498 lines
15 KiB
R
Executable File
498 lines
15 KiB
R
Executable File
#!/usr/bin/env Rscript
|
||
|
||
## =========================================================
|
||
## plot_motif.R
|
||
## 左：系统发育树（含基因 ID）
|
||
## 中：亚家族竖线
|
||
## 右：MEME motif 矩形条
|
||
## =========================================================
|
||
|
||
args <- commandArgs(trailingOnly = TRUE)
|
||
|
||
if (length(args) < 3) {
|
||
stop(
|
||
"用法:\n",
|
||
" Rscript plot_motif.R <treefile> <subfamily_file> <meme_xml> [output_prefix]\n\n",
|
||
"说明:\n",
|
||
" treefile : IQ-TREE Newick 树文件\n",
|
||
" subfamily_file : 亚家族文件路径（可为空字符串）\n",
|
||
" meme_xml : MEME XML 结果文件\n",
|
||
" output_prefix : 输出文件前缀（可选，默认与 treefile 同名）\n",
|
||
call. = FALSE
|
||
)
|
||
}
|
||
|
||
treefile <- args[1]
|
||
subfamily_file <- args[2]
|
||
meme_xml <- args[3]
|
||
|
||
# 第四个参数：输出前缀
|
||
if (length(args) >= 4 && nzchar(args[4])) {
|
||
output_prefix <- args[4]
|
||
} else {
|
||
output_prefix <- sub("\\.[^.]*$", "", treefile)
|
||
}
|
||
|
||
cat("树文件: ", treefile, "\n")
|
||
cat("亚家族文件: ", ifelse(nzchar(subfamily_file), subfamily_file, "(未提供)"), "\n")
|
||
cat("MEME XML 文件: ", meme_xml, "\n")
|
||
cat("输出前缀: ", output_prefix, "\n\n")
|
||
|
||
## ===================== 2. 加载 R 包 =====================
|
||
|
||
|
||
script_args_all <- commandArgs(trailingOnly = FALSE)
|
||
script_file_arg <- grep("^--file=", script_args_all, value = TRUE)
|
||
script_dir <- if (length(script_file_arg) > 0) dirname(normalizePath(sub("^--file=", "", script_file_arg[1]))) else getwd()
|
||
source(file.path(script_dir, "subfamily_palette.R"))
|
||
|
||
suppressPackageStartupMessages({
|
||
library(ape)
|
||
library(ggtree)
|
||
library(tidytree)
|
||
library(dplyr)
|
||
library(RColorBrewer)
|
||
library(ggplot2)
|
||
library(xml2)
|
||
library(ggnewscale)
|
||
})
|
||
|
||
make_distinct_cols <- function(n) {
|
||
if (n <= 0) return(character(0))
|
||
base <- c(
|
||
"#0072B2", "#D55E00", "#009E73", "#CC79A7", "#E69F00",
|
||
"#56B4E9", "#F0E442", "#000000", "#882255", "#44AA99",
|
||
"#AA4499", "#117733", "#332288", "#DDCC77", "#88CCEE"
|
||
)
|
||
if (n <= length(base)) return(base[seq_len(n)])
|
||
if (exists("hcl.colors", where = asNamespace("grDevices"), inherits = FALSE)) {
|
||
return(grDevices::hcl.colors(n, palette = "Dark 3"))
|
||
}
|
||
grDevices::colorRampPalette(base)(n)
|
||
}
|
||
|
||
## ===================== 3. 读亚家族文件 + 深色配色 =====================
|
||
|
||
add_confidence_labels <- function(subfam_df, subfamily_file) {
|
||
add_subfamily_confidence_labels(subfam_df, subfamily_file)
|
||
}
|
||
|
||
|
||
# 检查亚家族文件是否存在
|
||
has_subfamily <- nzchar(subfamily_file) && file.exists(subfamily_file)
|
||
|
||
if (has_subfamily) {
|
||
subfam <- read_subfamily_plot_table(subfamily_file)
|
||
subfam <- add_confidence_labels(subfam, subfamily_file)
|
||
|
||
subfam_levels <- sort(unique(subfam$subfamily))
|
||
n_subfam <- length(subfam_levels)
|
