0.16.6 文档
全站目录 · 按任务查找
绘制注释与处理重叠
本页目录
把真实注释画为独立图层，选择合适形状，并让重叠区间和文字共享堆叠位置。
本页准备
在新的 R 会话中先运行下方代码，再按页面顺序继续。配色和排版是可选的显示设置，输入只选择需要的列。
准备代码 · 在本页运行一次
代码
library(ggchord)
library(dplyr)
data(seq_data_example)
data(ribbon_data_example)
data(gene_data_example)
seqs <- seq_data_example |>
select(accver, length)
links <- ribbon_data_example |>
select(qaccver, saccver, qstart, qend, sstart, send)
# The fixture preserves biological strands separately from its old display strands.
genes <- gene_data_example |>
transmute(accver, start, end, strand = source_strand)
# Optional appearance choices; none of these columns or scales is required input.
library(ggchord)
seq_palette <- setNames(
c("#E64B35", "#233E4A", "#269B82", "#D59B17"),
c("MT108731.1", "MT118296.1", "OQ646790.1", "OR222515.1")
)
gene_palette <- c("+" = "#CE1536", "-" = "#346B9D", "." = "#8291A6")
library(ggchord)
feature_palette <- c(
CDS = "#993366", promoter = "#31849B", rep_origin = "#F1E51D",
primer_bind = "#A020F0", misc_feature = "#A6ACB3", protein_bind = "#31849B"
)
library(ggchord)
doc_background <- "#FFFCF5"
identity_palette <- c("#303B71", "#36537D", "#269B82", "#A5D52C", "#ECEB31")
identity_values <- c(0, 0.5, 0.8, 0.9, 1)
identity_breaks <- c(0, 50, 80, 90, 100)
doc_legend_theme <- theme(
legend.title = element_text(size = 13, face = "bold"),
legend.text = element_text(size = 11),
legend.key.width = unit(9, "mm"), legend.key.height = unit(5, "mm"),
legend.spacing.x = unit(9, "mm"), legend.spacing.y = unit(7, "mm"),
legend.margin = margin(l = 4, r = 4, unit = "mm")
)
sequence_guide <- guide_ggchord_legend(nrow = 1, theme = doc_legend_theme)
strand_guide <- guide_ggchord_legend(
nrow = 1, override.aes = list(strand = c("+", "-")), theme = doc_legend_theme
)
identity_guide <- guide_ggchord_colourbar(
position = "left", direction = "vertical",
theme = theme(
legend.key.height = unit(75, "mm"), legend.key.width = unit(5, "mm"),
legend.title = element_text(size = 13, face = "bold"),
legend.text = element_text(size = 11), legend.margin = margin(r = 7, unit = "mm")
)
)
doc_theme <- theme_ggchord_publication(
axis.text = element_text(size = 11),
axis.text.check.overlap = TRUE
) +
theme(
legend.position = "bottom",
legend.title = element_text(size = 13, face = "bold"),
legend.text = element_text(size = 11),
legend.key.width = unit(9, "mm"), legend.key.height = unit(5, "mm"),
legend.spacing.x = unit(9, "mm"), legend.spacing.y = unit(7, "mm"),
legend.box.spacing = unit(6, "mm"),
plot.background = element_rect(fill = doc_background, colour = NA),
panel.background = element_blank(),
plot.title = element_text(face = "bold", size = 18),
plot.subtitle = element_text(size = 10, colour = "#5C625A"),
plot.margin = margin(14, 18, 14, 18)
)
doc_axis <- function(coordinates = "relative") {
scale_seq_position_continuous(
coordinates = coordinates, n.breaks = 3, minor_breaks = NULL,
labels = function(x) format(x, scientific = FALSE, big.mark = ",", trim = TRUE)
)
}
library(dplyr)
data(plasmid_example_pUC19)
plasmid_seq <- plasmid_example_pUC19 |>
select(accver, length)
feature_source <- find_common_features(plasmid_example_pUC19)
features <- feature_source |>
select(accver, start, end, strand, type, anno)保留注释语义
本页准备代码已加载 pUC19 的实际注释。 这里保留 pUC19 中实际重叠的注释和原本未知的链方向。 几何和填色分别映射同一类别；显式固定 shape 会覆盖 shape 映射。
代码
stack_features <- features |>
select(accver, start, end, strand, type, anno)
stack_position <- position_feature_stack(spacing = .12)
feature_shapes <- setNames(ifelse(names(feature_palette) == "CDS", "arrow", "block"), names(feature_palette))
p_stack <- ggchord(seq_data = plasmid_seq) +
geom_seq(show.legend = FALSE) +
geom_feature(aes(feature_fill = type, feature_shape = type),
data = stack_features,
width = .08, position = stack_position
) +
geom_feature_label_repel(data = stack_features, position = stack_position, size = 3.8, label_fit = "shrink", label_min_size = 2.8) +
scale_feature_shape_manual(values = feature_shapes) +
scale_feature_fill_manual(values = feature_palette) +
coord_collinear() +
doc_axis() +
doc_theme
p_stack
position_feature_stack() 解决注释轨道重叠。标签层使用同一 Position，让文字锚点 跟随轨道。标签子集或重排时优先提供唯一 feature_id。严格的 gene 快捷层要求 已知 +/-，通用注释保留未知/双向语义。
按含义选择形状
| 几何 | 常见用途 | 重要区别 |
|---|---|---|
arrow, compact_arrow
|
有方向的编码/注释区间 | 已知方向来自证据，不由显示猜测 |
block, capped_line
|
区域或不填充区间 | 选择形状不推断生物学功能 |
promoter_arrow, primer_arrow, primer_arc
|
已声明的启动子/引物式注释 | 计算匹配与绘图分开 |
marker, chevron, lollipop
|
自定义区间/类点强调 | 保留真实区间元数据，显示形状属于映射 |
geom_gene()、geom_feature_plasmid() 是有用预设，默认值并不相同。 position_strand() 提供带符号位移，position_plasmid() 提供圆图放置预设， 后者不构成第四类坐标模式。
高亮区间而不改写观测
代码
regions <- tibble(
accver = links$qaccver[1], start = min(links$qstart[1], links$qend[1]),
end = max(links$qstart[1], links$qend[1]), category = "alignment interval"
)
p_decorated <- ggchord(seq_data = seqs, ribbon_data = links) +
geom_seq_region(aes(region_fill = category), data = regions, colour = NA) +
geom_link_ribbon(fill = "#6BAFA6", alpha = .4) +
geom_seq() +
geom_seq_label(size = 4) +
scale_region_fill_manual(values = c("alignment interval" = "#F4D35E")) +
scale_seq_colour_manual(values = seq_palette) +
geom_seq_scale(length = 10000) +
coord_collinear() +
doc_axis() +
doc_theme
p_decorated
区域叠层有自己的数据和 region_fill 标度。geom_seq_label() 命名序列， geom_seq_center_label() 在单圆图中心提供名称/长度，geom_seq_break() 标记裁剪或 分段末端。geom_seq_scale() 是仅用于共线性图的独立 bp 参照条，与控制序列基因组轴 的 scale_seq_position_continuous() 不同。普通 ggplot2 注释应使用 位置映射，不能把 bp 直接当作笛卡尔 x/y。
完成后检查
先检查区间与链，再看形状与标签。未知链仍保留在通用注释中；堆叠改变显示位置，不改变原始基因组坐标。