手把手带你复现NC图表之Figure5

生信技能树jimmy

发布于 2023-09-26 20:18:06

3200

发布于 2023-09-26 20:18:06

文章被收录于专栏：单细胞天地

复现文章信息：

文章题目：Single-cell analysis reveals prognostic fibroblast subpopulations linked to molecular and immunological subtypes of lung cancer 期刊：Nature Communications 日期：2023年1月31日 DOI: 10.1038/s41467-023-35832-6

复现图——Figure 5

基于机器学习的scRNA-seq数据和mxIHC分类显示外膜和肌成纤维细胞在胰腺癌、结直肠癌和口腔癌中是保守的，而肺泡成纤维细胞是肺特异性的

R包载入与数据准备

library(Seurat)
library(sctransform)
library(ggplot2)
library(WGCNA)
library(tidyverse)
library(ggpubr)
library(ggsci)
data_directory <- "H:\\文献复现\\6\\"
source(paste0(data_directory, "0_NewFunctions.R"))

load(paste0(data_directory, "IntegratedFibs_Zenodo.Rdata"))
load(paste0(data_directory, "CrossTissueAnalysis_Zenodo.Rdata"))
load(paste0(data_directory, "MxIHC_TMAdata_Zenodo.Rdata"))

Figure 5 A-C

分离自不同癌症类型并通过scRNA-seq分析的成纤维细胞的UMAP降维。检测这些成纤维细胞表型是否在不同癌症类型中是保守的，分析了PDAC49、HNSCC29和结肠直肠癌（CRC）。在每种情况下，成纤维细胞都是通过无监督聚类和壁细胞排除法鉴定

Sample_UMAP <- 
  Merged_MetaData %>%
  filter(Group %in% c("Pancreas", "Oral", "Colon")) %>%
  ggplot(aes(x = UMAP_1, y = UMAP_2, colour = Sample.type)) +
  geom_point(size = 0.1) +
  facet_wrap(~Group, scales = "free", nrow = 1) +
  theme_pubr(base_size = 15) +
  scale_color_npg(name = "Sample type") +
  theme(legend.position = "right",legend.key.size = unit(10, "pt"))+
  guides(colour = guide_legend(override.aes = list(size = 2)))
#突出显示机器学习分类器预测的与每个细胞相关的成纤维细胞亚群
Class_UMAP <- 
  Merged_MetaData %>%
  filter(Group %in% c("Pancreas", "Oral", "Colon")) %>%
  ggplot(aes(x = UMAP_1, y = UMAP_2, colour = predicted.id)) +
  geom_point(size = 0.1) +
  facet_wrap(~Group, scales = "free", nrow = 1) +
  theme_pubr(base_size = 15) +
  scale_colour_manual(values = Fibs_col.palette, name = "Predicted class") +
  theme(legend.position = "right",legend.key.size = unit(10, "pt")) +
  guides(colour = guide_legend(override.aes = list(size = 2)))
#小提琴图显示了按亚群分组的机器学习分类器模型预测的概率
Prob_VlnPlot <- 
  Merged_MetaData %>%
  filter(Group %in% c("Pancreas", "Oral", "Colon")) %>%
  ggplot(aes(x = predicted.id, y = prediction.score.max, fill = predicted.id)) +
  geom_violin(scale = "width") +
  geom_boxplot(width = 0.1, outlier.shape = NA, fill = "white") +
  facet_wrap(~Group, scales = "free", nrow = 1) +
  theme_pubr(base_size = 15) +
  scale_fill_manual(values = Fibs_col.palette, name = "Predicted class") +
  rotate_x_text(angle = 45) +
  theme(legend.position = "right", axis.title.x = element_blank(),
        legend.key.size = unit(10, "pt")) +
  ylab("Classification Probability") +
  ylim(c(0,1))

Fig_5ABC <- ggarrange(Sample_UMAP, Class_UMAP, Prob_VlnPlot, nrow = 3,
                   align = "v")

