-
Notifications
You must be signed in to change notification settings - Fork 1
/
genera.charts.Rmd
243 lines (192 loc) · 8.57 KB
/
genera.charts.Rmd
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
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
---
title: "Diversity of Fungal Genera"
date: '2022.04.29'
author: 'Nathan Malamud'
---
```{r setup, include=FALSE}
# markdown setup
library(knitr)
knitr::opts_chunk$set(echo = F) # Don't print code
knitr::opts_chunk$set(warning = F) # Don't print warnings
knitr::opts_chunk$set(message = F) # Don't print messages
knitr::opts_chunk$set(echo = TRUE)
# other important libraries
library(phyloseq)
library(vegan)
library(dplyr)
library(reshape2)
library(EcolUtils)
library(spaa)
library(ggplot2)
library(ggpubr)
library(tidyverse)
# clear all objects from workspace
rm(list = ls())
# Open serialized .rds data (generated by setup.R)
asvtab <- readRDS('./Data/asvtab.rds')
metadata <- readRDS('./Data/metadata.rds')
guilds <- readRDS('./Data/guilds.rds')
itsphyseq <- readRDS('./Data/itsphyseq.rds')
# Subset itsphyseq and metadata across soil and litter
itsphyseq.soil = subset_samples(itsphyseq, Soil_Litter=="Soil")
itsphyseq.litter = subset_samples(itsphyseq, Soil_Litter=="Litter")
metadata.soil = subset(metadata, Soil_Litter=="Soil")
metadata.litter = subset(metadata, Soil_Litter=="Litter")
# Subset ASVs across functional guilds
guilds.amf <- subset(guilds, Guild=="Arbuscular Mycorrhizal")
asvs.amf <- guilds.amf$ASV_ID
asvtab.amf <- subset(asvtab, ASV_ID %in% asvs.amf)
guilds$groups[grepl("Saprotroph", guilds$Guild)] = "Saprotroph"
guilds.sap <- subset(guilds, groups=="Saprotroph")
asvs.sap <- guilds.sap$ASV_ID
asvtab.sap <- subset(asvtab, ASV_ID %in% asvs.sap)
guilds$groups[grepl("Plant Pathogen", guilds$Guild)] = "Plant Pathogen"
guilds.pathogen <- subset(guilds, groups=="Plant Pathogen")
asvs.pathogen <- guilds.pathogen$ASV_ID
asvtab.pathogen <- subset(asvtab, ASV_ID %in% asvs.pathogen)
# Additional function for extracting figure legend
library(gridExtra)
g_legend<-function(a.gplot){
tmp <- ggplot_gtable(ggplot_build(a.gplot))
leg <- which(sapply(tmp$grobs, function(x) x$name) == "guide-box")
legend <- tmp$grobs[[leg]]
legend
}
```
```{r genbar function, include=F}
make.genbar <- function (asvtab, metadata, samples, guilds, colors30, other.label="other") {
# Generates a bar chart for microbial genera. Colors not included!
# Must provide list of chart colors as parameter colors30.
# NOTE: converts reads to relative abundances.
merged <- merge(guilds, asvtab, by="ASV_ID")
merged.2 = asvtab[,c("Genus", samples)]
collapsed = aggregate(. ~Genus, data=merged.2, FUN=sum) # summarize the data for plotting
row.names(collapsed) = collapsed$Genus
collapsed = collapsed[,-1]
fun = as.data.frame(t(collapsed))
fun = decostand(fun, 1, method = "total") # relative abundance using decostand.
fun$Sample_ID=rownames(fun) # rename otu id names
fun=merge(fun, metadata, by="Sample_ID")
dframe <- melt(fun) # long format now each row is a rel abundance with its metadata
names(dframe)[4] <- "Genus"
names(dframe)[names(dframe) == "value"] <- "Abundance"
# rename the groups
dframe$Genus=ifelse(is.na(dframe$Genus),"unidentified", as.character(dframe$Genus))
dframe$Genus=gsub(".*_","",dframe$Genus)
# Filter out only the top 15
dframe.genus <- dframe[, c("Genus", "Abundance")]
dframe.genus.collapsed = aggregate(.~Genus, data=dframe.genus, FUN=sum)
dframe.genus.collapsed <- dframe.genus.collapsed[order(-dframe.genus.collapsed$Abundance),]
# Find the top 15 genera and specify that
# the "other" category is last
top15 <- as.vector(head(dframe.genus.collapsed, 15)$Genus)
# group all other taxa in another bin
dframe$Genus.ordered = ifelse(
dframe$Genus %in% top15,
dframe$Genus,
other.label
)
print(length(unique(dframe$Genus)))
# Order the genera column alphabetically and give the "other" category a color
dframe$Genus.ordered <- factor(dframe$Genus.ordered, c(sort(top15), other.label))
colors30 <- c(colors30, "grey")
# Create the plot
genus.plot = ggplot(dframe, aes(x = Tree_species, y = Abundance, fill = Genus.ordered)) +
