG1’,‘CACNG8’,‘CASP12’,‘CD5’,‘CDA’,‘CEP72’,‘CPD’,‘CSF2RB’,‘CSN3’,‘DCT’,‘DLG3’,‘DLL3’,‘DPP4’,‘DSG1’,‘EDA2R’,‘ERP27’,‘EXD1’,‘GABBR2’,‘GADD45A’,‘1英镑’,‘HTR1F’,‘IFNK’,‘IRF2’,‘IYD’,‘KCNJ11’,‘KRTAP5-6’,‘MAFA’,‘MAGEB4’,‘MAP2K6’,‘MCTS1’,‘MMP15’,‘MMP9’,‘NFKBIA’,‘NLRC4’,‘NT5C1A’,‘OPN4’,‘OR13C5’,‘OR13C8’,‘OR2T6’,‘OR4K2’,‘OR52E6’,‘OR5D14’,‘OR5H1’,‘OR6C4’,‘OR7A17’,‘OR8J3’,“OSBPL1A”、“PAK6’,‘PDE11A’,‘PELO’,‘PGK1’,‘PIK3CB’,‘PMAIP1’,‘POLR2B’,‘POP1’,‘PPFIA3’,‘PSME1’,‘PSME2’,‘PTEN’,‘PTGES3’,‘qar’,‘RABGAP1’,‘RBM3’,‘RFC3’,‘RGPD8’,‘RPGRIP1L’,‘SAV1’,‘SDC1’,‘SDC3’,‘SEC16B’,‘SFPQ’,‘SFRP5’,‘SIPA1L1’,‘SLC2A14’,‘SLC6A9’,‘SPATA5L1’,‘SPINT1’,‘星’,‘STXBP5’,‘SUN3’,‘TACC2’,‘TACR1’,‘TAGLN2’,‘THPO’,‘TNIP1’,‘TP53’,‘TRMT2B’,‘TUBB1’,‘VDAC1’,‘VSIG8’,‘WNT3A’,‘WWOX’,‘XRCC4’,‘YME1L1’,‘ZBTB11’, 'ZSCAN21') %>% sample(size = 50) %>% sort # make sure we have 100 genes small.subset <- c(small.subset, sample(colnames(xdata.raw), 51)) %>% unique %>% sort xdata <- xdata.raw[, small.subset[small.subset %in% colnames(xdata.raw)]] ydata <- ydata.raw %>% dplyr::select(time, status) %>% dplyr::filter(!is.na(time) | time < 0)

• 构建与STRING数据重叠的数据集

# #给不在STRING网络中的基因添加度为0的值my.degree <- degree.network[small.子集]my.degreeString <- String .network.binary[small.子集，small.子集]

基因特征样本集的度分布(在xdata)．

set.seed(params$seed) foldid <- glmSparseNet:::balanced. csv .folds(!!ydata$status)$output . txt

简历。< -简历中心。glmHub(xdata, Surv(ydata$time, ydata$status)， family = 'cox'， foldid = foldid, network = my。字符串,网络。options = networkOptions(min.degree = 0.2))

## $pvalue ## [1] 9.628346e-05 ## ## $plot

## ## $km ##调用:survfit(公式=生存率::Surv(时间，状态)~组，数据= forecast .index.df) ## ## n事件中位数0.95LCL 0.95UCL ##低风险983 129 3959 3738 7455 ##高风险97 23 2911 2469 NA

简历。孤儿< - cv。glmOrphan(xdata, Surv(ydata$time, ydata$status)， family = 'cox'， foldid = foldid, network = my。字符串,网络。options = networkOptions(min.degree = 0.2))

## $pvalue ## [1] 0 ## ## $plot

## ## $km ##呼叫:survfit(公式=生存率::Surv(时间，状态)~组，数据= forecast .index.df) ## ## n事件中位数0.95LCL 0.95UCL ##低风险540 34 7455 6456 NA ##高风险540 118 2866 2573 3472

简历。全球语言监测机构< - cv。glmnet(xdata, Surv(ydata$time, ydata$status)， family = 'cox'， foldid = foldid)

## $pvalue ## [1] 0 ## ## $plot

## ## $km ##呼叫:survfit(公式=生存率::Surv(时间，状态)~组，数据= forecast .index.df) ## ## n事件中位数0.95LCL 0.95UCL ##低风险540 38 6593 4398 NA ##高风险540 114 2854 2551 3461

7会话信息

sessionInfo ()

