E.coli Lac operon
Click to see the code
lacZ_operon <- data.frame(
start = c(361249, 361926, 363231, 366428),
end = c(361860, 363179, 366305, 367510),
Gene_symbol = c("lacA", "lacY", "lacZ", "lacI"),
Strand = c("minus", "minus", "minus", "minus"),
NCBI_Gene_ID = as.character(c(945674, 949083, 945006, 945007)),
Description = c("galactoside O-acetyltransferase",
"lactose permease", "beta-galactosidase",
"DNA-binding transcriptional repressor LacI")
)
GC_chart(lacZ_operon, group = "Gene_symbol", height = "140px") %>%
GC_labels() %>%
GC_scaleBar(title = "0.2 kb", scaleBarUnit = 200, y=30) %>%
GC_tooltip(
formatter = "
<b>ID:</b> {NCBI_Gene_ID}<br>
<b>Description:</b> {Description}<br>
<b>Start:</b> {start}<br>
<b>End:</b> {end}",
) %>%
GC_clusterFooter(
align = "center",
y = -30,
subtitle = "<i>Escherichia coli</i> str. K-12 substr. MG1655"
) %>%
GC_coordinates(
rotate = 0,
tickValuesBottom = c(min(lacZ_operon$start), max(lacZ_operon$end)),
textStyle = list(fontSize = "10px", x = -2.2, y = 1.2),
tickStyle = list(lineLength = 10)
) %>%
GC_legend(FALSE)Omphalotin gene clusters
Click to see the code
GC_chart(ophA_clusters,
start = "start",
end = "end",
group = "class",
cluster = "cluster") %>%
GC_clusterFooter(
title = c("<i>Omphalotus olearius</i>", "<i>Dendrothele bispora</i>"),
subtitle = c("Locus: 2,522 - 21,484", "Locus: 19,236 - 43,005"),
align = "left",
x = 50) %>%
GC_legend(position = "top") %>%
GC_labels(label = "name") %>%
GC_scaleBar(y = 20) %>%
GC_scale(cluster = 1, scale_breaks = TRUE, hidden = TRUE) %>%
GC_scale(cluster = 2, reverse = TRUE, hidden = TRUE) %>%
GC_tooltip(
formatter = "<b>Gene:</b> {name}<br> <b>Start:</b> {start}<br><b>end:</b> {end}"
)
H. sapiens Hox genes using biomaRt
Click to see the code
# Get HOX gene positions
library(biomaRt)
ensembl <- useMart("ensembl", dataset = "hsapiens_gene_ensembl")
hox_gene_sets <- list(
HOXA = c("HOXA1", "HOXA2", "HOXA3", "HOXA4", "HOXA5", "HOXA6", "HOXA7", "HOXA9", "HOXA10", "HOXA11", "HOXA13"),
HOXB = c("HOXB1", "HOXB2", "HOXB3", "HOXB4", "HOXB5", "HOXB6", "HOXB7", "HOXB8", "HOXB9", "HOXB13"),
HOXC = c("HOXC4", "HOXC5", "HOXC6", "HOXC8", "HOXC9", "HOXC10", "HOXC11", "HOXC12", "HOXC13"),
HOXD = c("HOXD1", "HOXD3", "HOXD4", "HOXD8", "HOXD9", "HOXD10", "HOXD11", "HOXD12", "HOXD13")
)
get_gene_positions <- function(gene_list, cluster_name) {
result <- getBM(attributes = c('hgnc_symbol', 'chromosome_name', 'strand', 'start_position', 'end_position'),
filters = 'hgnc_symbol',
values = gene_list,
mart = ensembl)
transform(result, cluster = cluster_name)
}
# Apply get_gene_positions to each gene set
hox_gene_positions <- base::lapply(names(hox_gene_sets), function(cluster_name) {
get_gene_positions(hox_gene_sets[[cluster_name]], cluster_name)
})
# Combine the results into a single data frame
combined_hox_genes <- do.call(rbind, hox_gene_positions)
# Add gene names
combined_hox_genes$name <- paste0(substr(combined_hox_genes$hgnc_symbol, 1, 3), substr(combined_hox_genes$hgnc_symbol, 5, nchar(combined_hox_genes$hgnc_symbol)))
GC_chart(
