scatter_plots
Katharina E Hayer
10/21/2016
Scatter plots
Read in data.
cols <- c('character','character','character','character','character','character',
'numeric','character')
d = read.csv("~/Google Drive/AlignerBenchmarkLocal/default_summary.txt", head =T,sep = "\t", colClasses = cols)
d$algorithm = factor(d$algorithm)
nlevels(d$algorithm)## [1] 14Calculate the mean an standard deviation.
d$mean = rep(0,dim(d)[1])
d$sd = rep(0,dim(d)[1])
for (i in 1:dim(d)[1]) {
#print(i)
d$mean[i] = mean(d[d$species == d$species[i] & d$dataset == d$dataset[i] & d$algorithm == d$algorithm[i] & d$measurement == d$measurement[i] & d$level == d$level[i],]$value)
d$sd[i] = sd(d[d$species == d$species[i] & d$dataset == d$dataset[i] & d$algorithm == d$algorithm[i] & d$measurement == d$measurement[i] & d$level == d$level[i],]$value)
}Functions
Scatter plot version 1.
plot_my_data_scatter <- function(data, measurement1, measurement2, title, filename, write_file = TRUE) {
# data = k
# measurement one of #{recall, precision}
print(measurement1)
data$tmp1= data[,colnames(data) == measurement1]
print(measurement2)
data$color[data$color == "#F0E442"] = "cornflowerblue"
data$tmp2 = data[,colnames(data) == measurement2]
print(head(data))
print(data$tmp2)
data$algorithm = factor(data$algorithm)
print(levels(data$algorithm))
p = ggplot(data,aes(x=tmp1, y=tmp2, col = algorithm, shape= algorithm, label = algorithm)) +
geom_point(size=5) +
#geom_text(aes(label = tmp), size = 3) +
ggtitle(title) + theme_gray(base_size=20) +
scale_shape_manual(values=1:nlevels(data$algorithm) ) +
xlab("Algorithm") + xlab(measurement1)+ ylab(measurement2)+ #ylim(c(-0.0001,1.0001)) +
#scale_x_discrete(limits=data[order(data$tmp,decreasing = TRUE),]$algorithm) + theme_gray(base_size=17) +#theme_light()+
#theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = .5)) + #scale_fill_brewer(palette="Accent") +
#scale_fill_manual(values = data$color) +
scale_color_manual(values = data$color) +
#scale_colour_brewer(palette = "Dark2") +
#geom_text(hjust = 0, nudge_x = 0.005, check_overlap = TRUE) +
#xlim(c(.875,1.03)) +
theme(panel.background = element_rect(colour = "gray97", fill="gray97")) +
guides(fill=FALSE)
print(p)
if (write_file) {
ggsave(
filename,
width = 8.25,
height = 5.75,
dpi = 300
)
}
#data$tmp <- NULL
}Scatter plot version with labels.
plot_my_data_scatter_labels <- function(data, measurement1, measurement2, title, filename, write_file = TRUE) {
# data = k
# measurement one of #{recall, precision}
print(measurement1)
data$tmp1= data[,colnames(data) == measurement1]
print(measurement2)
data$color[data$color == "#F0E442"] = "cornflowerblue"
data$tmp2 = data[,colnames(data) == measurement2]
print(head(data))
print(data$tmp2)
data$algorithm = factor(data$algorithm)
print(levels(data$algorithm))
p = ggplot(data,aes(x=tmp1, y=tmp2, col = algorithm, shape= algorithm, label = algorithm)) +
geom_point(size=5) +
#geom_text(aes(label = tmp), size = 3) +
ggtitle(title) + theme_gray(base_size=20) +
scale_shape_manual(values=1:nlevels(data$algorithm) ) +
xlab("Algorithm") + xlab(measurement1)+ ylab(measurement2)+ #ylim(c(-0.0001,1.0001)) +
#scale_x_discrete(limits=data[order(data$tmp,decreasing = TRUE),]$algorithm) + theme_gray(base_size=17) +#theme_light()+
#theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = .5)) + #scale_fill_brewer(palette="Accent") +
#scale_fill_manual(values = data$color) +
scale_color_manual(values = data$color) +
#scale_colour_brewer(palette = "Dark2") +
#geom_text(hjust = 0, nudge_x = 0.005, check_overlap = TRUE) +
#xlim(c(.875,1.03)) +
theme(panel.background = element_rect(colour = "gray97", fill="gray97")) +
#geom_text_repel(point.padding = unit(0.25, "lines")) +
geom_text_repel(point.padding = unit(0.25, "lines")) +
guides(fill=FALSE)
print(p)
if (write_file) {
ggsave(
filename,
width = 8.25,
height = 5.75,
dpi = 300
)
}
#data$tmp <- NULL
}Scatter plot version with labels, but no shapes.
