packages <- c("phyloseq","stringr","dplyr","tidyr","ggplot2","patchwork","ggpubr",
"forcats","vegan","ade4","adespatial","ComplexHeatmap","circlize",
"tibble","readr","partykit","metagMisc","tseries","rio","lme4",
"sjPlot","ggridges","FactoMineR","ggside","factoextra","corrplot",
"microbiome","rdacca.hp","UpSetVP")
invisible(lapply(packages, library, character.only = TRUE))
data.frame(
Package = packages,
Version = sapply(packages, function(x) as.character(packageVersion(x)))
)
## Package Version
## phyloseq phyloseq 1.52.0
## stringr stringr 1.6.0
## dplyr dplyr 1.1.4
## tidyr tidyr 1.3.1
## ggplot2 ggplot2 4.0.1
## patchwork patchwork 1.3.2
## ggpubr ggpubr 0.6.2
## forcats forcats 1.0.1
## vegan vegan 2.7.2
## ade4 ade4 1.7.23
## adespatial adespatial 0.3.28
## ComplexHeatmap ComplexHeatmap 2.24.1
## circlize circlize 0.4.17
## tibble tibble 3.3.0
## readr readr 2.1.5
## partykit partykit 1.2.25
## metagMisc metagMisc 0.6.0.9000
## tseries tseries 0.10.59
## rio rio 1.2.4
## lme4 lme4 1.1.38
## sjPlot sjPlot 2.9.0
## ggridges ggridges 0.5.7
## FactoMineR FactoMineR 2.13
## ggside ggside 0.4.1
## factoextra factoextra 1.0.7
## corrplot corrplot 0.95
## microbiome microbiome 1.30.0
## rdacca.hp rdacca.hp 1.1.1
## UpSetVP UpSetVP 1.0.0
env_df <- read.csv("rawdata/data_env.csv", header = TRUE, dec = ",", sep = ";", stringsAsFactors = FALSE)
foram_df <- read.csv("rawdata/Foram_table.csv", header = TRUE, sep = ";", stringsAsFactors = FALSE)
ps_alpha <- readRDS("metaB_clean/ps_alpha.rds")
ps_rarefied <- readRDS("metaB_clean/ps_rarefied.rds")
ps_rs_rarefied <- readRDS("metaB_clean/ps_rs_rarefied.rds")
rs_db_df <- read.csv("rawdata/database_RestSt.csv", header = TRUE, sep = ";", stringsAsFactors = FALSE)
#Al and Ni as representative metals of ultramafic and vulcanosedimentary sources As highlighted by PMF 5.0 model (see method ans supplementary information)
metaux <- c("Li","Al","V","Cr","Mn","Fe","Co","Ni","Cu","Zn","As","Mo","Ag","Cd","Sn","Sb","Ba","Pb","U","Hg")
env_metaux <- env_df %>%
select(all_of(metaux))
env_metaux_nonzero <- env_metaux %>%
filter(rowSums(., na.rm = TRUE) > 0)
mcor_metaux <- cor(env_metaux_nonzero,
method = "spearman",
use = "complete.obs")
cor_mtest <- function(mat, method = "spearman") {
mat <- as.matrix(mat)
n <- ncol(mat)
p.mat <- matrix(NA, n, n)
diag(p.mat) <- 0
for (i in 1:(n - 1)) {
for (j in (i + 1):n) {
test <- cor.test(mat[, i], mat[, j], method = method)
p.mat[i, j] <- p.mat[j, i] <- test$p.value
}
}
colnames(p.mat) <- rownames(p.mat) <- colnames(mat)
return(p.mat)
}
p_mat_metaux <- cor_mtest(env_metaux_nonzero,
method = "spearman")
col_palette <- colorRampPalette(c("#BB4444", "#EE9988", "#FFFFFF",
"#77AADD", "#4477AA"))
corrplot(mcor_metaux,
method = "color",
col = col_palette(200),
type = "upper",
order = "hclust",
addCoef.col = "black",
tl.col = "black",
tl.srt = 45,
p.mat = p_mat_metaux,
sig.level = 0.05,
insig = "blank",
diag = FALSE,
number.cex = 0.50)
#PCA
Col_unit <- c("#782208","#DC7242","#FBCE64","#94BB67","#3D785F")
df_metaux_pca <- env_df %>%
select(Unite, all_of(metaux)) %>%
na.omit()
res_pca_all <- PCA(df_metaux_pca[, metaux], scale.unit = TRUE, graph = FALSE)
# Extraire les scores des individus
scores_all <- as.data.frame(res_pca_all$ind$coord)
scores_all$Unite <- df_metaux_pca$Unite
perc_var_comp1 <- res_pca_all$eig[1,2]
perc_var_comp2 <- res_pca_all$eig[2,2]
# Plot avec ggplot, avec ellipses pour chaque unité
pca_all_plot <- ggplot(scores_all, aes(x = Dim.1, y = Dim.2, color = Unite, fill = Unite)) +
geom_point(size = 3) +
#stat_ellipse(alpha = 0.2, geom = "polygon") +
geom_ysidedensity(aes(y=Dim.2, yfill = Unite), alpha = 0.4) +
geom_xsidedensity(aes(x=Dim.1, xfill = Unite), alpha = 0.4) +
labs(x = paste("PC1 -",round(perc_var_comp1,1),"%"),
y = paste("PC2 -",round(perc_var_comp2,1),"%"),
color = "Unit", fill = "Unit") +
theme_classic() +
theme(ggside.panel.scale = .2) +
theme_ggside_void() +
scale_color_manual(values = Col_unit)+
scale_fill_manual(values = Col_unit)+
scale_xfill_manual(values = Col_unit)+
scale_yfill_manual(values = Col_unit)
#Keeping only An and Ni
df_al_ni <- env_df %>%
select(Unite, Al, Ni) %>%
na.omit()
res_pca_alni <- PCA(df_al_ni[, c("Al","Ni")], scale.unit = TRUE, graph = FALSE)
scores_al_ni <- as.data.frame(res_pca_alni$ind$coord)
scores_al_ni$Unite <- df_al_ni$Unite
perc_var_alni_comp1 <- res_pca_alni$eig[1,2]
perc_var_alni_comp2 <- res_pca_alni$eig[2,2]
pca_alni_plot <- ggplot(scores_al_ni, aes(x = -Dim.1, y = Dim.2, color = Unite, fill = Unite)) +
geom_point(size = 3) +
#stat_ellipse(alpha = 0.2, geom = "polygon") +
geom_ysidedensity(aes(y=Dim.2, yfill = Unite,), alpha = 0.4) +
geom_xsidedensity(aes(x=-Dim.1, xfill = Unite), alpha = 0.4) +
labs(x = paste("PC1 -",round(perc_var_alni_comp1,1),"%"),
y = paste("PC2 -",round(perc_var_alni_comp2,1),"%"),
color = "Unit", fill = "Unit") +
theme_classic() +
theme(ggside.panel.scale = .2) +
theme_ggside_void() +
scale_color_manual(values = Col_unit)+
scale_fill_manual(values = Col_unit)+
scale_xfill_manual(values = Col_unit)+
scale_yfill_manual(values = Col_unit)
combined_plot <- pca_all_plot + pca_alni_plot +
plot_layout(guides = "collect") & theme(legend.position = "bottom")
combined_plot
ggsave("Outputs/Figure_suppl_double_PCA_metals.pdf", plot = combined_plot,
width = 200, height = 100, units = "mm", dpi = 400)
# Select relevant environmental variables
env_subset <- env_df %>%
select(Codification, Depth, Ni, Al)
# Filter out rows with no sediment or metal data
env_subset <- env_subset %>%
mutate(env_sum = rowSums(across(Ni:Al), na.rm = TRUE)) %>%
filter(env_sum > 0) %>%
select(-env_sum)
env_subset <- env_subset %>%
mutate(Depth_neg = -Depth)
# Conditional Inference Tree (ctree)
# Model depth partitioning based on Ni and Al concentration
env_ctree <- ctree(
Depth_neg ~ Ni + Al,
data = env_subset,
control = ctree_control(mincriterion = 0.995) # strict split criterion
)
# Print tree summary
print(env_ctree)
##
## Model formula:
## Depth_neg ~ Ni + Al
##
## Fitted party:
## [1] root
## | [2] Al <= 31846
## | | [3] Ni <= 5676: -24.765 (n = 17, err = 10819.1)
## | | [4] Ni > 5676: -73.538 (n = 13, err = 4241.2)
## | [5] Al > 31846
## | | [6] Ni <= 2243
## | | | [7] Ni <= 1920: -168.800 (n = 15, err = 5094.4)
## | | | [8] Ni > 1920: -210.286 (n = 7, err = 859.4)
## | | [9] Ni > 2243: -116.444 (n = 9, err = 1742.2)
##
## Number of inner nodes: 4
## Number of terminal nodes: 5
# Plot the tree
tree_plot <- plot(env_ctree, gp = gpar(fontsize = 10))
# Inspect samples matching a specific node rule
# (e.g. Unit IV)
env_subset_IV <- env_subset %>%
filter(Al > 31846) %>%
filter(Ni <= 1920)
print(env_subset_IV)
