如何用 R^2 为大数据矩阵绘制相关图？
How to plot correlation graphs with R^2 for a big datamatrix?
我有一个蛋白质组学数据矩阵。在数据矩阵中，我检测到每种蛋白质的肽数量不同（可检测的肽数量因蛋白质而异）。
Q1。我如何绘制每种蛋白质的相关图以比较其肽的行为方式。即对于蛋白质 A，我有肽 a1-a3，我想比较 a1 与 a2、a1 与 a3 以及 a2 与 a3。
示例数据
structure(list(Protein = c("A", "A", "A", "A", "B", "C", "C", "D", "D", "D"), Peptide = c("a1", "a2", "a3", "a4", "b1", "c1", "c2", "d1", "d2", "d3"), Sample1 = c(0.275755732, 0.683048798, 1.244604878, 0.850270313, 0.492175199, 0.269651338, 0.393004954, 0.157966662, 1.681672581, 0.298308801), Sample2 = c(0.408992244, 0.172488244, 1.749247694, 0.358172308, 0.142129982, 0.158636283, 0.243500648, 0.095019037, 0.667928805, 0.572162278), Sample3 = c(0.112265765, 0.377174168, 2.430040623, 0.497873323, 0.141136584, 0.250330266, 0.249783164, 0.107188279, 0.173623439, 0.242298602), Sample4 = c(0.87688073, 0.841826338, 0.831376575, 0.985900966, 0.891632525, 1.016533723, 0.292048735, 0.776351689, 0.800070173, 1.161882923), Sample5 = c(1.034093889, 0.304305772, 0.616445765, 1.000820463, 1.03124071, 0.995897846, 0.289542364, 0.578721727, 0.672592766, 1.168944588), Sample6 = c(1.063124715, 0.623917522, 0.613196611, 0.990921045, 1.014340981, 0.965631141, 0.316793011, 1.02220535, 1.182063616, 1.41196421), Sample7 = c(1.335677026, 0.628621656, 0.411171453, 1.050563412, 1.290233552, 1.1603839, 0.445372411, 1.077192698, 0.726669337, 1.09453338), Sample8 = c(1.139360562, 0.404024829, 0.263714711, 0.899959209, 1.356913804, 1.246338203, 0.426568548, 1.104988267, 0.964924824, 1.083654341), Sample9 = c(1.38146599, 0.582817437, 0.783698738, 1.118948066, 1.010795866, 1.277086848, 0.434025911, 1.238871048, 1.201184368, 1.476478831), Sample10 = c(1.111486801, 0.60513273, 0.460680037, 1.385702246, 1.448873253, 1.364329784, 0.375032044, 1.382750002, 0.741842319, 1.035657705)), row.names = c(NA, -10L), class = c("tbl_df", "tbl", "data.frame"), spec = structure(list( cols = list(Protein = structure(list(), class = c("collector_character", "collector")), Peptide = structure(list(), class = c("collector_character", "collector")), Sample1 = structure(list(), class = c("collector_double", "collector")), Sample2 = structure(list(), class = c("collector_double", "collector")), Sample3 = structure(list(), class = c("collector_double", "collector")), Sample4 = structure(list(), class = c("collector_double", "collector")), Sample5 = structure(list(), class = c("collector_double", "collector")), Sample6 = structure(list(), class = c("collector_double", "collector")), Sample7 = structure(list(), class = c("collector_double", "collector")), Sample8 = structure(list(), class = c("collector_double", "collector")), Sample9 = structure(list(), class = c("collector_double", "collector")), Sample10 = structure(list(), class = c("collector_double", "collector"))), default = structure(list(), class = c("collector_guess", "collector"))), class = "col_spec"))
因此，每种蛋白质的肽数都不同，我如何比较每个肽并将多面图保存为单个图，这样，我可以 select 仅需要的图。
"Hence peptide number varies for each protein, how can I compare each peptide and save the faceted graph into single plots, by this, I can select only required graphs." 我不完全确定 你到底想画什么。哪些数量的相关图？ Select 只有 哪个 需要图表？
无论如何，也许以下内容会有所帮助。
library(GGally)
library(tidyverse)
df %>%
gather(Sample, Value, -Protein, -Peptide) %>%
spread(Peptide, Value) %>%
filter(Protein == "A") %>%
ggpairs(columns = 3:6)
解释：我们重塑数据，使列中的每个 Peptide 都有 Value；然后我们过滤 Protein == "A" 的条目并使用 GGally::ggpairs 显示每个 Peptide.
