## ----设置，包括= false --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- knitr::opts_chunk$set(echo = TRUE) ## ---- include=FALSE-----------------------------------------------------------------------库（TFHAZ）图书馆（基因组汇总）库（iranges）库（S4VECTORS）数据（“ data_man”）## ------------------------------------------------------------------------------------------------------------------------------------------------------------加载和可视化数据集：data（“ ishikawa”）dim（as.data.frame（ishikawa））头（ishikawa）## -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- ＃w = 0 tf_acc_21_w_0 < - 累积（Ishikawa，“ tf”，“ chr21”，0）## ----------------------------------------------------------------------------------------------------------------------------------------------------- ＃＃绘制累加矢量＃plot_accumulation（tf_acc_21_w_0）## ----------- echo = false，fife，fig.align ='center'，out.width = '75％'，fig.cap ='*染色体21的向量，为W = 0获得。.png'）## ---------------------------------------------------------------------------------------------------------------------------------------＃找到密集的DNA区域，阈值步骤等于1 tf_dense_21_w_0 <-dense_zones（dense_zones（tf_acc_w_0，1，chr =“ chr21”）tf_dense_21_w_0 ## --------- echo = false，fife，fig.align ='center ='center'，fig.small = true，fir.cap =“针对转录因子累积阈值等于12的染色体21的七个密集DNA区的坐标。='Center'，图Cap =“*密集DNA区数的图，发现染色体21的TF累积阈值变化； the point with maximum slope change is plotted circulated with a red full line.*"---- plot_n_zones(TF_dense_w_0, chr = "chr21") ## ---- fig.align='center', fig.cap="*Plot of the number of dense DNA zones (red full line) and of the total number of bases belonging to dense DNA zones (blue dashed line) obtained with different values of neighborhood window half-width w for the chromosome 21.*"---- # l is a list with four objects obtained with the dense_zones function with # w = 10, 100, 1000, 10000. l <- list(TF_dense_w_10, TF_dense_w_100, TF_dense_w_1000, TF_dense_w_10000) # plot w_analysis(l, chr = "chr21") ## ----PCA, fig.keep="none"----------------------------------------------------- # TF_dense_21_w_10 is the output of dense_zones function applied to the # accumulation vector found with w=10, chr="chr21", acctype="TF". # reg_dense_21_w_10 is the output of dense_zones function applied to the # accumulation vector found with w=10, chr="chr21", acctype="reg". # base_dense_21_w_10 is the output of dense_zones function (with # threshold_step=21 in order to have 14 threshold values as in the other two # inputs) applied to the accumulation vector found with w=10, chr="chr21", # acctype="base". # PCA n_zones_PCA(TF_dense_w_10, reg_dense_w_10, base_dense_w_10, chr = "chr21") ## ----echo=FALSE, fig.align='center', out.width = '75%',fig.cap = "*Plot of the variances of the principal components.*"---- knitr::include_graphics('./PCA_1.png') ## ----echo=FALSE, fig.align='center', out.width='75%', fig.cap = "*Plot of the cumulate variances of the principal components.*"---- knitr::include_graphics('./PCA_2.png') ## ----echo=FALSE, fig.align='center', out.width='100%', fig.cap = "*Plot of the loadings of the three principle components.*"---- knitr::include_graphics('./PCA_3.png') ## ----------------------------------------------------------------------------- # find high accumulation DNA zones TF_acc_21_w_0 <- accumulation(Ishikawa, "TF", "chr21", 0) TFHAZ_21_w_0 <- high_accumulation_zones(TF_acc_21_w_0, method = "overlaps", threshold = "std") TFHAZ_21_w_0 ## ----echo=FALSE, fig.align="center", out.width='75%',fig.cap = "*Plot of the TF accumulation vector (for the chromosome 21, obtained for w=0) and of the high accumulation DNA zones (red boxes on the x axis) found; the threshold used to find these zones (7,268413) is shown with a red horizontal line.*"---- knitr::include_graphics('./high_accumulation_zones_TH_7.3_TF_acc_w_0_chr21.png') ## ----echo=FALSE, fig.align='center', fig.small = TRUE, fig.cap = "*Content of the 'bed' file with the coordinates of 31 out of the 93 high accumulation DNA zones found.*"---- knitr::include_graphics('./HAZ_bed.PNG')