This script streamlines and standardizes our handling of the steps taken to reach each dataset from an original sampleset. You will export some standardized csv and tsv tables for easy importing and manipulation with our other workflows.
To start, you should have four categories of csv files (I download the first three from working google spreadsheets, and the fourth category is a series of files automatically generated by each MinION sequencing run). Those files and their list of column headers to be used are as follows (note: it is fine to have extra columns, but you must at least have these to run the script as is):
You can use the sampleset setting under params in the header of this script to select which sampleset you will be working with. So long as the same name is used consistently, this should automatically filter for that name (e.g., loris or marmoset).
Next, you should make sure your config.yml file contains the path to locate each of the files you will be using. Below is an example excerpt from my config file.
default:
setup: "setup/setup.R"
conflicts: "setup/conflicts.R"
functions: "setup/functions.R"
packages: "setup/packages.R"
inputs: "setup/inputs.R"
knit_engines: "setup/knit_engines.R"
fonts: "setup/fonts/FA6_Free-Solid-900.otf"
tmp_tsv: "tmp/tmp_table.tsv"
tmp_downloads: "tmp/downloads/"
tmp_fetch: "tmp/fetch_references.txt"
tmp_fasta3: "tmp/tmp3.fasta"
tmp_fasta4: "tmp/tmp4.fasta"
scripts:
local:
basecall: "batch_scripts/basecall_local.sh"
trimWG: "batch_scripts/trimWG_local.sh"
isolates:
samplesets: "salci"
minQC: 10
bats:
inventories:
all_stages: "samples/inventories/bats/compilation_bats.tsv"
collection: "samples/inventories/bats/samples_bats.csv"
extraction: "samples/inventories/bats/extracts_bats.csv"
libraries: "samples/inventories/bats/libraries_bats.csv"
seqruns: "samples/inventories/bats/seqruns_bats.csv"
loris:
day1: "2023-10-26"
last: "2024-10-25"
sequencing:
coverage: "visuals/loris_depth_summary.html"
depth_plot: "visuals/loris_depth_hist.html"
metadata:
scripts: !expr list("metadata/loris/colors.R", "metadata/loris/metadata_key.R", "metadata/loris/nutrition.R", "metadata/loris/hdz_loris_log.R", "metadata/loris/diet_tables.R")
bristol: "metadata/loris/bristols.tsv"
studbook: "metadata/loris/subjects_loris.csv"
summary: "metadata/loris/samples_metadata.tsv"
key: "metadata/loris/metadata_key.R"
factors: "metadata/loris/factors.R"
foods: "metadata/loris/foods.tsv"
proteins: "metadata/loris/proteins.tsv"
fats: "metadata/loris/fats.tsv"
CHOs: "metadata/loris/CHOs.tsv"
Ash: "metadata/loris/Ash.tsv"
vitamins: "metadata/loris/vitamins.tsv"
reactable: "metadata/loris/loris_metadata_summary.html"
sample_table:
identifiers: "metadata/loris/identifier_key.tsv"
main: "metadata/loris/sample_table.tsv"
merged: "metadata/loris/sample_table_merged.tsv"
inventories:
all_stages: "samples/inventories/loris/compilation_loris.tsv"
collection: "samples/inventories/loris/samples_loris.csv"
extraction: "samples/inventories/loris/extracts_loris.csv"
libraries: "samples/inventories/loris/libraries_loris.csv"
seqruns: "samples/inventories/loris/seqruns_loris.csv"
outputs_wf16s: "data/loris/outputs_wf16s/"
barcodes_output: "dataframes/barcodes/loris/"
read_alignments: "data/loris/read_alignments"
taxa_reps:
aligned: "data/loris/taxonomy/refseqs_aligned.fasta"
tree: "data/loris/taxonomy/refseqs_tree.newick"
table: "data/loris/taxonomy/tax_table.tsv"
abundance_wf16s: "data/loris/wf16s_abundance/"