plot_my_data_scatter_labels_shapes <- function(data, measurement1, measurement2, title, filename, write_file = TRUE) {
# data = k
# measurement one of #{recall, precision}
print(measurement1)
data$tmp1= data[,colnames(data) == measurement1]
print(measurement2)
data$color[data$color == "#F0E442"] = "cornflowerblue"
data$tmp2 = data[,colnames(data) == measurement2]
print(head(data))
print(data$tmp2)
data$algorithm = factor(data$algorithm)
print(levels(data$algorithm))
xlim <- range( data$tmp1 )
ylim <- range( data$tmp2 )
xlim[2] = 1.01
ylim[2] = 1.01
p = ggplot(data,aes(x=tmp1, y=tmp2, col = algorithm, label = algorithm)) +
geom_point(size=3,alpha = 0.85) +
#geom_text(aes(label = tmp), size = 3) +
ggtitle(title) + theme_gray(base_size=20) +
scale_shape_manual(values=1:nlevels(data$algorithm) ) +
xlab("Algorithm") + xlab(measurement1)+ ylab(measurement2)+ #ylim(c(-0.0001,1.0001)) +
#scale_x_discrete(limits=data[order(data$tmp,decreasing = TRUE),]$algorithm) + theme_gray(base_size=17) +#theme_light()+
#theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = .5)) + #scale_fill_brewer(palette="Accent") +
#scale_fill_manual(values = data$color) +
scale_color_manual(values = data$color) +
#scale_colour_brewer(palette = "Dark2") +
#geom_text(hjust = 0, nudge_x = 0.005, check_overlap = TRUE) +
#xlim(c(.875,1.03)) +
theme(panel.background = element_rect(colour = "gray97", fill="gray97")) +
#geom_text_repel(point.padding = unit(0.25, "lines")) +
geom_text_repel(force = 5, point.padding = unit(0.65, "lines"),arrow = arrow(length = unit(0.01, 'npc'))) +
ylim(ylim) + xlim(xlim) +
guides(fill=FALSE)
print(p)
if (write_file) {
ggsave(
filename,
width = 8.25,
height = 5.75,
dpi = 300
)
}
#data$tmp <- NULL
}Scatter plot version with labels, but no shapes, different theme.
plot_my_data_scatter_bw_theme <- function(data, measurement1, measurement2, title, filename, write_file = TRUE) {
# data = k
# measurement one of #{recall, precision}
print(measurement1)
data$tmp1= data[,colnames(data) == measurement1]
print(measurement2)
data$color[data$color == "#F0E442"] = "cornflowerblue"
data$tmp2 = data[,colnames(data) == measurement2]
print(head(data))
print(data$tmp2)
data$algorithm = factor(data$algorithm)
print(levels(data$algorithm))
xlim <- range( data$tmp1 )
ylim <- range( data$tmp2 )
xlim[2] = 1.01
ylim[2] = 1.01
p = ggplot(data,aes(x=tmp1, y=tmp2, col = algorithm, label = algorithm)) +
geom_point(size=3,alpha = 0.85) +
#geom_text(aes(label = tmp), size = 3) +
ggtitle(title) + theme_bw(base_size=20) +
scale_shape_manual(values=1:nlevels(data$algorithm) ) +
xlab("Algorithm") + xlab(measurement1)+ ylab(measurement2)+ #ylim(c(-0.0001,1.0001)) +
#scale_x_discrete(limits=data[order(data$tmp,decreasing = TRUE),]$algorithm) + theme_gray(base_size=17) +#theme_light()+
#theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = .5)) + #scale_fill_brewer(palette="Accent") +
#scale_fill_manual(values = data$color) +
scale_color_manual(values = data$color) +
#scale_colour_brewer(palette = "Dark2") +
#geom_text(hjust = 0, nudge_x = 0.005, check_overlap = TRUE) +
