admin/PlantAI-dev
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity
Files
7097ecdec5e75fa1e21cbfa2bb2a641f670d9e51
PlantAI-dev/scripts/tree_motif_domain_structure.R/tree_motif_structure.R
T

615 lines
17 KiB
R
Raw Normal View History

Initial commit: PlantAI-dev
2026-08-03 18:42:47 +08:00
#!/usr/bin/env Rscript
## =========================================================
## combo_motif_structure.R
## 左：系统发育树（含基因 ID）
## 中：亚家族竖线（不压 gene ID）
## 右一：MEME motif（按 XML 实际长度比例）
## 右二：GFF3 基因结构（按 GFF3 实际长度比例；只画 CDS + UTR）
## 顶部：三个表头：Phylogenetic tree / Motif / Gene structure
##
## 用法:
## Rscript combo_motif_structure.R \
## <treefile> <subfamily_file> <meme_xml> <gff3_file> [output_pdf]
## =========================================================
args <- commandArgs(trailingOnly = TRUE)
if (length(args) < 4) {
stop(
"用法:\n",
" Rscript combo_motif_structure.R ",
"<treefile> <subfamily_file> <meme_xml> <gff3_file> [output_pdf]\n\n",
call. = FALSE
)
}
treefile <- args[1]
subfamily_file <- args[2]
meme_xml <- args[3]
gff3_file <- args[4]
## 第五个参数：输出 pdf 名称
if (length(args) >= 5 && nzchar(args[5])) {
output_pdf <- args[5]
} else {
prefix <- sub("\\.[^.]*$", "", treefile)
output_pdf <- paste0(prefix, ".tree_motif_structure.pdf")
}
cat("树文件: ", treefile, "\n")
cat("亚家族文件: ", subfamily_file, "\n")
cat("MEME XML 文件: ", meme_xml, "\n")
cat("GFF3 文件: ", gff3_file, "\n")
cat("输出文件: ", output_pdf, "\n\n")
## ===================== 2. 加载 R 包 =====================
suppressPackageStartupMessages({
library(ape)
library(ggtree)
library(tidytree)
library(dplyr)
library(RColorBrewer)
library(ggplot2)
library(xml2)
library(ggnewscale)
})
## ===================== 3. 读亚家族文件 + 深色配色 =====================
subfam <- read.table(subfamily_file,
header = FALSE,
stringsAsFactors = FALSE)
colnames(subfam) <- c("label", "subfamily")
subfam_levels <- sort(unique(subfam$subfamily))
n_subfam <- length(subfam_levels)
if (n_subfam == 0) {
stop("在亚家族文件中没有检测到任何 subfamily，请检查文件格式。", call. = FALSE)
}
## 深色调：Dark2，若类别多就循环使用
base_cols_sf <- RColorBrewer::brewer.pal(8, "Dark2")
subfam_cols_vec <- rep_len(base_cols_sf, n_subfam)
subfam_cols <- setNames(subfam_cols_vec, subfam_levels)
## ===================== 4. 树绘图函数（只画树 + tip/subfamily，不画竖线） =====================
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$tip.label)
tree_df <- dplyr::left_join(tree_df, subfam_df, by = "label")
tree_df$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)
) +
## tip 颜色 = subfamily
geom_tippoint(
aes(color = subfamily),
size = 2,
na.rm = TRUE
) +
scale_color_manual(
values = subfam_cols,
name = "Subfamily"
) +
## 基因 ID 标签，靠树一点
geom_tiplab(offset = label_offset, size = 3, hjust = 0) +
ggtitle(NULL) +
theme_tree() +
theme(
legend.background = element_rect(color = "#969696",
fill = "#d9d9d9")
)
attr(p, "label_offset") <- label_offset
return(p)
}
## ===================== 5. 解析 MEME XML，得到 motif 位点 + 序列长度 =====================
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 length / Length 大小写
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_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
sites$end <- sites$start + sites$width - 1
sites
}
## ===================== 6. 解析 GFF3，提取基因结构 =====================
parse_gff3_gene_structure <- function(gff3_file, tree_genes) {
gff <- read.table(gff3_file,
sep = "\t",
comment.char = "#",
quote = "",
stringsAsFactors = FALSE,
fill = TRUE)
if (ncol(gff) < 9) {
stop("GFF3 文件列数不足 9 列，请检查格式。", call. = FALSE)
}
colnames(gff)[1:9] <- c("seqid", "source", "type", "start",
"end", "score", "strand", "phase",
"attributes")
gff$start <- as.numeric(gff$start)
gff$end <- as.numeric(gff$end)
## 只保留关心的 feature 类型
feat_types <- c("exon", "CDS", "UTR",
"five_prime_UTR", "three_prime_UTR",
"5UTR", "3UTR")
feat_df <- gff[gff$type %in% feat_types, ]
if (nrow(feat_df) == 0) {
stop("在 GFF3 中没有找到 exon/CDS/UTR 等特征。", call. = FALSE)