## Codification Depth Ni Al Depth_neg
## 1 B-72 140 1845 38088 -140
## 2 B-76 144 1777 38186 -144
## 3 B-80 148 1690 33186 -148
## 4 B-84 152 1721 34174 -152
## 5 C-02 156 1767 33713 -156
## 6 C-06 160 1877 34565 -160
## 7 C-10 164 1920 35453 -164
## 8 C-14 168 1827 36436 -168
## 9 C-18 172 1851 42010 -172
## 10 C-22 176 1855 40606 -176
## 11 C-26 180 1896 42933 -180
## 12 C-30 184 1843 33613 -184
## 13 C-38 192 1840 37920 -192
## 14 C-42 196 1750 38262 -196
## 15 C-46 200 1868 36654 -200
Sharp changes in chemical and physical parameters
# Prepare long format for selected variables
env_vars <- c("Clay","Sand","Ni","Al")
env_long <- env_df %>%
select(Codification, Depth, all_of(env_vars)) %>%
pivot_longer(cols = all_of(env_vars), names_to = "Variable", values_to = "Value") %>%
mutate(Category = case_when(
Variable %in% c("Clay", "Sand") ~ "Grain size",
Variable == "Ni" ~ "Nickel",
Variable == "Al" ~ "Aluminium",
TRUE ~ "Other"
)) %>%
filter(!is.na(Value) & Value > 0) %>%
mutate(Depth_neg = -Depth)
env_long$Category <- factor(env_long$Category, levels = c("Nickel","Aluminium","Grain size"))
env_long$Variable <- factor(env_long$Variable, levels = c("Ni","Al","Clay","Sand"))
color_variable <- c("#FF794D","#59BDC0","#BB593E","#D9AB37")
fig1_env_profile <- ggplot(env_long, aes(x = Depth_neg, y = Value, color = Variable, fill = Variable)) +
geom_vline(xintercept = c(-46, -94, -138, -202), linetype = "dashed", color = "grey") + #sedimentary units
facet_grid(~Category, scales = "free", space = "free_y") +
geom_line(aes(group = Variable), linewidth = 0.8, alpha = 0.6) +
geom_point(size = 1) +
scale_fill_manual(values = color_variable) + scale_color_manual(values = color_variable) +
labs(x = "Depth (cm)", y = "Value") + coord_flip() +
theme_pubr(base_size = 9)
# Source composition (UB, VS)
source_long <- env_df %>% select(Codification, Depth, UB, VS) %>%
pivot_longer(cols = c("UB","VS"), names_to = "Source", values_to = "Value") %>%
mutate(Depth_neg = -Depth) %>%
filter(!is.na(Value) & Value > 0)
color_source <- c("#E75A1E","#2AADB6")
fig1_source <- ggplot(source_long, aes(x = Depth_neg, y = Value, fill = Source)) +
geom_vline(xintercept = c(-46, -94, -138, -202), linetype = "dashed", color = "grey") +
geom_area(alpha = 0.6, color = "white") +
scale_fill_manual(values = color_source) +
labs(y = "Value") + coord_flip() + theme_pubr(base_size = 9) +
theme(axis.title.y = element_blank(), axis.text.y = element_blank(), axis.ticks.y = element_blank())
fig1_combined <- fig1_env_profile + fig1_source + plot_layout(widths = c(3,1))
fig1_combined
ggsave("Outputs/Figure1_environment_profiles.pdf", plot = fig1_combined,
width = 180, height = 140, units = "mm", dpi = 600)
# Foraminifera
foram_df <- foram_df %>%
mutate(
Sed_rate = case_when(
Unit == "I" ~ 0.9,
Unit == "II" ~ 1.0,
Unit == "III" ~ 0.2,
Unit == "IV" ~ 0.2,
Unit == "V" ~ 0.1,
TRUE ~ NA_real_
)
)
# log-transform
foram_df2 <- foram_df %>%
filter(!is.na(Sum_genus), !is.na(Sed_rate)) %>%
mutate(
log_div = log(Sum_genus + 1),
log_sed = log(Sed_rate)
)
# Modele : diversity ~ sedimentation rate
mod_foram <- lm(log_div ~ log_sed, data = foram_df2)
summary(mod_foram)
##
## Call:
## lm(formula = log_div ~ log_sed, data = foram_df2)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.46771 -0.16888 0.04241 0.32858 1.09724
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.41957 0.07739 18.343 < 2e-16 ***
## log_sed -0.45683 0.05970 -7.652 4.78e-12 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.5781 on 124 degrees of freedom
## Multiple R-squared: 0.3208, Adjusted R-squared: 0.3153
## F-statistic: 58.56 on 1 and 124 DF, p-value: 4.778e-12
# Corrected diversity = residual
foram_df2$div_corr <- resid(mod_foram)
summary_foram_df2 <- foram_df2 %>%
group_by(Unit) %>%
summarise(mean_div_corr = mean(div_corr, na.rm = TRUE),
sd_div_corr = sd(div_corr, na.rm = TRUE),
min_date = min(date_median, na.rm = TRUE),
max_date = max(date_median, na.rm = TRUE)) %>%
mutate(med_date = (min_date + max_date)/2) %>% ungroup()
summary_foram_df2
## # A tibble: 5 × 6
## Unit mean_div_corr sd_div_corr min_date max_date med_date
## <chr> <dbl> <dbl> <int> <int> <dbl>
## 1 I -0.227 0.866 1976 2022 1999
## 2 II 0.233 0.675 1960 1975 1968.
## 3 III -0.0505 0.233 1757 1960 1858.
## 4 IV 0.166 0.133 1301 1738 1520.
## 5 V -0.208 0.137 1163 1279 1221
# Visualisation
sed_rate_foram <- ggplot(foram_df2, aes(y = div_corr, x = date_median)) +
geom_vline(xintercept = c(1976, 1960, 1757, 1301), linetype = "dashed", color = "grey") +
geom_ribbon(aes(ymin = 0, ymax = div_corr), alpha = 0.25) +
geom_point(data = summary_foram_df2, aes(x = med_date, y = mean_div_corr), inherit.aes = FALSE, size = 2) +
geom_line(data = summary_foram_df2, aes(x = med_date, y = mean_div_corr), inherit.aes = FALSE, size = 0.8) +
geom_linerange(data = summary_foram_df2, aes(x = med_date, ymin = mean_div_corr - sd_div_corr, ymax = mean_div_corr + sd_div_corr), inherit.aes = FALSE) +
labs(x = "Median date", y = "Corrected diversity") + xlim(1140,2030) +
theme_pubr(base_size = 12) + coord_flip()
# Microeukaryote
alpha_richness_df <- estimate_richness(ps_alpha, measures = c("Observed"))
alpha_richness_df$SampleID <- rownames(alpha_richness_df)
# Merge with sample metadata (ensure columns exist)
meta_alpha <- as.data.frame(sample_data(ps_alpha))
meta_alpha$SampleID <- rownames(meta_alpha)
meta_alpha <- as.matrix(meta_alpha)
meta_alpha <- as.data.frame(meta_alpha)
alpha_meta_df <- left_join(alpha_richness_df, meta_alpha, by = "SampleID")
# Ensure numeric columns
alpha_meta_df$Date_mean <- as.numeric(alpha_meta_df$Date_mean)
alpha_meta_df$Depth_reel <- as.numeric(alpha_meta_df$Depth_reel)
alpha_meta_df$alpha_observed <- as.numeric(alpha_meta_df$Observed)
alpha_meta_df <- alpha_meta_df %>%
mutate(
Sed_rate = case_when(
Unit == "I" ~ 0.9,
Unit == "II" ~ 1.0,
Unit == "III" ~ 0.2,
Unit == "IV" ~ 0.2,
Unit == "V" ~ 0.1,
TRUE ~ NA_real_
)
)
alpha_df2 <- alpha_meta_df %>%
filter(!is.na(alpha_observed), !is.na(Sed_rate)) %>%
mutate(
log_div = log(alpha_observed + 1),
log_sed = log(Sed_rate)
)
mod_alpha <- lm(log_div ~ log_sed, data = alpha_df2)
summary(mod_alpha)
##
## Call:
## lm(formula = log_div ~ log_sed, data = alpha_df2)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4080 -0.4208 0.1263 0.4524 1.0375
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.61270 0.11578 57.116 < 2e-16 ***
## log_sed 0.48187 0.08955 5.381 9.31e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6604 on 70 degrees of freedom
## Multiple R-squared: 0.2926, Adjusted R-squared: 0.2825
## F-statistic: 28.96 on 1 and 70 DF, p-value: 9.309e-07
alpha_df2$div_corr <- resid(mod_alpha)
summary_alpha_df2 <- alpha_df2 %>%
group_by(Unit) %>%
summarise(mean_div_corr = mean(div_corr, na.rm = TRUE),
sd_div_corr = sd(div_corr, na.rm = TRUE),
min_date = min(Date_mean, na.rm = TRUE),
max_date = max(Date_mean, na.rm = TRUE)) %>%
mutate(med_date = (min_date + max_date)/2) %>% ungroup()
summary_alpha_df2
## # A tibble: 5 × 6
## Unit mean_div_corr sd_div_corr min_date max_date med_date
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 I 0.464 0.365 1977 2022 2000.
