僅在 R 中按組的許多變量的相關性 plot
[英]correlation plot for many variables by group only in R
問題描述
我需要建立一個相關性 plot（類似於我們從“corrplot”包中得到的東西），但我有太多變量並且不想在 plot 上擁有所有變量名稱。 我希望同一組中的每個變量彼此相鄰，組名位於它們之上（請參閱底部的示例）。
我的數據集看起來像這樣
你可以從這里得到它
sub_my_data <-
structure(
list(
metabolites = c(
"Acetate",
"Acetoacetate",
"Acetone",
"Ala",
"Albumin",
"ApoA1",
"ApoB",
"ApoB_by_ApoA1",
"bOHbutyrate",
"Cholines",
"Citrate",
"Clinical_LDL_C",
"Creatinine",
"DHA",
"Gln",
"Glucose",
"Gly",
"GlycA",
"HDL_C",
"HDL_CE",
"HDL_FC",
"HDL_L",
"HDL_P",
"HDL_PL",
"HDL_size",
"HDL_TG",
"His",
"IDL_C",
"IDL_CE",
"IDL_FC",
"IDL_L",
"IDL_P",
"IDL_PL",
"IDL_TG",
"Ile",
"L_HDL_C",
"L_HDL_CE",
"L_HDL_FC",
"L_HDL_L",
"L_HDL_P",
"L_HDL_PL",
"L_HDL_TG",
"L_LDL_C",
"L_LDL_CE",
"L_LDL_FC",
"L_LDL_L",
"L_LDL_P",
"L_LDL_PL",
"L_LDL_TG",
"L_VLDL_C",
"L_VLDL_CE",
"L_VLDL_FC",
"L_VLDL_L",
"L_VLDL_P",
"L_VLDL_PL",
"L_VLDL_TG",
"LA",
"Lactate",
"LDL_C",
"LDL_CE",
"LDL_FC",
"LDL_L",
"LDL_P",
"LDL_PL",
"LDL_size",
"LDL_TG",
"Leu",
"M_HDL_C",
"M_HDL_CE",
"M_HDL_FC",
"M_HDL_L",
"M_HDL_P",
"M_HDL_PL",
"M_HDL_TG",
"M_LDL_C",
"M_LDL_CE",
"M_LDL_FC",
"M_LDL_L",
"M_LDL_P",
"M_LDL_PL",
"M_LDL_TG",
"M_VLDL_C",
"M_VLDL_CE",
"M_VLDL_FC",
"M_VLDL_L",
"M_VLDL_P",
"M_VLDL_PL",
"M_VLDL_TG",
"MUFA",
"non_HDL_C",
"Omega_3",
"Omega_6",
"Phe",
"Phosphatidylc",
"Phosphoglyc",
"PUFA",
"Pyruvate",
"Remnant_C",
"S_HDL_C",
"S_HDL_CE",
"S_HDL_FC",
"S_HDL_L",
"S_HDL_P",
"S_HDL_PL",
"S_HDL_TG",
"S_LDL_C",
"S_LDL_CE",
"S_LDL_FC",
"S_LDL_L",
"S_LDL_P",
"S_LDL_PL",
"S_LDL_TG",
"S_VLDL_C",
"S_VLDL_CE",
"S_VLDL_FC",
"S_VLDL_L",
"S_VLDL_P",
"S_VLDL_PL",
"S_VLDL_TG",
"SFA",
"Sphingomyelins",
"TG_by_PG",
"Total_BCAA",
"Total_C",
"Total_CE",
"Total_FA",
"Total_FC",
"Total_L",
"Total_P",
"Total_PL",
"Total_TG",
"Tyr",
"Unsaturation",
"Val",
"VLDL_C",
"VLDL_CE",
"VLDL_FC",
"VLDL_L",
"VLDL_P",
"VLDL_PL",
"VLDL_size",
"VLDL_TG",
"XL_HDL_C",
"XL_HDL_CE",
"XL_HDL_FC",
"XL_HDL_L",
"XL_HDL_P",
"XL_HDL_PL",
"XL_HDL_TG",
"XL_VLDL_C",
"XL_VLDL_CE",
"XL_VLDL_FC",
"XL_VLDL_L",
"XL_VLDL_P",
"XL_VLDL_PL",
"XL_VLDL_TG",
"XS_VLDL_C",
"XS_VLDL_CE",
"XS_VLDL_FC",
"XS_VLDL_L",
"XS_VLDL_P",
"XS_VLDL_PL",
"XS_VLDL_TG",
"XXL_VLDL_C",
"XXL_VLDL_CE",