#xlim(c(.875,1.03)) +
theme(panel.background = element_rect(colour = "gray97", fill="gray97")) +
#geom_text_repel(point.padding = unit(0.25, "lines")) +
geom_text_repel(force = 5, point.padding = unit(0.65, "lines"),arrow = arrow(length = unit(0.01, 'npc'))) +
ylim(ylim) + xlim(xlim) +
guides(fill=FALSE)
print(p)
if (write_file) {
ggsave(
filename,
width = 8.25,
height = 5.75,
dpi = 300
)
}
#data$tmp <- NULL
}Plot the versions
l = spread(d[,c("species","dataset","replicate","level","algorithm",
"color","measurement","mean")], measurement, mean)
k = l[l$species == "human" & l$level == "READLEVEL",]
k = k[k$dataset == "t3",]
plot_my_data_scatter(k,"precision","recall","human read level","read_level/human_t3_READ_scatter.pdf",TRUE)## [1] "precision"
## [1] "recall"
## species dataset replicate level algorithm color
## 183 human t3 r1 READLEVEL clc #CC79A7
## 184 human t3 r1 READLEVEL contextmap2 cornflowerblue
## 185 human t3 r1 READLEVEL crac #D55E00
## 186 human t3 r1 READLEVEL gsnap #999999
## 187 human t3 r1 READLEVEL hisat maroon
## 188 human t3 r1 READLEVEL hisat2 maroon3
## aligned_ambiguously aligned_incorrectly deletions_precision
## 183 0.0280 0.0242 NA
## 184 0.0000 0.0191 NA
## 185 0.0000 0.1041 NA
## 186 0.0200 0.0131 NA
## 187 0.0073 0.0013 NA
## 188 0.0081 0.0037 NA
## deletions_recall insertions_precision insertions_recall precision
## 183 NA NA NA 0.9721
## 184 NA NA NA 0.9698
## 185 NA NA NA 0.8856
## 186 NA NA NA 0.9858
## 187 NA NA NA 0.9934
## 188 NA NA NA 0.9878
## recall skipping_precision skipping_recall unaligned tmp1 tmp2
## 183 0.8463 NA NA 0.1015 0.9721 0.8463
## 184 0.6178 NA NA 0.3631 0.9698 0.6178
## 185 0.8066 NA NA 0.0893 0.8856 0.8066
## 186 0.9198 NA NA 0.0471 0.9858 0.9198
## 187 0.1975 NA NA 0.7939 0.9934 0.1975
## 188 0.3045 NA NA 0.6837 0.9878 0.3045
## [1] 0.8463 0.6178 0.8066 0.9198 0.1975 0.3045 0.8575 0.9726 0.2329 0.7273
## [11] 0.5682 0.8108 0.4849 0.1253
## [1] "clc" "contextmap2" "crac" "gsnap" "hisat"
## [6] "hisat2" "mapsplice2" "novoalign" "olego" "rum"
## [11] "soapsplice" "star" "subread" "tophat2"
plot_my_data_scatter_labels(k,"precision","recall","human read level","read_level/human_t3_READ_scatter_labels.pdf", TRUE)## [1] "precision"
## [1] "recall"
## species dataset replicate level algorithm color
## 183 human t3 r1 READLEVEL clc #CC79A7
## 184 human t3 r1 READLEVEL contextmap2 cornflowerblue
## 185 human t3 r1 READLEVEL crac #D55E00
## 186 human t3 r1 READLEVEL gsnap #999999
## 187 human t3 r1 READLEVEL hisat maroon
## 188 human t3 r1 READLEVEL hisat2 maroon3
## aligned_ambiguously aligned_incorrectly deletions_precision
## 183 0.0280 0.0242 NA
## 184 0.0000 0.0191 NA
## 185 0.0000 0.1041 NA
## 186 0.0200 0.0131 NA
## 187 0.0073 0.0013 NA
## 188 0.0081 0.0037 NA
## deletions_recall insertions_precision insertions_recall precision
## 183 NA NA NA 0.9721
## 184 NA NA NA 0.9698
## 185 NA NA NA 0.8856
## 186 NA NA NA 0.9858
## 187 NA NA NA 0.9934
## 188 NA NA NA 0.9878
## recall skipping_precision skipping_recall unaligned