## 2 II -0.790 0.717 1961 1976 1968.
## 3 III 0.601 0.190 1824 1960 1892
## 4 IV -0.180 0.399 1348 1803 1576.
## 5 V -0.335 0.218 1146 1309 1228.
sed_rate_alpha <- ggplot(alpha_df2, aes(y = div_corr, x = Date_mean)) +
geom_vline(xintercept = c(1976, 1960, 1757, 1301), linetype = "dashed", color = "grey") +
geom_ribbon(aes(ymin = 0, ymax = div_corr), alpha = 0.25) +
geom_point(data = summary_alpha_df2, aes(x = med_date, y = mean_div_corr), inherit.aes = FALSE, size = 2) +
geom_line(data = summary_alpha_df2, aes(x = med_date, y = mean_div_corr), inherit.aes = FALSE, size = 0.8) +
geom_linerange(data = summary_alpha_df2, aes(x = med_date, ymin = mean_div_corr - sd_div_corr, ymax = mean_div_corr + sd_div_corr), inherit.aes = FALSE) +
labs(x = "Median date", y = "Corrected diversity")+ xlim(1140,2030) +
theme_pubr(base_size = 12) + coord_flip()
# Podani partitioning (moving window) using ps_alpha abundance table
otu_alpha_mat <- t(as.data.frame(otu_table(ps_alpha))) # samples as rows
otu_alpha_mat <- otu_alpha_mat[order(rownames(otu_alpha_mat), decreasing = TRUE), ]
window_size <- 2
df_podani <- data.frame()
for(i in 1:(nrow(otu_alpha_mat) - window_size)) {
tmp <- otu_alpha_mat[i:(i + window_size), ]
tmp_beta <- adespatial::beta.div.comp(tmp, coef = "J", quant = FALSE)
tmp_beta <- data.frame(start = rownames(tmp)[1], end = rownames(tmp)[nrow(tmp)], tmp_beta$part) %>%
tibble::rownames_to_column("component")
df_podani <- dplyr::bind_rows(df_podani, tmp_beta)
}
# Merge with depth
df_podani<- df_podani %>%
mutate(period = paste(start, end, sep = "-")) %>%
mutate(Sample_ID = paste(end))
sample_depth <- select(alpha_meta_df, "Sample_ID","Depth_sampling", "Unit")
df_podani <- merge(df_podani, sample_depth, by = "Sample_ID")
df_podani$Depth_sampling <- as.numeric(df_podani$Depth_sampling)
# Plot data
comp_plot <- c("BDtotal","Repl","RichDif")
fig2_podani_plot <- ggplot(df_podani %>% filter(component %in% comp_plot), aes(x = -Depth_sampling, y = tmp_beta.part, color = component, fill = component)) +
geom_vline(xintercept = c(-41,-93,-137,-202,-226), linetype = "dashed", color = "grey") +
geom_line(size = 0.9, alpha = 0.6) +
scale_color_manual(values = c("#616161", "#72B678", "#407B7B")) +
geom_point(size = 1) +
coord_flip() + theme_pubr(base_size = 9) +
labs(
x = "Depth (cm)",
y = "Podani's indices"
)
# Combine Figure 2 panels
fig2_combined <- sed_rate_foram + sed_rate_alpha + fig2_podani_plot + plot_layout(ncol = 3)
fig2_combined
ggsave(filename = "Outputs/Figure2_alpha_diversity.pdf", plot = fig2_combined,
width = 200, height = 180, units = "mm", dpi = 600)
#Link DNA concentration, diversity and grain size
#DNA concentration profil
alpha_meta_df$ADN <- as.numeric(alpha_meta_df$ADN)
dna_conc <- ggplot(alpha_meta_df, aes(x = -Depth_reel, y = ADN, color = Part)) +
geom_point(size = 1) +
geom_vline(xintercept = c(-41, -93, -137, -202, -226), linetype = "dashed", color = "grey") +
geom_line(size = 0.9, alpha = 0.6) +
scale_color_manual(values = Col_unit) +
coord_flip() +
theme_pubr(base_size = 9) +
theme(legend.position = "none") +
labs(
x = "Depth (cm)",
y = "DNA concentration (ng/L)"
)
alpha_meta_df$Clay <- as.numeric(alpha_meta_df$Clay)
clay_dna <- ggplot(alpha_meta_df, aes(x = Clay, y = ADN, color = Part)) +
geom_point(size = 1) +
geom_smooth(aes(group = 1), method = "lm", se = TRUE, color = "black") +
stat_regline_equation(aes(label = paste(..rr.label..)),
formula = y ~ x,
label.x.npc = "left",
label.y.npc = 0.95,
color = "black") +
scale_color_manual(values = Col_unit) +
theme_pubr(base_size = 9) +
labs(
x = "Clay proportion (%)",
y = "DNA concentration (ng/L)"
)
asv_dna <- ggplot(alpha_meta_df, aes(x = Observed, y = ADN, color = Part)) +
geom_point(size = 1) +
geom_smooth(aes(group = 1), method = "lm", se = TRUE, color = "black") +
stat_regline_equation(aes(label = paste(..rr.label..)),
formula = y ~ x,
label.x.npc = "left",
label.y.npc = 0.95,
color = "black") +
scale_color_manual(values = Col_unit) +
theme_pubr(base_size = 9) +
labs(
x = "ASV number",
y = "DNA concentration (ng/L)"
)
plot_dna <- clay_dna / asv_dna
combined_plot_dna <- dna_conc + plot_dna +
plot_layout(guides = "collect") &
theme(legend.position = "bottom")
combined_plot_dna
Compare with microeukaryote rarefied dataset
# Microeukaryote
alpha_richness_df <- estimate_richness(ps_rarefied, measures = c("Observed"))
alpha_richness_df$SampleID <- rownames(alpha_richness_df)
# Merge with sample metadata (ensure columns exist)
meta_alpha <- as.data.frame(sample_data(ps_rarefied))
meta_alpha$SampleID <- rownames(meta_alpha)
meta_alpha <- as.matrix(meta_alpha)
meta_alpha <- as.data.frame(meta_alpha)
alpha_meta_df <- left_join(alpha_richness_df, meta_alpha, by = "SampleID")
# Ensure numeric columns
alpha_meta_df$Date_mean <- as.numeric(alpha_meta_df$Date_mean)
alpha_meta_df$Depth_reel <- as.numeric(alpha_meta_df$Depth_reel)
alpha_meta_df$alpha_observed <- as.numeric(alpha_meta_df$Observed)
alpha_meta_df <- alpha_meta_df %>%
mutate(
Sed_rate = case_when(
Unit == "I" ~ 0.9,
Unit == "II" ~ 1.0,
Unit == "III" ~ 0.2,
Unit == "IV" ~ 0.2,
Unit == "V" ~ 0.1,
TRUE ~ NA_real_
)
)
alpha_df2 <- alpha_meta_df %>%
filter(!is.na(alpha_observed), !is.na(Sed_rate)) %>%
mutate(
log_div = log(alpha_observed + 1),
log_sed = log(Sed_rate)
)
mod_alpha <- lm(log_div ~ log_sed, data = alpha_df2)
summary(mod_alpha)
##
## Call:
## lm(formula = log_div ~ log_sed, data = alpha_df2)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.31547 -0.25423 0.03362 0.43310 1.02832
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.5350 0.1151 56.773 <2e-16 ***
## log_sed 0.1950 0.1139 1.712 0.0926 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6436 on 54 degrees of freedom
## Multiple R-squared: 0.05151, Adjusted R-squared: 0.03394
## F-statistic: 2.932 on 1 and 54 DF, p-value: 0.09255
alpha_df2$div_corr <- resid(mod_alpha)