"XXL_VLDL_FC",
"XXL_VLDL_L",
"XXL_VLDL_P",
"XXL_VLDL_PL",
"XXL_VLDL_TG"
),
Group = c(
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Amino acids",
"Lipoprotein subclasses",
"Apolipoproteins",
"Apolipoproteins",
"Apolipoproteins",
"Lipoprotein subclasses",
"Other lipids",
"Lipoprotein subclasses",
"Cholesterol",
"Lipoprotein subclasses",
"Fatty acids",
"Glycolysis related metabolites",
"Fluid balance",
"Glycolysis related metabolites",
"Lipoprotein subclasses",
"Cholesterol",
"Cholesteryl esters",
"Free cholesterol",
"Total lipids",
"Lipoprotein particle concentrations",
"Phospholipids",
"Lipoprotein particle sizes",
"Triglycerides",
"Glycolysis related metabolites",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Glycolysis related metabolites",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Fatty acids",
"Fluid balance",
"Cholesterol",
"Cholesteryl esters",
"Free cholesterol",
"Total lipids",
"Lipoprotein particle concentrations",
"Phospholipids",
"Lipoprotein particle sizes",
"Triglycerides",
"Ketone bodies",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Fatty acids",
"Cholesterol",
"Fatty acids",
"Fatty acids",
"Ketone bodies",
"Other lipids",
"Other lipids",
"Fatty acids",
"Inflammation",
"Cholesterol",
"",
"",
"",
"",
"",
"",
"",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Fatty acids",
"Other lipids",
"Other lipids",
"Glycolysis related metabolites",
"Cholesterol",
"Cholesteryl esters",
"Fatty acids",
"Free cholesterol",
"Total lipids",
"Lipoprotein particle concentrations",
"Phospholipids",
"Triglycerides",
"Ketone bodies",
"Fatty acids",
"Ketone bodies",
"Cholesterol",
"Cholesteryl esters",
"Free cholesterol",
"Total lipids",
"Lipoprotein particle concentrations",
"Phospholipids",
"Lipoprotein particle sizes",
"Triglycerides",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses",
"Lipoprotein subclasses"
),
V1 = c(
0.44,
0.08,
0.11,
0.42,
0.58,
0.34,
0.22,
0.23,
0.12,
0.28,
0.34,
0.29,
0.56,
0.43,
0.43,
0.25,
0.62,
0.18,
0.37,
0.39,
0.33,
0.34,
0.35,
0.34,
0.39,
0.18,
0.51,
0.31,
0.3,
0.32,
0.25,
0.16,
0.21,
0.06,
0.51,
0.4,
0.42,
0.36,
0.38,
0.38,
0.38,
0.14,
0.31,
0.31,
