# From CRAN (when available)
install.packages("admetshiny")
# From GitHub
# devtools::install_github("xavierclementegarcia/admetshiny")Learning Guide
This document provides detailed tutorials for every function in the admetshiny package.
Installation
Launching the Shiny App
library(admetshiny)
run_app()Drug-Likeness Filters
lipinskiFilter()
Filters compounds according to the Rule of Five (Lipinski et al., 1997): MW <= 500, LogP <= 5, HBA <= 10, HBD <= 5.
d <- data.frame(
MW = c(300, 600, 450),
LogP = c(2, 7, 4),
`#H-bond acceptors` = c(4, 12, 6),
`#H-bond donors` = c(2, 5, 3),
`Lipinski #violations` = c(0, 3, 0),
check.names = FALSE)
lipinskiFilter(d)
lipinskiFilter(d, mw = 450, logp = 4) # Custom thresholdsghoseFilter()
Filters according to the Ghose qualifying range (1999): MW 160-480, MR 40-130, LogP -0.4 to 5.6, total atoms 20-70.
d <- data.frame(
MW = c(300, 600), MR = c(90, 150), LogP = c(2, 7),
`#Total atoms` = c(30, 80),
`Ghose #violations` = c(0, 4),
check.names = FALSE)
ghoseFilter(d)veberFilter()
Filters according to Veber (2002): RB <= 10 AND (TPSA <= 140 OR HBA+HBD <= 12).
d <- data.frame(
TPSA = c(80, 160), `#Rotatable bonds` = c(3, 14),
`#H-bond acceptors` = c(4, 12), `#H-bond donors` = c(2, 5),
`Veber #violations` = c(0, 1),
check.names = FALSE)
veberFilter(d)eganFilter()
Filters according to Egan (2000): TPSA <= 131.6, LogP <= 5.88.
d <- data.frame(
TPSA = c(80, 160), LogP = c(2, 7),
`Egan #violations` = c(0, 2),
check.names = FALSE)
eganFilter(d)mueggeFilter()
Filters according to Muegge (2001): MW 200-600, LogP -2 to 5, HBA <= 10, HBD <= 5, RB <= 15, TPSA <= 150, pharmacophore points >= 4.
d <- data.frame(
MW = c(300, 700), LogP = c(2, 7), TPSA = c(80, 160),
`#H-bond acceptors` = c(4, 12), `#H-bond donors` = c(2, 5),
`#Rotatable bonds` = c(3, 14),
`Muegge #violations` = c(0, 5),
check.names = FALSE)
mueggeFilter(d)applyFilters()
Apply multiple filters in sequence.
d <- data.frame(
MW = c(300, 600, 450), LogP = c(2, 7, 4), TPSA = c(80, 160, 100),
MR = c(90, 150, 100),
`#H-bond acceptors` = c(4, 12, 6),
`#H-bond donors` = c(2, 5, 3),
`#Rotatable bonds` = c(3, 14, 5),
`#Heavy atoms` = c(22, 80, 30),
`Lipinski #violations` = c(0, 3, 0),
`Ghose #violations` = c(0, 4, 0),
`Veber #violations` = c(0, 1, 0),
`Egan #violations` = c(0, 2, 0),
`Muegge #violations` = c(0, 5, 0),
check.names = FALSE)
applyFilters(d, filters = c("Lipinski", "Veber", "Egan"))computeViolationColumns()
Computes violation columns from physicochemical properties. Preserves pre-existing violation columns.
d <- data.frame(
MW = c(300, 600), LogP = c(2, 7), TPSA = c(80, 160),
MR = c(90, 150),
`#H-bond acceptors` = c(4, 12), `#H-bond donors` = c(2, 5),
`#Rotatable bonds` = c(3, 14), `#Heavy atoms` = c(22, 80),
check.names = FALSE)
d <- computeViolationColumns(d)
names(d)Data Normalization
mapADMETColumns()
Maps any user dataset to the standard schema.
d <- data.frame(
smiles = c("CCO", "CC(=O)O"),
mol_weight = c(46, 60),
logp = c(-0.3, -0.2))
mapping <- c(
"smiles" = "SMILES",
"mol_weight" = "MW",
"logp" = "LogP")
d_std <- mapADMETColumns(d, mapping)mapCDKDescriptors()
Maps CDK descriptor output to standard schema.
calcCDKDescriptors()
Calculates descriptors from SMILES using the Chemistry Development Kit.
smiles <- c("CCO", "CC(=O)Oc1ccccc1C(=O)O")
desc <- calcCDKDescriptors(smiles, which = c("mw", "logp", "tpsa"))getSmilesFromIdentifiers()
Retrieves SMILES from PubChem via compound names, CAS numbers, or InChIKeys.
result <- getSmilesFromIdentifiers(c("aspirin", "caffeine"))Plots
plotBoiledEgg()
BOILED-Egg model for GI absorption and BBB permeability prediction.
