R语言中的突变signature分析工具

一粒沙

发布于 2022-03-14 14:50:02

1.3K0

发布于 2022-03-14 14:50:02

新的一年开始了，今天给大家介绍一款用于发现、预测和探索突变特征的综合分析工具包musicatk。此包主要基于COSMIC突变数据中的最新数据进行肿瘤突变模式的探索。我们首先看下包的安装：

BiocManager::install("musicatk")

1. 数据源的导入

##TCGA数据库的MAF文件
lusc_maf <- system.file("extdata", "public_TCGA.LUSC.maf", package = "musicatk")
lusc.variants <- extract_variants_from_maf_file(maf_file = lusc_maf)

##VCF文件读入
luad_vcf <- system.file("extdata", "public_LUAD_TCGA-97-7938.vcf", package = "musicatk")
luad.variants <- extract_variants_from_vcf_file(vcf_file = luad_vcf)

##多个文件数据的导入
melanoma_vcfs <- list.files(system.file("extdata", package = "musicatk"), pattern = glob2rx("*SKCM*vcf"), full.names = TRUE)
variants <- extract_variants(c(lusc_maf, luad_vcf, melanoma_vcfs))

2. 参考基因组的选择

g <- select_genome("hg38")

3. 项目操作

##创建项目。check_ref_bases参数默认进行参考突变筛选；check_ref_chromosomes进行染色体筛选。
musica <- create_musica(x = variants, genome = g)

##载入突变基序数据。突变基序包括单碱基替换(SBS)、双碱基替换(DBS)、插入(INS)和删除(DEL)。
build_standard_table(musica, g = g, table_name = "SBS96")

##通过数据库批量载入突变基序数据。
build_standard_table(dbs_musica, g, "SBS96", overwrite = TRUE)

##对SBS突变进行转录本的注释
annotate_transcript_strand(musica, "38", build_table = FALSE)

##检测突变signature。在这里有两个方法进行获取：隐含狄利克雷分布（lda）和加速版本非负矩阵分解（nmf）
result <- discover_signatures(musica = musica, table_name = "SBS96", num_signatures = 3, algorithm = "nmf", nstart = 10)

##基于COSMIC进行signature和exposure的预测
# Load COSMIC V2 data
data("cosmic_v2_sigs")


# Predict pre-existing exposures using the "lda" method
pred_cosmic <- predict_exposure(musica = musica, table_name = "SBS96",
                               signature_res = cosmic_v2_sigs,
                               signatures_to_use =  c(1, 4, 7, 13),
                               algorithm = "lda")

4. 可视化结果

##可视化signature
plot_signatures(result)

##绘制单个样本的signature
samples <- sample_names(musica)
plot_sample_counts(musica, sample_names = samples[c(3,4,5)], table_name = "SBS96")

##对比下COSMIC数据库中的signature
compare_cosmic_v2(result, threshold = 0.75)

##查看样本exposure
plot_exposures(result, plot_type = "bar")

##比例型绘制bar图
plot_exposures(result, plot_type = "bar", proportional = TRUE)

##添加样本注释
annot <- read.table(system.file("extdata", "sample_annotations.txt",
                                package = "musicatk"), sep = "\t", header=TRUE)
samp_annot(result, "Tumor_Subtypes") <- annot$Tumor_Subtypes
plot_exposures(result, plot_type = "bar", group_by = "annotation",
                annotation = "Tumor_Subtypes")

##绘制箱线图
plot_exposures(result, plot_type = "box", group_by = "annotation", annotation = "Tumor_Subtypes")

##基于signature分组的箱线图绘制
plot_exposures(result, plot_type = "box", group_by = "signature",
               color_by = "annotation", annotation = "Tumor_Subtypes")