-
Notifications
You must be signed in to change notification settings - Fork 0
/
plot_properties.R
228 lines (203 loc) · 8.26 KB
/
plot_properties.R
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
################################################################################
#
# plot_properties.R
#
library(tidyverse)
library(ggplot2)
###############
## Import data
properties <- c('SMILES', 'FractionCSP3', 'MolWt', 'RingCount', 'TotalRing', 'NumBridges', 'ringFusionDensity',
'ringComplexityIndex', 'NumRingSystems', 'NumChiralCenters')
aod8 <- read.csv("properties/AOD8.csv") %>% select(properties) %>% mutate(library = 'Oncology Drugs')
oshea <- read.csv("properties/OSheaMoser_128.csv") %>% select(properties) %>% mutate(library = 'Antibiotics')
drugbank <- read.csv("properties/drugbank.csv") %>% select(properties) %>% mutate(library = 'Drugbank')
mlsmr <- read.csv("properties/MLSMR-NP.csv") %>% select(properties) %>% mutate(library = 'MLSMR - NP')
cl <- read.csv("properties/chembridge_dvs_cl.csv") %>% select(properties) %>% mutate(library = 'Chembridge - CL')
exp <- read.csv("properties/chembridge_dvs_exp.csv") %>% select(properties) %>% mutate(library = 'Chembridge - EXP')
microformat <- read.csv("properties/chembridge_microFormat.csv") %>% select(properties) %>% mutate(library = 'Microformat')
pnas_cc <- read.csv("properties/PNAS_CC.csv") %>% select(properties) %>% mutate(library = 'PNAS CC')
pnas_np <- read.csv("properties/PNAS_NP.csv") %>% select(properties) %>% mutate(library = 'PNAS NP')
pnas_dc <- read.csv("properties/PNAS_DC.csv") %>% select(properties) %>% mutate(library = 'PNAS DC')
plm <- read.csv("properties/pleuromutilin.csv") %>% select(properties) %>% mutate(library = 'Pleuromutilin')
lic <- read.csv("properties/lycorine.csv") %>% select(properties) %>% mutate(library = 'Lycorine')
df <- rbind(aod8, oshea, drugbank, mlsmr, cl, exp, microformat, pnas_cc, pnas_np, pnas_dc, lic)
##############
## Histograms
# Fraction SP3
pdf(file = "figures/hist_fraction_sp3.pdf",
width=7, height=5)
ggplot(df, aes(x = FractionCSP3, fill = library)) +
geom_histogram(color = "black",
binwidth = 0.1) +
geom_vline(data = plyr::ddply(df, "library", summarize, avg = mean(FractionCSP3)),
aes(xintercept=avg),
color="blue", linetype="dashed", size=1) +
facet_wrap(~library, scales = "free_y") +
labs(title = "Distribution of Fraction sp3",
x = "Fraction sp3",
y = "Count") +
theme(legend.position = "none")
dev.off()
# Num Chiral Centers
pdf(file = "figures/hist_chiral_centers.pdf",
width=7, height=5)
ggplot(df, aes(x = NumChiralCenters, fill = library)) +
geom_histogram(binwidth = 1,
color = "black") +
geom_vline(data = plyr::ddply(df, "library", summarize, avg = mean(NumChiralCenters)),
aes(xintercept=avg),
color="blue", linetype="dashed", size=1) +
xlim(-1,12) +
facet_wrap(~library, scales = "free_y") +
labs(title = "Distribution of Number of Chiral Centers",
x = "# Chiral Centers",
y = "Count") +
theme(legend.position = "none")
dev.off()
# Ring Complexity Index
pdf(file = "figures/hist_ring_complexity_index.pdf",
width=7, height=5)
ggplot(filter(df, !is.na(ringComplexityIndex)), aes(x = ringComplexityIndex, fill = library)) +
geom_histogram(binwidth = 0.1, color = "black") +
geom_vline(data = plyr::ddply(filter(df, !is.na(ringComplexityIndex)), "library", summarize, avg = mean(ringComplexityIndex)),
aes(xintercept=avg),
color="blue", linetype="dashed", size=1) +
xlim(0.9,2.1) +
facet_wrap(~library, scales = "free_y") +
labs(title = "Distribution of Ring Complexity",
x = "Ring Complexity Index",
y = "Count") +
theme(legend.position = "none")
dev.off()
####################
## Box-wisker plots
selection <- c('Drugbank', 'Oncology Drugs', 'Antibiotics', 'Chembridge - EXP', 'Chembridge - CL', 'Microformat', 'MLSMR - NP', 'PNAS CC', 'PNAS DC', 'PNAS NP', 'Lycorine')
selection <- rev(selection)
to_plot <- filter(df, library %in% selection)
to_plot$library <- factor(to_plot$library, levels = selection)
# Fraction SP3
pdf(file = "figures/bw_fraction_sp3.pdf",
