{"id":36892,"date":"2024-04-22T10:21:57","date_gmt":"2024-04-22T02:21:57","guid":{"rendered":"http:\/\/www.biocloudservice.com\/wordpress\/?p=36892"},"modified":"2024-04-22T10:21:58","modified_gmt":"2024-04-22T02:21:58","slug":"%e8%b7%9f%e7%9d%80%e5%b0%8f%e4%ba%91%e5%ad%a6%e5%a4%8d%e7%8e%b0-%e6%89%8b%e6%8a%8a%e6%89%8b%e5%b8%a6%e4%bd%a0%e6%8b%bf%e4%b8%8bif46-9nature-%e7%ba%a7%e5%88%ab%e7%9a%84%e4%b8%bb%e6%88%90%e5%88%86","status":"publish","type":"post","link":"http:\/\/www.biocloudservice.com\/wordpress\/?p=36892","title":{"rendered":"\u8ddf\u7740\u5c0f\u4e91\u5b66\u590d\u73b0-\u624b\u628a\u624b\u5e26\u4f60\u62ff\u4e0bIF=46.9Nature \u7ea7\u522b\u7684\u4e3b\u6210\u5206\u5206\u6790\uff08PCA\uff09\u56fe\uff01\uff01"},"content":{"rendered":"

\"\"<\/strong><\/p>\n

\u5c0f\u4e91\u6700\u8fd1\u9605\u8bfb\u4e86\u8bb8\u591a\u7684\u6587\u732e\uff0c\u5fc3\u91cc\u4e00\u76f4\u5728\u601d\u8003\uff0c\u79d1\u7814\u4eba\u5458\u5982\u4f55\u53d1\u8868\u6210\u529f\u7684\u9ad8\u5206\u7684\u751f\u4fe1\u6587\u7ae0\u3002\u6700\u7ec8\u5462\u5c0f\u4e91\u867d\u7136\u6ca1\u6709\u5b8c\u5168\u53d1\u6398\u5176\u4e2d\u7684\u5965\u79d8\uff0c\u4f46\u662f\u5c0f\u4e91\u53d1\u73b0\u4e00\u4e2a\u89c4\u5f8b\uff0c\u8fd9\u4e9b\u9ad8\u5206\u6587\u7ae0\u4e2d\u5bf9\u6570\u636e\u7684\u628a\u63a7\u662f\u5f88\u5230\u4f4d\uff0c\u5982\u4f55\u7406\u89e3\u5462\uff0c\u5c0f\u4e91\u770b\u7684Nature\u7ea7\u522b\u7684\u6587\u7ae0\u4e2d\uff0c\u4ed6\u4eec\u90fd\u6570\u636e\u91cf\u90fd\u5f88\u5e9e\u5927\uff0c<\/p>\n

\u6240\u4ee5\u5c0f\u4e91\u5c31\u60f3\u8bf4\uff0c\u5c0f\u4f19\u4f34\u5982\u679c\u60f3\u53d1\u9ad8\u5206\u6587\u7ae0\u4e00\u5f00\u59cb\u5904\u7406\u7684\u6570\u636e\u4e00\u5b9a\u4e0d\u80fd\u5c11\uff0c\u6837\u672c\u91cf\u591f\u5927\uff0c\u8fd9\u6837\u4e5f\u53ef\u4ee5\u4fa7\u9762\u7684\u8bf4\u660e\u5de5\u4f5c\u91cf\u5927\uff0c\u90a3\u4e48\u8981\u662f\u89e3\u51b3\u8fd9\u4e2a\u95ee\u9898\uff0c\u540e\u7eed\u7684\u601d\u8def\u7b49\u5c31\u8fce\u5203\u800c\u89e3\u4e86\u3002<\/p>\n

\"\"<\/p>\n

\u8bf4\u5230\u6570\u636e\uff0c\u5c0f\u4f19\u4f34\u505a\u5206\u6790\u8981\u662f\u7528\u5f88\u5927\u7684\u6570\u636e\uff0c\u90a3\u5c31\u5c11\u4e0d\u4e86\u5bf9\u6570\u636e\u7684\u8d28\u63a7\u3002\u90a3\u8be5\u5982\u4f55\u6307\u63a7\u5462\uff0c\u5c0f\u4e91\u544a\u8bc9\u5c0f\u4f19\u4f34\u7528\u7684\u6700\u591a\u7684\u5c31\u662f\u4e3b\u6210\u5206\u5206\u6790(PCA)\uff0c<\/p>\n