microeco:
dataset:
main:
keg: "microeco/loris/datasets/main/keg"
njc: "microeco/loris/datasets/main/njc"
fpt: "microeco/loris/datasets/main/fpt"
tax: "microeco/loris/datasets/main"
culi:
keg: "microeco/loris/datasets/culi/keg"
njc: "microeco/loris/datasets/culi/njc"
fpt: "microeco/loris/datasets/culi/fpt"
tax: "microeco/loris/datasets/culi"
warb:
keg: "microeco/loris/datasets/warble/keg"
njc: "microeco/loris/datasets/warble/njc"
fpt: "microeco/loris/datasets/warble/fpt"
tax: "microeco/loris/datasets/warble"
abund:
main:
keg: "microeco/loris/abundance/main/keg"
fpt: "microeco/loris/abundance/main/fpt"
njc: "microeco/loris/abundance/main/njc"
tax: "microeco/loris/abundance/main"
culi:
keg: "microeco/loris/abundance/culi/keg"
fpt: "microeco/loris/abundance/culi/fpt"
njc: "microeco/loris/abundance/culi/njc"
tax: "microeco/loris/abundance/culi"
warb:
keg: "microeco/loris/abundance/warble/keg"
fpt: "microeco/loris/abundance/warble/fpt"
njc: "microeco/loris/abundance/warble/njc"
tax: "microeco/loris/abundance/warble"
alpha:
main: "microeco/loris/alphadiversity/main"
culi: "microeco/loris/alphadiversity/culi"
warb: "microeco/loris/alphadiversity/warble"
beta:
main:
kegg: "microeco/loris/betadiversity/main/keg"
fpt: "microeco/loris/betadiversity/main/fpt"
njc: "microeco/loris/betadiversity/main/njc"
tax: "microeco/loris/betadiversity/main"
culi:
kegg: "microeco/loris/betadiversity/culi/keg"
fpt: "microeco/loris/betadiversity/culi/fpt"
njc: "microeco/loris/betadiversity/culi/njc"
tax: "microeco/loris/betadiversity/culi"
warb:
kegg: "microeco/loris/betadiversity/warble/keg"
fpt: "microeco/loris/betadiversity/warble/fpt"
njc: "microeco/loris/betadiversity/warble/njc"
tax: "microeco/loris/betadiversity/warble"
data:
main:
feature: "microeco/loris/datasets/main/feature_table.tsv"
tree: "microeco/loris/datasets/main/phylo_tree.tre"
fasta: "microeco/loris/datasets/main/rep_fasta.fasta"
samples: "microeco/loris/datasets/main/sample_table.tsv"
taxa: "microeco/loris/datasets/main/tax_table.tsv"
culi:
feature: "microeco/loris/datasets/culi/feature_table.tsv"
tree: "microeco/loris/datasets/culi/phylo_tree.tre"
fasta: "microeco/loris/datasets/culi/rep_fasta.fasta"
samples: "microeco/loris/datasets/culi/sample_table.tsv"
taxa: "microeco/loris/datasets/culi/tax_table.tsv"
warb:
feature: "microeco/loris/datasets/warb/feature_table.tsv"
tree: "microeco/loris/datasets/warb/phylo_tree.tre"
fasta: "microeco/loris/datasets/warb/rep_fasta.fasta"
samples: "microeco/loris/datasets/warb/sample_table.tsv"
taxa: "microeco/loris/datasets/warb/tax_table.tsv"
sample_sheets:
compilations:
bats: "samples/sample_sheets/bats/nwr_combined_sample_sheet.csv"
loris: "samples/sample_sheets/loris/hdz_combined_sample_sheet.csv"
nwr1: "samples/sample_sheets/bats/nwr1_sample_sheet.csv"
hdz1: "samples/sample_sheets/loris/hdz1_sample_sheet.csv"
hdz2: "samples/sample_sheets/loris/hdz2_sample_sheet.csv"
hdz3: "samples/sample_sheets/loris/hdz3_sample_sheet.csv"
hdz4: "samples/sample_sheets/loris/hdz4_sample_sheet.csv"
hdz5: "samples/sample_sheets/loris/hdz5_sample_sheet.csv"
hdz6: "samples/sample_sheets/loris/hdz6_sample_sheet.csv"
hdz7: "samples/sample_sheets/loris/hdz7_sample_sheet.csv"
hdz8: "samples/sample_sheets/loris/hdz8_sample_sheet.csv"
hdz9: "samples/sample_sheets/loris/hdz9_sample_sheet.csv"
hdz10: "samples/sample_sheets/loris/hdz10_sample_sheet.csv"
hdz11: "samples/sample_sheets/loris/hdz11_sample_sheet.csv"
