wine rpb2 ok

real_samples.Rmd

@@ -81,6 +81,7 @@ scp orue@genotoul.toulouse.inra.fr:/work/frogsfungi/FungiPubli/Real_mock/METABAR
 scp orue@genotoul.toulouse.inra.fr:/work/frogsfungi/FungiPubli/Real_mock/METABARFOOD/REAL/results/DADA2_FROGS/RPB2/filters.fasta .
 ##########################
 
+biom_to_tsv.py --input-biom affiliation.biom --output-tsv affiliation.tsv --input-fasta filters.fasta
 otu_filters.py --input-biom affiliation.biom --input-fasta filters.fasta --contaminant /db/frogs_databanks/assignation/Unite_Fungi_8.2_20200204/Unite_Fungi_8.2_20200204.fasta --output-biom 1.biom --output-fasta 1.fasta --nb-cpus 4
 otu_filters.py --input-biom 1.biom --input-fasta 1.fasta --contaminant /db/frogs_databanks/assignation/SILVA_132_LSU/SILVA_132_LSU.fasta --nb-cpus 4 --output-biom 2.biom --output-fasta 2.fasta
 otu_filters.py --input-biom 2.biom --input-fasta 2.fasta --contaminant /db/frogs_databanks/assignation/silva_138_SSU/silva_138_SSU.fasta --nb-cpus 4 --output-biom 3.biom --output-fasta 3.fasta 
@@ -96,15 +97,15 @@ biom_to_tsv.py --input-biom affiliation-filtered.biom --output-tsv affiliation-f
 
 affiliation_OTU.py --input-fasta affiliation-filtered.fasta --input-biom affiliation-filtered.biom --nb-cpus 8 --output-biom affiliation.biom --summary affiliation.html --reference D1D2.fasta
 
-biom_to_tsv.py --input-biom affiliation.biom --output-tsv affiliation.tsv
+biom_to_tsv.py --input-biom affiliation.biom --output-tsv affiliation2.tsv --input-fasta affiliation-filtered.fasta
 
 head -n 1 4.tsv > final.tsv
-awk -F'\t' '{ if ($4 < 80 && $5 > 95 && length($8 > 400)) { print } }' affiliation.tsv >> final.tsv
+awk -F'\t' '{ if ($4 < 80 && $5 > 95 && length($8 > 400)) { print } }' affiliation2.tsv >> final.tsv
 
 awk -F'\t' '{print $8}' <(grep -v "^#" final.tsv) > to_keep.lst
 
 head -n 1 4.tsv > affiliation-filtered-final.tsv
-grep -f to_keep.lst affiliation-filtered.tsv >> affiliation-filtered-final.tsv
+grep -f to_keep.lst affiliation.tsv >> affiliation-filtered-final.tsv
 ```
 
 
@@ -278,7 +279,7 @@ saveRDS(physeq_rpb2_final,"REAL_MEAT/RPB2_final.rds")
 #if (!file.exists("REAL_MEAT/meat_final.rds")){
 meat_all_final <- merge_phyloseq(physeq_its1_final, physeq_its2_final, physeq_d1d2_final, physeq_rpb2_final)
 sample_data(meat_all_final)$Marker <- factor(sample_data(meat_all_final)$Marker, levels=c("ITS1","ITS2","D1D2","RPB2"))  
-saveRDS(meat_all_final,"REAL_CHEESE/meat_final.rds")
+saveRDS(meat_all_final,"REAL_WINE/meat_final.rds")
 #}else{
 #  meat_all_final <- readRDS("REAL_MEAT/meat_final.rds") 
 #}
@@ -408,6 +409,9 @@ awk -F'\t' '{print $8}' <(grep -v "^#" final.tsv) > to_keep.lst
 
 head -n 1 4.tsv > affiliation-filtered-final.tsv
 grep -f to_keep.lst affiliation-filtered.tsv >> affiliation-filtered-final.tsv
+
+# pour avoir les séquences à rajouter à to_remove :
+grep -v -f to_keep.lst affiliation.tsv | grep -v "^#" | awk -F'\t' '{print $8}'
 ```
 
