I have 3 data.frames with the data to plot genes. The problem that I want to solve, is to keep the genes legends in x (geneA to geneF), as well as the scale bar with the numbers in x, I have tried the next code; maybe the problem is scale_x_continuous, when I don’t use it the scale bar is ok, but I want the genes labels also in x (or could be in top!!!)
df1
sample gene width start end orientation
1 GENOME326 geneA 15630 1 15630 FALSE
2 GENOME326 geneC 396 15631 16026 FALSE
3 GENOME326 geneF 360 16027 16386 FALSE
4 GENOME300 geneA 15630 1 15630 FALSE
5 GENOME300 geneC 396 15631 16026 FALSE
6 GENOME300 geneF 360 16027 16386 FALSE
7 GENOME594 geneA 15630 1 15630 FALSE
8 GENOME594 geneC 396 15631 16026 FALSE
9 GENOME594 geneF 360 16027 16386 FALSE
10 GENOME326 geneB 2106 16826 18931 TRUE
11 GENOME326 geneD 1362 18932 20293 TRUE
12 GENOME326 geneE 2169 20294 22462 TRUE
13 GENOME300 geneB 2106 16826 18931 TRUE
14 GENOME300 geneD 1362 18932 20293 TRUE
15 GENOME300 geneE 2169 20294 22462 TRUE
16 GENOME594 geneB 2106 16826 18931 TRUE
17 GENOME594 geneD 1362 18932 20293 TRUE
18 GENOME594 geneE 2169 20294 22462 TRUE
df2
gene width start end position n
1 geneA 15630 1 15630 7815.5 21
2 geneC 396 15631 16026 15828.5 21
3 geneF 360 16027 16386 16206.5 21
4 geneB 2106 16387 18492 17439.5 21
5 geneD 1362 18493 19854 19612.5 21
6 geneE 2169 19855 22023 20939.0 21
df3
sample gene start end domains from to orientation gap
1 GENOME326 geneA 1 15627 DomainA 8587 9751 TRUE <NA>
2 GENOME326 geneA 1 15627 DomainB 6903 8541 TRUE <NA>
3 GENOME326 geneA 1 15627 DomainC 6013 6913 TRUE <NA>
4 GENOME326 geneA 1 15627 DomainD 5053 5778 TRUE <NA>
5 GENOME326 geneA 1 15627 DomainE 3421 4833 TRUE <NA>
6 GENOME326 geneA 1 15627 DomainF 3097 3420 TRUE <NA>
7 GENOME300 geneA 1 15627 DomainA 8587 9751 TRUE <NA>
8 GENOME300 geneA 1 15627 DomainB 6903 8541 TRUE <NA>
9 GENOME300 geneA 1 15627 DomainC 6013 6913 TRUE <NA>
10 GENOME300 geneA 1 15627 DomainD 5053 5778 TRUE <NA>
11 GENOME300 geneA 1 15627 DomainE 3421 4833 TRUE <NA>
12 GENOME300 geneA 1 15627 DomainF 3097 3420 TRUE <NA>
13 GENOME594 geneA 1 15627 DomainA 8587 9751 TRUE <NA>
14 GENOME594 geneA 1 15627 DomainB 6903 8541 TRUE <NA>
15 GENOME594 geneA 1 15627 DomainC 6013 6913 TRUE <NA>
16 GENOME594 geneA 1 15627 DomainD 5053 5778 TRUE <NA>
17 GENOME594 geneA 1 15627 GAP 3421 4921 TRUE ---GAP---
18 GENOME594 geneA 1 15627 DomainF 3097 3420 TRUE <NA>
code:
ggplot() +
# rtx gene
geom_gene_arrow(data =df1,
aes(xmin=start, xmax=end, y= sample, forward=orientation),
fill="white", size=0.5, color="black",
arrowhead_width = grid::unit(11, "mm"),
arrowhead_height = grid::unit(11, "mm"),
arrow_body_height = grid::unit(9, "mm")) +
scale_x_continuous(expand = expansion(mult = c(0.002, 0.001)), #
position = "bottom",
breaks = df2$position, #
labels = df2$gene) +
scale_shape_manual(values = c(15, 16)) +
# Domains
geom_subgene_arrow(data = df3,
aes(xsubmin = from, xsubmax = to, fill = domains, xmin=start, xmax=end, y=sample), alpha=0.5,
arrowhead_width = unit(15, "mm"),
arrowhead_height = unit(7, "mm"),
arrow_body_height = unit(7.4, "mm")) +