的 Value 的成对相关图
您可以非常灵活地自定义 ggpairs 的输出图（例如添加回归线、删除面板等）；我建议看看 GGally GitHub project page and at Multiple regression lines in ggpairs.
更新
如果您只想显示某些 Peptide 的相关图，您可以执行以下操作
pep_of_interest <- c("a2", "a4")
df %>%
gather(Sample, Value, -Protein, -Peptide) %>%
spread(Peptide, Value) %>%
filter(Protein == "A") %>%
ggpairs(columns = match(pep_of_interest, colnames(.)))
如果您正在寻找相关性的视觉表示，这里有一个使用 corrplot 库的解决方案。库中提供了更多绘图选项（查看 corrplot vignette）。
# sample data
dd <- structure(list(Protein = c("A", "A", "A", "A", "B", "C", "C", "D", "D", "D"), Peptide = c("a1", "a2", "a3", "a4", "b1", "c1", "c2", "d1", "d2", "d3"), Sample1 = c(0.275755732, 0.683048798, 1.244604878, 0.850270313, 0.492175199, 0.269651338, 0.393004954, 0.157966662, 1.681672581, 0.298308801), Sample2 = c(0.408992244, 0.172488244, 1.749247694, 0.358172308, 0.142129982, 0.158636283, 0.243500648, 0.095019037, 0.667928805, 0.572162278), Sample3 = c(0.112265765, 0.377174168, 2.430040623, 0.497873323, 0.141136584, 0.250330266, 0.249783164, 0.107188279, 0.173623439, 0.242298602), Sample4 = c(0.87688073, 0.841826338, 0.831376575, 0.985900966, 0.891632525, 1.016533723, 0.292048735, 0.776351689, 0.800070173, 1.161882923), Sample5 = c(1.034093889, 0.304305772, 0.616445765, 1.000820463, 1.03124071, 0.995897846, 0.289542364, 0.578721727, 0.672592766, 1.168944588), Sample6 = c(1.063124715, 0.623917522, 0.613196611, 0.990921045, 1.014340981, 0.965631141, 0.316793011, 1.02220535, 1.182063616, 1.41196421), Sample7 = c(1.335677026, 0.628621656, 0.411171453, 1.050563412, 1.290233552, 1.1603839, 0.445372411, 1.077192698, 0.726669337, 1.09453338), Sample8 = c(1.139360562, 0.404024829, 0.263714711, 0.899959209, 1.356913804, 1.246338203, 0.426568548, 1.104988267, 0.964924824, 1.083654341), Sample9 = c(1.38146599, 0.582817437, 0.783698738, 1.118948066, 1.010795866, 1.277086848, 0.434025911, 1.238871048, 1.201184368, 1.476478831), Sample10 = c(1.111486801, 0.60513273, 0.460680037, 1.385702246, 1.448873253, 1.364329784, 0.375032044, 1.382750002, 0.741842319, 1.035657705)), row.names = c(NA, -10L), class = c("tbl_df", "tbl", "data.frame"), spec = structure(list( cols = list(Protein = structure(list(), class = c("collector_character", "collector")), Peptide = structure(list(), class = c("collector_character", "collector")), Sample1 = structure(list(), class = c("collector_double", "collector")), Sample2 = structure(list(), class = c("collector_double", "collector")), Sample3 = structure(list(), class = c("collector_double", "collector")), Sample4 = structure(list(), class = c("collector_double", "collector")), Sample5 = structure(list(), class = c("collector_double", "collector")), Sample6 = structure(list(), class = c("collector_double", "collector")), Sample7 = structure(list(), class = c("collector_double", "collector")), Sample8 = structure(list(), class = c("collector_double", "collector")), Sample9 = structure(list(), class = c("collector_double", "collector")), Sample10 = structure(list(), class = c("collector_double", "collector"))), default = structure(list(), class = c("collector_guess", "collector"))), class = "col_spec"))
# for Protein A, build subset of data
tempdd <- dd[dd$Protein == "A",][,-1]
cc <- tempdd[,1]
tempdd <- t(tempdd[,-1])
colnames(tempdd) <- cc
# calculate the correlations for all samples
rr <- cor(tempdd)
# install.packages("corrplot")
library(corrplot)