 
@@ -987,10 +991,10 @@ scp orue@genologin.toulouse.inra.fr:/work/frogsfungi/FungiPubli/Real_mock/METABA
 scp orue@genologin.toulouse.inra.fr:/work/frogsfungi/FungiPubli/Real_mock/METABARFOOD/WINE_REAL/results/DADA2_FROGS/D1D2/affiliation.biom REAL_WINE/D1D2.biom
 scp orue@genologin.toulouse.inra.fr:/work/frogsfungi/FungiPubli/Real_mock/METABARFOOD/WINE_REAL/results/DADA2_FROGS/RPB2/affiliation.biom REAL_WINE/RPB2.biom
 
-#scp orue@genologin.toulouse.inra.fr:/work/frogsfungi/FungiPubli/Real_mock/METABARFOOD/BREAD_REAL/results/DADA2_FROGS/ITS1/affiliation.tsv REAL_BREAD/ITS1.tsv
-#scp orue@genologin.toulouse.inra.fr:/work/frogsfungi/FungiPubli/Real_mock/METABARFOOD/BREAD_REAL/results/DADA2_FROGS/ITS2/affiliation.tsv REAL_BREAD/ITS2.tsv
-#scp orue@genologin.toulouse.inra.fr:/work/frogsfungi/FungiPubli/Real_mock/METABARFOOD/BREAD_REAL/results/DADA2_FROGS/D1D2/affiliation.tsv REAL_BREAD/D1D2.tsv
-#scp orue@genologin.toulouse.inra.fr:/work/frogsfungi/FungiPubli/Real_mock/METABARFOOD/BREAD_REAL/results/DADA2_FROGS/RPB2/affiliation.tsv REAL_BREAD/RPB2.tsv
+scp orue@genologin.toulouse.inra.fr:/work/frogsfungi/FungiPubli/Real_mock/METABARFOOD/BREAD_REAL/results/DADA2_FROGS/ITS1/affiliation.tsv REAL_BREAD/ITS1.tsv
+scp orue@genologin.toulouse.inra.fr:/work/frogsfungi/FungiPubli/Real_mock/METABARFOOD/BREAD_REAL/results/DADA2_FROGS/ITS2/affiliation.tsv REAL_BREAD/ITS2.tsv
+scp orue@genologin.toulouse.inra.fr:/work/frogsfungi/FungiPubli/Real_mock/METABARFOOD/BREAD_REAL/results/DADA2_FROGS/D1D2/affiliation.tsv REAL_BREAD/D1D2.tsv
+scp orue@genologin.toulouse.inra.fr:/work/frogsfungi/FungiPubli/Real_mock/METABARFOOD/BREAD_REAL/results/DADA2_FROGS/RPB2/affiliation.tsv REAL_BREAD/RPB2.tsv
 
 #scp orue@genologin.toulouse.inra.fr:/work/frogsfungi/FungiPubli/Real_mock/METABARFOOD/CHEESE_REAL/results/DADA2_FROGS/ITS1/multiaff.tsv REAL_CHEESE/ITS1_multiaff.tsv
 #scp orue@genologin.toulouse.inra.fr:/work/frogsfungi/FungiPubli/Real_mock/METABARFOOD/CHEESE_REAL/results/DADA2_FROGS/ITS2/multiaff.tsv REAL_CHEESE/ITS2_multiaff.tsv
@@ -1059,6 +1063,7 @@ if (!file.exists("REAL_WINE/RPB2.rds")) {
 }
 ```
 