summary_alpha_df2 <- alpha_df2 %>%
group_by(Unit) %>%
summarise(mean_div_corr = mean(div_corr, na.rm = TRUE),
sd_div_corr = sd(div_corr, na.rm = TRUE),
min_date = min(Date_mean, na.rm = TRUE),
max_date = max(Date_mean, na.rm = TRUE)) %>%
mutate(med_date = (min_date + max_date)/2) %>% ungroup()
sed_rate_alpha <- ggplot(alpha_df2, aes(y = div_corr, x = Date_mean)) +
geom_vline(xintercept = c(1976, 1960, 1757), linetype = "dashed", color = "grey") +
geom_ribbon(aes(ymin = 0, ymax = div_corr), alpha = 0.25) +
geom_point(data = summary_alpha_df2, aes(x = med_date, y = mean_div_corr), inherit.aes = FALSE, size = 2) +
geom_line(data = summary_alpha_df2, aes(x = med_date, y = mean_div_corr), inherit.aes = FALSE, size = 0.8) +
geom_linerange(data = summary_alpha_df2, aes(x = med_date, ymin = mean_div_corr - sd_div_corr, ymax = mean_div_corr + sd_div_corr), inherit.aes = FALSE) +
labs(x = "Median date", y = "Corrected diversity") +
theme_pubr(base_size = 12) + coord_flip()
# Podani partitioning (moving window) using ps_alpha abundance table
otu_alpha_mat <- t(as.data.frame(otu_table(ps_rarefied))) # samples as rows
otu_alpha_mat <- otu_alpha_mat[order(rownames(otu_alpha_mat), decreasing = TRUE), ]
window_size <- 2
df_podani <- data.frame()
for(i in 1:(nrow(otu_alpha_mat) - window_size)) {
tmp <- otu_alpha_mat[i:(i + window_size), ]
tmp_beta <- adespatial::beta.div.comp(tmp, coef = "J", quant = FALSE)
tmp_beta <- data.frame(start = rownames(tmp)[1], end = rownames(tmp)[nrow(tmp)], tmp_beta$part) %>%
tibble::rownames_to_column("component")
df_podani <- dplyr::bind_rows(df_podani, tmp_beta)
}
# Merge with depth
df_podani<- df_podani %>%
mutate(period = paste(start, end, sep = "-")) %>%
mutate(Sample_ID = paste(end))
sample_depth <- select(alpha_meta_df, "Sample_ID","Depth_sampling", "Unit")
df_podani <- merge(df_podani, sample_depth, by = "Sample_ID")
df_podani$Depth_sampling <- as.numeric(df_podani$Depth_sampling)
# Plot data
comp_plot <- c("BDtotal","Repl","RichDif")
fig2_podani_plot <- ggplot(df_podani %>% filter(component %in% comp_plot), aes(x = -Depth_sampling, y = tmp_beta.part, color = component, fill = component)) +
geom_vline(xintercept = c(-41,-93,-137), linetype = "dashed", color = "grey") +
geom_line(size = 0.9, alpha = 0.6) +
scale_color_manual(values = c("#616161", "#72B678", "#407B7B")) +
geom_point(size = 1) +
coord_flip() + theme_pubr(base_size = 12) +
labs(
x = "Depth (cm)",
y = "Podani's indices"
)
fig2_rarefied_combined <- sed_rate_alpha + fig2_podani_plot
fig2_rarefied_combined
ggsave(filename = "Outputs/Fig2_rarefied.pdf", plot = fig2_combined,
width = 200, height = 180, units = "mm", dpi = 600)
## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_ribbon()`).
# Pairwise Wilcoxon among units
pairwise_result_asv <- pairwise.wilcox.test(
x = alpha_meta_df$alpha_observed,
g = alpha_meta_df$Unit,
p.adjust.method = "bonferroni")
pval_asv <- as.data.frame(pairwise_result_asv$p.value)
pval_asv$type <- "ASV"
pval_asv
## I II III type
## II 3.879378e-07 NA NA ASV
## III 1.085375e-04 0.02336884 NA ASV
## IV 1.116067e-06 1.00000000 0.0005103256 ASV
pairwise_result_foram <- pairwise.wilcox.test(
x = foram_df$Sum_genus,
g = foram_df$Unit,
p.adjust.method = "bonferroni")
pval_foram <- as.data.frame(pairwise_result_foram$p.value)
pval_foram$type <- "Foram"
pval_foram
## I II III IV type
## II 6.586559e-01 NA NA NA Foram
## III 1.059947e-03 7.158574e-02 NA NA Foram
## IV 2.574194e-07 4.666828e-07 0.003762026 NA Foram
## V 8.257217e-04 1.463566e-03 0.343871053 1 Foram
# Resting-stage and unknown-genus subsets (using rs_db_df)
asv_rs_all <- rs_db_df %>% filter(RestingStage == 1) %>% pull(1) %>% na.omit() #based on functional database of Ramond et al., 2018 and additional literature when necessary
asv_unk <- rs_db_df %>% filter(is.na(RestingStage) & Unk_genus == 1) %>% pull(1) %>% na.omit() # i.e., no genus assignment
ps_rs_rar <- prune_taxa(taxa_names(ps_rarefied) %in% asv_rs_all, ps_rarefied)
ps_rs_unk_rar <- prune_taxa(taxa_names(ps_rarefied) %in% asv_unk, ps_rarefied)
# Richness observed
rich_rs <- estimate_richness(ps_rs_rar, measures = "Observed")
rich_rs$SampleID <- rownames(rich_rs)
colnames(rich_rs)[1] <- "Observed_rs"
reads_rs <- colSums(otu_table(ps_rs_rar))
reads_rs_df <- data.frame(SampleID = names(reads_rs), TotalReads_rs = reads_rs, stringsAsFactors = FALSE)
rich_tot <- estimate_richness(ps_rarefied, measures = "Observed")
rich_tot$SampleID <- rownames(rich_tot)
colnames(rich_tot)[1] <- "Observed_tot"
reads_tot <- colSums(otu_table(ps_rarefied))
reads_tot_df <- data.frame(SampleID = names(reads_tot), TotalReads_tot = reads_tot, stringsAsFactors = FALSE)
rich_unk <- estimate_richness(ps_rs_unk_rar, measures = "Observed")
rich_unk$SampleID <- rownames(rich_unk); colnames(rich_unk)[1] <- "Observed_rs_unk"
reads_unk <- colSums(otu_table(ps_rs_unk_rar))
reads_unk_df <- data.frame(SampleID = names(reads_unk), TotalReads_rs_unk = reads_unk, stringsAsFactors = FALSE)
# Merge richness/read summaries
rich_merge <- purrr::reduce(list(rich_tot[,c("Observed_tot","SampleID")], rich_rs[,c("Observed_rs","SampleID")],
rich_unk[,c("Observed_rs_unk","SampleID")], reads_tot_df, reads_rs_df, reads_unk_df),
function(x,y) full_join(x,y, by = "SampleID"))
# Add sample depth
colnames(sample_depth) <- c("SampleID","Depth_sampling","Unit")
rich_merge <- merge(rich_merge, sample_depth, by = "SampleID")
# Compute percentages
rich_merge <- rich_merge %>%
mutate(Observed_add = coalesce(Observed_rs,0) + coalesce(Observed_rs_unk,0),
TotalReads_add = coalesce(TotalReads_rs,0) + coalesce(TotalReads_rs_unk,0),