||
|
||
if (n_subfam == 0) {
|
||
warning("在亚家族文件中没有检测到任何 subfamily，将使用默认着色")
|
||
has_subfamily <- FALSE
|
||
} else {
|
||
subfam_cols <- make_subfamily_cols(subfam_levels)
|
||
cat("检测到", n_subfam, "个亚家族\n")
|
||
}
|
||
} else {
|
||
cat("未提供亚家族文件，将使用默认着色\n")
|
||
# 创建空的 subfam 数据框
|
||
subfam <- data.frame(label = character(), subfamily = character(), low_confidence = logical(), display_label = character(), stringsAsFactors = FALSE)
|
||
subfam_levels <- character()
|
||
subfam_cols <- character()
|
||
}
|
||
|
||
## ===================== 4. 树绘图函数 =====================
|
||
|
||
plot_iqtree_by_subfamily <- function(treefile, subfam_df, subfam_cols, label_offset = 0.4) {
|
||
tree <- read.tree(treefile)
|
||
tree_df <- as_tibble(tree)
|
||
tree_df$isTip <- tree_df$node <= length(tree$tip.label)
|
||
|
||
if (nrow(subfam_df) > 0) {
|
||
tree_df <- dplyr::left_join(tree_df, subfam_df, by = "label")
|
||
} else {
|
||
tree_df$subfamily <- NA_character_
|
||
tree_df$display_label <- tree_df$label
|
||
}
|
||
tree_df$display_label <- ifelse(is.na(tree_df$display_label), tree_df$label, tree_df$display_label)
|
||
|
||
tree_df$support <- ifelse(
|
||
tree_df$isTip,
|
||
NA_real_,
|
||
suppressWarnings(as.numeric(tree_df$label))
|
||
)
|
||
|
||
p <- ggtree(tree, branch.length = "none") %<+% tree_df +
|
||
## bootstrap
|
||
geom_nodepoint(
|
||
aes(fill = cut(support, c(0, 50, 75, 100))),
|
||
shape = 21,
|
||
size = 2,
|
||
na.rm = TRUE
|
||
) +
|
||
scale_fill_manual(
|
||
values = c("black", "grey40", "grey80"),
|
||
guide = "legend",
|
||
name = "Bootstrap Percentage (BP)",
|
||
breaks = c("(75,100]", "(50,75]", "(0,50]"),
|
||
labels = expression(BP > 75,
|
||
50 < BP * "<=75",
|
||
BP <= 50)
|
||
) +
|
||
geom_text2(
|
||
aes(label = ifelse(!isTip & !is.na(support), round(support), "")),
|
||
hjust = -0.2, vjust = -0.4, size = 2.2,
|
||
na.rm = TRUE, show.legend = FALSE
|
||
)
|
||
|
||
# 只有提供亚家族时才着色
|
||
if (nrow(subfam_df) > 0) {
|
||
p <- p + geom_tippoint(
|
||
aes(color = subfamily),
|
||
size = 2,
|
||
na.rm = TRUE
|
||
) +
|
||
scale_color_manual(
|
||
values = subfam_cols,
|
||
name = "Subfamily",
|
||
na.value = "grey70"
|
||
)
|
||
} else {
|
||
p <- p + geom_tippoint(size = 2, color = "grey50")
|
||
}
|
||
|
||
p <- p + geom_tiplab(aes(label = display_label), offset = label_offset, size = 3, hjust = 0) +
|
||
ggtitle(NULL) +
|
||
theme_tree() +
|
||
theme(
|
||
legend.position = "right",
|
||
legend.background = element_rect(color = "#969696", fill = "#d9d9d9")
|
||
)
|
||
|
||
attr(p, "label_offset") <- label_offset
|
||
return(p)
|
||
}
|
||
|
||
## ===================== 5. 解析 MEME XML =====================
|
||
|
||
parse_meme_xml <- function(meme_file) {
|
||
|
||
doc <- xml2::read_xml(meme_file)
|
||
|
||
## 所有序列的 id/name/length
|
||
seq_nodes <- xml2::xml_find_all(doc, ".//sequence")
|
||
seq_ids <- xml2::xml_attr(seq_nodes, "id")
|
||
seq_names <- xml2::xml_attr(seq_nodes, "name")