+
 ```{r, eval=T}
 if (!file.exists("REAL_WINE/wine.rds")){
   wine_all <- merge_phyloseq(physeq_its1, physeq_its2, physeq_d1d2, physeq_rpb2)
@@ -1136,36 +1141,77 @@ x <- list(
   )
 ggVennDiagram(x,label_alpha = 0) + 
   scale_fill_gradient(low = "#F4FAFE", high = "#4981BF") 
+  
+
+
+
+```
+
+### Common species
+
+```{r, eval=T}
+x <- list(
+  ITS1 = as_tibble(tax_table(physeq_its1))$Species %>% as.vector(), 
+  ITS2 = as_tibble(tax_table(physeq_its2))$Species %>% as.vector(),
+  D1D2 = as_tibble(tax_table(physeq_d1d2))$Species %>% as.vector(),
+  RPB2 = as_tibble(tax_table(physeq_rpb2))$Species %>% as.vector()
+  )
+ggVennDiagram(x,label_alpha = 0) + 
+  scale_fill_gradient(low = "#F4FAFE", high = "#4981BF") 
 ```
 
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 ## Manual curation {.tabset}
 
-```{r, eval=F}
-tax_table(physeq_its1) <- t
-keptTaxa <- setdiff(taxa_names(physeq_its1), to_remove)
-physeq_its1_final <- prune_taxa(keptTaxa, physeq_its1)
-saveRDS(physeq_its1_final,"REAL_BREAD/ITS1_final.rds")
+```{r, eval=T}
+#physeq_its1_final <- curation_wine_its1(physeq_its1)
+#saveRDS(physeq_its1_final,"REAL_WINE/ITS1_final.rds")
+
+#physeq_its2_final <- curation_wine_its2(physeq_its2)
+#saveRDS(physeq_its2_final,"REAL_WINE/ITS2_final.rds")
+
+#physeq_d1d2_final <- curation_wine_d1d2(physeq_d1d2)
+#saveRDS(physeq_d1d2_final,"REAL_WINE/D1D2_final.rds")
+
+physeq_rpb2_final <- curation_wine_rpb2(physeq_rpb2)
+saveRDS(physeq_rpb2_final,"REAL_WINE/RPB2_final.rds")
 
 ```
 
 
-```{r, eval=F}
-if (!file.exists("REAL_MEAT/bread_final.rds")){
-  bread_all_final <- merge_phyloseq(physeq_its1_final, physeq_its2, physeq_d1d2, physeq_rpb2)
-  sample_data(bread_all_final)$Marker <- factor(sample_data(bread_all_final)$Marker, levels=c("ITS1","ITS2","D1D2","RPB2"))  
-  saveRDS(bread_all_final,"REAL_MEAT/bread_final.rds")
-}else{
-  bread_all_final <- readRDS("REAL_MEAT/bread_final.rds") 
-}
+```{r, eval=T}
+#if (!file.exists("REAL_WINE/wine_final.rds")){
+wine_all_final <- merge_phyloseq(physeq_its1, physeq_its2, physeq_d1d2, physeq_rpb2_final)
+sample_data(wine_all_final)$Marker <- factor(sample_data(wine_all_final)$Marker, levels=c("ITS1","ITS2","D1D2","RPB2"))  
+saveRDS(wine_all_final,"REAL_WINE/wine_final.rds")
+#}else{
+#  wine_all_final <- readRDS("REAL_WINE/wine_final.rds") 
+#}
 ```
 
 
 ### Sequencing depth {.tabset}
 
-```{r, eval=F}
-df <- sample_data(bread_all_final) %>% as("data.frame") %>% 
+```{r, eval=T}
+df <- sample_data(wine_all_final) %>% as("data.frame") %>% 
   as_tibble(rownames = "SampleID") %>% 
-  mutate(Final   = sample_sums(meat_all_final)) %>% 
+  mutate(Final   = sample_sums(wine_all_final)) %>% 
   rename(Initial = Reads)
 ggplot(df %>% pivot_longer(cols = c(Initial, Final), names_to = "Step", values_to = "Reads"), 
        aes(x = SampleID, y = Reads, fill=Step)) + 
@@ -1179,32 +1225,32 @@ ggplot(df %>% pivot_longer(cols = c(Initial, Final), names_to = "Step", values_t
 
 ### Compositions
 
-```{r, eval=F}
-p <- plot_composition(physeq = bread_all_final, taxaRank1 = "Kingdom", taxaSet1 = "Fungi", taxaRank2 = "Species", numberOfTaxa = 22, x = "Sample")
+```{r, eval=T}
+p <- plot_composition(physeq = wine_all_final, taxaRank1 = "Kingdom", taxaSet1 = "Fungi", taxaRank2 = "Species", numberOfTaxa = 22, x = "Sample")
 p + facet_grid(". ~ Marker", scales = "free_x", space = "free")
 