\u76ee\u524d\u8bb8\u591a\u7684\u751f\u4fe1\u5206\u7ec4\u867d\u7136\u4ed6\u4eec\u7ecf\u5e38\u4f1a\u505aPCA\u5206\u6790\uff0c\u4f46\u662f\u4ed6\u4eec\u90fd\u662f\u5f88\u666e\u901a\u7684\u53ef\u89c6\u5316\u65b9\u5f0f\uff0c\u6700\u591a\u7684\u5c31\u662f\u6a2a\u7eb5\u5750\u6807\u7684PCA\u4e8c\u7ef4\u56fe\uff0c\u518d\u8005\u5c31\u662f\u4e09\u7ef4\u7684PCA\u56fe\u3002\u5c0f\u4e91\u60f3\u6559\u7ed9\u5c0f\u4f19\u4f34\u4e0d\u4e00\u6837\u65b9\u5f0f\u7684PCA\u56fe\uff0c\u7136\u540e\u5c31\u53d1\u73b0\u4e00\u7bc7Nature\u6587\u7ae0\u4e2d\u7684PCA\u56fe\uff0c\u8fd9\u5e45\u56fe\u6253\u7834\u6b63\u5e38\u6211\u4eec\u89c1\u8fc7\u7684PCA\u56fe\uff0c\u6211\u4eec\u5148\u770b\u56fe\u5728\u4e86\u89e3\u4e00\u4e0b\u8fd9\u4e2a\u56fe\u7684\u7279\u8272\uff0c\u8fd9\u662f\u6765\u81eaIF\u5f71\u54cd\u56e0\u5b50\u670946.9\u300aNatue biotechnology\u300b\u4e2d\u7684\u300aRemoving unwanted variation from large-scale RNA sequencing data with PRPS\u300b\u56fe2a\uff0c\u6765\u770b\u4e00\u4e0b\uff1a<\/p>\n

<\/p>\n

\u5c0f\u4f19\u4f34\u770b\u7684\u7b2c\u4e00\u773c\u662f\u4e0d\u662f\u89c9\u5f97\u8fd9\u4e0d\u662fPCA\u56fe\uff0c\u5c0f\u4e91\u4e5f\u662f\u7b2c\u4e00\u773c\u5c31\u88ab\u5438\u5f15\u4e86\uff0c\u8fd9\u5e45\u56fe\uff0cPCA\u4e3b\u8981\u7684\u5185\u5bb9\u5e94\u6709\u5c3d\u6709\uff0c\u5e76\u4e14\u8fd8\u975e\u5e38\u7684\u597d\u770b\uff0c\u90a3\u4e48\u4eca\u5929\u5c0f\u4e91\u5c31\u5e26\u5c0f\u4f19\u4f34\u53bb\u590d\u73b0\u8fd9\u5f20\u56fe\uff0c\u6211\u4eec\u4ee5\u540e\u505aPCA\u5c31\u53ef\u4ee5\u7528\u5230\u8fd9\u79cd\u56fe\u4e86\uff0c<\/p>\n

\u4f5c\u56fe\u7684\u524d\u63d0\u5462\uff0c\u5c0f\u4e91\u8fd8\u662f\u5e26\u5c0f\u4f19\u4f34\u4e86\u89e3\u4e00\u4e0b\u4ec0\u4e48\u662fPCA\uff0c\u6211\u4eec\u4e5f\u8981\u660e\u767d\u4e3a\u4ec0\u4e48\u8981\u505a\u8fd9\u4e2a\u56fe\uff0c\u5176\u5b9e\u4e3b\u6210\u5206\u5206\u6790\u5c5e\u4e8e\u4e00\u79cd\u964d\u7ef4\u7b97\u6cd5\uff0c\u5f53\u6211\u4eec\u7684\u6570\u636e\u91cf\u5f88\u5e9e\u5927\u7684\u65f6\u5019\u5c31\u9700\u8981\u53bb\u628a\u6570\u636e\u964d\u7ef4\uff0c\u800c\u964d\u7ef4\u5462\u5c31\u662f\u4e00\u79cd\u5bf9\u9ad8\u7ef4\u5ea6\u7279\u5f81\u6570\u636e\u9884\u5904\u7406\u65b9\u6cd5\u3002\u964d\u7ef4\u662f\u5c06\u9ad8\u7ef4\u5ea6\u7684\u6570\u636e\u4fdd\u7559\u4e0b\u6700\u91cd\u8981\u7684\u4e00\u4e9b\u7279\u5f81\uff0c\u53bb\u9664\u566a\u58f0\u548c\u4e0d\u91cd\u8981\u7684\u7279\u5f81\uff0c\u4ece\u800c\u5b9e\u73b0\u63d0\u5347\u6570\u636e\u5904\u7406\u901f\u5ea6\u7684\u76ee\u7684\u3002<\/p>\n