Fig_5ABC

这表明，在分析的所有癌症类型中，外膜细胞和肌成纤维细胞群都是高度保守的，而分配给肺泡亚群的成纤维细胞的概率得分一直较低，表明与肺的表型差异程度更大。

Figure 5D

来自组织微阵列（TMA）的mxIHC分析的代表性图像，所述组织微阵列由胰腺癌、口腔癌和结肠癌组织块构建。可视化显示成纤维细胞亚群的空间分布

s = "PANCREAS"
PDAC_CTR_C01 <- 
  All_TMA.data.df %>%
  filter(TvN == "Normal" & Core == "C01") %>%
  ggplot(aes(x = X.Center..Pxl., y = Y.Center..Pxl.,
             colour = Cell.type2)) +
  geom_point(size = 1.5) +
  theme_void(base_size = 15) +
  theme(legend.position = "none") +
  guides(colour = guide_legend(override.aes = list(size = 4))) +
  scale_colour_manual(values = Fibs_col.palette,
                      na.value = "grey80")
PDAC_Tumour_CO2 <- 
  All_TMA.data.df %>%
  filter(TvN == "Tumour" & Core == "C02") %>%
  ggplot(aes(x = X.Center..Pxl., y = Y.Center..Pxl.,
             colour = Cell.type2)) +
  geom_point(size = 1.5) +
  theme_void(base_size = 15) +
  theme(legend.position = "none") +
  guides(colour = guide_legend(override.aes = list(size = 4))) +
  scale_colour_manual(values = Fibs_col.palette,
                      na.value = "grey80")

HNSCC_CTR_E07 <- 
  All_TMA.data.df %>%
  filter(TvN == "Normal" & Core == "E07") %>%
  ggplot(aes(x = X.Center..Pxl., y = Y.Center..Pxl.,
             colour = Cell.type2)) +
  geom_point(size = 1.5) +
  theme_void(base_size = 15) +
  theme(legend.position = "none") +
  guides(colour = guide_legend(override.aes = list(size = 4))) +
  scale_colour_manual(values = Fibs_col.palette,
                      na.value = "grey80")

HNSCC_Tumour_E07 <- 
  All_TMA.data.df %>%
  filter(TvN == "Tumour" & Core == "E07") %>%
  ggplot(aes(x = X.Center..Pxl., y = Y.Center..Pxl.,
             colour = Cell.type2)) +
  geom_point(size = 1.5) +
  theme_void(base_size = 15) +
  theme(legend.position = "none") +
  guides(colour = guide_legend(override.aes = list(size = 4))) +
  scale_colour_manual(values = Fibs_col.palette,
                      na.value = "grey80")

COLON_CTR_B03 <- 
  All_TMA.data.df %>%
  filter(TvN == "Normal" & Core == "B03") %>%
  ggplot(aes(x = X.Center..Pxl., y = Y.Center..Pxl.,
             colour = Cell.type2)) +
  geom_point(size = 1.5) +
  theme_void(base_size = 15) +
  theme(legend.position = "none") +
  guides(colour = guide_legend(override.aes = list(size = 4))) +
  scale_colour_manual(values = Fibs_col.palette,
                      na.value = "grey80")

COLON_Tumour_B05 <- 
  All_TMA.data.df %>%
  filter(TvN == "Tumour" & Core == "B05") %>%
  ggplot(aes(x = X.Center..Pxl., y = Y.Center..Pxl.,
             colour = Cell.type2)) +
  geom_point(size = 1.5) +
  theme_void(base_size = 15) +
  theme(legend.position = "none") +
  guides(colour = guide_legend(override.aes = list(size = 4))) +
  scale_colour_manual(values = Fibs_col.palette,
                      na.value = "grey80")

Fig_5D <- ggarrange(PDAC_CTR_C01, PDAC_Tumour_CO2,
                    HNSCC_CTR_E07, HNSCC_Tumour_E07,
                    COLON_CTR_B03, COLON_Tumour_B05,
                    nrow = 6, ncol = 1)

Fig_5D

通过将多重免疫组化面板应用于由来自PDAC、HNSCC和CRC的肿瘤和对照组织核心组成的组织微阵列来验证这些结果。与scRNA-seq结果一致，这表明在每种癌症类型中，外膜和肌成纤维细胞是主要的亚群

