Science这张惊艳图表终于完成了：最终稳定版本
ggcor在微生物生态领域的使用
目前厚哥这个包还在不断开发中，不知不觉内容已经相当丰富和完善了，上一篇推送问题也慢慢出现，主要是函数修改问题，这里我不仅仅补充了新的内容，并且将之前推送全部函数都进行了更新，也就是说你之前学过了，只需要做很少的修改就好了。为读者负责，请关注这篇推送。封面看到的，你可以轻松做出来。如果迫不及待和厚哥交流，以及交流本篇文章的种种问题，那就添加小编微信，带你入群：
简单来说一下这个包用来干什么的？
相关系数矩阵可视化已经至少有两个版本的实现了，魏太云基于base绘图系统写了corrplot包，应该说是相关这个小领域中最精美的包了，使用简单，样式丰富，只能用惊艳来形容。Kassambara的ggcorrplot基于ggplot2重写了corrplot，实现了corrplot中绝大多数的功能，但仅支持“square”和“circle”的绘图标记，样式有些单调，不过整个ggcorrplot包的代码大概300行，想学习用ggplot2来自定义绘图函数，看这个包的源代码很不错。还有部分功能相似的corrr包（在写ggcor之前完全没有看过这个包，写完之后发现在相关系数矩阵变data.frame方面惊人的相似），这个包主要在数据相关系数提取、转换上做了很多的工作。ggcor的核心是为相关性分析、数据提取、转换、可视化提供一整套解决方案.
## 首先我们共同来学习一下厚哥这些函数
待会咱们要使用这些函数完成实战，也挑选出来我喜欢的几个可视化方案。这里的示例数据都是现成的，所以大家在这里对照运行即可。
if(!require(devtools)) install.packages(“devtools”) if(!require(ggcor)) devtools::install_github(“houyunhuang/ggcor”)导入r包和示例数据
suppressWarnings(suppressMessages(library("ggcor")))quickcor提供相关计算和出图转化的合并
首先快速计算和出图，默认使用cor计算相关，没有计算显著性
quickcor(mtcars) + geom_star()因为矩阵对象一样，所以需要学习如何修改为一半矩阵
quickcor(mtcars, type = "lower", show.diag = FALSE) + geom_square()没有显著性计算，我们是没办法进行确定下结论的，所以这里设置cor.test = TRUE。这是厚哥包中推荐的显著性标记凡方式，但是不免看出有些冗余
add_diag_label:功能似乎没有找到，？？？丢弃了吗？比较包是我刚下载的最新版本。
quickcor(mtcars, cor.test = TRUE) +
geom_square(data = get_data(type = "lower")) +
geom_mark(data = get_data(type = "upper")) +
# add_diag_label(size = 5, colour = "red") +
remove_axis()#
quickcor(mtcars, cor.test = TRUE,type = "lower", show.diag = FALSE) +
geom_square(data = get_data(p.value < 0.05, type = "lower")) +
geom_number(data = get_data(p.value < 0.05, type = "lower"),aes(num = r))quickcor(mtcars, cor.test = TRUE,type = "lower", show.diag = FALSE) +
geom_star(data = get_data(p.value < 0.05, type = "lower"))虽然可以出现我们喜欢的图片，但是相关求取的算法，还是需要可以修改和调整的,调整起来当然很简单，method = “kendall”参数修改即可：就是corr.test d的三个距离：“pearson”, “kendall”， “spearman”
quickcor(mtcars, cor.test = TRUE,type = "lower", show.diag = FALSE,method = "kendall") +
geom_star(data = get_data(p.value < 0.05, type = "lower"))提供两组数据之间相关的简易模式
这将简化我们的数据处理过程。
library(vegan)
data("varechem")
data("varespec")
quickcor(varespec, varechem,cor.test = TRUE,method = "pearson") +
geom_star()了解内部工作机制 ，如果你想了解的话，比较前面已经够用了
library(ggplot2)
library(tidyverse)
correlate(mtcars, cor.test = TRUE) %>%
as_cor_tbl() %>%
ggcor() + geom_point(aes(size = r, fill = r), shape = 21) +
scale_size_area(max_size = 10) +
theme(axis.title = element_blank()) +
coord_fixed(xlim = c(0.5, 11.5), ylim = c(0.5, 11.5))下面是我第一次学习ggcor的时候写的，现在需要修改
下面介绍几种本人喜欢的可视化方式，我这里统一将图例修改为离散型颜色：fill.bin = TRUE, legend.breaks = seq(-1, 1, length.out = 5)
注意一下开发版本才能添加颜色设置参数：,fill.bin = TRUE, legend.breaks = seq(-1, 1, length.out = 5) ，文末尾安装方式
#这里不仅仅展示了相关值，而且展示了置信区间,geom_cross用于排除不显著相关。
#
quickcor(mtcars, type = "full", cor.test = TRUE) + geom_confbox()+ geom_cross()# 这里使用方形我觉得高档一些，本人比较喜欢