0.35,
0.28,
0.23,
0.28,
0.06,
0.16,
0.19,
0.13,
0.1,
0.09,
0.1,
0.09,
0.14,
0.4,
0.3,
0.29,
0.34,
0.27,
0.24,
0.28,
0.63,
0.06,
0.73,
0.4,
0.42,
0.35,
0.4,
0.39,
0.4,
0.2,
0.29,
0.26,
0.35,
0.27,
0.27,
0.28,
0.07,
0.25,
0.26,
0.22,
0.18,
0.22,
0.2,
0.12,
0.11,
0.24,
0.3,
0.19,
0.54,
0.31,
0.3,
0.21,
0.2,
0.17,
0.49,
0.6,
0.32,
0.35,
0.47,
0.35,
0.18,
0.27,
0.24,
0.37,
0.25,
0.22,
0.25,
0.05,
0.19,
0.18,
0.23,
0.16,
0.15,
0.21,
0.15,
0.15,
0.27,
0.1,
0.69,
0.3,
0.31,
0.16,
0.23,
0.22,
0.34,
0.27,
0.07,
0.49,
0.57,
0.74,
0.16,
0.17,
0.15,
0.1,
0.14,
0.12,
0.36,
0.07,
0.35,
0.36,
0.3,
0.32,
0.31,
0.32,
0.1,
0.12,
0.17,
0.09,
0.08,
0.08,
0.08,
0.07,
0.13,
0.16,
0.07,
0.08,
0.09,
0.05,
0.12,
0.03,
0.01,
0.05,
0.03,
0.02,
0.03,
0.04
),
V2 = c(
0.48,
0,
0.38,
0.18,
0.25,
0.5,
0.16,
0.12,
0.6,
0.43,
0.5,
0.09,
0.3,
0.29,
0.09,
0.22,
0.46,
0.21,
0.45,
0.45,
0.47,
0.51,
0.41,
0.55,
0.55,
0.52,
0.08,
0.17,
0.17,
0.17,
0.18,
0.06,
0.19,
0.38,
0.06,
0.51,
0.52,
0.49,
0.53,
0.52,
0.56,
0.42,
0.15,
0.17,
0.13,
0.15,
0.19,
0.09,
0.33,
0.25,
0.27,
0.22,
0.19,
0.19,
0.23,
0.17,
0.26,
0.35,
0.15,
0.17,
0.09,
0.15,
0.17,
0.11,
0.75,
0.35,
0.08,
0.5,
0.51,
0.49,
0.57,
0.54,
0.61,
0.55,
0.14,
0.16,
0.09,
0.16,
0.12,
0.14,
0.35,
0.16,
0.12,
0.2,
0.23,
0.22,
0.22,
0.24,
0.38,
0.14,
0.42,
0.36,
0.13,
0.51,
0.49,
0.38,
0.12,
0.13,
0.38,
0.46,
0.41,
0.43,
0.4,
0.49,
0.45,
0.14,
0.16,
0.07,
0.16,
0.18,
0.15,
0.28,
0.22,
0.23,
0.21,
0.3,
0.3,
0.26,
0.4,
0.33,
0.24,
0.28,
0.11,
0.23,
0.24,
0.38,
0.2,
0.29,
0.39,
0.4,
0.25,
0.16,
0.46,
0.16,
0.21,
0.19,
0.23,
0.21,
0.26,
0.24,
0.44,
0.21,
0.42,
0.44,
0.34,
0.44,
0.43,
0.46,
0.35,
0.21,
0.22,
0.19,
0.19,
0.2,
0.19,
0.2,
0.18,
0.17,
0.2,
0.24,
0.22,
0.25,
0.48,
0.18,
0.15,
0.21,
0.17,
0.18,
0.19,
0.16
),
V3 = c(
0.66,
0,
0.25,
0.21,
0.31,
0.74,
0.31,
0.14,
0.48,
0.66,
0.43,
0.36,
0.37,
0.45,
0.31,
0.2,
1,
0.29,
0.72,
0.71,
0.74,
0.76,
0.66,
0.8,
0.65,
0.49,
0.3,
0.48,
0.47,
0.49,
0.47,
0.31,
0.46,
0.39,
0.08,
0.74,
0.74,
0.71,
0.76,
0.73,
0.81,
0.48,
0.43,
0.43,
0.44,
0.42,
0.31,
0.38,
0.38,
0.15,
0.19,
0.12,
0.09,
0.09,
0.11,
0.06,
0.36,
0.37,
0.4,
0.4,
0.41,
0.39,
0.31,
0.36,
0.66,
0.37,
0.13,
0.75,