# Basic usage
d <- data.frame(LogP = c(2, 5), TPSA = c(50, 150))
plotBoiledEgg(d)
# With WLOGP (uses official polygons, axis = "WLOGP")
d2 <- data.frame(
LogP = c(1.5, 3.0, 4.5),
WLOGP = c(1.8, 2.8, 4.2),
TPSA = c(40, 80, 120))
plotBoiledEgg(d2)
# With P-gp substrate
d3 <- data.frame(
LogP = c(1.5, 3.0, 4.5),
TPSA = c(40, 80, 120),
`Pgp substrate` = c("Yes", "No", "Yes"),
check.names = FALSE)
plotBoiledEgg(d3)
# Suppress console statistics
plotBoiledEgg(d, console_stats = FALSE)plotMW(), plotTPSA(), plotLogP()
Simple distribution histograms.
d <- data.frame(
MW = c(300, 350, 400, 450, 500, 320, 380, 420),
TPSA = c(40, 60, 80, 100, 120, 50, 70, 90),
LogP = c(1, 2, 3, 4, 5, 1.5, 2.5, 3.5))
plotMW(d)
plotTPSA(d)
plotLogP(d)plotCorrHeatmap()
Correlation heatmap with Pearson or Spearman method and significance asterisks.
d <- data.frame(
MW = c(300, 400, 500, 350, 450),
LogP = c(2, 3, 4, 2.5, 3.5),
TPSA = c(60, 80, 100, 70, 90),
MR = c(70, 90, 110, 80, 100))
# Pearson (default)
plotCorrHeatmap(d)
# Spearman
plotCorrHeatmap(d, method = "spearman")
# Custom properties
plotCorrHeatmap(d, props = c("MW", "LogP", "TPSA"))
# Suppress console
plotCorrHeatmap(d, console_stats = FALSE)plotHistogramCustom()
Customizable histogram with automatic statistical test selection.
# Ungrouped: Shapiro-Wilk
d1 <- data.frame(MW = c(300, 350, 400, 320, 380, 360, 340, 370))
plotHistogramCustom(d1, variable = "MW")
# 2 groups: Wilcoxon
d2 <- data.frame(
MW = c(300, 320, 350, 380, 400, 500, 520, 550, 580, 600),
GI = c("High", "High", "High", "High", "High",
"Low", "Low", "Low", "Low", "Low"))
plotHistogramCustom(d2, variable = "MW", group_by = "GI")
# 4 groups: Kruskal-Wallis + post-hoc
d3 <- data.frame(
MW = c(300, 320, 350, 600, 620, 650, 400, 420, 450, 480, 500, 520),
Class = rep(c("A", "B", "C", "D"), each = 3))
plotHistogramCustom(d3, variable = "MW", group_by = "Class")
# Suppress console
plotHistogramCustom(d2, variable = "MW", group_by = "GI",
console_stats = FALSE)plotViolin()
Violin plot with automatic Wilcoxon / Kruskal-Wallis selection.
# 2 groups: Wilcoxon
d2 <- data.frame(
MW = c(300, 320, 350, 380, 400, 500, 520, 550, 580, 600),
GI = c("High", "High", "High", "High", "High",
"Low", "Low", "Low", "Low", "Low"))
plotViolin(d2, variable = "MW", group_by = "GI")
# 4 groups: Kruskal-Wallis + post-hoc
d4 <- data.frame(
MW = c(300, 320, 350, 600, 620, 650, 400, 420, 450, 480, 500, 520),
Class = rep(c("A", "B", "C", "D"), each = 3))
plotViolin(d4, variable = "MW", group_by = "Class",
show_box = TRUE, show_points = TRUE)plotPCA()
PCA chemical space plot with PERMANOVA and loading arrows.
d <- data.frame(
MW = c(300, 400, 500, 350, 450, 380, 320, 420, 480, 360),
LogP = c(2, 3, 4, 2.5, 3.5, 2.8, 2.2, 3.2, 3.8, 2.6),
TPSA = c(60, 80, 100, 70, 90, 65, 55, 75, 95, 68),
group = rep(c("A", "B"), each = 5))
plotPCA(d, variables = c("MW", "LogP", "TPSA"), color_by = "group")
plotPCA(d, variables = c("MW", "LogP", "TPSA"),
color_by = "group", scale_data = FALSE)
plotPCA(d, variables = c("MW", "LogP", "TPSA"),
color_by = "group", console_stats = FALSE)plotTSNE()
t-SNE chemical space with PERMANOVA.
set.seed(42)
d <- data.frame(
MW = c(rnorm(25, 350, 50), rnorm(25, 500, 50)),
LogP = c(rnorm(25, 2.5, 1), rnorm(25, 4.5, 1)),
TPSA = c(rnorm(25, 70, 20), rnorm(25, 100, 20)),
group = rep(c("A", "B"), each = 25))
plotTSNE(d, variables = c("MW", "LogP", "TPSA"),
color_by = "group", perplexity = 5)plotUMAP()
UMAP chemical space with PERMANOVA.
