我需要创建一个散点图来查看所有 44 种组织中 90K 转录本的 uORF（未翻译 ORF）中的读数与 mORF（主 ORF）中的读数之间的相关性。
我在两个数据帧中拥有所有这些值：uORF_df 和 mORF_df。两者都将转录本 ID 作为 rowname，将组织名称作为 colname。每个细胞内的 uORF 或 mORF 中都有与该组织中的转录本相对应的计数。
我想保存每个生成的图，并用相应转录本的名称为图添加标题。
我做的第一件事是转置两个数据帧，以便组织名称成为行名称，转录本 ID 成为列名称。
# Transpose the uORF and mORF dataframes into large matrices
uORF_df_T <- t(uORF_df)
mORF_df_T <- t(mORF_df)
# Create a character vector for the for lop
samples = c("OneLeaf1", "OneLeaf2", "OneRoot1", "OneRoot2", "ThreeLeaf1", "ThreeLeaf2", "Ear1", "Ear2", "Ear5mm1", "Ear5mm2", "Embryo15_1", "Embryo15_2", "Embryo20_1", "Embryo20_2", "Endosperm15_1", "Endosperm15_2", "Endosperm20_1", "Endosperm20_2", "Inflorescence1", "Inflorescence2", "Kernel1", "Kernel2", "Leaf1", "Leaf2", "Root1", "Root2", "Root6DAS1", "Root6DAS2", "SAM_V1_1", "SAM_V1_2", "SAM_V3_1", "SAM_V3_2", "Seedling1", "Seedling2", "Seedling6DAS1", "Seedling6DAS2", "Stem1", "Stem2", "Tassel1", "Tassel2", "Tassel1cm1", "Tassel1cm2", "TopLeaf1", "TopLeaf2")
uORF_names <- colnames(uORF_TPM_log2_T)
# Plotting the reads in uORF and mORF for each transcript
for (i in 1:nrow(mORF_df)){
# Create a dataframe from the reads in the uORF and in the mORF
df = as.data.frame(cbind(uORF_df_T[,i],mORF_df_T[,i]))
# Rename the rows (I would like to eventually ID each point in the plot with the corresponding tissue name)
rownames(df) <- samples
# Basic scatter plot
jpeg(filename = "/home/stef/Downloads/plot_"i".jpeg")
plot_i <- ggplot(df, aes(x=V1, y=V2)) + geom_point() + geom_smooth(method=lm)
dev.off()
}
这是两个数据帧的前 10 行。我的数据框有超过 99,000 行。
> dput(mORF_TPM_10)
structure(list(TPM_mORF_1Leaf1 = c(0, 0, 15.9577310906664, 15.9775954862149,2.78678991038632, 2.78678991038632, 2.78678991038632, 2.78678991038632,14.0225801608805, 14.0225801608805), TPM_mORF_1Leaf2 = c(0, 0,10.9721879068452, 10.9858462320404, 5.23135534859068, 5.23135534859068, 5.23135534859068, 5.23135534859068, 8.81519572796751, 8.81519572796751), TPM_mORF_1Root1 = c(0, 0, 15.2545295583641, 15.2735185993082, 0, 0, 0, 0, 10.0842351029196, 10.0842351029196), TPM_mORF_1Root2 = c(0.343544763388441, 0.365321371340932, 14.9610683447621, 14.9796920812908, 0, 0, 0, 0, 13.8771566804707, 13.8771566804707), TPM_mORF_3Leaf1 = c(0, 0, 13.7407553130073, 13.7578599876708, 0, 0, 0, 0, 7.11530150881452, 7.11530150881452), TPM_mORF_3Leaf2 = c(0, 0, 15.0898218275324, 15.1086058381061, 0.662658150794125, 0.662658150794125, 0.662658150794125, 0.662658150794125, 13.4925500827389, 13.4925500827389), TPM_mORF_Ear1 = c(0.0760966486956441, 0.0809202613998489, 8.8167202339968, 8.82769540441256, 0.409637837791766, 0.409637837791766, 0.409637837791766, 0.409637837791766, 3.63109781853219, 3.63109781853219), TPM_mORF_Ear2 = c(0.0989407598144533, 0.105212414534932, 11.4182721224643, 11.4324857392142, 0, 0, 0, 0, 5.34284426702046, 5.34284426702046), TPM_mORF_Ear5mm_1 = c(0.104551293297911, 0.111178588392205, 32.2090774974947, 32.2491717848359, 0, 0, 0, 0, 10.1135671840607, 10.1135671840607), TPM_mORF_Ear5mm_2 = c(0.685769475329068, 0.72923901584173, 24.7489457541728, 24.7797535704643, 0, 0, 0, 0, 9.47665487265555, 9.47665487265555), TPM_mORF_Embryo15_1 = c(0.438970125615888, 0.466795554343452, 27.3602274978775, 27.3942858723561, 0, 0, 0, 0, 2.68865205489207, 2.68865205489207), TPM_mORF_Embryo15_2 = c(0.183828153543562, 0.19548064852228, 24.0092443355057, 24.0391313616495, 0, 0, 0, 0, 5.60173788500298, 5.60173788500298), TPM_mORF_Embryo20_1 = c(0.0492631332412111,0.0523858236543152, 25.8635736817635, 