hdz12: "samples/sample_sheets/loris/hdz12_sample_sheet.csv"
hdz13: "samples/sample_sheets/loris/hdz13_sample_sheet.csv"
hdz14: "samples/sample_sheets/loris/hdz14_sample_sheet.csv"
hdz15: "samples/sample_sheets/loris/hdz15_sample_sheet.csv"
hdz16: "samples/sample_sheets/loris/hdz16_sample_sheet.csv"
hdz17: "samples/sample_sheets/loris/hdz17_sample_sheet.csv"
hdz18: "samples/sample_sheets/loris/hdz18_sample_sheet.csv"
barcode_alignments:
compilations:
loris: "samples/barcode_alignments/loris/hdz_combined_barcode_alignment.tsv"
bats: "samples/barcode_alignments/bats/nwr_combined_barcode_alignment.tsv"
nwr1: "samples/barcode_alignments/bats/nwr1_barcode_alignment.tsv"
hdz1: "samples/barcode_alignments/loris/hdz1_barcode_alignment.tsv"
hdz2: "samples/barcode_alignments/loris/hdz2_barcode_alignment.tsv"
hdz3: "samples/barcode_alignments/loris/hdz3_barcode_alignment.tsv"
hdz4: "samples/barcode_alignments/loris/hdz4_barcode_alignment.tsv"
hdz5: "samples/barcode_alignments/loris/hdz5_barcode_alignment.tsv"
hdz6: "samples/barcode_alignments/loris/hdz6_barcode_alignment.tsv"
hdz7: "samples/barcode_alignments/loris/hdz7_barcode_alignment.tsv"
hdz8: "samples/barcode_alignments/loris/hdz8_barcode_alignment.tsv"
hdz9: "samples/barcode_alignments/loris/hdz9_barcode_alignment.tsv"
hdz10: "samples/barcode_alignments/loris/hdz10_barcode_alignment.tsv"
hdz11: "samples/barcode_alignments/loris/hdz11_barcode_alignment.tsv"
hdz12: "samples/barcode_alignments/loris/hdz12_barcode_alignment.tsv"
hdz13: "samples/barcode_alignments/loris/hdz13_barcode_alignment.tsv"
hdz14: "samples/barcode_alignments/loris/hdz14_barcode_alignment.tsv"
hdz15: "samples/barcode_alignments/loris/hdz15_barcode_alignment.tsv"
hdz16: "samples/barcode_alignments/loris/hdz16_barcode_alignment.tsv"
hdz17: "samples/barcode_alignments/loris/hdz17_barcode_alignment.tsv"
hdz18: "samples/barcode_alignments/loris/hdz18_barcode_alignment.tsv"
abund_wf16s_files:
hdz1: "data/loris/wf16s_abundance/hdz1_abundance_table_species.tsv"
hdz2: "data/loris/wf16s_abundance/hdz2_abundance_table_species.tsv"
hdz3: "data/loris/wf16s_abundance/hdz3_abundance_table_species.tsv"
hdz4: "data/loris/wf16s_abundance/hdz4_abundance_table_species.tsv"
hdz5: "data/loris/wf16s_abundance/hdz5_abundance_table_species.tsv"
hdz6: "data/loris/wf16s_abundance/hdz6_abundance_table_species.tsv"
hdz7: "data/loris/wf16s_abundance/hdz7_abundance_table_species.tsv"
hdz8: "data/loris/wf16s_abundance/hdz8_abundance_table_species.tsv"
hdz9: "data/loris/wf16s_abundance/hdz9_abundance_table_species.tsv"
hdz10: "data/loris/wf16s_abundance/hdz10_abundance_table_species.tsv"
hdz11: "data/loris/wf16s_abundance/hdz11_abundance_table_species.tsv"
hdz12: "data/loris/wf16s_abundance/hdz12_abundance_table_species.tsv"
hdz13: "data/loris/wf16s_abundance/hdz13_abundance_table_species.tsv"
hdz14: "data/loris/wf16s_abundance/hdz14_abundance_table_species.tsv"
hdz15: "data/loris/wf16s_abundance/hdz15_abundance_table_species.tsv"
hdz16: "data/loris/wf16s_abundance/hdz16_abundance_table_species.tsv"
hdz17: "data/loris/wf16s_abundance/hdz17_abundance_table_species.tsv"
hdz18: "data/loris/wf16s_abundance/hdz18_abundance_table_species.tsv"
methods_16s:
libprep_workflow: "'rapid16s'"
dorado_model: "'dna_r10.4.1_e8.2_400bps_sup@v5.0.0'"
min_length: 1000
max_length: 2000
min_qual: 7
min_id: 85
min_cov: 80
kit_name: "'SQK-16S114-24'"
tax_rank: "S"
n_taxa_barplot: 12
abund_threshold: 0
loris:
rarefy: 4500
norm: "SRS"
min_abund: 0.00001