tmp1 tmp2
## 183 0.8463 NA NA 0.1015 0.9721 0.8463
## 184 0.6178 NA NA 0.3631 0.9698 0.6178
## 185 0.8066 NA NA 0.0893 0.8856 0.8066
## 186 0.9198 NA NA 0.0471 0.9858 0.9198
## 187 0.1975 NA NA 0.7939 0.9934 0.1975
## 188 0.3045 NA NA 0.6837 0.9878 0.3045
## [1] 0.8463 0.6178 0.8066 0.9198 0.1975 0.3045 0.8575 0.9726 0.2329 0.7273
## [11] 0.5682 0.8108 0.4849 0.1253
## [1] "clc" "contextmap2" "crac" "gsnap" "hisat"
## [6] "hisat2" "mapsplice2" "novoalign" "olego" "rum"
## [11] "soapsplice" "star" "subread" "tophat2"
plot_my_data_scatter_labels_shapes(k,"precision","recall","human read level","read_level/human_t3_READ_scatter_labels_shapes.pdf", TRUE)## [1] "precision"
## [1] "recall"
## species dataset replicate level algorithm color
## 183 human t3 r1 READLEVEL clc #CC79A7
## 184 human t3 r1 READLEVEL contextmap2 cornflowerblue
## 185 human t3 r1 READLEVEL crac #D55E00
## 186 human t3 r1 READLEVEL gsnap #999999
## 187 human t3 r1 READLEVEL hisat maroon
## 188 human t3 r1 READLEVEL hisat2 maroon3
## aligned_ambiguously aligned_incorrectly deletions_precision
## 183 0.0280 0.0242 NA
## 184 0.0000 0.0191 NA
## 185 0.0000 0.1041 NA
## 186 0.0200 0.0131 NA
## 187 0.0073 0.0013 NA
## 188 0.0081 0.0037 NA
## deletions_recall insertions_precision insertions_recall precision
## 183 NA NA NA 0.9721
## 184 NA NA NA 0.9698
## 185 NA NA NA 0.8856
## 186 NA NA NA 0.9858
## 187 NA NA NA 0.9934
## 188 NA NA NA 0.9878
## recall skipping_precision skipping_recall unaligned tmp1 tmp2
## 183 0.8463 NA NA 0.1015 0.9721 0.8463
## 184 0.6178 NA NA 0.3631 0.9698 0.6178
## 185 0.8066 NA NA 0.0893 0.8856 0.8066
## 186 0.9198 NA NA 0.0471 0.9858 0.9198
## 187 0.1975 NA NA 0.7939 0.9934 0.1975
## 188 0.3045 NA NA 0.6837 0.9878 0.3045
## [1] 0.8463 0.6178 0.8066 0.9198 0.1975 0.3045 0.8575 0.9726 0.2329 0.7273
## [11] 0.5682 0.8108 0.4849 0.1253
## [1] "clc" "contextmap2" "crac" "gsnap" "hisat"
## [6] "hisat2" "mapsplice2" "novoalign" "olego" "rum"
## [11] "soapsplice" "star" "subread" "tophat2"
plot_my_data_scatter_bw_theme(k,"precision","recall","human read level","read_level/human_t3_READ_scatter_bw_theme.pdf", TRUE)## [1] "precision"
## [1] "recall"
## species dataset replicate level algorithm color
## 183 human t3 r1 READLEVEL clc #CC79A7
## 184 human t3 r1 READLEVEL contextmap2 cornflowerblue
## 185 human t3 r1 READLEVEL crac #D55E00
## 186 human t3 r1 READLEVEL gsnap #999999
## 187 human t3 r1 READLEVEL hisat maroon
## 188 human t3 r1 READLEVEL hisat2 maroon3
## aligned_ambiguously aligned_incorrectly deletions_precision
## 183 0.0280 0.0242 NA
## 184 0.0000 0.0191 NA
## 185 0.0000 0.1041 NA
## 186 0.0200 0.0131 NA
## 187 0.0073 0.0013 NA
## 188 0.0081 0.0037 NA
## deletions_recall insertions_precision insertions_recall precision
## 183 NA NA NA 0.9721
## 184 NA NA NA 0.9698
## 185 NA NA NA 0.8856
## 186 NA NA NA 0.9858
## 187 NA NA NA 0.9934
## 188 NA NA NA 0.9878
## recall skipping_precision skipping_recall unaligned tmp1 tmp2
## 183 0.8463 NA NA 0.1015 0.9721 0.8463
## 184 0.6178 NA NA 0.3631 0.9698 0.6178
## 185 