quickcor(mtcars, type = "full", cor.test = TRUE) +
geom_square() + geom_cross()配合颜色填充和相关标注，加上显著性标签很容易整体把控指标的相关性。使用r = 这里厚哥添加的五角星，我们来了解一下。
# 这里使用方形我觉得高档一些，本人比较喜欢
quickcor(mtcars, type = "full", cor.test = TRUE) +
# geom_square() +
geom_star(n = 5)+
geom_cross()NA参数去除相关值，因为颜色已经表示过相关大小了，值就省略掉吧,mark = “*”参数规范统一的显著性标签。
#配合颜色填充和相关标注，加上显著性标签很容易整体把控指标的相关性。使用r = NA参数去除相关值，因为颜色已经表示过相关大小了，值就省略掉吧,mark = "*"参数规范统一的显著性标签。
quickcor(mtcars, type = "full", cor.test = TRUE, cluster.type = "all") +
# geom_raster() +
geom_colour()+
geom_mark(r = NA,sig.thres = 0.05, size = 3, colour = "grey90")群落矩阵和环境因子相关,这一套下来比较完整，并且可以很好的实现。
我们需要注意的是
data("varespec", package = "vegan")
data("varechem", package = "vegan")
df <- mantel_test(varespec, varechem)
library(ggplot2)
df <- df %>%
mutate(lty = cut(r, breaks = c(-Inf, 0, Inf),
labels = c("r <= 0", "r > 0")),
col = cut(p.value, breaks = c(0, 0.01, 0.05, 1),
labels = c("< 0.01", "< 0.05", ">= 0.05"),
right = FALSE, include.lowest = TRUE))
quickcor(varechem, type = "upper") +
geom_square() +
# add_diag_label() +
add_link(df, mapping = aes(colour = col,
size = r,
linetype = lty),diag.label = TRUE) +
scale_fill_gradient2n() +
scale_size_area(max_size = 3) +
scale_linetype_manual(values = c("dotted", "solid")) +
guides(
fill = guide_colourbar(title = "corr", order = 1),
colour = guide_legend(title = "Mantel's p", order = 2),
size = guide_legend(title = "Mantel's r", order = 3),
linetype = "none"
)df02 <- mantel_test(varespec, varechem,
spec.select = list(spec01 = 1:5,
spec02 = 6:12,
spec03 = 13:15,
spec03 = 13:17
)) %>%
mutate(lty = cut(r, breaks = c(-Inf, 0, Inf),
labels = c("r <= 0", "r > 0")),
col = cut(p.value, breaks = c(0, 0.01, 0.05, 1),
labels = c("< 0.01", "< 0.05", ">= 0.05"),
right = FALSE, include.lowest = TRUE))
extra.params <- extra_params(
spec.label = text_params(colour = "red", size = 7),
env.point = point_params(size = 2, fill = "grey80"),
spec.point = point_params(size = 4, shape = 24, fill = "red"),
link.params = link_params(env.point.hjust = -0.5,
env.point.vjust = -0.1,
spec.point.hjust = 1)
)
quickcor(varechem, type = "lower") +
geom_square() +
add_link(df02, mapping = aes(colour = col,
size = r,
linetype = lty),
diag.label = TRUE, spec.label.hspace = 0.5,
extra.params = extra.params) +
# add_diag_label(angle = 45) +
remove_axis("y") +
expand_axis(x = 25) + ## 扩展x轴范围
scale_fill_gradient2n() +
scale_colour_manual(values = c("#D95F02", "#1B9E77", "#D2D2D2")) +
scale_size_area(max_size = 3) +
scale_linetype_manual(values = c("dotted", "solid")) +
guides(
fill = guide_colourbar(title = "corr", order = 1),
colour = guide_legend(title = "Mantel's p", order = 2),
size = guide_legend(title = "Mantel's r", order = 3),
linetype = "none"