\u5728\u5b9e\u9645\u7684\u751f\u4ea7\u548c\u5e94\u7528\u4e2d\uff0c\u964d\u7ef4\u5728\u4e00\u5b9a\u7684\u4fe1\u606f\u635f\u5931\u8303\u56f4\u5185\uff0c\u53ef\u4ee5\u4e3a\u6211\u4eec\u8282\u7701\u5927\u91cf\u7684\u65f6\u95f4\u548c\u6210\u672c\u3002\u964d\u7ef4\u4e5f\u6210\u4e3a\u5e94\u7528\u975e\u5e38\u5e7f\u6cdb\u7684\u6570\u636e\u9884\u5904\u7406\u65b9\u6cd5\u3002<\/p>\n

\u8fd9\u4e48\u505a\u662f\u6709\u5229\u4e8e\u6211\u4eec\u5206\u6790\u7684\uff0c\u53ef\u4ee5\u4f7f\u5f97\u6570\u636e\u96c6\u66f4\u6613\u4f7f\u7528\u3002\u4e5f\u53ef\u4ee5\u4f7f\u5f97\u7ed3\u679c\u5bb9\u6613\u7406\u89e3\u3002<\/p>\n

\u90a3\u4e48\u8bdd\u4e0d\u591a\u8bf4\uff0c\u6211\u4eec\u5c31\u5f00\u59cb\u4e0b\u9762\u7684\u5b66\u4e60\u5427\uff01<\/p>\n

\u8fd9\u91cc\u5462\u5c0f\u4e91\u8fd8\u8981\u8bf4\u660e\u4e00\u4e0b\uff0c\u6211\u4eec\u505aPCA\uff0c\u6570\u636e\u5e93\u5f88\u5927\u7684\u82b1\uff0c\u90a3\u4e48\u6211\u4eec\u64cd\u4f5c\u5360\u7528\u5185\u5b58\u6bd4\u8f83\u5927\uff0c\u6240\u4ee5\u5efa\u8bae\u5404\u4f4d\u5c0f\u4f19\u4f34\u53ef\u4ee5\u4f7f\u7528\u670d\u52a1\u5668\u53bb\u8fd0\u884c\uff0c\u5982\u679c\u6ca1\u6709\u81ea\u5df1\u7684\u670d\u52a1\u5668\u4e5f\u6ca1\u6709\u5173\u7cfb\uff0c\u53ef\u4ee5\u6b22\u8fce\u8054\u7cfb\u6211\u4eec\u4f7f\u7528\u670d\u52a1\u5668\u79df\u8d41~<\/p>\n

\u597d\u4e86\uff0c\u6211\u4eec\u5f00\u59cb\u5427\uff01<\/p>\n

\u6211\u4eec\u5728\u505aPCA\u5206\u6790\u7684\u65f6\u5019\uff0c\u56e0\u4e3a\u5bf9\u8bb8\u591a\u6570\u636e\u8fdb\u884c\u5904\u7406\uff0c\u8fd9\u5c31\u9700\u8981\u7528\u5230\u4e00\u4e9b\u51fd\u6570\u53bb\u8ba1\u7b97\uff0c<\/p>\n

\u8fd9\u6b21\u5c0f\u4e91\u5c31\u5206\u4eab\u7ed9\u5c0f\u4f19\u4f34\u4e24\u4e2a\u51fd\u6570\uff0c\u6765\u5b9e\u73b0\u6211\u4eec\u8fd9\u6b21\u7684\u590d\u73b0\u5185\u5bb9\uff0c<\/p>\n