|
||
|
||
## 兼容可能出现的 Length / length 大小写问题
|
||
seq_lengths <- xml2::xml_attr(seq_nodes, "length")
|
||
if (any(is.na(seq_lengths))) {
|
||
seq_lengths2 <- xml2::xml_attr(seq_nodes, "Length")
|
||
idx <- which(is.na(seq_lengths) & !is.na(seq_lengths2))
|
||
seq_lengths[idx] <- seq_lengths2[idx]
|
||
}
|
||
seq_lengths <- suppressWarnings(as.numeric(seq_lengths))
|
||
|
||
name_map <- setNames(seq_names, seq_ids) # id -> gene
|
||
length_map <- setNames(seq_lengths, seq_names) # gene -> seqlen
|
||
|
||
## motif + site 信息
|
||
motif_nodes <- xml2::xml_find_all(doc, ".//motif")
|
||
site_list <- list()
|
||
motif_index <- 1L
|
||
|
||
for (m in motif_nodes) {
|
||
motif_id <- xml2::xml_attr(m, "id")
|
||
if (is.na(motif_id) || motif_id == "") {
|
||
motif_id <- xml2::xml_attr(m, "name")
|
||
}
|
||
if (is.na(motif_id) || motif_id == "") {
|
||
motif_id <- paste0("Motif_", motif_index)
|
||
}
|
||
|
||
motif_width <- xml2::xml_attr(m, "width")
|
||
motif_width <- suppressWarnings(as.numeric(motif_width))
|
||
if (is.na(motif_width)) motif_width <- 10
|
||
|
||
sites <- xml2::xml_find_all(m, ".//contributing_site")
|
||
if (length(sites) == 0) next
|
||
|
||
seq_id <- xml2::xml_attr(sites, "sequence_id")
|
||
start <- xml2::xml_attr(sites, "position")
|
||
start <- suppressWarnings(as.numeric(start))
|
||
|
||
width <- rep(motif_width, length(sites))
|
||
|
||
df <- data.frame(
|
||
seq_id = seq_id,
|
||
start = start,
|
||
width = width,
|
||
motif = motif_id,
|
||
stringsAsFactors = FALSE
|
||
)
|
||
|
||
site_list[[length(site_list) + 1L]] <- df
|
||
motif_index <- motif_index + 1L
|
||
}
|
||
|
||
if (length(site_list) == 0) {
|
||
stop("在 MEME XML 中没有找到任何 motif site，请检查文件或 XML 结构。", call. = FALSE)
|
||
}
|
||
|
||
sites <- dplyr::bind_rows(site_list)
|
||
|
||
## 序列名 & 序列长度来自 XML 中的 sequence 区
|
||
sites$gene <- unname(name_map[sites$seq_id])
|
||
sites$seqlen <- length_map[sites$gene]
|
||
|
||
## motif 终点坐标（同样用 XML 的真实坐标）
|
||
sites$end <- sites$start + sites$width - 1
|
||
|
||
sites
|
||
}
|
||
|
||
## ===================== 6. 画树 & 基本坐标信息 =====================
|
||
|
||
label_offset <- 0.4
|
||
p_tree <- plot_iqtree_by_subfamily(treefile, subfam, subfam_cols, label_offset = label_offset)
|
||
|
||
tree_dat <- p_tree$data
|
||
tip_dat <- tree_dat %>%
|
||
dplyr::filter(isTip) %>%
|
||
dplyr::select(label, x, y, subfamily)
|
||
|
||
if (nrow(tip_dat) == 0) {
|
||
stop("树中没有 tip 节点，请检查 treefile。", call. = FALSE)
|
||
}
|
||
|
||
x_tree_min <- min(tree_dat$x, na.rm = TRUE)
|
||
x_tip_max <- max(tip_dat$x, na.rm = TRUE)
|
||
max_y <- max(tree_dat$y, na.rm = TRUE)
|
||
|
||
## 树的"主干宽度"（不算标签）
|
||
tree_core_width <- x_tip_max - x_tree_min
|
||
if (!is.finite(tree_core_width) || tree_core_width <= 0) {
|
||
stop("树的宽度计算异常，请检查 treefile。", call. = FALSE)
|
||
}
|
||
|
||
## gene ID 左边界（文本起点）
|
||
x_label_left <- x_tip_max + label_offset
|
||
|
||