)三组数据做相关
厚哥这个设计我认为很好，因为综合环境指标，和其他指标相关，同时将群落纳入其中，更加丰度了数据和合并处理和结论的流畅度。
corr <- fortify_cor(varechem, varespec[1:6])
extra.params <- extra_params(
spec.label = text_params(colour = "red", size = 7),
env.point = point_params(size = 2, fill = "grey80"),
spec.point = point_params(size = 4, shape = 24, fill = "red"),
link.params = link_params(spec.point.hjust = 3)
)
quickcor(corr) +
geom_square() +
add_link(df02, mapping = aes(colour = col,
size = r,
linetype = lty),
spec.label.hspace = 0.5,
extra.params = extra.params) +
expand_axis(x = 15) +
scale_fill_gradient2n() +
scale_colour_manual(values = c("#D95F02", "#1B9E77", "#D2D2D2")) +
scale_size_area(max_size = 3) +
scale_linetype_manual(values = c("dotted", "solid")) +
guides(
fill = guide_colourbar(title = "corr", order = 1),
colour = guide_legend(title = "Mantel's p", order = 2),
size = guide_legend(title = "Mantel's r", order = 3),
linetype = "none"
)另外一种方式组合
library(cowplot)
mantel <- fortify_mantel(varespec, varechem,
spec.select = list(spec01 = 22:25,
spec02 = 1:4,
spec03 = 38:43,
spec04 = 15:20),
mantel.fun = "mantel.randtest")
mantel$p <- cut(mantel$p.value, breaks = c(0, 0.001, 0.01, 0.05, 1),
labels = c("< 0.001", "< 0.01", "< 0.05", ">= 0.05"),
right = FALSE, include.lowest = TRUE)
p1 <- quickcor(varechem) + geom_square() + remove_axis("x")
p2 <- quickcor(mantel, mapping = aes(fill = p.value), is.minimal = TRUE, keep.name = TRUE) +
geom_star(aes(r = 0.65), n = 5, ratio = 0.6)
plot_grid(p1, p2, ncol = 1, align = "v", labels = c('A', 'B'),
rel_heights = c(0.135*dim( varechem)[2], 1))实战
基于phloseq我开发了一系列基于扩增子的数据分析脚本，我也将再不久将这个脚本纳入，这里大家必须学习phyloseq的封装格式和基本用法。```{r began, echo=TRUE, message=FALSE, warning=FALSE, paged.print=FALSE}
library(“phyloseq”) library(microbiomeSeq) library(“vegan”) library(“grid”) library(“gridExtra”) library(“ggplot2”) ps = readRDS(“.//psOTU.rds”) ps1 = ps ps1 = filter_taxa(ps1, function(x) sum(x ) > 200 , TRUE);ps1 ps1 = transform_sample_counts(ps1, function(x) x / sum(x) );ps1
path = “./phyloseq_5_RDA_CCA_cor/“ dir.create(path)
vegan_otu <- function(physeq){ OTU <- otu_table(physeq) if(taxa_are_rows(OTU)){ OTU <- t(OTU) } return(as(OTU,”matrix”)) } otu = as.data.frame(t(vegan_otu(ps1)))
mapping = as.data.frame( sample_data(ps1)) env.dat = mapping[,3:ncol(sample_data(ps1))] env.st = decostand(env.dat, method=”standardize”, MARGIN=2)# env_dat = env.st
```{R}
#这里不仅仅展示了相关值，而且展示了置信区间,geom_cross用于排除不显著相关。
quickcor(env_dat, type = "full", cor.test = TRUE) + geom_confbox()+ geom_cross()这里使用方形我觉得高档一些，本人比较喜欢，将不显著的去掉。
# 这里使用方形我觉得高档一些，本人比较喜欢
quickcor(env_dat, type = "full", cor.test = TRUE) +
geom_square() + geom_cross()#配合颜色填充和相关标注，加上显著性标签很容易整体把控指标的相关性。使用r = NA参数去除相关值，因为颜色已经表示过相关大小了，值就省略掉吧,mark = "*"参数规范统一的显著性标签。