\u7b2c\u4e00\u4e2a\u5c31\u662f\u6211\u4eec\u7528\u6765\u8ba1\u7b97\u4e3b\u6210\u5206\u5206\u6790\u7684pca\u51fd\u6570<\/p>\n

.pca <- function(data, is.log) {<\/p>\n

if (is.log)<\/p>\n

data <- data<\/p>\n

else<\/p>\n

data <- log2(data + 1)<\/p>\n

svd <- base::svd(scale(<\/p>\n

x = t(data),<\/p>\n

center = TRUE,<\/p>\n

scale = FALSE<\/p>\n

))<\/p>\n

percent <- svd$d ^ 2 \/ sum(svd$d ^ 2) * 100<\/p>\n

percent <-<\/p>\n

sapply(seq_along(percent),<\/p>\n

function(i) {<\/p>\n

round(percent[i], 1)<\/p>\n

})<\/p>\n

return(list(<\/p>\n

sing.val = svd,<\/p>\n

variation = percent))<\/p>\n

}<\/p>\n

\u8fd9\u4e2a\u51fd\u6570\u53ef\u4ee5\u8ba1\u7b97\u6211\u4eec\u7684\u6240\u6709\u7684\u6570\u636e\uff0c\u5c0f\u4f19\u4f34\u4e5f\u4e0d\u7528\u7406\u89e3\u8fd9\u4e2a\u51fd\u6570\u5177\u4f53\u610f\u601d\uff0c<\/p>\n

\u7b2c\u4e8c\u4e2a\u51fd\u6570\u5c31\u662f\u7528\u6765\u4f5c\u56fe\u7684\uff0c\u8fd9\u4e2a\u5c31\u9700\u8981\u7528\u5230\u6211\u4eec\u7684\u8001\u670b\u53cbggplot2\u5305\u4e2d\u7684ggpubr\u8fd8\u6709cowplot\u5305\uff0c<\/p>\n