25.8957690016993, 0, 0, 0, 0, 5.09702999415875, 5.09702999415875), TPM_mORF_Embryo20_2 = c(0, 0, 15.4492008332927, 15.4684322036246, 0, 0, 0, 0, 3.37328874561412, 3.37328874561412), TPM_mORF_Endosperm15_1 = c(0.284960191689523, 0.303023242091701, 16.5820101656358, 16.6026516720661, 0, 0, 0, 0, 4.93713195264232, 4.93713195264232), TPM_mORF_Endosperm15_2 = c(0.414532526807716, 0.440808905556183, 15.7123804255646, 15.7319394053474, 0, 0, 0, 0, 4.13826302736584, 4.13826302736584), TPM_mORF_Endosperm20_1 = c(0.755067264729411, 0.802929452001876, 14.309979727866, 14.3277929806393, 0, 0, 0, 0, 5.49684769183169, 5.49684769183169), TPM_mORF_Endosperm20_2 = c(0.415271301202561, 0.441594509366221, 16.0334218643644, 16.0533804807931, 0, 0, 0, 0, 4.37755081503468, 4.37755081503468), TPM_mORF_Inflorescence1 = c(0.962658543958137, 1.02367952270084, 30.8346128127823, 30.8729961482339, 0, 0, 0, 0, 14.148327878666, 14.148327878666), TPM_mORF_Inflorescence2 = c(0.253064810686685, 0.172996764026799, 26.5095614564813, 26.5425609105765, 0.0729792711316374, 0.0729792711316374, 0.0729792711316374, 0.0729792711316374, 12.489660767776, 12.489660767776), TPM_mORF_Kernel1 = c(0, 0, 22.0153898488796, 22.042794898484, 0.386564992374038, 0.386564992374038, 0.386564992374038, 0.386564992374038, 11.3239110681831, 11.3239110681831), TPM_mORF_Kernel2 = c(0.288839940994747, 0.307148920861081, 21.4012979695502, 21.4279385894293, 0.534483728988032, 0.534483728988032, 0.534483728988032, 0.534483728988032, 13.8337256590664, 13.8337256590664), TPM_mORF_Leaf1 = c(0, 0, 5.60652347398228, 5.61350254884616, 0, 0, 0, 0, 0, 0), TPM_mORF_Leaf2 = c(0, 0, 3.61049607609657, 3.61499046955229, 1.37526811341663, 1.37526811341663, 1.37526811341663, 1.37526811341663, 1.93118494003443, 1.93118494003443), TPM_mORF_Root1 = c(0.075966119209846, 0.0807814579138581, 12.9573391538621, 12.9734686216885, 0.766753464638798, 0.766753464638798, 0.766753464638798, 0.766753464638798, 9.69024480583571, 9.69024480583571), TPM_mORF_Root2 = c(0, 0, 11.9844233034174, 11.9993416726748, 0.485803306586024, 0.485803306586024, 0.485803306586024, 0.485803306586024, 13.2171759049679, 13.2171759049679), TPM_mORF_Root6DAS_1 = c(0, 0, 3.68099341662474, 3.68557556610601, 0, 0, 0, 0, 8.54861027025474, 8.54861027025474), TPM_mORF_Root6DAS_2 = c(0.0859279434500381, 0.0913747420512427, 20.9712701215337, 20.9973754370377, 0.607111227010591, 0.607111227010591, 0.607111227010591, 0.607111227010591, 8.76878078126128, 8.76878078126128), TPM_mORF_SAM_V1_1 = c(0.111113029385815, 0.118156259663823, 21.670386860971, 21.6973624462751, 0.822436205751297, 0.822436205751297, 0.822436205751297, 0.822436205751297, 10.5908197277331, 10.5908197277331), TPM_mORF_SAM_V1_2 = c(0.337618989220899, 0.239346649553322, 23.8243155365058, 23.8539723608251, 0, 0, 0, 0, 11.2186115309571, 11.2186115309571), TPM_mORF_SAM_V3_1 = c(0.19244911952294, 0.204648080104722, 24.483348273863, 24.5138254708844, 0, 0, 0, 0, 11.5243102210465, 11.5243102210465), TPM_mORF_SAM_V3_2 = c(0.885797519484353, 0.941946433287732, 21.1824657296363, 21.2088339442375, 0.621959939713711, 0.621959939713711, 0.621959939713711, 0.621959939713711, 8.67912706842305, 8.67912706842305), TPM_mORF_Seedling1 = c(0.0577068647184253, 0.0613647861978446, 6.86443842289814, 6.87298336699304, 1.28140367859192, 1.28140367859192, 1.28140367859192, 1.28140367859192, 2.8626471638543, 2.8626471638543), TPM_mORF_Seedling2 = c(1.0274385206843, 1.09256577117576, 4.55726253082638, 4.56293547173612, 