min_freq: 1
include_lowest: TRUE
unifrac: TRUE
betadiv: "aitchison"
alpha_pd: TRUE
tax4fun_db: "Ref99NR"
loris_rarefy: 4500
keg_minID: 97
Note that I also include paths to files that this script will create. If the file is already there, then it will be overwritten, if not, it will be created there. Run the code below to set up your paths from the config file for the working sampleset you identified in the header:
global <- config::get(config = "default")
swan <- config::get(config = "swan")
micro <- config::get(config = "microbiome")
loris <- config::get(config = "loris")
marmoset <- config::get(config = "marmoset")
isolates <- config::get(config = "isolates")
bats <- config::get(config = "bats")
methods_16s <- config::get(config = "methods_16s")
sample_sheets <- config::get(config = "sample_sheets")
abund_wf16s_files <- config::get(config = "abund_wf16s_files")
barcode_alignments<- config::get(config = "barcode_alignments")
seqruns <- seqruns %>% keep_at(params$sampleset) %>% list_flatten(name_spec = "")
subject_list <- keep_at(subjects, paste0(params$sampleset)) %>% list_flatten(name_spec = "{inner}")
path <- config::get(config = paste0(params$sampleset))
The code in the chunk above also generated a list of formatted codes for each available sequencing run to date, separated by taxa/samplesets (currently just for loris and marmoset). Make sure the end number matches the highest integer we have for that sampleset to date.
The script that I pasted above sources additional scripts that I run routinely at the start of any work to bring in functions and other inputs with shorter code chunks as well as the text of the yaml header for this R Markdown file. You can flip through the text from those below.
---
output:
html_document:
theme:
bslib: true
css: journal.css
toc: true
toc_float: true
df_print: paged
params:
sampleset: "loris"
seqrun: "hdz18"
---
samplesets <- list(
"Omaha Zoo Pygmy Lorises" = "loris" ,
"UNO Marmosets" = "marmoset",
"Wild North American Bats" = "bats",
"North American eDNA" = "envir",
"Bacterial Isolates" = "isolates"
)
subjects <- list(
marmoset = list(
HAM = "Hamlet",
HER = "Hera",
JAR = "JarJar BINKS",
OPH = "Ophelia",
KUB = "Kubo",
KOR = "Korra",
WOL = "Wolverine",
IRI = "Iris",
GOO = "Goose",
LAM = "Lambchop",
FRA = "Franc",
IVY = "Ivy",
CHA = "Charles",
PAD = "Padme",
BUB = "Bubblegum",
GRO = "Grogu",
MAR = "Marshmallow",
BUD = "Buddy",
JOA = "Joans",
HEN = "Henry",
GIN = "Ginger"
),
loris = list(
WARB = "Warble",
CULI = "Culi"
),
bats = list(
UNK = "Unknown"
),
envir = list(
UNK = "Unknown"
),
isolates = list(
UNK = "Unknown"
)
)
seqruns <- list(
loris = as.list(paste0("hdz", 1:18)),
marmoset = as.list(sprintf("cm%03d", 1:10)),
isolates = as.list(paste0("salci", 1))
)
colors <- list(
f = "#D53288FF",
m = "#3F459BFF",
u = "#21B14BFF",
sire = "#3F459B33",
dam = "#D5328833",
emph = "#DC8045FF",
seq = "rcartocolor::Sunset",
div = "rcartocolor::Temps",
rand = "khroma::stratigraphy"
)
knitr::knit_engines$set(terminal = function(options) {
code <- paste(options$code, collapse = "\n")
params <- map(params, ~ if (is.atomic(.)) {list(.)} else {(.)}) %>%
list_flatten()
patterns <- list(
params = list(
sampleset = paste0(params$sampleset),
seqrun = paste0(params$seqrun),
samplesheet = as.character(sample_sheets[paste0(tolower(params$seqrun))])
) ,
global = global ,
swan = swan ,
micro = micro ,
loris = loris ,
isolates = isolates ,
bats = bats ,
methods_16s = methods_16s ,