\u6765\u770b\u4e00\u4e0b\uff1a<\/p>\n

.scatter.density.pc <- function(<\/p>\n

pcs,<\/p>\n

pc.var,<\/p>\n

group.name,<\/p>\n

group,<\/p>\n

color,<\/p>\n

strokeSize,<\/p>\n

pointSize,<\/p>\n

strokeColor,<\/p>\n

alpha,<\/p>\n

title<\/p>\n

){<\/p>\n

pair.pcs <- utils::combn(ncol(pcs), 2)<\/p>\n

pList <- list()<\/p>\n

for(i in 1:ncol(pair.pcs)){<\/p>\n

if(i == 1){<\/p>\n

x <- pair.pcs[1,i]<\/p>\n

y <- pair.pcs[2,i]<\/p>\n

p <- ggplot(mapping = aes(<\/p>\n

x = pcs[,x],<\/p>\n

y = pcs[,y],<\/p>\n

fill = group)) +<\/p>\n

xlab(paste0(‘PC’, x, ‘ (‘, pc.var[x], ‘%)’)) +<\/p>\n

ylab(paste0(‘PC’, y, ‘ (‘, pc.var[y], ‘%)’)) +<\/p>\n

geom_point(<\/p>\n

aes(fill = group),<\/p>\n

pch = 21,<\/p>\n

color = strokeColor,<\/p>\n

stroke = strokeSize,<\/p>\n

size = pointSize,<\/p>\n

alpha = alpha) +<\/p>\n

scale_x_continuous(breaks = scales::pretty_breaks(n = 5)) +<\/p>\n

scale_y_continuous(breaks = scales::pretty_breaks(n = 5)) +<\/p>\n

ggtitle(title) +<\/p>\n

theme(<\/p>\n

legend.position = “right”,<\/p>\n

panel.background = element_blank(),<\/p>\n

axis.line = element_line(colour = “black”, size = 1.1),<\/p>\n

legend.background = element_blank(),<\/p>\n

legend.text = element_text(size = 12),<\/p>\n

legend.title = element_text(size = 14),<\/p>\n

legend.key = element_blank(),<\/p>\n

axis.text.x = element_text(size = 10),<\/p>\n

axis.text.y = element_text(size = 10),<\/p>\n

axis.title.x = element_text(size = 14),<\/p>\n

axis.title.y = element_text(size = 14)) +<\/p>\n

guides(fill = guide_legend(override.aes = list(size = 4))) +<\/p>\n

scale_fill_manual(name = group.name, values = color)<\/p>\n

le <- ggpubr::get_legend(p)<\/p>\n

}else{<\/p>\n

x <- pair.pcs[1,i]<\/p>\n

y <- pair.pcs[2,i]<\/p>\n

p <- ggplot(mapping = aes(<\/p>\n

x = pcs[,x],<\/p>\n

y = pcs[,y],<\/p>\n

fill = group)) +<\/p>\n

xlab(paste0(‘PC’, x, ‘ (‘,pc.var[x], ‘%)’)) +<\/p>\n

ylab(paste0(‘PC’, y, ‘ (‘,pc.var[y], ‘%)’)) +<\/p>\n

geom_point(<\/p>\n

aes(fill = group),<\/p>\n

pch = 21,<\/p>\n

color = strokeColor,<\/p>\n

stroke = strokeSize,<\/p>\n

size = pointSize,<\/p>\n

alpha = alpha) +<\/p>\n

scale_x_continuous(breaks = scales::pretty_breaks(n = 5)) +<\/p>\n

scale_y_continuous(breaks = scales::pretty_breaks(n = 5)) +<\/p>\n

theme(<\/p>\n

panel.background = element_blank(),<\/p>\n

axis.line = element_line(colour = “black”, size = 1.1),<\/p>\n

legend.position = “none”,<\/p>\n

axis.text.x = element_text(size = 10),<\/p>\n

axis.text.y = element_text(size = 10),<\/p>\n

axis.title.x = element_text(size = 14),<\/p>\n

axis.title.y = element_text(size = 14)) +<\/p>\n

scale_fill_manual(values = color, name = group.name)<\/p>\n

}<\/p>\n

p <- p + theme(legend.position = “none”)<\/p>\n

xdens <- cowplot::axis_canvas(p, axis = “x”)+<\/p>\n

geom_density(<\/p>\n

mapping = aes(<\/p>\n

x = pcs[,x],<\/p>\n

fill = group),<\/p>\n

alpha = 0.7,<\/p>\n

size = 0.2<\/p>\n

) +<\/p>\n

theme(legend.position = “none”) +<\/p>\n

scale_fill_manual(values = color)<\/p>\n

ydens <- cowplot::axis_canvas(<\/p>\n

p,<\/p>\n

axis = “y”,<\/p>\n

coord_flip = TRUE) +<\/p>\n

geom_density(<\/p>\n

mapping = aes(<\/p>\n

x = pcs[,y],<\/p>\n

fill = group),<\/p>\n

alpha = 0.7,<\/p>\n

size = 0.2) +<\/p>\n

theme(legend.position = “none”) +<\/p>\n

scale_fill_manual(name = group.name, values = color) +<\/p>\n

coord_flip()<\/p>\n

p1 <- insert_xaxis_grob(<\/p>\n

p,<\/p>\n

xdens,<\/p>\n

grid::unit(.2, “null”),<\/p>\n

position = “top”<\/p>\n

)<\/p>\n

p2 <- insert_yaxis_grob(<\/p>\n

p1,<\/p>\n

ydens,<\/p>\n

grid::unit(.2, “null”),<\/p>\n

position = “right”<\/p>\n

)<\/p>\n

pList[[i]] <- ggdraw(p2)<\/p>\n

}<\/p>\n

pList[[i+1]] <- le<\/p>\n

return(pList)<\/p>\n

}<\/p>\n

\u5c0f\u4f19\u4f34\u53ef\u4ee5\u76f4\u63a5\u8fd0\u884c\u8fd9\u4e24\u4e2a\u51fd\u6570\uff0c\u6216\u8005\u4e5f\u53ef\u4ee5\u60f3\u5c0f\u4e91\u4e00\u6837\u6574\u7406\u5728\u4e00\u4e2aR\u6587\u4ef6\u91cc\u9762\uff0c\u65b9\u4fbf\u4e0b\u6b21\u4f7f\u7528\uff0c<\/p>\n