#Build the plot
corrplot(rr,method='circle')
我有一个蛋白质组学数据矩阵。在数据矩阵中，我检测到每种蛋白质的肽数量不同（可检测的肽数量因蛋白质而异）。
Q1。我如何绘制每种蛋白质的相关图以比较其肽的行为方式。即对于蛋白质 A，我有肽 a1-a3，我想比较 a1 与 a2、a1 与 a3 以及 a2 与 a3。
示例数据
structure(list(Protein = c("A", "A", "A", "A", "B", "C", "C", "D", "D", "D"), Peptide = c("a1", "a2", "a3", "a4", "b1", "c1", "c2", "d1", "d2", "d3"), Sample1 = c(0.275755732, 0.683048798, 1.244604878, 0.850270313, 0.492175199, 0.269651338, 0.393004954, 0.157966662, 1.681672581, 0.298308801), Sample2 = c(0.408992244, 0.172488244, 1.749247694, 0.358172308, 0.142129982, 0.158636283, 0.243500648, 0.095019037, 0.667928805, 0.572162278), Sample3 = c(0.112265765, 0.377174168, 2.430040623, 0.497873323, 0.141136584, 0.250330266, 0.249783164, 0.107188279, 0.173623439, 0.242298602), Sample4 = c(0.87688073, 0.841826338, 0.831376575, 0.985900966, 0.891632525, 1.016533723, 0.292048735, 0.776351689, 0.800070173, 1.161882923), Sample5 = c(1.034093889, 0.304305772, 0.616445765, 1.000820463, 1.03124071, 0.995897846, 0.289542364, 0.578721727, 0.672592766, 1.168944588), Sample6 = c(1.063124715, 0.623917522, 0.613196611, 0.990921045, 1.014340981, 0.965631141, 0.316793011, 1.02220535, 1.182063616, 1.41196421), Sample7 = c(1.335677026, 0.628621656, 0.411171453, 1.050563412, 1.290233552, 1.1603839, 0.445372411, 1.077192698, 0.726669337, 1.09453338), Sample8 = c(1.139360562, 0.404024829, 0.263714711, 0.899959209, 1.356913804, 1.246338203, 0.426568548, 1.104988267, 0.964924824, 1.083654341), Sample9 = c(1.38146599, 0.582817437, 0.783698738, 1.118948066, 1.010795866, 1.277086848, 0.434025911, 1.238871048, 1.201184368, 1.476478831), Sample10 = c(1.111486801, 0.60513273, 0.460680037, 1.385702246, 1.448873253, 1.364329784, 0.375032044, 1.382750002, 0.741842319, 1.035657705)), row.names = c(NA, -10L), class = c("tbl_df", "tbl", "data.frame"), spec = structure(list( cols = list(Protein = structure(list(), class = c("collector_character", "collector")), Peptide = structure(list(), class = c("collector_character", "collector")), Sample1 = structure(list(), class = c("collector_double", "collector")), Sample2 = structure(list(), class = c("collector_double", "collector")), Sample3 = structure(list(), class = c("collector_double", "collector")), Sample4 = structure(list(), class = c("collector_double", "collector")), Sample5 = structure(list(), class = c("collector_double", "collector")), Sample6 = structure(list(), class = c("collector_double", "collector")), Sample7 = structure(list(), class = c("collector_double", "collector")), Sample8 = structure(list(), class = c("collector_double", "collector")), Sample9 = structure(list(), class = c("collector_double", "collector")), Sample10 = structure(list(), class = c("collector_double", "collector"))), default = structure(list(), class = c("collector_guess", "collector"))), class = "col_spec"))
因此，每种蛋白质的肽数都不同，我如何比较每个肽并将多面图保存为单个图，这样，我可以 select 仅需要的图。
"Hence peptide number varies for each protein, how can I compare each peptide and save the faceted graph into single plots, by this, I can select only required graphs." 我不完全确定 你到底想画什么。哪些数量的相关图？ Select 只有 哪个 需要图表？
无论如何，也许以下内容会有所帮助。
library(GGally)
library(tidyverse)
df %>%
gather(Sample, Value, -Protein, -Peptide) %>%
spread(Peptide, Value) %>%
filter(Protein == "A") %>%
ggpairs(columns = 3:6)
解释：我们重塑数据，使列中的每个 Peptide 都有 Value；然后我们过滤 Protein == "A" 的条目并使用 GGally::ggpairs 显示每个 Peptide.