0.75,
0.76,
0.8,
0.77,
0.84,
0.52,
0.36,
0.35,
0.37,
0.35,
0.31,
0.32,
0.36,
0.3,
0.31,
0.28,
0.22,
0.25,
0.26,
0.13,
0.36,
0.36,
0.41,
0.45,
0.16,
0.72,
0.7,
0.47,
0.12,
0.31,
0.58,
0.61,
0.64,
0.57,
0.57,
0.63,
0.34,
0.31,
0.3,
0.36,
0.32,
0.29,
0.34,
0.22,
0.27,
0.26,
0.3,
0.28,
0.26,
0.3,
0.28,
0.42,
0.55,
0.1,
0.14,
0.53,
0.54,
0.43,
0.45,
0.48,
0.64,
0.65,
0.16,
0.19,
0.47,
0.17,
0.25,
0.26,
0.22,
0.15,
0.27,
0.2,
0.21,
0.09,
0.6,
0.62,
0.52,
0.6,
0.59,
0.61,
0.38,
0.13,
0.17,
0.09,
0.07,
0.08,
0.08,
0.06,
0.37,
0.39,
0.32,
0.35,
0.34,
0.31,
0.43,
0.05,
0.03,
0.08,
0.03,
0.04,
0.05,
0.02
),
V4 = c(
0.66,
0.14,
0.14,
0.43,
0.38,
0.3,
0.28,
0.31,
0.15,
0.28,
0.47,
0.38,
0.22,
0.23,
0.07,
0.28,
0.5,
0.51,
0.32,
0.33,
0.28,
0.28,
0.32,
0.28,
0.31,
0.16,
0.29,
0.39,
0.37,
0.41,
0.32,
0.26,
0.29,
0.07,
0.41,
0.32,
0.33,
0.3,
0.3,
0.3,
0.3,
0.1,
0.38,
0.37,
0.43,
0.35,
0.31,
0.37,
0.09,
0.18,
0.22,
0.14,
0.09,
0.08,
0.11,
0.06,
0.21,
0.53,
0.37,
0.35,
0.43,
0.35,
0.31,
0.36,
0.73,
0.09,
0.5,
0.35,
0.38,
0.3,
0.35,
0.34,
0.35,
0.18,
0.35,
0.31,
0.44,
0.34,
0.29,
0.36,
0.1,
0.32,
0.35,
0.27,
0.19,
0.25,
0.24,
0.08,
0.21,
0.31,
0.1,
0.26,
0.37,
0.25,
0.29,
0.24,
0.34,
0.25,
0.52,
0.64,
0.31,
0.37,
0.51,
0.37,
0.2,
0.34,
0.31,
0.44,
0.31,
0.28,
0.31,
0.07,
0.25,
0.24,
0.28,
0.17,
0.15,
0.24,
0.09,
0.17,
0.36,
0.08,
0.47,
0.34,
0.36,
0.21,
0.28,
0.25,
0.32,
0.29,
0.06,
0.93,
0.48,
0.47,
0.22,
0.23,
0.2,
0.11,
0.17,
0.16,
0.36,
0.05,
0.31,
0.32,
0.29,
0.28,
0.27,
0.27,
0.06,
0.16,
0.22,
0.11,
0.09,
0.09,
0.11,
0.06,
0.18,
0.21,
0.12,
0.12,
0.14,
0.1,
0.11,
0.08,
0.06,
0.1,
0.08,
0.06,
0.09,
0.08
),
V5 = c(
0.44,
0.36,
0.06,
0.55,
0.79,
0.57,
0.2,
0.13,
0.16,
0.45,
0.55,
0.27,
0.24,
0.44,
0.15,
0.17,
0.47,
0.62,
0.59,
0.6,
0.55,
0.59,
0.53,
0.61,
0.55,
0.26,
0.34,
0.34,
0.32,
0.36,
0.3,
0.13,
0.27,
0.18,
0.35,
0.61,
0.62,
0.56,
0.6,
0.57,
0.63,
0.24,
0.28,
0.28,
0.32,
0.27,
0.22,
0.27,
0.19,
0.13,
0.15,
0.1,
0.08,
0.07,
0.08,
0.07,
0.21,
0.58,
0.28,
0.27,
0.3,
0.26,
0.23,
0.26,
0.68,
0.19,
0.36,
0.63,
0.64,
0.59,
0.64,
0.62,
0.68,
0.28,
0.28,
0.27,
0.29,
0.27,
0.25,
0.24,
0.19,
0.23,
0.26,
0.19,
0.16,
0.19,
0.17,
0.1,
0.23,
0.23,