0.8066 NA NA 0.0893 0.8856 0.8066
## 186 0.9198 NA NA 0.0471 0.9858 0.9198
## 187 0.1975 NA NA 0.7939 0.9934 0.1975
## 188 0.3045 NA NA 0.6837 0.9878 0.3045
## [1] 0.8463 0.6178 0.8066 0.9198 0.1975 0.3045 0.8575 0.9726 0.2329 0.7273
## [11] 0.5682 0.8108 0.4849 0.1253
## [1] "clc" "contextmap2" "crac" "gsnap" "hisat"
## [6] "hisat2" "mapsplice2" "novoalign" "olego" "rum"
## [11] "soapsplice" "star" "subread" "tophat2"
k = l[l$species == "human" & l$level == "READLEVEL",]
k = k[k$dataset == "t2",]
plot_my_data_scatter(k,"precision","recall","human read level","read_level/human_t2_READ_scatter.pdf",TRUE)## [1] "precision"
## [1] "recall"
## species dataset replicate level algorithm color
## 113 human t2 r1 READLEVEL clc #CC79A7
## 114 human t2 r1 READLEVEL contextmap2 cornflowerblue
## 115 human t2 r1 READLEVEL crac #D55E00
## 116 human t2 r1 READLEVEL gsnap #999999
## 117 human t2 r1 READLEVEL hisat maroon
## 118 human t2 r1 READLEVEL hisat2 maroon3
## aligned_ambiguously aligned_incorrectly deletions_precision
## 113 0.0141 0.0205 NA
## 114 0.0000 0.0109 NA
## 115 0.0000 0.0839 NA
## 116 0.0188 0.0029 NA
## 117 0.0189 0.0031 NA
## 118 0.0192 0.0040 NA
## deletions_recall insertions_precision insertions_recall precision
## 113 NA NA NA 0.9770
## 114 NA NA NA 0.9888
## 115 NA NA NA 0.9159
## 116 NA NA NA 0.9969
## 117 NA NA NA 0.9964
## 118 NA NA NA 0.9955
## recall skipping_precision skipping_recall unaligned tmp1 tmp2
## 113 0.8741 NA NA 0.0913 0.9770 0.8741
## 114 0.9655 NA NA 0.0236 0.9888 0.9655
## 115 0.9147 NA NA 0.0014 0.9159 0.9147
## 116 0.9783 NA NA 0.0000 0.9969 0.9783
## 117 0.8937 NA NA 0.0843 0.9964 0.8937
## 118 0.9073 NA NA 0.0695 0.9955 0.9073
## [1] 0.8741 0.9655 0.9147 0.9783 0.8937 0.9073 0.9776 0.9745 0.8849 0.9456
## [11] 0.9083 0.9723 0.9155 0.8120
## [1] "clc" "contextmap2" "crac" "gsnap" "hisat"
## [6] "hisat2" "mapsplice2" "novoalign" "olego" "rum"
## [11] "soapsplice" "star" "subread" "tophat2"
plot_my_data_scatter_labels(k,"precision","recall","human read level","read_level/human_t2_READ_scatter_labels.pdf", TRUE)## [1] "precision"
## [1] "recall"
## species dataset replicate level algorithm color
## 113 human t2 r1 READLEVEL clc #CC79A7
## 114 human t2 r1 READLEVEL contextmap2 cornflowerblue
## 115 human t2 r1 READLEVEL crac #D55E00
## 116 human t2 r1 READLEVEL gsnap #999999
## 117 human t2 r1 READLEVEL hisat maroon
## 118 human t2 r1 READLEVEL hisat2 maroon3
## aligned_ambiguously aligned_incorrectly deletions_precision
## 113 0.0141 0.0205 NA
## 114 0.0000 0.0109 NA
## 115 0.0000 0.0839 NA
## 116 0.0188 0.0029 NA
## 117 0.0189 0.0031 NA
## 118 0.0192 0.0040 NA
## deletions_recall insertions_precision insertions_recall precision
## 113 NA NA NA 0.9770
## 114 NA NA NA 0.9888
## 115 NA NA NA 0.9159
## 116 NA NA NA 0.9969
## 117 NA NA NA 0.9964
## 118 NA NA NA 0.9955
## recall skipping_precision skipping_recall unaligned tmp1 tmp2
## 113 0.8741 NA NA 0.0913 0.9770 0.8741
## 114 0.9655 NA NA 0.0236 0.9888 0.9655
## 115 0.9147 NA NA 0.0014 0.9159 0.9147
## 116 0.9783 NA NA 0.0000 