quickcor(env_dat, type = "full", cor.test = TRUE, cluster.type = "all") +
# geom_raster() +
geom_colour()+
geom_mark(r = NA,sig.thres = 0.05, size = 3, colour = "grey90")# 非对称相关图形可以节省空间，很多人曾求助怎么做，其实就是将最后的出图矩阵做相应的裁剪就好了，之前我都是自己裁剪的，现在厚哥包装进去了，方便了很多。
#计算相关
#太多OTU展示起来不太好看，这里我选择30个展示
ss = t(otu)[,1:30]
df03 <- fortify_cor(x = env_dat, y = ss, cluster.type = "col")
quickcor(df03) + geom_square()现在我们来组合群落和环境因子关系，这里我模拟了两个群落，这两个群落都是一样的，我通过list收纳这两个群落. xlim = c(-5, (dim(env_dat)[2] +0.5)):在厚哥的指点下修改为环境因子数量加0.5，厚哥表示可能之后这个参数会被写到函数内部。
#转置otu表格，作为第一个群落
otu2 = t(otu)
#同样赋值为第二个群落
otu3 = t(otu)
#无论多少个群落，将其使用list包起来，注意设置名称
spe = list(A = otu2,B = otu3,C = otu3,D = otu3)
a = dim(spe[[1]])[2]
b = dim(spe[[2]])[2]
c = dim(spe[[3]])[2]
d = dim(spe[[4]])[2]
spec.select = list(A = 1:a,
B = (a+1) :(b +a ),
C = (a +b +1) :(b +a +c),
D = (a +b +c +1) :(b +a +c +d)
)
df02 <- mantel_test(as.data.frame(spe), env_dat,
spec.select = spec.select) %>%
mutate(lty = cut(r, breaks = c(-Inf, 0, Inf),
labels = c("r <= 0", "r > 0")),
col = cut(p.value, breaks = c(0, 0.01, 0.05, 1),
labels = c("< 0.01", "< 0.05", ">= 0.05"),
right = FALSE, include.lowest = TRUE))
extra.params <- extra_params(
spec.label = text_params(colour = "red", size = 7),
env.point = point_params(size = 2, fill = "grey80"),
spec.point = point_params(size = 4, shape = 24, fill = "red"),
link.params = link_params(env.point.hjust = -0.5,
env.point.vjust = -0.1,
spec.point.hjust = 1)
)
quickcor(env_dat, type = "lower") +
geom_square() +
add_link(df02, mapping = aes(colour = col,
size = r,
linetype = lty),
diag.label = TRUE, spec.label.hspace = 0.5,
extra.params = extra.params) +
# add_diag_label(angle = 45) +
remove_axis("y") +
expand_axis(x = 25) + ## 扩展x轴范围
scale_fill_gradient2n() +
scale_colour_manual(values = c("#D95F02", "#1B9E77", "#D2D2D2")) +
scale_size_area(max_size = 3) +
scale_linetype_manual(values = c("dotted", "solid")) +
guides(
fill = guide_colourbar(title = "corr", order = 1),
colour = guide_legend(title = "Mantel's p", order = 2),
size = guide_legend(title = "Mantel's r", order = 3),
linetype = "none"
)另外一种可视化群落和环境因子关系的组合图表，B图需要调整大小，这里我本来以为是线性映射，做一个变量，显然不是，我还是老老实实修改了一下大小。
library(cowplot)
library(cowplot)
mantel <- fortify_mantel(as.data.frame(spe), env_dat,
spec.select = spec.select,
mantel.fun = "mantel.randtest")
mantel$p <- cut(mantel$p.value, breaks = c(0, 0.001, 0.01, 0.05, 1),
labels = c("< 0.001", "< 0.01", "< 0.05", ">= 0.05"),
right = FALSE, include.lowest = TRUE)
p1 <- quickcor(env_dat) + geom_square() + remove_axis("x")
p2 <- quickcor(mantel, mapping = aes(fill = p.value), is.minimal = TRUE, keep.name = TRUE) +
geom_star(aes(r = 0.65), n = 5, ratio = 0.6)
plot_grid(p1, p2, ncol = 1, align = "v", labels = c('A', 'B'),
rel_heights = c(0.14*dim( varechem)[2], 1))