perc_asv_rs = Observed_rs_unk / Observed_tot * 100,
perc_read_rs = TotalReads_rs_unk / TotalReads_tot * 100)
# Visual panels (observed ASV numbers)
rich_merge <- rich_merge %>%
arrange(Depth_sampling) %>% # tri par profondeur croissante
mutate(SampleID = factor(SampleID, levels = SampleID)) # fixe l’ordre pour ggplot
rich_long <- data.frame(SampleID = factor(rep(rich_merge$SampleID, 3), levels = rich_merge$SampleID),
Value = c(rich_merge$Observed_tot, rich_merge$Observed_rs, rich_merge$Observed_add),
Depth = rep(rich_merge$Depth_sampling, 3),
Type = factor(rep(c("Observed_tot","Observed_rs","Observed_rs_unk_add"), each = nrow(rich_merge))))
rich_long$Lower <- 0
rich_long$Depth <- as.numeric(rich_long$Depth)
rich_long$Type <- factor(rich_long$Type, levels = c("Observed_tot","Observed_rs_unk_add","Observed_rs"))
fig3_obs_plot <- ggplot(rich_long, aes(y = Value, x = -Depth, group = Type, color = Type, fill = Type)) +
geom_ribbon(aes(ymin = Lower, ymax = Value), alpha = 1) +
geom_line(alpha = 1, size = 1) +
geom_vline(xintercept = c(-41,-93,-137), linetype = "dashed", color = "grey") +
ylab("Number of ASV") + xlab("Depth (cm)") + coord_flip() + theme_pubr(base_size = 9) +
scale_color_manual(values = c("black","#636363","#69C9C9")) +
scale_fill_manual(values = c("white","#9C9C9C","#95DCDC")) +
theme(legend.position = "none")
# Reads panel
reads_long <- data.frame(SampleID = factor(rep(rich_merge$SampleID, 3), levels = rich_merge$SampleID),
Value = c(rich_merge$TotalReads_tot, rich_merge$TotalReads_rs, rich_merge$TotalReads_add),
Depth = rep(rich_merge$Depth_sampling, 3),
Type = factor(rep(c("TotalReads_tot","TotalReads_rs","TotalRead_rs_unk_add"), each = nrow(rich_merge))))
reads_long$Lower <- 0
reads_long$Depth <- as.numeric(reads_long$Depth)
reads_long$Type <- factor(reads_long$Type, levels = c("TotalReads_tot","TotalRead_rs_unk_add","TotalReads_rs"))
fig3_read_plot <- ggplot(reads_long, aes(y = Value, x = -Depth, group = Type, color = Type, fill = Type)) +
geom_ribbon(aes(ymin = Lower, ymax = Value), alpha = 1) +
geom_line(alpha = 1, size = 1) +
geom_vline(xintercept = c(-41,-93,-137), linetype = "dashed", color = "grey") +
ylab("Number of reads") + coord_flip() + theme_pubr(base_size = 9) +
scale_color_manual(values = c("black","#636363","#69C9C9")) +
scale_fill_manual(values = c("white","#9C9C9C","#95DCDC"))+
theme(axis.title.y = element_blank(), axis.text.y = element_blank(), axis.ticks.y = element_blank())
# Composition of resting-stage taxa (relative abundance)
ps_rs_rel <- transform_sample_counts(ps_rs_rar, function(x) x * 100 / sum(x))
rs_melt <- psmelt(ps_rs_rel)
rs_melt <- rs_melt %>%
mutate(Subdivision = if_else(Subdivision == "", paste0(.$Division, "_X"), .$Subdivision))%>%
mutate(Subdivision = if_else(Subdivision == "_X", " Eukaryota_X", .$Subdivision))
rs_agg <- rs_melt %>%
group_by(Sample, Depth_sampling, Subdivision, Part) %>%
summarise(Abundance_per_Subdivision = sum(Abundance), .groups = "drop")
# Collapse rare subdivisions into "Others"
rare_subs <- rs_agg %>%
group_by(Subdivision) %>%
summarise(maxA = max(Abundance_per_Subdivision, na.rm = TRUE)) %>%
filter(maxA < 1) %>% pull(Subdivision)
rs_agg <- rs_agg %>%
mutate(Subdivision = fct_collapse(as.factor(Subdivision), Others = rare_subs))
# Add filler rows to get nice depth scale (only visualisation purpose)
filler_samples <- data.frame(Sample = c("A40", "A44", "A48", "A52", "A57", "A62", "A66", "A74", "A80", "A86",
"A108", "A112", "A117", "A122", "A126", "A130", "A134", "A138", "A142",
"A150", "A156", "A162", "A166", "A170", "A174"),
Depth_sampling = c(40,44,48,52,57,62,66,74,80,86,108,112,117,122,126,130,134,138,142,150,156,162,166,170,174),
Subdivision = "", Part = "None", Abundance_per_Subdivision = 100,
stringsAsFactors = FALSE)
filler_samples$Depth_sampling <- as.numeric(filler_samples$Depth_sampling)
rs_agg$Depth_sampling <- as.numeric(rs_agg$Depth_sampling)
rs_plot_df <- bind_rows(rs_agg, filler_samples)
# Factor ordering by depth values (adjust levels if needed)
unique_depths <- sort(unique(as.numeric(rs_plot_df$Depth_sampling)))
rs_plot_df$Depth_sampling <- factor(rs_plot_df$Depth_sampling, levels = as.character(unique_depths))
# Color vector - adjust as desired
col_vector_rs <- c("#F3EB51","#EAE289","#FFA54B","#931C0F","#824600","#F5C17D",
"#6373DB","#01579E","#1F91B6","#7DD9F8","#BAF2E9","#FAACEB",
"#5A9451","#6BDB57","#979797","white")
rs_plot_df$Subdivision <- factor(rs_plot_df$Subdivision,
levels=c(" Evosea_X"," Tubulinea_X",
" Chlorophyta_X",
" Haptophyta_X",
" Fungi"," Ichthyosporea",
" Apicomplexa"," Chrompodellids"," Ciliophora"," Dinoflagellata"," Perkinsea",
" Cercozoa",
" Bigyra"," Gyrista",
"Others",""
))
fig3_compo_rs_plot <- ggplot(rs_plot_df, aes(x = Abundance_per_Subdivision, y = fct_rev(Depth_sampling), fill = Subdivision)) +
geom_bar(stat = "identity", position = "stack") +
scale_fill_manual(values = col_vector_rs, guide = guide_legend(ncol = 1)) +
theme_minimal(base_size = 9) + labs(x = "Relative abundance (%)", y = "Depth") + theme(panel.grid = element_blank())
# For the complete community composition (rarefied)
ps_complet_rel <- transform_sample_counts(ps_rarefied, function(x) x * 100 / sum(x))
complet_melt <- psmelt(ps_complet_rel)
complet_melt <- complet_melt %>%
mutate(Subdivision = if_else(Subdivision == "", paste0(.$Division, "_X"), .$Subdivision))%>%
mutate(Subdivision = if_else(Subdivision == "_X", " Eukaryota_X", .$Subdivision))
complet_agg <- complet_melt %>%
group_by(Sample, Depth_sampling, Subdivision, Part) %>%
summarise(Abundance_per_Subdivision = sum(Abundance), .groups = "drop")
rare_subs2 <- complet_agg %>%
group_by(Subdivision) %>%
summarise(maxA = max(Abundance_per_Subdivision, na.rm = TRUE)) %>%
filter(maxA < 2) %>%
pull(Subdivision)