0.9969 0.9783
## 117 0.8937 NA NA 0.0843 0.9964 0.8937
## 118 0.9073 NA NA 0.0695 0.9955 0.9073
## [1] 0.8741 0.9655 0.9147 0.9783 0.8937 0.9073 0.9776 0.9745 0.8849 0.9456
## [11] 0.9083 0.9723 0.9155 0.8120
## [1] "clc" "contextmap2" "crac" "gsnap" "hisat"
## [6] "hisat2" "mapsplice2" "novoalign" "olego" "rum"
## [11] "soapsplice" "star" "subread" "tophat2"
plot_my_data_scatter_labels_shapes(k,"precision","recall","human read level","read_level/human_t2_READ_scatter_labels_shapes.pdf", TRUE)## [1] "precision"
## [1] "recall"
## species dataset replicate level algorithm color
## 113 human t2 r1 READLEVEL clc #CC79A7
## 114 human t2 r1 READLEVEL contextmap2 cornflowerblue
## 115 human t2 r1 READLEVEL crac #D55E00
## 116 human t2 r1 READLEVEL gsnap #999999
## 117 human t2 r1 READLEVEL hisat maroon
## 118 human t2 r1 READLEVEL hisat2 maroon3
## aligned_ambiguously aligned_incorrectly deletions_precision
## 113 0.0141 0.0205 NA
## 114 0.0000 0.0109 NA
## 115 0.0000 0.0839 NA
## 116 0.0188 0.0029 NA
## 117 0.0189 0.0031 NA
## 118 0.0192 0.0040 NA
## deletions_recall insertions_precision insertions_recall precision
## 113 NA NA NA 0.9770
## 114 NA NA NA 0.9888
## 115 NA NA NA 0.9159
## 116 NA NA NA 0.9969
## 117 NA NA NA 0.9964
## 118 NA NA NA 0.9955
## recall skipping_precision skipping_recall unaligned tmp1 tmp2
## 113 0.8741 NA NA 0.0913 0.9770 0.8741
## 114 0.9655 NA NA 0.0236 0.9888 0.9655
## 115 0.9147 NA NA 0.0014 0.9159 0.9147
## 116 0.9783 NA NA 0.0000 0.9969 0.9783
## 117 0.8937 NA NA 0.0843 0.9964 0.8937
## 118 0.9073 NA NA 0.0695 0.9955 0.9073
## [1] 0.8741 0.9655 0.9147 0.9783 0.8937 0.9073 0.9776 0.9745 0.8849 0.9456
## [11] 0.9083 0.9723 0.9155 0.8120
## [1] "clc" "contextmap2" "crac" "gsnap" "hisat"
## [6] "hisat2" "mapsplice2" "novoalign" "olego" "rum"
## [11] "soapsplice" "star" "subread" "tophat2"
plot_my_data_scatter_bw_theme(k,"precision","recall","human read level","read_level/human_t2_READ_scatter_bw_theme.pdf", TRUE)## [1] "precision"
## [1] "recall"
## species dataset replicate level algorithm color
## 113 human t2 r1 READLEVEL clc #CC79A7
## 114 human t2 r1 READLEVEL contextmap2 cornflowerblue
## 115 human t2 r1 READLEVEL crac #D55E00
## 116 human t2 r1 READLEVEL gsnap #999999
## 117 human t2 r1 READLEVEL hisat maroon
## 118 human t2 r1 READLEVEL hisat2 maroon3
## aligned_ambiguously aligned_incorrectly deletions_precision
## 113 0.0141 0.0205 NA
## 114 0.0000 0.0109 NA
## 115 0.0000 0.0839 NA
## 116 0.0188 0.0029 NA
## 117 0.0189 0.0031 NA
## 118 0.0192 0.0040 NA
## deletions_recall insertions_precision insertions_recall precision
## 113 NA NA NA 0.9770
## 114 NA NA NA 0.9888
## 115 NA NA NA 0.9159
## 116 NA NA NA 0.9969
## 117 NA NA NA 0.9964
## 118 NA NA NA 0.9955
## recall skipping_precision skipping_recall unaligned tmp1 tmp2
## 113 0.8741 NA NA 0.0913 0.9770 0.8741
## 114 0.9655 NA NA 0.0236 0.9888 0.9655
## 115 0.9147 NA NA 0.0014 0.9159 0.9147
## 116 0.9783 NA NA 0.0000 0.9969 0.9783
## 117 0.8937 NA NA 0.0843 0.9964 0.8937
## 118 0.9073 NA NA 0.0695 0.9955 0.9073
## [1] 0.8741 0.9655 0.9147 0.9783 0.8937 0.9073 0.9776 0.9745 0.8849 0.9456
## [11] 0.9083 0.9723 0.9155 0.8120
## [1] "clc" "contextmap2" "crac" "gsnap" "hisat"
## [6] "hisat2" "mapsplice2" "novoalign" "olego" "rum"
## [11] "soapsplice" "star" "subread" "tophat2"
k = l[l$species == "human" & l$level == "READLEVEL",]