sample_sheets = sample_sheets ,
abund_wf16s_files = abund_wf16s_files ,
barcode_alignments= barcode_alignments
)
# Replace placeholders group by group
for (group in names(patterns)) {
placeholder_list <- patterns[[group]]
for (name in names(placeholder_list)) {
placeholder <- paste(group, name, sep = "\\$") # Match exact placeholder
value <- placeholder_list[[name]]
# Replace placeholders exactly and avoid breaking suffixes
code <- gsub(placeholder, value, code, perl = TRUE)
}
}
options$warning <- FALSE
knitr::engine_output(options, code, out = code)
})
knitr::opts_chunk$set(message = FALSE,
warning = FALSE,
echo = TRUE,
include = TRUE,
eval = TRUE,
comment = "")
barcodes <- imap(seqruns, ~ {
map(.x, ~ read_table(barcode_alignments[[.x]]) %>% mutate(seqrun = .x))
}) %>%
bind_rows() %>%
as_tibble() %>%
filter(barcode != "unclassified") %>%
mutate(SeqDateTime = as_datetime(started)) %>%
mutate(SeqDate = floor_date(SeqDateTime, unit = "day")) %>%
mutate(SeqRunID = str_replace_all(sample_id, "pool1", "PL001")) %>%
mutate(LibraryCode = str_squish(str_trim(seqrun , "both")),
FlowCellSerial = str_squish(str_trim(flow_cell_id, "both"))
) %>%
mutate(LibraryBarcode = as.numeric(str_remove_all(barcode, "16S|barcode0|barcode"))) %>%
select(LibraryCode,
LibraryBarcode,
reads_unclassified = target_unclassified,
FlowCellSerial,
protocol_group_id,
SeqRunID,
SeqDate,
SeqDateTime)
write.table(barcodes, barcode_alignments$compilations[[paste0(params$sampleset)]],
row.names = F,
sep = "\t")seqrun.tbl <- read_csv(path$inventories$seqruns) %>%
rename_with(~str_replace_all(., "\\s", "_")) %>%
mutate(SampleSet = case_when(
str_detect(Pooled_Library_Code, "CM") ~ "marmoset",
str_detect(Pooled_Library_Code, "PL") ~ "loris",
str_detect(Pooled_Library_Code, "NWR") ~ "bats", .default = "unknown"),
LibraryCode = str_to_lower(Pooled_Library_Code),
LibPrepWorkflow = case_when(
str_detect(Kit, "LSK") & Pipeline == "16S" ~ "lsk16s",
Pipeline == "Host mtDNA" ~ "lskadaptive",
str_detect(Kit, "SQK-16S") & Pipeline == "16S" ~ "rapid16s"),
LibPrepDate = mdy(Run_Date),
SeqRunDate = ymd(str_remove_all(str_trim(Run_ID, "both"), "MIN_16_|MIN_16-|MIN_MT_"))) %>%
mutate(LibraryCode = str_replace_all(LibraryCode, "pl00|pl0", "hdz"),
strands = 2,
fragment_type = if_else(Pipeline == "16S", 3, 1),
Length = if_else(Pipeline == "16S", 1500, 10000),
InputMassStart = if_else(Pipeline == "16S", 10, 1000),
TemplateVolPrep = if_else(LibPrepWorkflow == "rapid16s", 15, 47),
PoolSamples = if_else(Pipeline == "16S", "yes", "no"),
InputMassFinal = 50
) %>%
filter(SampleSet == params$sampleset) %>%
select(
SampleSet,
LibraryCode,
LibPrepDate,
LibPrepWorkflow,
LibPrepKit = Kit,
FlowCellSerial = Flow_Cell_ID,
FlowCellType = Flow_Cell_Type,
FlongleAdapter = Flongle_Adapter,
SeqDevice = Sequencer,
strands,
fragment_type,
Length,
InputMassStart,
TemplateVolPrep,
PoolSamples,
InputMassFinal)samples <- read_csv(path$inventories$collection) %>%
rename_with(~str_replace_all(., "\\s", "_")) %>%
filter(str_starts(SampleID, "\\w+")) %>%
select(-SampleBox) %>%
mutate(SampleID = str_squish(str_trim(SampleID, "both"))) %>% distinct() %>%
mutate(CollectionDate = mdy(SampleDate),
Subject = str_squish(str_trim(SampleSubject)),
.keep = "unused") %>% distinct() %>%
mutate(Subj_Certainty = if_else(Subject %in% subject_list, "yes", "no")) %>%
mutate(Subject = str_remove_all(Subject, "\\?"))We will also join the previous sample records to this table at the end of the chunk.