complet_agg <- complet_agg %>%
mutate(Subdivision = fct_collapse(as.factor(Subdivision), Others = rare_subs2))
filler_big <- data.frame(Sample = c("A40", "A44", "A48", "A52", "A57", "A62", "A66", "A74", "A80", "A86",
"A108", "A112", "A117", "A122", "A126", "A130", "A134", "A138", "A142",
"A150", "A156", "A162", "A166", "A170", "A174"),
Depth_sampling = c(40,44,48,52,57,62,66,74,80,86,108,112,117,122,126,130,134,138,142,150,156,162,166,170,174),
Subdivision = "", Part = "None", Abundance_per_Subdivision = 100,
stringsAsFactors = FALSE)
complet_agg$Depth_sampling <- as.numeric(complet_agg$Depth_sampling)
filler_big$Depth_sampling <- as.numeric(filler_big$Depth_sampling)
complet_plot_df <- bind_rows(complet_agg, filler_big)
unique_depths2 <- sort(unique(as.numeric(complet_plot_df$Depth_sampling)))
complet_plot_df$Depth_sampling <- factor(as.character(complet_plot_df$Depth_sampling), levels = as.character(unique_depths2))
col_vector_complet <- c("#F3EB51","#FFA54B","#DD5757","#931C0F","#740B97","#824600","#F5C17D", "#573000",
"#6373DB","#01579E","#1F91B6","#7DD9F8","#023667","#FAACEB","#5A9451","#6BDB57",
"#096306","#000000","#979797","white")
complet_plot_df$Subdivision <- factor(complet_plot_df$Subdivision,
levels=c(" Evosea_X",
" Chlorophyta_X",
" Cryptophyta_X"," Haptophyta_X",
" Breviatea_X",
" Fungi"," Ichthyosporea"," Opisthokonta_X",
" Apicomplexa"," Chrompodellids"," Ciliophora"," Dinoflagellata"," Alveolata_X",
" Cercozoa",
" Bigyra"," Gyrista"," Stramenopiles_X",
" Eukaryota_X","Others",""
))
fig3_compo_rar_plot <- ggplot(complet_plot_df, aes(x = Abundance_per_Subdivision, y = fct_rev(Depth_sampling), fill = Subdivision)) +
geom_bar(stat = "identity", position = "stack") +
scale_fill_manual(values = col_vector_complet, guide = guide_legend(ncol = 1)) +
theme_minimal(base_size = 9) + labs(x = "Relative abundance (%)", y = "Depth") + theme(panel.grid = element_blank())
fig3_combined <- fig3_obs_plot + fig3_read_plot + fig3_compo_rs_plot + fig3_compo_rar_plot + plot_layout(ncol = 4,nrow=1, heights = c(1,1,1,1))
fig3_combined
ggsave(filename = "Outputs/Figure3_rarefied_composition.pdf", plot = fig3_combined,
width = 250, height = 200, units = "mm", dpi = 600)
#All aggregate at the genus level for homogeneity
#microeukaryote community: ps_rarefied / ps_alpha
ps_genus <- aggregate_taxa(ps_alpha, 'Genus')
#resting stage subcommunity: ps_rs_rar
physeq_rs <- prune_taxa(taxa_names(ps_alpha) %in% asv_rs_all, ps_alpha)
physeq_rs_genus <- aggregate_taxa(physeq_rs, 'Genus')
#foram: foram_df
foram_df$Sample <- sub("_F$", "", foram_df$Sample)
rownames(foram_df) <- foram_df$Sample
foram_df[is.na(foram_df)] <- 0
foram_sup0 <- foram_df %>%
filter(Sum_genus > 0) #remove 10 samples with 0 individual found
foram <- foram_sup0[,c(9:33)]
#Microeuk
microeuk_df <- t(as.data.frame(otu_table(ps_genus)))
rs_df <- t(as.data.frame(otu_table(physeq_rs_genus)))
microeuk_df <- ifelse(microeuk_df > 0, 1, 0)
rs_df <- ifelse(rs_df > 0, 1, 0)
mat_microeuk <- vegdist(microeuk_df, method = "jaccard")
mat_rs <- vegdist(rs_df, method = "jaccard")
mat_foram <- vegdist(foram, method = "jaccard")
pcoa_microeuk <- wcmdscale(mat_microeuk, k=2, eig = TRUE)
pcoa_rs <- wcmdscale(mat_rs, k=2, eig = TRUE)
pcoa_foram <- wcmdscale(mat_foram, k=2, eig = TRUE)
point_microeuk <- as.data.frame(pcoa_microeuk$points)
point_rs <- as.data.frame(pcoa_rs$points)
point_foram <- as.data.frame(pcoa_foram$points)
point_microeuk$unit <- sample_data(ps_genus)$Part
point_rs$unit <- sample_data(physeq_rs_genus)$Part
point_foram$unit <- foram_sup0$Unit
plot_microeuk <- ggplot(data = point_microeuk, aes(x = Dim1, y = Dim2, color = unit)) +
geom_point(size = 2) +
geom_ysidedensity(aes(y=Dim2, yfill = unit,), alpha = 0.4) +
geom_xsidedensity(aes(x=Dim1, xfill = unit), alpha = 0.4) +
scale_xfill_manual(values = Col_unit)+
scale_yfill_manual(values = Col_unit) +
scale_color_manual(values = Col_unit)+
xlab(paste(format((pcoa_microeuk$eig[1]*10), digit = 3),"%")) +
ylab(paste(format((pcoa_microeuk$eig[2]*10), digit = 3),"%"))+
labs(title = "Microeukaryote community")+
theme_classic() +
theme(ggside.panel.scale = .2) +
theme_ggside_void()
plot_rs <- ggplot(data = point_rs, aes(x = Dim1, y = Dim2, color = unit)) +
geom_point(size = 2) +
geom_ysidedensity(aes(y=Dim2, yfill = unit,), alpha = 0.4) +
geom_xsidedensity(aes(x=Dim1, xfill = unit), alpha = 0.4) +
scale_color_manual(values = Col_unit)+
scale_xfill_manual(values = Col_unit)+
scale_yfill_manual(values = Col_unit) +
xlab(paste(format((pcoa_rs$eig[1]*10), digit = 3),"%")) +
ylab(paste(format((pcoa_rs$eig[2]*10), digit = 3),"%"))+
labs(title = "Resting stage")+
theme_classic() +
theme(ggside.panel.scale = .2) +
theme_ggside_void()
plot_foram <- ggplot(data = point_foram, aes(x = Dim1, y = Dim2, color = unit)) +
geom_point(size = 2) +
geom_ysidedensity(aes(y=Dim2, yfill = unit,), alpha = 0.4) +
geom_xsidedensity(aes(x=Dim1, xfill = unit), alpha = 0.4) +
scale_color_manual(values = Col_unit)+
scale_xfill_manual(values = Col_unit)+
scale_yfill_manual(values = Col_unit) +
xlab(paste(format((pcoa_foram$eig[1]*10), digit = 3),"%")) +
ylab(paste(format((pcoa_foram$eig[2]*10), digit = 3),"%"))+
labs(title = "Foraminifera")+
theme_classic() +
theme(ggside.panel.scale = .2) +
theme_ggside_void()
combined_pcoa <- plot_microeuk + plot_rs + plot_foram + plot_layout(guides = "collect") & theme(legend.position = "bottom")
combined_pcoa
ggsave(filename = "Outputs/Figure4_pcoax3.pdf", plot = combined_pcoa,
width = 200, height = 85, units = "mm", dpi = 600)
#First need interpolation to compare biological and environmental data at the same depth
env <- env_df %>% mutate(across(c(UB, VS, Clay, Silt, Sand, Ni, Al, COP_perc, NT_perc),
~as.numeric(gsub(",", ".", .))))