Figure 5E-F

All_TMA.data.df.Fibroblasts <- All_TMA.data.df %>%
  filter(Cell.type2 %in% c("Alveolar", "Adventitial", "Myo"))
table(All_TMA.data.df.Fibroblasts$Cell.type2)
All_TMA.data.df.Fibroblasts$Cell.type2 <- factor(
  as.character(All_TMA.data.df.Fibroblasts$Cell.type2),
  levels = c("Adventitial", "Alveolar",  "Myo")
)
dt <- as.table(as.matrix(table(All_TMA.data.df.Fibroblasts$Core_ID,
                               All_TMA.data.df.Fibroblasts$Cell.type2)))
Sample.pct_long <- as.data.frame(dt/rowSums(dt)*100)
CoreData_long <- merge(MxIHC_TMA_metaData, Sample.pct_long,
                       by.x = "Core_ID", by.y = "Var1")
names(CoreData_long)[names(CoreData_long) == "Freq"] <- "Core.pct"
names(CoreData_long)[names(CoreData_long) == "Var2"] <- "Fibs_SubPop"

CoreData_long$Group <- factor(CoreData_long$Structure,
                              levels = unique(CoreData_long$Structure)[c(3,5,2,7,6,4,1)],
                              labels = c("Pancreas", "Oral", "Colon", "Lung", "Skin", "Breast", "Kidney"))
names(CoreData_long)
#箱形图显示肿瘤或对照组织中外膜成纤维细胞的相对丰度，通过TMA细胞核的mxIHC分析测定
Fig_5E <- 
  CoreData_long[] %>%
  drop_na(Structure.filtered) %>%
  filter(Fibs_SubPop == "Adventitial") %>%
  filter(Structure %in% c("COLON", "PANCREAS", "HNSCC")) %>%
  ggplot(aes(x = TvN, y = Core.pct)) +
  theme_pubr(base_size = 15) +
  facet_wrap(~Group) +
  geom_boxplot(outlier.shape = NA, aes(fill = Fibs_SubPop)) +
  geom_jitter(alpha = 0.5, width = 0.2) +
  scale_fill_manual(values = Fibs_col.palette) +
  rotate_x_text(angle = 45) +
  scale_y_continuous(breaks = c(0,25,50, 75, 100),
                     limits = c(0,125)) +
  stat_compare_means(comparisons = list(c("Normal", "Tumour")), size = 3,
                     label.y = 110, size = 2.5) +
  ylab("% of all fibroblast per core\n(MxIHC)") +
  theme(axis.title.x = element_blank(), legend.position = "none")
Fig_5E
#箱形图显示肿瘤或对照组织中肌成纤维细胞的相对丰度，通过TMA细胞核的mxIHC分析测定
Fig_5F <- 
  CoreData_long[] %>%
  drop_na(Structure.filtered) %>%
  filter(Fibs_SubPop == "Myo") %>%
  filter(Structure %in% c("COLON", "PANCREAS", "HNSCC")) %>%
  ggplot(aes(x = TvN, y = Core.pct)) +
  theme_pubr(base_size = 15) +
  facet_wrap(~Group) +
  geom_boxplot(outlier.shape = NA, aes(fill = Fibs_SubPop)) +
  geom_jitter(alpha = 0.5, width = 0.2) +
  scale_fill_manual(values = Fibs_col.palette) +
  rotate_x_text(angle = 45) +
  scale_y_continuous(breaks = c(0,25,50, 75, 100),
                     limits = c(0,125)) +
  stat_compare_means(comparisons = list(c("Normal", "Tumour")), size = 3,
                     #label = "p.signif", method = "wilcox",
                     label.y = 110, size = 2.5) +
  ylab("% of all fibroblast per core\n(MxIHC)") +
  theme(axis.title.x = element_blank(), legend.position = "none")
Fig_5F

Fig_5EF <- ggarrange(Fig_5E, Fig_5F, nrow = 2,
                   align = "v")

Fig_5EF

Figure 5

正如在非小细胞肺癌中发现的那样，与所有三种肿瘤类型的肿瘤组织相比，对照组中上皮成纤维细胞的丰度明显更高，而肿瘤组织中肌成纤维细胞的丰度更高。为了测试肺泡表型是否对肺纤维化具有特异性，对特发性肺纤维化(IPF)样本中产生的scRNA-seq数据进行了类似的分析，结果表明所有三个亚群都具有高概率得分,值得注意的是，该分析还显示，IPF中与肌成纤维细胞分类相关的概率低于癌症数据集，这表明癌症和纤维化中发现的肌成纤维细胞之间可能存在细微差异。

本文参与腾讯云自媒体同步曝光计划，分享自微信公众号。

原始发表：2023-06-13 21:52，如有侵权请联系 cloudcommunity@tencent.com 删除

机器学习