geom_text(data = subset(df3, gap != "NA") %>% mutate(posgap = (from + 250) ), #
aes(y=sample, x=posgap, label=gap), angle = 0, hjust = 0, size = 5, color="black") +
# agregar color a cada dominio de manera individual
scale_fill_manual(labels = list(expression(DomainA),
expression(DomainB),
expression(DomainC), #
expression(DomainD),
expression(DomainE),
expression(DomainF),
expression(GAP) ),
values = c( "dodgerblue3", "#FB8072", "#FDB462", "#BC80BD", "#FFED6F", "#9997FC", "grey50") ) +
xlab("base pair (bp)") +
scale_y_discrete(position="right") + theme_classic() +
theme(panel.background = element_rect(fill = 'white', color = 'white'), #
axis.text.y = element_text(size = 14, family="Times New Roman", face="bold"),
panel.border = element_blank(),
panel.grid = element_blank(),
panel.spacing = element_blank(),
axis.title.y= element_blank(),
# axis.ticks.x = element_blank(), #
axis.ticks.y = element_blank(), #
axis.title.x = element_text(size = 10, face = "bold"),
axis.text.x = element_text(angle = 90,
vjust = 0.5,
hjust=1,
size = 15, #
face="bold.italic", #
family="Times New Roman"),
legend.text=element_text(size=14),
legend.position="bottom", #
legend.title=element_blank(), #
) +
guides(fill=guide_legend(nrow=1)) #
Without scale_x_continuous, but the genes in x do not appear !!!
ggplot() +
# rtx gene
geom_gene_arrow(data =df1,
aes(xmin=start, xmax=end, y= sample, forward=orientation),
fill="white", size=0.5, color="black",
arrowhead_width = grid::unit(11, "mm"),
arrowhead_height = grid::unit(11, "mm"),
arrow_body_height = grid::unit(9, "mm")) +
scale_shape_manual(values = c(15, 16)) +
# Domains
geom_subgene_arrow(data = df3,
aes(xsubmin = from, xsubmax = to, fill = domains, xmin=start, xmax=end, y=sample), alpha=0.5,
arrowhead_width = unit(15, "mm"),
arrowhead_height = unit(7, "mm"),
arrow_body_height = unit(7.4, "mm")) +
geom_text(data = subset(df3, gap != "NA") %>% mutate(posgap = (from + 250) ), #
aes(y=sample, x=posgap, label=gap), angle = 0, hjust = 0, size = 5, color="black") +
# agregar color a cada dominio de manera individual
scale_fill_manual(labels = list(expression(DomainA),
expression(DomainB),
expression(DomainC), #
expression(DomainD),
expression(DomainE),
expression(DomainF),
expression(GAP) ),
values = c( "dodgerblue3", "#FB8072", "#FDB462", "#BC80BD", "#FFED6F", "#9997FC", "grey50") ) +
xlab("base pair (bp)") +
scale_y_discrete(position="right") + theme_classic() +
theme(panel.background = element_rect(fill = 'white', color = 'white'), #
axis.text.y = element_text(size = 14, family="Times New Roman", face="bold"),
panel.border = element_blank(),
panel.grid = element_blank(),
panel.spacing = element_blank(),
axis.title.y= element_blank(),
# axis.ticks.x = element_blank(), #
axis.ticks.y = element_blank(), #
axis.title.x = element_text(size = 10, face = "bold"),
axis.text.x = element_text(angle = 90,
vjust = 0.5,
hjust=1,
size = 15, #
face="bold.italic", #
family="Times New Roman"),
legend.text=element_text(size=14),
legend.position="bottom", #
legend.title=element_blank(), #
) +
guides(fill=guide_legend(nrow=1)) #
Any solution ?
Thanks