<\/p>\n

\u7136\u540e\u6211\u4eec\u5c31\u53ef\u4ee5\u4f7f\u7528<\/p>\n

source(“pca.r”)#\u8f7d\u5165\u4f7f\u7528<\/p>\n

\u4e0b\u9762\u6211\u4eec\u5c31\u662f\u6765\u770b\u4e0b\u8f7d\u5165\u6570\u636e\u7684\u683c\u5f0f\uff0c<\/p>\n

\u8fd9\u662f\u5c0f\u4e91\u81ea\u5df1\u7684\u6570\u636e\uff0c\u5c0f\u4f19\u4f34\u53ef\u4ee5\u6309\u7167\u5f62\u5f0f\u81ea\u884c\u53bb\u8bbe\u7f6e\uff0c<\/p>\n

df<-read.csv(“pca1.csv” )<\/p>\n

df<\/p>\n

<\/p>\n

\u6211\u4eec\u5c55\u793a\u6700\u91cd\u8981\u7684\u4e00\u90e8\u5206\uff0c\u524d\u9762\u90fd\u662f\u57fa\u56e0\u7684\u8868\u8fbe\u91cf\uff0c\u7eb5\u7684\u8868\u793a\u6837\u672c\uff0c\u6700\u540e\u4e00\u4e2a\u6211\u4eec\u8bbe\u7f6e\u4e00\u4e0b\u5206\u7ec4\uff0c\u4f5c\u4e3a\u6211\u4eecPCA\u5206\u6790\u7684\u6570\u636e\u5f62\u5f0f\uff0c\u5c31\u662fClassification,\u5c0f\u4e91\u8fd9\u91cc\u5206\u4e86\u56db\u7ec4\uff0c\u6587\u732e\u4e2d\u5206\u4e865\u7ec4\uff0c\u8fd9\u4e2a\u770b\u5c0f\u4f19\u4f34\u81ea\u5df1\u7684\u9700\u6c42\uff0c<\/p>\n

\u7136\u540e\u6211\u4eec\u8ba1\u7b97\u4e00\u4e0b<\/p>\n

pca.ncg<-.pca(data = df[,1:8767], ##<\/p>\n

is.log = FALSE)<\/p>\n

\u4e0a\u9762\u8fd9\u4e2a\u6570\u5b57\u4ee3\u8868\u57fa\u56e0\u6570\u91cf\uff0c\u5c0f\u4e91\u8fd9\u91cc\u5c31\u9009\u62e9\u8fd9\u4e00\u4e9b<\/p>\n

\u8fd0\u884c\u5b8c\u5c31<\/p>\n

\u51fa\u73b0\uff0c\u6211\u4eec\u5c31\u5c06\u8ba1\u7b97\u597d\u7684\u503c\u8fdb\u884c\u53ef\u89c6\u5316\uff0c<\/p>\n

.scatter.density.pc(pcs = pca.ncg$sing.val$v[, 1:3], ##\u5c55\u793a\u51e0\u4e2a<\/p>\n

pc.var = pca.ncg$variation,<\/p>\n

strokeColor = ‘gray30’,<\/p>\n

strokeSize = .2,<\/p>\n

pointSize = 2,<\/p>\n

alpha = .6,<\/p>\n

title = “A”, ##\u6807\u9898\u540d<\/p>\n

group.name = “Stage”, # legned name<\/p>\n

group=df$classification, # \u9009\u62e9\u5206\u7ec4<\/p>\n

color=c(“darkorchid4″,”cornflowerblue”,”sandybrown”,”mediumaquamarine”)) -> p#\u989c\u8272<\/p>\n

\u4e0b\u9762\u6211\u4eec\u4f7f\u7528\u4ee3\u7801\u8fdb\u884c\u5c55\u793a\uff0c<\/p>\n

do.call(<\/p>\n

gridExtra::grid.arrange,<\/p>\n

c(p,ncol=4,nrow=1))<\/p>\n

<\/p>\n

\u8fd9\u6837\u4e00\u770b\uff0c\u548c\u6587\u732e\u4e2d\u6709\u70b9\u4e0d\u4e00\u6837\uff0c\u592a\u957f\u4e86\uff0c\u6211\u4eec\u628a\u51fa\u56fe\u7684\u6392\u5217\u6539\u4e00\u4e0b<\/p>\n

do.call(<\/p>\n

gridExtra::grid.arrange,<\/p>\n

c(p,ncol=2,nrow=2))<\/p>\n

<\/p>\n

\u8fd9\u6837\u4e00\u6765\u5c31\u5dee\u4e0d\u591a\u4e86\uff0c\u6700\u540e\u518d\u628a\u70b9\u7684\u5927\u5c0f\u8c03\u4e00\u4e0b\uff0c\u7136\u540e\u51fa\u56fe\uff0c<\/p>\n