0, 0, 0, 0, 3.34931488046525, 3.34931488046525), TPM_mORF_Seedling6DAS1 = c(0.170047092744869, 0.180826034142905, 10.3881296800559, 10.4010609618153, 0, 0, 0, 0, 6.62787339274703, 6.62787339274703), TPM_mORF_Seedling6DAS2 = c(0.200225443771896, 0.212917329825197, 14.4519953855864, 14.469985421336, 0, 0, 0, 0, 8.51359170240591, 8.51359170240591), TPM_mORF_Stem1 = c(0.07452871786933, 0.0792529426085881, 12.3335051788672, 12.3488580898782, 1.80538860963132, 1.80538860963132, 1.80538860963132, 1.80538860963132, 6.12666229313586, 6.12666229313586), TPM_mORF_Stem2 = c(0, 0, 10.2054007660267, 10.2181045844076, 0.532192947104563, 0.532192947104563, 0.532192947104563, 0.532192947104563, 4.4305298183051, 4.4305298183051), TPM_mORF_Tassel1 = c(0.424885586034637, 0.395340946240699, 14.6485160508083, 14.6667507180915, 0.804098175333964, 0.804098175333964, 0.804098175333964, 0.804098175333964, 3.76378072843866, 3.76378072843866), TPM_mORF_Tassel2 = c(0.149978447560262, 0.159485278115995, 14.673033890032, 14.691299077447, 1.09749529429666, 1.09749529429666, 1.09749529429666, 1.09749529429666, 5.553380764842, 5.553380764842), TPM_mORF_Tassel1cm1 = c(0.291650426819245, 0.310137557699591, 32.7720159395946, 32.8128109801833, 0, 0, 0, 0, 13.0210338773437, 13.0210338773437), TPM_mORF_Tassel1cm2 = c(0.150791469374745, 0.160349835739483, 25.112060164431, 25.1433199903619, 0, 0, 0, 0, 12.2890105358246, 12.2890105358246), TPM_mORF_TopLeaf1 = c(0.185266040760669, 0.197009680502875, 8.35765398911196, 8.3680577077706, 0.934978514834704, 0.934978514834704, 0.934978514834704, 0.934978514834704, 7.25388065238328, 7.25388065238328), TPM_mORF_TopLeaf2 = c(0, 0, 8.10490776009202, 8.11499685688881, 1.40080302886771, 1.40080302886771, 1.40080302886771, 1.40080302886771, 6.07069762787997, 6.07069762787997)), row.names = c("Zm00001eb000210_T001_1", "Zm00001eb000210_T002_9", "Zm00001eb000340_T001_1", "Zm00001eb000340_T002_1", "Zm00001eb000470_T001_1", "Zm00001eb000470_T001_2", "Zm00001eb000470_T001_3", "Zm00001eb000470_T001_4", "Zm00001eb000590_T001_1", "Zm00001eb000590_T001_2"), class = "data.frame")
> dput(uORF_TPM_10)
structure(list(TPM_uORF_1Leaf1 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_1Leaf2 = c(0, 0, 0, 0, 83.4955169709039, 0, 147.722837717753, 125.243275456356, 0, 0), TPM_uORF_1Root1 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_1Root2 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_3Leaf1 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_3Leaf2 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Ear1 = c(0, 0, 0, 0, 0, 0, 0, 41.8068094051703, 0, 0), TPM_uORF_Ear2 = c(0, 0, 0, 0, 28.7464807043411, 0, 50.8591581692189, 45.9943691269458, 0, 0), TPM_uORF_Ear5mm_1 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Ear5mm_2 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Embryo15_1 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Embryo15_2 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Embryo20_1 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Embryo20_2 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Endosperm15_1 = c(11.4347855154007, 11.4347855154007, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Endosperm15_2 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Endosperm20_1 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Endosperm20_2 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Inflorescence1 = c(0, 0, 0, 0, 11.2406460145824, 0, 19.8872967950304, 0, 0, 