## 给 gene ID 单独留一块"标签区域"，宽度与树宽成比例，且不少于 1.5
|
||
label_panel_width <- max(1.5, tree_core_width * 0.5)
|
||
|
||
## Panel A（树 + gene ID）的右边界
|
||
x_A_right <- x_label_left + label_panel_width
|
||
x_A_left <- x_tree_min
|
||
|
||
## ===================== 7. 解析 MEME XML，并与树对齐（Y 对齐） =====================
|
||
|
||
motif_sites <- parse_meme_xml(meme_xml)
|
||
|
||
motif_sites <- motif_sites %>%
|
||
dplyr::filter(!is.na(gene)) %>%
|
||
dplyr::filter(gene %in% tip_dat$label)
|
||
|
||
if (nrow(motif_sites) == 0) {
|
||
stop("在 MEME 结果中没有找到与树 tip.label 匹配的基因。", call. = FALSE)
|
||
}
|
||
|
||
## 合并 tip 的 y / subfamily
|
||
motif_sites <- motif_sites %>%
|
||
dplyr::left_join(tip_dat, by = c("gene" = "label"))
|
||
|
||
## 只保留 seqlen 不缺失的条目（完全依赖 XML 的 length）
|
||
motif_sites <- motif_sites %>%
|
||
dplyr::filter(!is.na(seqlen))
|
||
|
||
## 检查长度范围
|
||
cat("motif 对应序列长度范围: ",
|
||
min(motif_sites$seqlen, na.rm = TRUE), " ~ ",
|
||
max(motif_sites$seqlen, na.rm = TRUE), "\n")
|
||
|
||
## ===================== 8. motif 高对比配色（不循环复用） =====================
|
||
|
||
motif_levels <- sort(unique(motif_sites$motif))
|
||
n_motif <- length(motif_levels)
|
||
|
||
motif_cols_vec <- make_distinct_cols(n_motif)
|
||
motif_cols <- setNames(motif_cols_vec, motif_levels)
|
||
|
||
motif_sites$motif <- factor(motif_sites$motif, levels = motif_levels)
|
||
|
||
## ===================== 9. 三个 Panel 的 X 布局 =====================
|
||
|
||
## 间隔和比例（可调）：
|
||
gap1 <- max(0.3, tree_core_width * 0.1) # Panel A 和 B 之间空隙
|
||
gap2 <- max(0.3, tree_core_width * 0.1) # Panel B 和 C 之间空隙
|
||
r_B <- 0.4 # Panel B 宽度 = 树宽 * 0.4
|
||
r_C <- 1.6 # Panel C 宽度 = 树宽 * 1.6
|
||
|
||
## Panel B（亚家族竖线区域）
|
||
x_B_left <- x_A_right + gap1
|
||
width_B <- tree_core_width * r_B
|
||
x_B_right <- x_B_left + width_B
|
||
x_subfam <- (x_B_left + x_B_right) / 2
|
||
|
||
## Panel C（motif 区域）
|
||
x_C_left <- x_B_right + gap2
|
||
width_C <- tree_core_width * r_C
|
||
x_C_right <- x_C_left + width_C
|
||
|
||
## 用"XML 中最长的序列长度"作为统一尺子
|
||
max_len <- max(motif_sites$seqlen, na.rm = TRUE)
|
||
scale_factor <- width_C / max_len # 每 1 个 aa/nt 对应多少 x 轴单位
|
||
|
||
cat("最长序列长度: ", max_len,
|
||
"；motif 面板宽度: ", width_C,
|
||
"；scale_factor: ", scale_factor, "\n")
|
||
|
||
## ===================== 10. 基因主干线 + motif 矩形坐标 =====================
|
||
|
||
## 基因主干线：从 0 到 seqlen（在 Panel C 中）
|
||
gene_tracks <- motif_sites %>%
|
||
dplyr::distinct(gene, y, seqlen) %>%
|
||
dplyr::mutate(
|
||
x_gene_start = x_C_left,
|
||
x_gene_end = x_C_left + seqlen * scale_factor
|
||
)
|
||
|
||
## motif 矩形：start / end 完全用 XML 的坐标，乘以全局比例尺
|
||
motif_rect <- motif_sites %>%
|
||
dplyr::mutate(
|
||
xmin = x_C_left + (start - 1) * scale_factor,
|
||
xmax = x_C_left + end * scale_factor,
|
||
ymin = y - 0.25,
|
||
ymax = y + 0.25
|
||
)
|
||
|
||
## ===================== 11. 亚家族竖线的 Y 范围（完全跟树对齐） =====================
|
||
|
||
if (has_subfamily) {
|
||
subfam_ranges <- make_subfamily_ranges(tip_dat)