k = k[k$dataset == "t1",]
plot_my_data_scatter(k,"precision","recall","human read level","read_level/human_t1_READ_scatter.pdf",TRUE)## [1] "precision"
## [1] "recall"
## species dataset replicate level algorithm color
## 43 human t1 r1 READLEVEL clc #CC79A7
## 44 human t1 r1 READLEVEL contextmap2 cornflowerblue
## 45 human t1 r1 READLEVEL crac #D55E00
## 46 human t1 r1 READLEVEL gsnap #999999
## 47 human t1 r1 READLEVEL hisat maroon
## 48 human t1 r1 READLEVEL hisat2 maroon3
## aligned_ambiguously aligned_incorrectly deletions_precision
## 43 0.0119 0.0202 NA
## 44 0.0000 0.0098 NA
## 45 0.0000 0.0806 NA
## 46 0.0191 0.0022 NA
## 47 0.0184 0.0026 NA
## 48 0.0196 0.0029 NA
## deletions_recall insertions_precision insertions_recall precision
## 43 NA NA NA 0.9773
## 44 NA NA NA 0.9899
## 45 NA NA NA 0.9193
## 46 NA NA NA 0.9977
## 47 NA NA NA 0.9972
## 48 NA NA NA 0.9969
## recall skipping_precision skipping_recall unaligned tmp1 tmp2
## 43 0.8771 NA NA 0.0908 0.9773 0.8771
## 44 0.9765 NA NA 0.0137 0.9899 0.9765
## 45 0.9192 NA NA 0.0002 0.9193 0.9192
## 46 0.9787 NA NA 0.0000 0.9977 0.9787
## 47 0.9676 NA NA 0.0114 0.9972 0.9676
## 48 0.9697 NA NA 0.0078 0.9969 0.9697
## [1] 0.8771 0.9765 0.9192 0.9787 0.9676 0.9697 0.9804 0.9744 0.9507 0.9679
## [11] 0.9481 0.9768 0.9467 0.9464
## [1] "clc" "contextmap2" "crac" "gsnap" "hisat"
## [6] "hisat2" "mapsplice2" "novoalign" "olego" "rum"
## [11] "soapsplice" "star" "subread" "tophat2"
plot_my_data_scatter_labels(k,"precision","recall","human read level","read_level/human_t1_READ_scatter_labels.pdf", TRUE)## [1] "precision"
## [1] "recall"
## species dataset replicate level algorithm color
## 43 human t1 r1 READLEVEL clc #CC79A7
## 44 human t1 r1 READLEVEL contextmap2 cornflowerblue
## 45 human t1 r1 READLEVEL crac #D55E00
## 46 human t1 r1 READLEVEL gsnap #999999
## 47 human t1 r1 READLEVEL hisat maroon
## 48 human t1 r1 READLEVEL hisat2 maroon3
## aligned_ambiguously aligned_incorrectly deletions_precision
## 43 0.0119 0.0202 NA
## 44 0.0000 0.0098 NA
## 45 0.0000 0.0806 NA
## 46 0.0191 0.0022 NA
## 47 0.0184 0.0026 NA
## 48 0.0196 0.0029 NA
## deletions_recall insertions_precision insertions_recall precision
## 43 NA NA NA 0.9773
## 44 NA NA NA 0.9899
## 45 NA NA NA 0.9193
## 46 NA NA NA 0.9977
## 47 NA NA NA 0.9972
## 48 NA NA NA 0.9969
## recall skipping_precision skipping_recall unaligned tmp1 tmp2
## 43 0.8771 NA NA 0.0908 0.9773 0.8771
## 44 0.9765 NA NA 0.0137 0.9899 0.9765
## 45 0.9192 NA NA 0.0002 0.9193 0.9192
## 46 0.9787 NA NA 0.0000 0.9977 0.9787
## 47 0.9676 NA NA 0.0114 0.9972 0.9676
## 48 0.9697 NA NA 0.0078 0.9969 0.9697
## [1] 0.8771 0.9765 0.9192 0.9787 0.9676 0.9697 0.9804 0.9744 0.9507 0.9679
## [11] 0.9481 0.9768 0.9467 0.9464
## [1] "clc" "contextmap2" "crac" "gsnap" "hisat"
## [6] "hisat2" "mapsplice2" "novoalign" "olego" "rum"
## [11] "soapsplice" "star" "subread" "tophat2"
plot_my_data_scatter_labels_shapes(k,"precision","recall","human read level","read_level/human_t1_READ_scatter_labels_shapes.pdf", TRUE)## [1] "precision"