0), TPM_uORF_Inflorescence2 = c(33.3338244380922, 33.3338244380922, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Kernel1 = c(0, 0, 0, 0, 21.4246067462734, 0, 54.1501049631087, 3.06065810661049, 0, 0), TPM_uORF_Kernel2 = c(0, 0, 0, 0, 3.79467228769529, 0, 6.71365097053781, 3.79467228769529, 0, 0), TPM_uORF_Leaf1 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Leaf2 = c(361.143298701066, 361.143298701066, 0, 0, 15.7018825522203, 0, 27.7802537462358, 0, 0, 0), TPM_uORF_Root1 = c(0, 0, 0, 0, 18.5389127807478, 0, 32.7996149197846, 0, 0, 0), TPM_uORF_Root2 = c(0, 0, 0, 0, 0, 0, 0, 144.251178847067, 0, 0), TPM_uORF_Root6DAS_1 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Root6DAS_2 = c(0, 0, 0, 0, 27.5534687981229, 0, 64.9979263955721, 36.7379583974973, 0, 0), TPM_uORF_SAM_V1_1 = c(0, 0, 0, 0, 2.40281615863606, 0, 4.25113628066379, 4.80563231727211, 0, 0), TPM_uORF_SAM_V1_2 = c(0, 0, 0, 0, 0, 0, 0, 11.8552123025014, 0, 0), TPM_uORF_SAM_V3_1 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_SAM_V3_2 = c(73.9301306725009, 73.9301306725009, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Seedling1 = c(0, 0, 0, 0, 0, 0, 0, 190.042200283117, 0, 0), TPM_uORF_Seedling2 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Seedling6DAS1 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Seedling6DAS2 = c(0, 0, 0, 0, 18.6624163966679, 0, 33.0181213171818, 24.8832218622239, 0, 0), TPM_uORF_Stem1 = c(0, 0, 0, 0, 0, 0, 14.1747578900174, 52.0768279002814, 0, 0), TPM_uORF_Stem2 = c(0, 0, 0, 0, 101.319692897418, 0, 179.257918203124, 55.2652870349554, 0, 0), TPM_uORF_Tassel1 = c(0, 0, 0, 0, 0, 0, 15.7804228950156, 8.91936946240015, 0, 0), TPM_uORF_Tassel2 = c(0, 0, 0, 0, 18.1722085926888, 0, 85.7355482321728, 24.2296114569184, 0, 0), TPM_uORF_Tassel1cm1 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_Tassel1cm2 = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0), TPM_uORF_TopLeaf1 = c(0, 0, 0, 0, 121.429685770491, 25.7804563635811, 214.837136363176, 14.5715622924589, 0, 0), TPM_uORF_TopLeaf2 = c(0, 0, 0, 0, 23.4813161069057, 0, 49.852640350046, 4.69626322138114, 0, 0)), row.names = c("Zm00001eb000210_T001_1", "Zm00001eb000210_T002_9", "Zm00001eb000340_T001_1", "Zm00001eb000340_T002_1", "Zm00001eb000470_T001_1", "Zm00001eb000470_T001_2", "Zm00001eb000470_T001_3", "Zm00001eb000470_T001_4", "Zm00001eb000590_T001_1", "Zm00001eb000590_T001_2"), class = "data.frame")
这是一个行之有效的一般策略：
library(tidyverse)
plots <-
mtcars |>
group_by(cyl) |>
group_split() |>
map(\(x) ggplot(x) +
geom_point(aes(disp, hp)))
map2(plots,
paste("plot", 1:length(plots)),
\(x, y) ggsave(paste0(y, ".png"), plot = x))
您的数据如下所示：
library(tidyverse)
# `pivot_longer()` here can be used to achieve the same as you do with `t()`.
# We add an id that equals the row number so we can join on that id in the next
# step.
morf_long <-
mORF_TPM |>
mutate(id = row_number()) |>
pivot_longer(-id)
uorf_long <-
uORF_TPM |>
mutate(id = row_number()) |>
pivot_longer(-id)
# Join `morf` and `uorf`.
big_df <-
full_join(morf_long,
uorf_long,
by = "id",
relationship = "many-to-many")
# Now we split `df` by `id` and we get a list where each element is
# a `data.frame` for we want to turn into one plot.
big_list <-
split(big_df, big_df$id)
# Now we can apply the steps described above.
plots <-
big_list |>
map(\(x) ggplot(x, aes(x = value.x, y = value.y)) +
geom_point() +
geom_smooth(method = lm))
map2(plots,
paste("plot", 1:length(plots)),
\(x, y) ggsave(paste0(y, ".png"), plot = x))