|
||
} else {
|
||
# 没有亚家族时创建空数据框
|
||
subfam_ranges <- data.frame(
|
||
subfamily = character(),
|
||
ymin = numeric(),
|
||
ymax = numeric(),
|
||
ymid = numeric(),
|
||
stringsAsFactors = FALSE
|
||
)
|
||
}
|
||
|
||
## ===================== 12. 顶部两个表头的位置 =====================
|
||
|
||
tree_header_x <- (x_A_left + x_A_right) / 2
|
||
motif_header_x <- (x_C_left + x_C_right) / 2
|
||
header_y <- max_y + 1.2
|
||
|
||
## ===================== 13. 拼合：树 + 基因主干线 + motif + 竖线 + 表头 =====================
|
||
|
||
p_combo <- p_tree +
|
||
## 先画基因主干线（浅灰）
|
||
geom_segment(
|
||
data = gene_tracks,
|
||
inherit.aes = FALSE,
|
||
aes(
|
||
x = x_gene_start,
|
||
xend = x_gene_end,
|
||
y = y,
|
||
yend = y
|
||
),
|
||
colour = "grey70",
|
||
linewidth = 0.4
|
||
) +
|
||
## motif 用新的 fill scale（不影响 bootstrap 的 fill）
|
||
ggnewscale::new_scale_fill() +
|
||
geom_rect(
|
||
data = motif_rect,
|
||
inherit.aes = FALSE,
|
||
aes(
|
||
xmin = xmin,
|
||
xmax = xmax,
|
||
ymin = ymin,
|
||
ymax = ymax,
|
||
fill = motif
|
||
),
|
||
color = NA
|
||
) +
|
||
scale_fill_manual(values = motif_cols, name = "Motif")
|
||
|
||
# 只有有亚家族时才添加亚家族竖线
|
||
if (nrow(subfam_ranges) > 0) {
|
||
p_combo <- p_combo +
|
||
geom_segment(
|
||
data = subfam_ranges,
|
||
inherit.aes = FALSE,
|
||
aes(
|
||
x = x_subfam,
|
||
xend = x_subfam,
|
||
y = ymin,
|
||
yend = ymax,
|
||
colour = subfamily
|
||
),
|
||
linewidth = 1
|
||
) +
|
||
geom_text(
|
||
data = subfam_ranges,
|
||
inherit.aes = FALSE,
|
||
aes(
|
||
x = x_subfam + width_B * 0.05,
|
||
y = ymid,
|
||
label = subfamily,
|
||
colour = subfamily
|
||
),
|
||
hjust = 0,
|
||
size = 3
|
||
) +
|
||
scale_color_manual(values = subfam_cols, name = "Subfamily")
|
||
}
|
||
|
||
p_combo <- p_combo +
|
||
## 顶部两个表头（各在自己 panel 正上方）
|
||
annotate(
|
||
"text",
|
||
x = tree_header_x,
|
||
y = header_y,
|
||
label = "Phylogenetic tree",
|
||
fontface = "bold",
|
||
size = 4
|
||
) +
|
||
annotate(
|
||
"text",
|
||
x = motif_header_x,
|
||
y = header_y,
|
||
label = "Motif",
|
||
fontface = "bold",
|
||
size = 4
|
||
) +
|
||
## 画板 x 轴范围 = 从树最左到 motif panel 右边，再留一点边距
|
||
coord_cartesian(
|
||
xlim = c(x_A_left, x_C_right + tree_core_width * 0.1)
|
||
) +
|
||
## 给表头留出一点空间
|
||
expand_limits(y = header_y + 0.5) +
|
||
theme(
|
||
legend.position = "right",
|
||
legend.background = element_rect(color = "#969696", fill = "#d9d9d9")
|
||
)
|
||
|
||
## 输出 PDF 和 PNG
|
||
output_pdf <- paste0(output_prefix, ".tree_motif.pdf")
|
||
output_png <- paste0(output_prefix, ".tree_motif.png")
|
||
|
||
# 保存PDF
|
||
ggsave(output_pdf, p_combo, width = 14, height = 10)
|
||
|
||
# 保存PNG（使用png()函数避免conda R的API冲突）
|
||
png(filename = output_png, width = 4200, height = 3000, res = 300)
|
||
print(p_combo)
|
||
dev.off()
|
||
|
||
cat("[OK] PDF: ", output_pdf, "\n", sep = "")
|
||
cat("[OK] PNG: ", output_png, "\n", sep = "")
|
||
cat("已输出树 + motif 组合图\n")
|