## R版本4.2.0(22-04-22)##平台:x86_64-pc-linux-gnu(64位)##运行在:Ubuntu 20.04.4 LTS ## ##矩阵产品:default ## BLAS: /home/biocbuild/bbs-3.15-bioc/R/lib/libRblas. #因此## LAPACK: /home/biocbuild/bbs-3.15-bio /R/lib/libRlapack。因此## ## locale: ## [1] LC_CTYPE=en_US。UTF-8 LC_NUMERIC= c# [3] LC_TIME=en_GB LC_COLLATE= c# [5] LC_MONETARY=en_US。utf - 8 LC_MESSAGES = en_US。UTF-8 ## [7] LC_PAPER=en_US。UTF-8 LC_NAME= c# [9] LC_ADDRESS=C LC_TELEPHONE= c# [11] LC_MEASUREMENT=en_US。UTF-8 LC_IDENTIFICATION=C ## ##附加的基本包:## [1]grid parallel stats4 stats graphics grDevices utils ## [8] datasets methods base ## ##其他附加包:# # # # [1] VennDiagram_1.7.3 reshape2_1.4.4 [3] forcats_0.5.1 glmSparseNet_1.14.1 # # [5] glmnet_4.1-4 Matrix_1.4-1 # # [7] TCGAutils_1.16.0 curatedTCGAData_1.18.0 # # [9] MultiAssayExperiment_1.22.0 SummarizedExperiment_1.26.1 # # [11] Biobase_2.56.0 GenomicRanges_1.48.0 # # [13] GenomeInfoDb_1.32.2 IRanges_2.30.0 # # [15] S4Vectors_0.34.0 BiocGenerics_0.42.0 # # [17] MatrixGenerics_1.8.0 matrixStats_0.62.0 # # [19] futile.logger_1.4.3 survival_3.3-1 # # [21] ggplot2_3.3.6 dplyr_1.0.9 # # [23]BiocStyle_2.24.0 ## ##通过命名空间加载(不附加):# # # # [1] backports_1.4.1 AnnotationHub_3.4.0 [3] BiocFileCache_2.4.0 plyr_1.8.7 # # [5] splines_4.2.0 BiocParallel_1.30.2 # # [7] digest_0.6.29 foreach_1.5.2 # # [9] htmltools_0.5.2 magick_2.7.3 # # [11] fansi_1.0.3 magrittr_2.0.3 # # [13] memoise_2.0.1 tzdb_0.3.0 # # [15] Biostrings_2.64.0 readr_2.1.2 # # [17] prettyunits_1.1.1 colorspace_2.0-3 # # [19] blob_1.2.3 rvest_1.0.2 # # [21] rappdirs_0.3.3 xfun_0.31 # # [23] crayon_1.5.1 rcurl_1.98 - 1.6 # # [25] jsonlite_1.8.0 zoo_1.8-10 # # [27] iterators_1.0.14glue_1.6.2 ## [29] survminer_0.4.9 GenomicDataCommons_1.20.1 ## [31] gtable_0.3.0 zlibbioc_1.42.0 ## [33] XVector_0.36.0 DelayedArray_0.22.0 ## [35] car_3.0-13 shape_1.4.6 ## [37] abind_1.4-5 scales_1.2.0 ## [39] futile.options_1.0.1 DBI_1.1.2 ## [41] rstatix_0.7.0 Rcpp_1.0.8.3 ## [43] xtable_1.8-4 progress_1.2.2 ## [45] bit_4.0.4 km.ci_0.5-6 ## [47] httr_1.4.3 ellipsis_0.3.2 ## [49] pkgconfig_2.0.3 XML_3.99-0.9 ## [51] farver_2.1.0 sass_0.4.1 ## [53] dbplyr_2.1.1 utf8_1.2.2 ## [55] tidyselect_1.1.2 labeling_0.4.2 ## [57] rlang_1.0.2 later_1.3.0 ## [59] AnnotationDbi_1.58.0 munsell_0.5.0 ## [61] BiocVersion_3.15.2 tools_4.2.0 ## [63] cachem_1.0.6 cli_3.3.0 ## [65] generics_0.1.2 RSQLite_2.2.14 ## [67] ExperimentHub_2.4.0 broom_0.8.0 ## [69] evaluate_0.15 stringr_1.4.0 ## [71] fastmap_1.1.0 yaml_2.3.5 ## [73] knitr_1.39 bit64_4.0.5 ## [75] survMisc_0.5.6 purrr_0.3.4 ## [77] KEGGREST_1.36.0 mime_0.12 ## [79] formatR_1.12 xml2_1.3.3 ## [81] biomaRt_2.52.0 compiler_4.2.0 ## [83] filelock_1.0.2 curl_4.3.2 ## [85] png_0.1-7 interactiveDisplayBase_1.34.0 ## [87] ggsignif_0.6.3 tibble_3.1.7 ## [89] bslib_0.3.1 stringi_1.7.6 ## [91] highr_0.9 GenomicFeatures_1.48.1 ## [93] lattice_0.20-45 KMsurv_0.1-5 ## [95] vctrs_0.4.1 pillar_1.7.0 ## [97] lifecycle_1.0.1 BiocManager_1.30.17 ## [99] jquerylib_0.1.4 data.table_1.14.2 ## [101] bitops_1.0-7 httpuv_1.6.5 ## [103] rtracklayer_1.56.0 R6_2.5.1 ## [105] BiocIO_1.6.0 bookdown_0.26 ## [107] promises_1.2.0.1 gridExtra_2.3 ## [109] codetools_0.2-18 lambda.r_1.2.4 ## [111] assertthat_0.2.1 rjson_0.2.21 ## [113] withr_2.5.0 GenomicAlignments_1.32.0 ## [115] Rsamtools_2.12.0 GenomeInfoDbData_1.2.8 ## [117] hms_1.1.1 tidyr_1.2.0 ## [119] rmarkdown_2.14 carData_3.0-5 ## [121] ggpubr_0.4.0 pROC_1.18.0 ## [123] shiny_1.7.1 restfulr_0.0.13