set.seed(42)
d <- data.frame(
MW = c(rnorm(25, 350, 50), rnorm(25, 500, 50)),
LogP = c(rnorm(25, 2.5, 1), rnorm(25, 4.5, 1)),
TPSA = c(rnorm(25, 70, 20), rnorm(25, 100, 20)),
group = rep(c("A", "B"), each = 25))
plotUMAP(d, variables = c("MW", "LogP", "TPSA"),
color_by = "group", n_neighbors = 10)plotParallel()
Parallel coordinates plot with PERMANOVA.
d <- data.frame(
MW = c(300, 400, 500, 350, 450, 380),
LogP = c(2, 3, 4, 2.5, 3.5, 2.8),
TPSA = c(60, 80, 100, 70, 90, 65),
group = c("A", "A", "A", "B", "B", "B"))
plotParallel(d, variables = c("MW", "LogP", "TPSA"), color_by = "group")
plotParallel(d, variables = c("MW", "LogP", "TPSA"),
color_by = "group", scale_data = FALSE)plotRadar()
Radar chart comparing up to 5 molecules.
d <- data.frame(
Name = c("Aspirin", "Ibuprofen", "Caffeine"),
MW = c(180, 206, 194),
LogP = c(1.2, 3.5, 0.1),
TPSA = c(63, 37, 62),
`#H-bond acceptors` = c(4, 1, 6),
`#H-bond donors` = c(1, 0, 0),
`#Rotatable bonds` = c(3, 4, 0),
check.names = FALSE)
plotRadar(d, id_col = "Name",
ids = c("Aspirin", "Ibuprofen", "Caffeine"))plotTanimoto()
Tanimoto similarity / AGNES clustering dendrogram.
d <- data.frame(
Name = c("ethanol", "aspirin", "benzene", "toluene", "phenol"),
SMILES = c("CCO", "CC(=O)Oc1ccccc1C(=O)O", "c1ccccc1",
"Cc1ccccc1", "Oc1ccccc1"),
stringsAsFactors = FALSE)
# Different linkage methods
plotTanimoto(d, smiles_col = "SMILES", label_col = "Name",
method = "average")
plotTanimoto(d, smiles_col = "SMILES", label_col = "Name",
method = "complete")
plotTanimoto(d, smiles_col = "SMILES", label_col = "Name",
method = "single")
plotTanimoto(d, smiles_col = "SMILES", label_col = "Name",
method = "ward")plotClusterHeatmap()
Cluster heatmap with dendrogram using pheatmap.
d <- data.frame(
Name = c("Drug A", "Drug B", "Drug C", "Drug D", "Drug E",
"Drug F", "Drug G", "Drug H"),
MW = c(300, 350, 600, 320, 450, 380, 500, 410),
LogP = c(2, 3, 5, 1, 4, 2.5, 4.5, 3.5),
TPSA = c(50, 60, 120, 40, 90, 70, 100, 80),
MR = c(70, 85, 130, 65, 100, 80, 110, 95),
check.names = FALSE)
# Basic
plotClusterHeatmap(d, id_col = "Name")
# With cell values and cutting
plotClusterHeatmap(d, id_col = "Name", display_numbers = TRUE,
cutree_rows = 2, palette = "viridis")
# With correlation distance
plotClusterHeatmap(d, id_col = "Name",
clustering_distance = "correlation",
method = "average")
# With annotation
d$Class <- c("A", "A", "B", "A", "B", "A", "B", "B")
plotClusterHeatmap(d, id_col = "Name",
annotation_row = "Class", cutree_rows = 2)Plot Customization
palette_selector_ui() and apply_palette()
Shared colour palette selector and ggplot2 palette applicator.
# In Shiny UI:
# palette_selector_ui("my_palette")
# In Shiny server:
# p <- apply_palette(p, input$my_palette, data, color_col)ADMET Properties
computeADMETProperties()
Computes BOILED-Egg ADMET classification (GI absorption, BBB permeant, Pgp substrate).
d <- data.frame(LogP = c(2, 5), TPSA = c(50, 150), MW = c(300, 500),
`#H-bond donors` = c(2, 5),
`#H-bond acceptors` = c(4, 10),
check.names = FALSE)
d <- computeADMETProperties(d)Report Generation
generateReport()
Generates a comprehensive report (HTML, PDF, or Word) from one or more datasets.
d <- data.frame(
Name = c("druglike", "violator"),
SMILES = c("CCO", "CCCCCCCCCCCCCCCCCCCCCCCCCC"),
MW = c(300, 650), LogP = c(2, 7), TPSA = c(40, 160),
MR = c(70, 150),
`#H-bond acceptors` = c(4, 12), `#H-bond donors` = c(2, 7),
`#Rotatable bonds` = c(3, 14), `#Heavy atoms` = c(20, 80),
`#Aromatic heavy atoms` = c(6, 9),
check.names = FALSE)
d <- computeViolationColumns(d)
# HTML report
generateReport(d, filters = c("Lipinski", "Veber"),
format = "html", source_name = "Example")Running the App
run_app()
Launches the interactive Shiny application.
library(admetshiny)
run_app()