## [1] "recall"
## species dataset replicate level algorithm color
## 43 human t1 r1 READLEVEL clc #CC79A7
## 44 human t1 r1 READLEVEL contextmap2 cornflowerblue
## 45 human t1 r1 READLEVEL crac #D55E00
## 46 human t1 r1 READLEVEL gsnap #999999
## 47 human t1 r1 READLEVEL hisat maroon
## 48 human t1 r1 READLEVEL hisat2 maroon3
## aligned_ambiguously aligned_incorrectly deletions_precision
## 43 0.0119 0.0202 NA
## 44 0.0000 0.0098 NA
## 45 0.0000 0.0806 NA
## 46 0.0191 0.0022 NA
## 47 0.0184 0.0026 NA
## 48 0.0196 0.0029 NA
## deletions_recall insertions_precision insertions_recall precision
## 43 NA NA NA 0.9773
## 44 NA NA NA 0.9899
## 45 NA NA NA 0.9193
## 46 NA NA NA 0.9977
## 47 NA NA NA 0.9972
## 48 NA NA NA 0.9969
## recall skipping_precision skipping_recall unaligned tmp1 tmp2
## 43 0.8771 NA NA 0.0908 0.9773 0.8771
## 44 0.9765 NA NA 0.0137 0.9899 0.9765
## 45 0.9192 NA NA 0.0002 0.9193 0.9192
## 46 0.9787 NA NA 0.0000 0.9977 0.9787
## 47 0.9676 NA NA 0.0114 0.9972 0.9676
## 48 0.9697 NA NA 0.0078 0.9969 0.9697
## [1] 0.8771 0.9765 0.9192 0.9787 0.9676 0.9697 0.9804 0.9744 0.9507 0.9679
## [11] 0.9481 0.9768 0.9467 0.9464
## [1] "clc" "contextmap2" "crac" "gsnap" "hisat"
## [6] "hisat2" "mapsplice2" "novoalign" "olego" "rum"
## [11] "soapsplice" "star" "subread" "tophat2"
plot_my_data_scatter_bw_theme(k,"precision","recall","human read level","read_level/human_t1_READ_scatter_bw_theme.pdf", TRUE)## [1] "precision"
## [1] "recall"
## species dataset replicate level algorithm color
## 43 human t1 r1 READLEVEL clc #CC79A7
## 44 human t1 r1 READLEVEL contextmap2 cornflowerblue
## 45 human t1 r1 READLEVEL crac #D55E00
## 46 human t1 r1 READLEVEL gsnap #999999
## 47 human t1 r1 READLEVEL hisat maroon
## 48 human t1 r1 READLEVEL hisat2 maroon3
## aligned_ambiguously aligned_incorrectly deletions_precision
## 43 0.0119 0.0202 NA
## 44 0.0000 0.0098 NA
## 45 0.0000 0.0806 NA
## 46 0.0191 0.0022 NA
## 47 0.0184 0.0026 NA
## 48 0.0196 0.0029 NA
## deletions_recall insertions_precision insertions_recall precision
## 43 NA NA NA 0.9773
## 44 NA NA NA 0.9899
## 45 NA NA NA 0.9193
## 46 NA NA NA 0.9977
## 47 NA NA NA 0.9972
## 48 NA NA NA 0.9969
## recall skipping_precision skipping_recall unaligned tmp1 tmp2
## 43 0.8771 NA NA 0.0908 0.9773 0.8771
## 44 0.9765 NA NA 0.0137 0.9899 0.9765
## 45 0.9192 NA NA 0.0002 0.9193 0.9192
## 46 0.9787 NA NA 0.0000 0.9977 0.9787
## 47 0.9676 NA NA 0.0114 0.9972 0.9676
## 48 0.9697 NA NA 0.0078 0.9969 0.9697
## [1] 0.8771 0.9765 0.9192 0.9787 0.9676 0.9697 0.9804 0.9744 0.9507 0.9679
## [11] 0.9481 0.9768 0.9467 0.9464
## [1] "clc" "contextmap2" "crac" "gsnap" "hisat"
## [6] "hisat2" "mapsplice2" "novoalign" "olego" "rum"
## [11] "soapsplice" "star" "subread" "tophat2"