variables_to_interpolate <- c("UB", "VS", "Ni", "Al", "COP_perc", "NT_perc", "Clay", "Silt", "Sand")
env_long_status <- env %>%
pivot_longer(cols = all_of(variables_to_interpolate), names_to = "variable", values_to = "value") %>%
mutate(status = ifelse(is.na(value), "interpolated", "measured")) %>%
select(Codification, Depth, variable, status)
interpolate_full_cm <- function(df, variables) {
full_depth <- seq(min(df$Depth, na.rm = TRUE),
max(df$Depth, na.rm = TRUE),
by = 0.5)
df_full <- data.frame(Depth = full_depth)
for (var in variables) {
interp_values <- approx(
x = df$Depth[!is.na(df[[var]])],
y = df[[var]][!is.na(df[[var]])],
xout = full_depth,
method = "linear",
rule = 2
)$y
df_full[[var]] <- interp_values
}
return(df_full)
}
df_interp <- interpolate_full_cm(env, variables_to_interpolate)
#visual check
env_measured_long <- env %>%
pivot_longer(cols = all_of(variables_to_interpolate),
names_to = "variable",
values_to = "measured_value") %>%
filter(!is.na(measured_value))
df_long <- df_interp %>%
pivot_longer(cols = all_of(variables_to_interpolate),
names_to = "variable",
values_to = "value") %>%
left_join(env_measured_long,
by = c("Depth", "variable")) %>%
mutate(status = ifelse(!is.na(measured_value),
"measured",
"interpolated"))
ggplot(df_long, aes(x = Depth, y = value)) +
geom_line(color = "black") +
geom_point(aes(color = status), size = 2) +
scale_y_reverse() +
facet_wrap(~variable, scales = "free_x", nrow = 1) +
scale_color_manual(values = c("measured" = "black",
"interpolated" = "red")) +
labs(title = "Measured vs interpolated",
x = "Value",
y = "Depth (cm)") +
theme_minimal(base_size = 8) +
coord_flip()
#Hierarchical partitioning
hp_function <- function(otutable, env_data) {
env_data <- env_data[match(rownames(otutable), env_data$SampleID), ]
otu_pa <- ifelse(otutable > 0, 1, 0)
otu.jacc <- vegdist(otu_pa, method = "jaccard")
env.list <- list(
Grain_size = env_data[,c("Clay","Sand")],
Metal = env_data[,c("Ni","Al")],
OM = env_data[,c("COP_perc","NT_perc")],
Sources = env_data["UB"],
Depth = env_data["Depth"],
Unit = env_data["Unite"]
)
dbRDA.vp <- rdacca.hp(
otu.jacc,
env.list,
method = "dbRDA",
var.part = TRUE,
type = "adjR2"
)
summary(dbRDA.vp)
barplot_hp(dbRDA.vp, col.fill = "var")
return(dbRDA.vp)
}
env_inter <- df_interp %>% left_join(env_df[, c("SampleID","Depth","Unite")], by = "Depth")
env_inter$Unite <- as.factor(env_inter$Unite)
env_microeuk <- env_inter %>% filter(SampleID %in% rownames(sample_data(ps_genus)))
env_foram <- env_inter %>% filter(SampleID %in% foram_df$Sample[foram_df$Sum_genus > 0])
micro_all <- t(as.data.frame(otu_table(ps_genus)))
micro_rs <- t(as.data.frame(otu_table(physeq_rs_genus)))
plot1_microeuk <- hp_function(micro_all, env_microeuk)
plot2_rs_microeuk <- hp_function(micro_rs, env_microeuk)
plot3_foram <- hp_function(foram, env_foram)
# total explained variance for each group of parameter
make_hp_table <- function(hp_obj) {
df <- data.frame(
Factor = rownames(hp_obj$Hier.part),
Perc_total = hp_obj$Hier.part[,"I.perc(%)"]
)
return(df)
}
# Tables
hp_table_microeuk <- make_hp_table(plot1_microeuk)
hp_table_rs_microeuk <- make_hp_table(plot2_rs_microeuk)
hp_table_foram <- make_hp_table(plot3_foram)
plot_hp <- function(df, title) {
df$Factor <- factor(df$Factor, levels = c("Unit","Depth","Metal","Sources", "OM","Grain_size")) # same order
ggplot(df, aes(x = Factor, y = Perc_total)) +
geom_bar(stat = "identity", fill = "black") +
coord_flip() +
labs(x = "Factor", y = "Total contribution (%)", title = title) +
theme_bw() +
theme(
legend.position = "none",
text = element_text(size = 11),
axis.line = element_line(color = "black"),
panel.border = element_blank(),
panel.background = element_blank()
) +
scale_y_continuous(limits = c(0, 45)) # même échelle
}
p1 <- plot_hp(hp_table_microeuk, "Microeukaryote")
p2 <- plot_hp(hp_table_rs_microeuk, "Resting stage")
p3 <- plot_hp(hp_table_foram, "Foraminifera")
# Combine
combined_hp_plot <- p1 + p2 + p3 + plot_layout(ncol = 3, guides = "collect")
combined_hp_plot
ggsave(filename = "Outputs/Figure4B_hpx3.pdf", plot = combined_hp_plot,
width = 200, height = 70, units = "mm", dpi = 600)
# Prepare foram data
foram_df[is.na(foram_df)] <- 0
rownames(foram_df) <- foram_df$Sample
foram_div <- foram_df[, c(9:33)] # select relevant columns (species presence/absence)
# Identify non-random distribution patterns using runs test
# Convert abundance to presence/absence
abundance_data <- foram_div
# Identify ubiquitous taxa present in all samples
genus_all <- colnames(abundance_data)[colSums(abundance_data) == nrow(abundance_data)]
# Remove these columns temporarily to test only the variable taxa
abundance_data2 <- abundance_data[, !(colnames(abundance_data) %in% genus_all)]
# Identify taxa with significantly non-random distributions (p < 0.05)
significant_species <- c()
for (i in 1:ncol(abundance_data2)) {
species_data <- abundance_data2[, i]
test_result <- runs.test(as.factor(species_data > 0), alternative = "less")
if (test_result$p.value < 0.05) {
significant_species <- c(significant_species, colnames(abundance_data2)[i])
}
}
# Subset abundance matrix to keep significant + ubiquitous species
subset_abundance_data <- abundance_data[, colnames(abundance_data) %in% c(significant_species, genus_all)]
rownames(subset_abundance_data) <- as.factor(foram_df$Depth) # use depth as row labels
# Convert to long format for ggplot heatmap
abundance_data_long <- subset_abundance_data %>%
as.data.frame() %>%
rownames_to_column("Row") %>%
pivot_longer(cols = -Row, names_to = "Column", values_to = "Value")
# Order rows (depths) and columns (taxa)
abundance_data_long$Row <- factor(abundance_data_long$Row, levels = rev(rownames(subset_abundance_data)))
abundance_data_long$Column <- factor(abundance_data_long$Column, levels = c(
"Ammonia","Quinqueloculina", "Nonion", "Haynesina",
"Triloculina","Spiroloculina","Wiesnerella","Eggerella",
"Amphistegina","Planorbulinella"
))
# Color scale
col_fun <- colorRamp2(c(-1, 0, 1), c("#662141", "#FBFBFB", "#524657"))
# Plot heatmap of selected foraminiferal genera
fig5_foram <- ggplot(abundance_data_long, aes(x = Column, y = Row, fill = Value)) +
geom_tile(color = "white", linewidth = 0.1) +
scale_fill_gradientn(colors = col_fun(seq(min(abundance_data_long$Value), max(abundance_data_long$Value), length.out = 100))) +
labs(fill = "Foraminifera presence") +
theme_minimal(base_size = 10) +
theme(
axis.text.x = element_text(angle = 90, vjust = 0.5, size = 10),
axis.text.y = element_text(size = 7),
axis.title = element_blank(),
legend.position = "none"
)
### Barpolts of filtered microeukaryote genera
# Collapse ASVs to genus level: ps_rs_rarefied
physeq_rs_rar_genus <- aggregate_taxa(ps_rs_rarefied, 'Genus')
# Relative abundance per sample
physeq_rs_genus_rel <- transform_sample_counts(physeq_rs_rar_genus, function(x) x * 100 / sum(x))
# Filter genera: present in >4 samples
physeq_rs_genus_rel_n4 <- filter_taxa(
physeq_rs_genus_rel,
function(x) sum(x > 0) > ((1/56*4)*length(x)),
TRUE
)
# Convert to long format for tests
genus_n4 <- psmelt(physeq_rs_genus_rel_n4)
# Aggregate data by genus, depth, and stratigraphic unit (Part2)
df_genus <- aggregate(
Abundance ~ Sample + Genus + OTU + Unit + Depth_sampling,
data = genus_n4,
sum
)
# Wilcoxon non-parametric analysis
genus.all <- levels(factor(df_genus$OTU))
tmp <- df_genus[-which(df_genus$Abundance==0),] # remove null values
genus.non.null <- table(tmp$OTU)
#table(tmp$OTU, tmp$Unit) # non null samples per genus and periods