Value 的成对相关图
您可以非常灵活地自定义 ggpairs 的输出图（例如添加回归线、删除面板等）；我建议看看 GGally GitHub project page and at Multiple regression lines in ggpairs.
更新
如果您只想显示某些 Peptide 的相关图，您可以执行以下操作
pep_of_interest <- c("a2", "a4")
df %>%
gather(Sample, Value, -Protein, -Peptide) %>%
spread(Peptide, Value) %>%
filter(Protein == "A") %>%
ggpairs(columns = match(pep_of_interest, colnames(.)))
如果您正在寻找相关性的视觉表示，这里有一个使用 corrplot 库的解决方案。库中提供了更多绘图选项（查看 corrplot vignette）。
# sample data
dd <- structure(list(Protein = c("A", "A", "A", "A", "B", "C", "C", "D", "D", "D"), Peptide = c("a1", "a2", "a3", "a4", "b1", "c1", "c2", "d1", "d2", "d3"), Sample1 = c(0.275755732, 0.683048798, 1.244604878, 0.850270313, 0.492175199, 0.269651338, 0.393004954, 0.157966662, 1.681672581, 0.298308801), Sample2 = c(0.408992244, 0.172488244, 1.749247694, 0.358172308, 0.142129982, 0.158636283, 0.243500648, 0.095019037, 0.667928805, 0.572162278), Sample3 = c(0.112265765, 0.377174168, 2.430040623, 0.497873323, 0.141136584, 0.250330266, 0.249783164, 0.107188279, 0.173623439, 0.242298602), Sample4 = c(0.87688073, 0.841826338, 0.831376575, 0.985900966, 0.891632525, 1.016533723, 0.292048735, 0.776351689, 0.800070173, 1.161882923), Sample5 = c(1.034093889, 0.304305772, 0.616445765, 1.000820463, 1.03124071, 0.995897846, 0.289542364, 0.578721727, 0.672592766, 1.168944588), Sample6 = c(1.063124715, 0.623917522, 0.613196611, 0.990921045, 1.014340981, 0.965631141, 0.316793011, 1.02220535, 1.182063616, 1.41196421), Sample7 = c(1.335677026, 0.628621656, 0.411171453, 1.050563412, 1.290233552, 1.1603839, 0.445372411, 1.077192698, 0.726669337, 1.09453338), Sample8 = c(1.139360562, 0.404024829, 0.263714711, 0.899959209, 1.356913804, 1.246338203, 0.426568548, 1.104988267, 0.964924824, 1.083654341), Sample9 = c(1.38146599, 0.582817437, 0.783698738, 1.118948066, 1.010795866, 1.277086848, 0.434025911, 1.238871048, 1.201184368, 1.476478831), Sample10 = c(1.111486801, 0.60513273, 0.460680037, 1.385702246, 1.448873253, 1.364329784, 0.375032044, 1.382750002, 0.741842319, 1.035657705)), row.names = c(NA, -10L), class = c("tbl_df", "tbl", "data.frame"), spec = structure(list( cols = list(Protein = structure(list(), class = c("collector_character", "collector")), Peptide = structure(list(), class = c("collector_character", "collector")), Sample1 = structure(list(), class = c("collector_double", "collector")), Sample2 = structure(list(), class = c("collector_double", "collector")), Sample3 = structure(list(), class = c("collector_double", "collector")), Sample4 = structure(list(), class = c("collector_double", "collector")), Sample5 = structure(list(), class = c("collector_double", "collector")), Sample6 = structure(list(), class = c("collector_double", "collector")), Sample7 = structure(list(), class = c("collector_double", "collector")), Sample8 = structure(list(), class = c("collector_double", "collector")), Sample9 = structure(list(), class = c("collector_double", "collector")), Sample10 = structure(list(), class = c("collector_double", "collector"))), default = structure(list(), class = c("collector_guess", "collector"))), class = "col_spec"))
# for Protein A, build subset of data
tempdd <- dd[dd$Protein == "A",][,-1]
cc <- tempdd[,1]
tempdd <- t(tempdd[,-1])
colnames(tempdd) <- cc
# calculate the correlations for all samples
rr <- cor(tempdd)
# install.packages("corrplot")
library(corrplot)
#Build the plot
corrplot(rr,method='circle')