combined_hox_genes,
start = "start_position",
end = "end_position",
group = "cluster",
height = "400px",
strand = "strand",
cluster = "cluster") %>%
GC_sequence(y=45) %>%
GC_legend(FALSE) %>%
GC_clusterLabel(title = unique(human_hox_genes$cluster)) %>%
GC_genes(
marker = "boxarrow",
markerHeight = 10,
arrowheadHeight = 10,
arrowheadWidth = 3
) %>%
GC_labels(label = "name", fontSize = "10px", adjustLabels = FALSE) %>%
GC_labels(cluster = 2, label = "name", itemStyle = list(list(index = 5, x = -4))) %>%
GC_scale(
cluster = c(1,2),
hidden = TRUE,
reverse = TRUE
) %>%
GC_cluster(prevent_gene_overlap = TRUE, overlap_spacing=20)H. sapiens Dystrophin transcript variants
Click to see the code
GC_chart(hs_dystrophin_transcripts,
start = "start",
end = "end",
group = "type",
cluster = "transcript") %>%
GC_title("Dystrophin transcript variants") %>%
GC_genes(
stroke = "#1f77b4",
) %>%
GC_scale(
cluster = c(1, 2, 3, 4),
start = 1,
end = max(hs_dystrophin_transcripts$length),
hidden = TRUE
) %>%
GC_scale(
cluster = 5,
y = 25,
ticksCount = 8,
start = 1,
end = max(hs_dystrophin_transcripts$length),
) %>%
GC_clusterLabel(title = unique(hs_dystrophin_transcripts$transcript)) %>%
GC_legend(
position = "top"
)Saccharopolyspora erythraea Erythromycin
Click to see the code
colors <- list(
"Tailoring (Hydroxylation)" = "#d62728",
"Precursor biosynthesis" = "#2ca02c",
"Tailoring (Glycosylation)" = "#e6b0aa",
"Scaffold biosynthesis" = "#9467bd",
"Tailoring (Methylation)" = "#8b0000",
"Activation / processing" = "#1f77b4",
"Resistance / immunity" = "#f7dc6f" ,
"Other" = "#808080"
)
GC_chart(erythromycin_cluster,
start = "Start",
end = "End",
height = "160px",
group = "Functions") %>%
GC_title(
title = "Erythromycin A biosynthetic gene cluster from <i>Saccharopolyspora erythraea</i>",
height = 40,
align = "left"
) %>%
GC_genes(
marker = "boxarrow",
marker_size = "small"
) %>%
GC_tooltip(
formatter = "<b>{Identifiers}</b>
<br>{Product}
<br>{start} - {end}({Strand})"
) %>%
GC_scale(
start = 778000,
end = 832000,
ticksCount = 8
) %>%
GC_legend(
legendTextOptions = list(fontSize = "12px"),
order = c(setdiff(sort(erythromycin_cluster$Functions), "Other"), "Other")
) %>%
GC_color(customColors = colors)Saccharopolyspora erythraea Erythromycin BlastP
Click to see the code
### Erythromycin BlastP
GC_chart(erythromycin_BlastP,
cluster = "cluster",
strand = "strand",
group = "Functions",
height = 700) %>%
GC_title(
title = "BlastP Results"
) %>%
GC_labels("Gene", cluster = 1) %>%
GC_links(group = "Gene",
show_links = FALSE,
labelStyle = list(fontSize = "10px")
) %>%
GC_clusterLabel()Click to see the code
library(dplyr)
### Erythromycin BlastP
GC_chart(erythromycin_BlastP %>% dplyr::filter(cluster %in% c("BGC0000055", "BGC0000054")),
cluster = "cluster",
strand = "strand",
group = "BlastP",
height = 250) %>%
GC_labels("Gene", cluster = 1) %>%
GC_genes(marker_size = "small", marker = "rbox", markerHeight = 15) %>%
GC_links(group = "BlastP",
show_links = TRUE,
identity_label = FALSE
) %>%
GC_clusterLabel() %>%
GC_legend(FALSE)