0.31,
0.29,
0.39,
0.41,
0.46,
0.3,
0.36,
0.19,
0.55,
0.63,
0.46,
0.47,
0.53,
0.51,
0.2,
0.25,
0.23,
0.31,
0.23,
0.19,
0.22,
0.12,
0.17,
0.15,
0.19,
0.15,
0.14,
0.19,
0.17,
0.27,
0.51,
0.08,
0.38,
0.36,
0.38,
0.28,
0.29,
0.31,
0.5,
0.44,
0.09,
0.39,
0.6,
0.41,
0.16,
0.16,
0.15,
0.1,
0.15,
0.12,
0.27,
0.07,
0.49,
0.51,
0.42,
0.48,
0.45,
0.47,
0.18,
0.1,
0.13,
0.08,
0.06,
0.07,
0.07,
0.05,
0.18,
0.21,
0.14,
0.15,
0.15,
0.12,
0.22,
0.06,
0.03,
0.09,
0.06,
0.05,
0.06,
0.07
)
),
class = "data.frame",
row.names = c(NA,-170L)
)
名稱為 Va、V2、...等的列代表參與者。
我嘗試了這段代碼，但它給了我一個小姐 plot，組名在每個變量上重復
sub_my_data<- sub_my_data[,-1]
tra3<- t( sub_my_data)
rownames(tra3) <- NULL
colnames(tra3) <- tra3[1,]
tra3 <- tra3[-1, ]
tra3<- as.data.frame(tra3)
str(tra3)
names(tra3)
for (t in 1:170) {
tra3[,t]<-as.numeric(tra3[,t])
}
tiff('metabolites correlation plot2.jpg', width = 5000, height = 6000, res=300)
corrplot(cor(tra3))
dev.off()
但是，它沒有用！
希望有這樣的東西
先感謝您！
1 個解決方案
解決方案1
0 2022-08-05 13:14:14
我仍然不太相信這種表示，但這里有一些提示可以讓它看起來像你想要的那樣：
sub_my_data<- sub_my_data[order(sub_my_data$Group),]
sub_my_data$metabolites=factor(sub_my_data$metabolites,levels=sub_my_data$metabolites)
Group=table(sub_my_data$Group)
sub_my_data<- sub_my_data[,-2]
tra3<- t( sub_my_data)
rownames(tra3) <- NULL
colnames(tra3) <- tra3[1,]
tra3 <- tra3[-1, ]
tra3<- as.data.frame(tra3)
str(tra3)
names(tra3)
for (t in 1:170) {
tra3[,t]<-as.numeric(tra3[,t])
}
par(mar=c(5,5,5,5),xpd=NA)
corrplot(cor(tra3),tl.pos='n',mar=c(5,5,5,5))
n=sum(Group)
for (k in 1:length(names(Group))){
mtext(text = names(Group)[k], side = 2, line = -2.5, at = n-(Group[[k]]/2), las = 1,cex=0.5 )
n=n-Group[[k]]
}
n=0
for (k in 1:length(names(Group))){
text(labels = names(Group)[k], y=sum(Group)+1, x = n+(Group[[k]]/2),srt = 90,adj=0,cex=0.5)
n=n+Group[[k]]
}
您需要調整參數以使其適應您的 R session，尤其是邊距。 使用 mtext 和 text，我將 label Group 添加到與 Group 相關的樣本集群的中間。 假設您可以在之后添加一些條形來區分集群，您可以根據需要對其進行調整，但這是基礎，因為 corrplot() 沒有選項可以根據需要進行調整：您需要使用自定義代碼行來調整它.
Plot R 中由兩組分面的變量之間的相關性
[英]Plot correlation between variables separated by two groups with facets in R
聲明:本站的技術帖子網頁，遵循CC BY-SA 4.0協議，如果您需要轉載，請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.