width=7, height=5)
ggplot(to_plot, aes(x = library, y = FractionCSP3)) +
geom_boxplot(outlier.color = "NA") +
labs(title = "Distribution of Fraction sp3",
x = "Compound Library",
y = "Fraction sp3") +
coord_flip()
dev.off()
# Num Chiral Centers
pdf(file = "figures/bw_chiral_centers.pdf",
width=7, height=5)
ggplot(to_plot, aes(x = library, y = NumChiralCenters)) +
geom_boxplot(outlier.color = "NA") +
ylim(0,12) +
labs(title = "Distribution of Number of Chiral Centers",
x = "Compound Library",
y = "# Chiral Centers") +
coord_flip()
dev.off()
# Ring Complexity Index
pdf(file = "figures/bw_ring_complexity_index.pdf",
width=7, height=5)
ggplot(to_plot, aes(x = library, y = ringComplexityIndex)) +
geom_boxplot(outlier.color = "NA") +
ylim(1,2) +
labs(title = "Distribution of Ring Complexity",
x = "Compound Library",
y = "Ring Complexity Index") +
coord_flip()
dev.off()
################
## Violin plots
selection <- c('Oncology Drugs', 'Antibiotics', 'Drugbank', 'Chembridge - CL', 'Chembridge - EXP', 'Microformat', 'MLSMR - NP', 'PNAS CC', 'Pleuromutilin')
to_plot <- filter(df, library %in% selection)
to_plot$library <- factor(to_plot$library, levels = selection)
data_summary <- function(x) {
m <- mean(x)
ymin <- m-sd(x)
ymax <- m+sd(x)
return(c(y=m,ymin=ymin,ymax=ymax))
}
# Fraction SP3
pdf(file = "figures/violin_fraction_sp3.pdf",
width=7, height=5)
ggplot(to_plot, aes(x = library, y = FractionCSP3)) +
geom_violin(scale = "width", adjust = 1.5) +
stat_summary(fun.data=data_summary, color = "blue") +
labs(title = "Distribution of Fraction sp3",
x = "Compound Library",
y = "Fraction sp3") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
dev.off()
# Num Chiral Centers
pdf(file = "figures/violin_chiral_centers.pdf",
width=7, height=5)
ggplot(to_plot, aes(x = library, y = NumChiralCenters)) +
geom_violin(scale = "width", adjust = 1.5) +
stat_summary(fun.data=data_summary, color = "blue") +
ylim(-2,20) +
labs(title = "Distribution of Number of Chiral Centers",
x = "Compound Library",
y = "# Chiral Centers") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
dev.off()
# Ring Complexity Index
pdf(file = "figures/violin_ring_complexity_index.pdf",
width=7, height=5)
ggplot(to_plot, aes(x = library, y = ringComplexityIndex)) +
geom_violin(scale = "width", adjust = 1.5) +
stat_summary(fun.data=data_summary, color = "blue") +
ylim(0.9,3) +
labs(title = "Distribution of Ring Complexity",
x = "Compound Library",
y = "Ring Complexity Index") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
dev.off()
###############
## 2D Hexbins
my_breaks = c(2,10,50,250,1250,6000,30000)
# Fraction sp3 vs Chiral Centers
pdf(file = "figures/bin2d_chiral_fsp3.pdf",
width=7, height=5)
ggplot(df, aes(x = NumChiralCenters, y = FractionCSP3)) +
geom_bin2d(binwidth = c(1,0.1)) +
scale_fill_distiller(palette= "Spectral", direction=-1,
trans = "log",
breaks = my_breaks, labels = my_breaks) +
xlim(NA,20) +
facet_wrap(~library) +
labs(title = "Fsp3 vs. # Chiral Centers",
x = "# Chiral Centers",
y = "Fsp3") +
theme_bw()
dev.off()
# Fraction sp3 vs Ring Complexity
pdf(file = "figures/bin2d_ring_fsp3.pdf",
width=7, height=5)
ggplot(df, aes(x = ringComplexityIndex, y = FractionCSP3)) +
geom_bin2d(binwidth = c(0.2,0.1)) +
scale_fill_distiller(palette= "Spectral", direction=-1,
trans = "log",
breaks = my_breaks, labels = my_breaks) +
xlim(NA, 3) +
facet_wrap(~library) +
labs(title = "Fsp3 vs. Ring Complexity",
x = "Ring Complexity Index",
y = "Fsp3") +
theme_bw()
dev.off()
# Num chiral centers vs Ring Complexity
pdf(file = "figures/bin2d_chiral_ring.pdf",
width=7, height=5)
ggplot(df, aes(x = ringComplexityIndex, y = NumChiralCenters)) +
geom_bin2d(binwidth = c(0.2,1)) +
scale_fill_distiller(palette= "Spectral", direction=-1,
trans = "log",
breaks = my_breaks, labels = my_breaks) +
lims(x = c(NA, 3), y = c(NA, 20)) +
facet_wrap(~library) +
labs(title = "Fsp3 vs. # Chiral Centers",
x = "Ring Complexity Index",
y = "# Chiral Centers") +
theme_bw()
dev.off()