Skip to content

Commit

Permalink
multiqc report now shows unassigned ASVs
Browse files Browse the repository at this point in the history
  • Loading branch information
@a4000
a4000 committed Oct 10, 2024
1 parent a74b91a commit 0cd095b
Showing 1 changed file with 20 additions and 8 deletions.
28 changes: 20 additions & 8 deletions bin/amplicon_report.Rmd
View file
Original file line number Diff line number Diff line change
Expand Up @@ -167,6 +167,7 @@ if (any(grepl("_primer_contam_stats.txt", list.files()))) {
if (any(grepl("final_taxa", list.files()))) {
taxa_bool <- TRUE
tax_dfs <- list()
na_dfs <- list()
seq_types <- c()
analysis_types <- c()
Expand All @@ -177,7 +178,8 @@ if (any(grepl("final_taxa", list.files()))) {
curr_taxa <- read.table("asv_final_taxa_filtered.tsv",
sep = "\t", header = TRUE)
tax_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA != "NA"))
tax_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA != "NA" & ! is.na(LCA)))
na_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA == "NA" | is.na(LCA)))
} else if (file.exists("asv_final_taxa.tsv")) {
seq_type <- "ASV"
Expand All @@ -186,7 +188,8 @@ if (any(grepl("final_taxa", list.files()))) {
curr_taxa <- read.table("asv_final_taxa.tsv",
sep = "\t", header = TRUE)
tax_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA != "NA"))
tax_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA != "NA" & ! is.na(LCA)))
na_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA == "NA" | is.na(LCA)))
}
if (file.exists("asv_lulucurated_final_taxa_filtered.tsv")) {
Expand All @@ -195,15 +198,17 @@ if (any(grepl("final_taxa", list.files()))) {
curr_taxa <- read.table("asv_lulucurated_final_taxa_filtered.tsv",
sep = "\t", header = TRUE)
tax_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA != "NA"))
tax_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA != "NA" & ! is.na(LCA)))
na_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA == "NA" | is.na(LCA)))
} else if (file.exists("asv_lulucurated_final_taxa.tsv")) {
seq_type <- "ASV_LULUCURATED"
analysis_types <- append(analysis_types, seq_type)
curr_taxa <- read.table("asv_lulucurated_final_taxa.tsv",
sep = "\t", header = TRUE)
tax_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA != "NA"))
tax_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA != "NA" & ! is.na(LCA)))
na_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA == "NA" | is.na(LCA)))
}
if (file.exists("zotu_final_taxa_filtered.tsv")) {
Expand All @@ -213,7 +218,8 @@ if (any(grepl("final_taxa", list.files()))) {
curr_taxa <- read.table("zotu_final_taxa_filtered.tsv",
sep = "\t", header = TRUE)
tax_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA != "NA"))
tax_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA != "NA" & ! is.na(LCA)))
na_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA == "NA" | is.na(LCA)))
} else if (file.exists("zotu_final_taxa.tsv")) {
seq_type <- "ZOTU"
Expand All @@ -222,7 +228,8 @@ if (any(grepl("final_taxa", list.files()))) {
curr_taxa <- read.table("zotu_final_taxa.tsv",
sep = "\t", header = TRUE)
tax_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA != "NA"))
tax_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA != "NA" & ! is.na(LCA)))
na_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA == "NA" | is.na(LCA)))
}
if (file.exists("zotu_lulucurated_final_taxa_filtered.tsv")) {
Expand All @@ -231,15 +238,17 @@ if (any(grepl("final_taxa", list.files()))) {
curr_taxa <- read.table("zotu_lulucurated_final_taxa_filtered.tsv",
sep = "\t", header = TRUE)
tax_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA != "NA"))
tax_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA != "NA" & ! is.na(LCA)))
na_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA == "NA" | is.na(LCA)))
} else if (file.exists("zotu_lulucurated_final_taxa.tsv")) {
seq_type <- "ZOTU_LULUCURATED"
analysis_types <- append(analysis_types, seq_type)
curr_taxa <- read.table("zotu_lulucurated_final_taxa.tsv",
sep = "\t", header = TRUE)
tax_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA != "NA"))
tax_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA != "NA" & ! is.na(LCA)))
na_dfs[[seq_type]] <- list(filter(data.frame(curr_taxa), LCA == "NA" | is.na(LCA)))
}
species <- list()
Expand All @@ -249,6 +258,7 @@ if (any(grepl("final_taxa", list.files()))) {
class <- list()
phylum <- list()
domain <- list()
nas <- list()
# Calculate LCA counts for all sequence types
for (i in analysis_types) {
Expand All @@ -259,6 +269,7 @@ if (any(grepl("final_taxa", list.files()))) {
class[[i]] <- 0
phylum[[i]] <- 0
domain[[i]] <- 0
nas[[i]] <- nrow(na_dfs[[i]][[1]])
# Calculate LCA counts for different taxa levels
for (row in seq_len(nrow(tax_dfs[[i]][[1]]))) {
Expand Down Expand Up @@ -538,6 +549,7 @@ text_lca <- c(
'LCAs at class level: ', class[['{{i}}']], ' \n',
'LCAs at phylum level: ', phylum[['{{i}}']], ' \n',
'LCAs at domain level: ', domain[['{{i}}']], ' \n',
'No assignments: ', nas[['{{i}}']], ' \n',
' \n')",
"``` \n"
)
Expand Down

0 comments on commit 0cd095b

Please sign in to comment.