# We want to test differences between periods III and IV (shovel vs. pristine); II and III (tractor vs. shovel); I and II (Regulation effect)
df.test <- NULL
for(i in 1:length(genus.all)){
# Select a genius
genus.i <- df_genus[which(df_genus$OTU == genus.all[i]),]
# define the periods
genus.i.period.1 <- genus.i[which(genus.i$Unit == "I"),]
genus.i.period.2 <- genus.i[which(genus.i$Unit == "II"),]
genus.i.period.3 <- genus.i[which(genus.i$Unit == "III"),]
genus.i.period.4 <- genus.i[which(genus.i$Unit == "IV"),]
# Proportion of non null samples in each period
prop.non.null <- tapply(genus.i$Abundance, genus.i$Unit, function(x)length(which(x==0))/length(x))
# Proportion of non null samples in all sample
prop.non.null.tot <- length(which(genus.i$Abundance==0))/length(genus.i$Abundance)
# Average abundance in each period
avg.abd <- tapply(genus.i$Abundance, genus.i$Unit, mean)
#---- test 1 (shovel vs. pristine)
test1 <- wilcox.test(genus.i.period.3$Abundance, genus.i.period.4$Abundance)
rel.chge1 <- ((avg.abd[3]+1) - (avg.abd[4]+1))/(avg.abd[4]+1)*100
pval1 <- test1$p.value
#---- test 2 (tractor vs. shovel)
test2 <- wilcox.test(genus.i.period.2$Abundance, genus.i.period.3$Abundance)
rel.chge2 <- ((avg.abd[2]+1) - (avg.abd[3]+1))/(avg.abd[3]+1)*100
pval2 <- test2$p.value
#---- test 3 (Regulation effect)
test3 <- wilcox.test(genus.i.period.1$Abundance, genus.i.period.2$Abundance)
rel.chge3 <- ((avg.abd[1]+1) - (avg.abd[2]+1))/(avg.abd[2]+1)*100
pval3 <- test3$p.value
# Store results
out <- c(genus.all[i], prop.non.null, prop.non.null.tot, avg.abd, rel.chge1, pval1, rel.chge2, pval2, rel.chge3, pval2)
df.test <- rbind(df.test, out)
}
df.test <- as.data.frame(df.test)
colnames(df.test) <- c("genus",
"prop0.I", "prop0.II", "prop0.III", "prop0.IV","prop0.tot",
"avgAbd.I", "avgAbd.II", "avgAbd.III", "avgAbd.IV",
"rel.chge.test1", "pval.test1", "rel.chge.test2", "pval.test2", "rel.chge.test3", "pval.test3")
df.test[,-1] <- apply(df.test[,-1], 2, function(x)round(as.numeric(x), 3))
rownames(df.test) <- NULL
# FDR Benjamini-Hochberg
df.test$pval.test1.fdr <- p.adjust(df.test$pval.test1, method = "BH")
df.test$pval.test2.fdr <- p.adjust(df.test$pval.test2, method = "BH")
df.test$pval.test3.fdr <- p.adjust(df.test$pval.test3, method = "BH")
#--- Some summary statistics
tmp <- as.matrix(df.test[c("rel.chge.test1", "rel.chge.test2", "rel.chge.test3")])
rownames(tmp) <- df.test$genus
prop.signif <- apply(df.test[c("pval.test1.fdr", "pval.test2.fdr", "pval.test3.fdr")], 2, function(x)length(which(x<0.1))/length(x)) # proportion of species with significant effects
prop.decline <- apply(tmp, 2, function(x)length(which(x<0))/length(x)) # proportion of species declining regardless of significance
prop.increase <- apply(tmp, 2, function(x)length(which(x>0))/length(x)) # proportion of species increasing regardless of significance
n.signif <- apply(df.test[c("pval.test1.fdr", "pval.test2.fdr", "pval.test3.fdr")], 2, function(x) length(which(x < 0.1)))
n.decline <- apply(tmp, 2, function(x) length(which(x < 0)))
n.increase <- apply(tmp, 2, function(x) length(which(x > 0)))
# Créer des matrices logiques pour significativité
sig1 <- df.test$pval.test1.fdr < 0.1
sig2 <- df.test$pval.test2.fdr < 0.1
sig3 <- df.test$pval.test3.fdr < 0.1
# Nombre de genres en déclin significatif
n.decline.sig <- c(
sum(tmp[,1] < 0 & sig1),
sum(tmp[,2] < 0 & sig2),
sum(tmp[,3] < 0 & sig3)
)
# Proportion de genres en déclin significatif
prop.decline.sig <- n.decline.sig / nrow(df.test)
# Nombre de genres en augmentation significative
n.increase.sig <- c(
sum(tmp[,1] > 0 & sig1, na.rm = TRUE),
sum(tmp[,2] > 0 & sig2, na.rm = TRUE),
sum(tmp[,3] > 0 & sig3, na.rm = TRUE)
)
# Proportion de genres en augmentation significative
prop.increase.sig <- n.increase.sig / nrow(df.test)
#--- add Genus
taxo <- select(genus_n4, "Genus", "OTU")
colnames(df.test)[1] <- "OTU"
df.test2 <- merge(df.test,taxo, by = "OTU")
df.test2 <- df.test2 %>% distinct(OTU, .keep_all = TRUE)
# --- Filter significant genera ---
df_filtered <- df.test2 %>%
filter(
pval.test1.fdr < 0.05 |
pval.test2.fdr < 0.05 |
pval.test3.fdr < 0.05 |
prop0.tot < 0.25)
selection_genera <- df_filtered$OTU
genera_filtered <- df_genus %>%
filter(OTU %in% selection_genera)
genera_filtered$Depth_sampling <- as.numeric(genera_filtered$Depth_sampling) # 23 genera
# Visualisation of some of these genera (based on theur temporal distribution and bibliographic information)
genera_selected <- c(" Desmodesmus"," Amoebogregarina", " Colpodella",
" Fungi_XXXX", " Selenidium1"," Paracercomonas", " Scrippsiella",
" Eocercomonas"," Polyplicarium")
genera_figure <- df_genus %>% filter(Genus %in% genera_selected)
genera_figure$Genus <- factor(genera_figure$Genus,
levels = c(" Paracercomonas", " Amoebogregarina"," Colpodella"," Scrippsiella",
" Selenidium1"," Eocercomonas"," Desmodesmus"," Polyplicarium",
" Fungi_XXXX" ))
col_vector_genus <- c("#FAACEB","#6376DB","#01579E","#7DD9F8",
"#6376DB","#FAACEB","#FFA54B","#6376DB",
"#824600")
genera_figure$Depth_sampling <- as.numeric(genera_figure$Depth_sampling)
fig5_genus <- ggplot(genera_figure, aes(x = -Depth_sampling, y = Abundance, fill = Genus)) +
geom_vline(aes(xintercept = -41), linetype = "dashed", color = "grey", size = 0.5) +
geom_vline(aes(xintercept = -93), linetype = "dashed", color = "grey", size = 0.5) +
geom_vline(aes(xintercept = -137), linetype = "dashed", color = "grey", size = 0.5) +
geom_bar(stat = "identity", position = "stack") +
scale_fill_manual(values = col_vector_genus, guide = guide_legend(ncol = 1)) +
geom_point(
data = subset(genera_figure, Abundance == 0),
aes(x = -Depth_sampling, y = 0), # y = 0 to highlight absence in the sample
shape = 21,
size = 1,
fill = "white"
) +
facet_grid(. ~ Genus, scales = "free_x") +
theme_pubr(base_size = 8) +
labs(
x = "Depth (cm)",
y = "Relative Abundance among resting stage taxa"
) +
theme(
axis.text.x = element_text(angle = 0, hjust = 1),
strip.text.y = element_text(angle = 0, size = 10),
legend.position = "none",
panel.grid.minor.y = element_blank()
) +
coord_flip()
#Panel of Nickel concentration along the core
# Define a helper function to linearly interpolate missing values (to create a continuous visualisation)
interpolate_na <- function(df, variables) {
df <- df %>%
mutate(across(
all_of(variables),
~ approx(
Depth[!is.na(.)],
.[!is.na(.)],
xout = Depth,
method = "linear",
rule = 2
)$y
)) %>%
ungroup()
return(df)
}
# --- Apply interpolation to selected variables ---
variables_to_interpolate <- "Ni" #possible to select several variables
df_interpolated <- interpolate_na(env_df, variables_to_interpolate)
df_interpolated <- interpolate_na(env_df, variables_to_interpolate)
# --- Plot Nickel concentration as a vertical gradient ---
fig5_nickel <- ggplot(df_interpolated, aes(x = as.factor(rev(Depth)) , y = 1, fill = Ni)) +
geom_tile() +
scale_fill_gradientn(colours = c("#023436", "#FFC65C", "#FF5416")) +
labs(x = "Depth (cm)", y = NULL, fill = "Nickel (mg kg -1)") +
coord_flip() +
theme_minimal() +
theme(
axis.text.x = element_text(angle = 90, vjust = 0.5, size = 6),
axis.title.y = element_blank(),
axis.text.y = element_text(size = 4),
panel.grid = element_blank(),
legend.position = "bottom"
)
panel_genus <- fig5_genus / plot_spacer() + plot_layout(heights = c(4,0.8))
fig5_combined <- fig5_nickel + fig5_foram + panel_genus + plot_layout(ncol = 3,nrow=1, width = c(0.2,2,3))
fig5_combined
ggsave(filename = "Outputs/Figure5_genus.pdf", plot = fig5_combined,
width = 200, height = 300, units = "mm", dpi = 600)