geom_bar(stat = "identity", position = "fill") +
ylab("Relative Abundance") +
xlab("") +
scale_fill_manual(values=colors30) +
scale_x_discrete(labels = function(x) str_wrap(x, width = 10)) +
coord_cartesian(ylim = c(0.0, 1.0))+ # cutoff y value minimum
theme_classic() +
theme(legend.title=element_blank())+
theme(axis.text.x = element_text(angle = 90, hjust = 1,vjust = .1))+
theme(strip.text.x = element_text(margin = margin(.05, 0, .05, 0, "cm")))+
theme(strip.text = element_text(colour = 'white'),
axis.line = element_line(colour = "black"),
text = element_text(size=18),
legend.text=element_text(size=14))
return(genus.plot)
}
```
```{r amf}
# sample names for soil and litter
names.amf.soil <- sample_names(subset_samples(
subset_taxa(itsphyseq, ASV_ID %in% asvs.amf),
Soil_Litter == "Soil"
)
)
names.amf.litter <- sample_names(subset_samples(
subset_taxa(itsphyseq, ASV_ID %in% asvs.amf),
Soil_Litter == "Litter"
)
)
# manually set the colors for the plot. http://medialab.github.io/iwanthue/
colors15 = c("#8499ff", "#6eb638", "#ab48b8",
"#018621", "#cc88ff", "#008839",
"#c60f72", "#005317", "#ff92d8",
"#798600", "#131f5f", "#ffce4a",
"#0060b1", "#e7d566", "#680058")
amfplot.s <- make.genbar(asvtab.amf, metadata.soil, names.amf.soil, guilds.amf, colors15)
amfplot.l <- make.genbar(asvtab.amf, metadata.litter, names.amf.litter, guilds.amf, colors15)
plot(amfplot.s)
plot(amfplot.l)
```
```{r decomposers}
# sample names for soil and litter
names.sap.soil <- sample_names(subset_samples(
subset_taxa(itsphyseq, ASV_ID %in% asvs.sap),
Soil_Litter == "Soil"
)
)
names.sap.litter <- sample_names(subset_samples(
subset_taxa(itsphyseq, ASV_ID %in% asvs.sap),
Soil_Litter == "Litter"
)
)
colors15.s = c("#628ed6", "#9cb241", "#6971d7", "#c99135", "#543889",
"#5bbc72", "#a2408e", "#43c8ac", "#d14a64", "#6b8b3a",
"#c881d5", "#b67d47", "#9b3c40", "#c25137", "#bb4c7e")
colors15.l = c("#628ed6", "#9cb241", "#6971d7", "#c99135", "#543889",
"#5bbc72", "#a2408e", "#43c8ac", "#d14a64", "#6b8b3a",
"#c881d5", "#b67d47", "#bb4c7e", "#c25137", "#9b3c40")
sapplot.s <- make.genbar(asvtab.sap, metadata.soil, names.sap.soil, guilds.sap, colors15.s, "Other decomposers")
sapplot.l <- make.genbar(asvtab.sap, metadata.litter, names.sap.litter, guilds.sap, colors15.l, "Other decomposers")
plot(sapplot.s)
plot(sapplot.l)
```
```{r pathogens}
# sample names for soil and litter
names.pathogen.soil <- sample_names(subset_samples(
subset_taxa(itsphyseq, ASV_ID %in% asvs.pathogen),
Soil_Litter == "Soil"
)
)
names.pathogen.litter <- sample_names(subset_samples(
subset_taxa(itsphyseq, ASV_ID %in% asvs.pathogen),
Soil_Litter == "Litter"
)
)
colors15.s = c("#7fcc49", "#947eeb", "#d5cb36", "#df6bcc","#e375a4",
"#82c862", "#6dcb87", "#c792d6", "#c5ba4f", "#6fa4df",
"#d7892d", "#5acfbc", "#e67553", "#c1b372", "#e2737d")
colors15.l = c("#7fcc49", "#947eeb", "#d5cb36", "#df6bcc", "#82c862",
"#e375a4", "#6dcb87", "#c792d6", "#c5ba4f", "#d7892d", "#6fa4df",
"#5acfbc", "#e67553", "#c1b372", "#e2737d")
pathogenplot.s <- make.genbar(asvtab.pathogen, metadata.soil, names.pathogen.soil, guilds.pathogen, colors15.s, "Other pathogens")
pathogenplot.l <- make.genbar(asvtab.pathogen, metadata.litter, names.pathogen.litter, guilds.pathogen, colors15.l, "Other pathogens")
plot(pathogenplot.s)
plot(pathogenplot.l)
```
```{r save all plots separately}
# Soil on the left, litter on the right
amf.charts <- ggarrange(amfplot.s, amfplot.l,
nrow=1, labels=c("A", "B"))
sap.charts <- ggarrange(sapplot.s, sapplot.l,
nrow=1, labels=c("C", "D"))
pathogen.charts <- ggarrange(pathogenplot.s, pathogenplot.l,
nrow=1, labels=c("E", "F"))
ggsave(filename = "Figures/thesis.fig2AB.amf.tiff", plot=amf.charts, width=10, height = 5, units="in", dpi=300, compression="lzw")
ggsave(filename = "Figures/thesis.fig2CD.saps.tiff", plot=sap.charts, width=10, height = 5, units="in", dpi=300, compression="lzw")
ggsave(filename = "Figures/thesis.fig2EF.pathogens.tiff", plot=pathogen.charts, width=10, height = 5, units="in", dpi=300, compression="lzw")
```