.scatter.density.pc(pcs = pca.ncg$sing.val$v[, 1:3], ##<\/p>\n

pc.var = pca.ncg$variation,<\/p>\n

strokeColor = ‘gray30’,<\/p>\n

strokeSize = .2,<\/p>\n

pointSize = 4,<\/p>\n

alpha = .6,<\/p>\n

title = “A”, ##<\/p>\n

group.name = “Stage”, # legned name<\/p>\n

group=df$classification, #<\/p>\n

color=c(“darkorchid4″,”cornflowerblue”,”sandybrown”,”mediumaquamarine”)) -> p<\/p>\n

do.call(<\/p>\n

gridExtra::grid.arrange,<\/p>\n

c(p,ncol=2,nrow=2))<\/p>\n

<\/p>\n

\u8fd9\u5c31\u4e00\u6837\u4e86\u57fa\u672c\u4e0a\u5c31\u4e00\u6837\u4e86\uff0c\u989c\u8272\u5c0f\u4e91\u5c31\u968f\u673a\u8bbe\u7f6e\u7684\uff0c\u5c0f\u4f19\u4f34\u770b\u4e86\u6709\u6ca1\u6709\u5fc3\u52a8\u4e86\uff0c\u8981\u591a\u591a\u7406\u89e3\u4ee3\u7801\u7684\u610f\u601d\uff0c\u4e0a\u8ff0\u51fd\u6570\u7684\u6587\u4ef6\u5462\uff0c\u5c0f\u4f19\u4f34\u9700\u8981\u7684\u53ef\u4ee5\u627e\u6211\u4eec\u516c\u4f17\u53f7\u9886\u53d6\u54e6<\/p>\n

\u6700\u540e\u5462\uff0c\u5c0f\u4e91\u7ed9\u5c0f\u4f19\u4f34\u5e26\u4e2a\u5c0f\u798f\u5229\uff0c\u5982\u679c\u5c0f\u4f19\u4f34\u89c9\u5f97\u81ea\u5df1\u8fd0\u884c\u4ee3\u7801\u592a\u9ebb\u70e6\uff0c\u53ef\u4ee5\u8bd5\u8bd5\u6211\u4eec\u7684\u4e91\u751f\u4fe1\u5c0f\u5de5\u5177\u54df\uff0c\u91cc\u9762\u6709\u6210\u719f\u7684\u4ee3\u7801\uff0c\u53ea\u8981\u8f93\u5165\u5408\u9002\u7684\u6570\u636e\u5c31\u53ef\u4ee5\u76f4\u63a5\u51fa\u60f3\u8981\u7684\u56fe\u5462\u3002<\/p>\n

\u591a\u591a\u5173\u6ce8\u6211\u4eec\u516c\u4f17\u53f7\uff0c\u4e91\u751f\u4fe1\uff01<\/p>\n

\"\"<\/p>\n","protected":false},"excerpt":{"rendered":"

\u5c0f\u4e91\u6700\u8fd1\u9605\u8bfb\u4e86\u8bb8\u591a\u7684\u6587\u732e\uff0c\u5fc3\u91cc\u4e00\u76f4\u5728\u601d\u8003\uff0c\u79d1\u7814\u4eba\u5458\u5982\u4f55\u53d1\u8868\u6210\u529f\u7684\u9ad8\u5206\u7684\u751f\u4fe1\u6587\u7ae0\u3002\u6700\u7ec8\u5462\u5c0f\u4e91\u867d\u7136\u6ca1\u6709\u5b8c\u5168\u53d1\u6398\u5176\u4e2d […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":""},"categories":[1],"tags":[],"jetpack_featured_media_url":"","_links":{"self":[{"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/36892"}],"collection":[{"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=36892"}],"version-history":[{"count":1,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/36892\/revisions"}],"predecessor-version":[{"id":36900,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/36892\/revisions\/36900"}],"wp:attachment":[{"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=36892"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=36892"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=36892"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}