}
## 解析 attributes 里的 Parent=...
get_attr <- function(attr_vec, key) {
sapply(strsplit(attr_vec, ";"), function(fields) {
kv <- strsplit(fields, "=")
res <- NA_character_
for (p in kv) {
if (length(p) == 2 && p[1] == key) {
res <- p[2]
break
}
}
res
})
}
feat_df$Parent <- get_attr(feat_df$attributes, "Parent")
## 只保留 Parent 出现在树 tip.label 的转录本
feat_df <- feat_df[!is.na(feat_df$Parent) &
feat_df$Parent %in% tree_genes, ]
if (nrow(feat_df) == 0) {
stop("GFF3 中的 Parent 与树 tip.label 无交集，请检查 ID 是否一致。", call. = FALSE)
}
feat_df$gene <- feat_df$Parent
## 每个 gene 的基因区域：真实 genomic 坐标范围
gene_ranges <- feat_df %>%
dplyr::group_by(gene) %>%
dplyr::summarise(
gene_start = min(start, end, na.rm = TRUE),
gene_end = max(start, end, na.rm = TRUE),
gene_len = gene_end - gene_start + 1,
.groups = "drop"
)
## 特征相对该基因起点的坐标
feat_df <- feat_df %>%
dplyr::left_join(gene_ranges, by = "gene") %>%
dplyr::mutate(
rel_start = pmin(start, end) - gene_start,
rel_end = pmax(start, end) - gene_start
) %>%
dplyr::mutate(
Type = dplyr::case_when(
type %in% c("five_prime_UTR", "three_prime_UTR",
"5UTR", "3UTR", "UTR") ~ "UTR",
TRUE ~ type
)
)
list(features = feat_df, ranges = gene_ranges)
}
## ===================== 7. 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
## Panel A（树 + gene ID）
label_panel_width <- max(1.5, tree_core_width * 0.5)
x_A_left <- x_tree_min
x_A_right <- x_label_left + label_panel_width
## ===================== 8. 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$label)
if (nrow(motif_sites) == 0) {
stop("在 MEME 结果中没有找到与树 tip.label 匹配的基因。", call. = FALSE)
}
motif_sites <- motif_sites %>%
dplyr::left_join(tip_dat, by = c("gene" = "label")) %>%
dplyr::filter(!is.na(seqlen))
cat("motif 序列长度范围 (XML): ",
min(motif_sites$seqlen, na.rm = TRUE), " ~ ",
max(motif_sites$seqlen, na.rm = TRUE), "\n")
## motif 配色
motif_levels <- sort(unique(motif_sites$motif))
n_motif <- length(motif_levels)
base_cols_m <- RColorBrewer::brewer.pal(8, "Dark2")
motif_cols_vec <- rep_len(base_cols_m, n_motif)
motif_cols <- setNames(motif_cols_vec, motif_levels)
motif_sites$motif <- factor(motif_sites$motif, levels = motif_levels)
## ===================== 9. 解析 GFF3（gene structure），并与树对齐 =====================
gs <- parse_gff3_gene_structure(gff3_file, tip_dat$label)
gene_feat <- gs$features
gene_ranges <- gs$ranges
gene_ranges <- gene_ranges %>%
dplyr::left_join(tip_dat, by = c("gene" = "label"))
gene_feat <- gene_feat %>%
dplyr::left_join(tip_dat, by = c("gene" = "label"))
gene_ranges <- gene_ranges %>% dplyr::filter(!is.na(y))
gene_feat <- gene_feat %>% dplyr::filter(!is.na(y))
if (nrow(gene_feat) == 0) {
stop("GFF3 中匹配到树 tip.label 的基因结构为空。", call. = FALSE)
}
cat("基因长度范围 (GFF3): ",
min(gene_ranges$gene_len, na.rm = TRUE), " ~ ",
max(gene_ranges$gene_len, na.rm = TRUE), "\n")
## ===================== 10. 四个 Panel 的 X 布局 =====================
## 间隔和比例（可以微调）：
gap1 <- max(0.3, tree_core_width * 0.10) # A-B 间隔
gap2 <- max(0.3, tree_core_width * 0.10) # B-C 间隔
gap3 <- max(0.3, tree_core_width * 0.10) # C-D 间隔
r_B <- 0.4 # Panel B 宽度 = 树宽 * 0.4
r_C <- 1.6 # Panel C 宽度 = 树宽 * 1.6
r_D <- 2.2 # Panel D 宽度 = 树宽 * 2.2（结构面板更大）
## Panel B（亚家族竖线）
x_B_left <- x_A_right + gap1
width_B <- tree_core_width * r_B
x_B_right <- x_B_left + width_B
x_subfam <- (x_B_left + x_B_right) / 2
## Panel C（motif）
x_C_left <- x_B_right + gap2
width_C <- tree_core_width * r_C