 ```
 
 ### Richness
 
-```{r, eval=F}
-p <- plot_richness(physeq = bread_all_final, x = "Marker", color = "Marker", shape = NULL, title = "Alpha diversity graphics", measures = c("Observed", "Chao1", "ACE", "Shannon", "Simpson", "InvSimpson"))
+```{r, eval=T}
+p <- plot_richness(physeq = wine_all_final, x = "Marker", color = "Marker", shape = NULL, title = "Alpha diversity graphics", measures = c("Observed", "Chao1", "ACE", "Shannon", "Simpson", "InvSimpson"))
 p + geom_boxplot() + NULL
 ```
 
 ### $\beta$ diversity
 
-```{r, eval=F}
-beta.dist <- distance(bread_all_final, method = "bray")
-ord <- ordinate(bread_all_final, method = "MDS", distance = beta.dist)
-p <- plot_ordination(physeq = bread_all_final, ordination = ord, type = "samples", axes = c(1, 2), color = "Marker", shape = NULL, label = NULL, title = "Samples ordination graphic, bray-curtis distance")
+```{r, eval=T}
+beta.dist <- distance(wine_all_final, method = "bray")
+ord <- ordinate(wine_all_final, method = "MDS", distance = beta.dist)
+p <- plot_ordination(physeq = wine_all_final, ordination = ord, type = "samples", axes = c(1, 2), color = "Marker", shape = NULL, label = NULL, title = "Samples ordination graphic, bray-curtis distance")
 p <- p + stat_ellipse(aes_string(group = "Marker"))
 p + theme_bw()
 ```
 
 ### Common families
 
-```{r, eval=F}
+```{r, eval=T}
 x <- list(
   ITS1 = as_tibble(tax_table(physeq_its1_final))$Family %>% as.vector(), 
   ITS2 = as_tibble(tax_table(physeq_its2_final))$Family %>% as.vector(),
@@ -1217,7 +1263,7 @@ ggVennDiagram(x,label_alpha = 0) +
 
 ### Common genus
 
-```{r, eval=F}
+```{r, eval=T}
 x <- list(
   ITS1 = as_tibble(tax_table(physeq_its1_final))$Genus %>% as.vector(), 
   ITS2 = as_tibble(tax_table(physeq_its2_final))$Genus %>% as.vector(),
@@ -1227,3 +1273,16 @@ x <- list(
 ggVennDiagram(x,label_alpha = 0) + 
   scale_fill_gradient(low = "#F4FAFE", high = "#4981BF") 
 ```
+
+### Common species
+
+```{r, eval=T}
+x <- list(
+  ITS1 = as_tibble(tax_table(physeq_its1_final))$Species %>% as.vector(), 
+  ITS2 = as_tibble(tax_table(physeq_its2_final))$Species %>% as.vector(),
+  D1D2 = as_tibble(tax_table(physeq_d1d2_final))$Species %>% as.vector(),
+  RPB2 = as_tibble(tax_table(physeq_rpb2_final))$Species %>% as.vector()
+  )
+ggVennDiagram(x,label_alpha = 0) + 
+  scale_fill_gradient(low = "#F4FAFE", high = "#4981BF") 
+```