x_C_right <- x_C_left + width_C
## Panel D（gene structure）
x_D_left <- x_C_right + gap3
width_D <- tree_core_width * r_D
x_D_right <- x_D_left + width_D
## ===================== 11. motif 坐标（按 XML 实际长度） =====================
max_len_motif <- max(motif_sites$seqlen, na.rm = TRUE)
scale_motif <- width_C / max_len_motif
cat("最长 motif 序列长度: ", max_len_motif,
"；motif 面板宽度: ", width_C,
"；scale_motif: ", scale_motif, "\n")
## motif 基因主干线
motif_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_motif
)
## motif 矩形
motif_rect <- motif_sites %>%
dplyr::mutate(
xmin = x_C_left + (start - 1) * scale_motif,
xmax = x_C_left + end * scale_motif,
ymin = y - 0.25,
ymax = y + 0.25
)
## ===================== 12. gene structure 坐标（按 GFF3 实际长度；只画 CDS + UTR） =====================
max_gene_len <- max(gene_ranges$gene_len, na.rm = TRUE)
scale_gene <- width_D / max_gene_len
cat("最长基因长度: ", max_gene_len,
"；gene 面板宽度: ", width_D,
"；scale_gene: ", scale_gene, "\n")
## 基因主干线（Panel D）
gene_tracks <- gene_ranges %>%
dplyr::mutate(
x_gene_start = x_D_left,
x_gene_end = x_D_left + gene_len * scale_gene
)
## 各 feature 矩形（先算坐标）
gene_feat_rect <- gene_feat %>%
dplyr::mutate(
xmin = x_D_left + rel_start * scale_gene,
xmax = x_D_left + rel_end * scale_gene,
ymin = y - 0.25,
ymax = y + 0.25
)
## 只保留 CDS 和 UTR，不画 exon 等其它类型
gene_feat_rect <- gene_feat_rect %>%
dplyr::filter(Type %in% c("CDS", "UTR"))
## gene structure 深色配色（只针对 CDS 和 UTR）
gene_palette <- c(
CDS = "#1b9e77", # 深蓝绿
UTR = "#d95f02" # 深橙
)
gene_types <- sort(unique(gene_feat_rect$Type))
gene_cols_vec <- gene_palette[gene_types]
names(gene_cols_vec) <- gene_types
## ===================== 13. 亚家族竖线的 Y 范围 =====================
subfam_ranges <- tip_dat %>%
dplyr::filter(!is.na(subfamily)) %>%
dplyr::group_by(subfamily) %>%
dplyr::summarise(
ymin = min(y),
ymax = max(y),
ymid = (ymin + ymax) / 2,
.groups = "drop"
)
## ===================== 14. 顶部三个表头的位置 =====================
tree_header_x <- (x_A_left + x_A_right) / 2
motif_header_x <- (x_C_left + x_C_right) / 2
gene_header_x <- (x_D_left + x_D_right) / 2
header_y <- max_y + 1.2
## ===================== 15. 拼合：树 + motif + gene + 竖线 + 表头 =====================
p_combo <- p_tree +
## Panel C：motif 基因主干线（浅灰）
geom_segment(
data = motif_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
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") +
## Panel D：gene 基因主干线
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
) +
## gene structure 用新的 fill scale（CDS / UTR 深色）
ggnewscale::new_scale_fill() +
geom_rect(
data = gene_feat_rect,
inherit.aes = FALSE,
aes(
xmin = xmin,
xmax = xmax,
ymin = ymin,
ymax = ymax,
fill = Type
),
color = NA
) +
scale_fill_manual(
values = gene_cols_vec,
name = "Gene Structure"
) +
## Panel B：亚家族竖线 + 标签
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
) +
## 顶部三个表头
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
) +
annotate(
"text",
x = gene_header_x,
y = header_y,
label = "Gene structure",
fontface = "bold",
size = 4
) +
## X 轴范围从树最左到 gene panel 最右
coord_cartesian(
xlim = c(x_A_left, x_D_right + tree_core_width * 0.1)
) +
expand_limits(y = header_y + 0.5) +
theme(
legend.position = "right",
legend.background = element_rect(color = "#969696", fill = "#d9d9d9")
)
## 整体宽一点，容得下四个 panel
ggsave(output_pdf, p_combo, width = 18, height = 10)
cat("已输出 树 + motif + 基因结构 组合图到: ", output_pdf, "\n")
Reference in New Issue Copy Permalink