extracts <- read_csv(path$inventories$extraction) %>%
rename_with(~str_replace_all(., "\\s", "_")) %>%
filter(str_starts(SampleID, "\\w+")) %>%
mutate(SampleID = if_else(str_detect(SampleID, "#N/A") | is.na(SampleID), "ExtractControl", SampleID)) %>%
mutate(SampleID = str_squish(str_trim(SampleID, "both")),
ExtractID= str_squish(str_trim(ExtractID, "both")),
ExtractDate = mdy(ExtractDate)) %>%
mutate(ExtractConc = str_remove_all(ExtractConcentration, ">"), .keep = "unused") %>%
mutate(ExtractConc = if_else(str_detect(ExtractConc, "Higher"), "100", ExtractConc),
ExtractConc = if_else(str_detect(ExtractConc, "HIGHER"), "100", ExtractConc),
ExtractConc = if_else(ExtractConc == "LOW", "0", ExtractConc),
ExtractConc = if_else(ExtractConc == "", NA, ExtractConc)) %>%
mutate(ExtractConc = round(as.numeric(ExtractConc), 1)) %>% filter(ExtractType == "DNA" | ExtractType == "dna") %>%
select(-ExtractType) %>%
right_join(samples) %>% distinct()compilation <- read_csv(path$inventories$libraries) %>%
rename_with(~str_replace_all(., "\\s", "_")) %>%
rename_with(~str_remove_all(., "\\(|\\)")) %>%
filter(str_starts(SequenceID, "\\w+") & Seq_ID != "#N/A") %>%
mutate(LibraryCode = str_to_lower(Seq_ID)) %>%
mutate(LibraryCode = str_replace_all(LibraryCode, "pl00|pl0" , "hdz"),
SampVolPool = round(as.numeric(Volume_Added_to_Pool_uL), 0),
LibraryBarcode = as.numeric(str_remove_all(LibraryBarcode, "16S|barcode0|barcode"))) %>%
mutate(TotalPoolVol = sum(SampVolPool), .by = LibraryCode) %>%
mutate(BeadVol = TotalPoolVol * 0.6) %>%
select(SequenceID,
LibraryCode,
LibraryTube,
LibraryBarcode,
ExtractID,
SampVolPool,
TotalPoolVol,
BeadVol,
Conc_QC2 = Final_Library_Concentration) %>%
full_join(extracts, by = join_by(ExtractID)) %>%
mutate(SampleID = if_else(is.na(SampleID) & !is.na(ExtractID), "NTC", SampleID)) %>%
full_join(barcodes, by = join_by(LibraryCode, LibraryBarcode)) %>%
left_join(seqrun.tbl, by = join_by(LibraryCode, FlowCellSerial)) %>% distinct() %>%
mutate(steps_remaining = case_when(
is.na(ExtractID) ~ "sample not extracted",
is.na(SequenceID) ~ "extract not sequenced",
!is.na(ExtractID) & !is.na(SequenceID) & !is.na(SampleID) ~ "sample extracted and sequenced"
)) %>%
relocate(SampleID, ExtractID, SequenceID, steps_remaining) %>%
arrange(CollectionDate, Subject)We will use this spreadsheet for building the metadata table but also for calling up sample info in our protocol apps.
write.table(compilation,
path$inventories$all_stages,
row.names = F,
sep = "\t")count.extracts <- extracts %>% select(ExtractID, SampleID) %>% distinct() %>%
group_by(SampleID) %>%
mutate(n_dna_extracts = n_distinct(ExtractID)) %>% ungroup() %>% select(-ExtractID)
count.libraries <- compilation %>% select(SequenceID, ExtractID, SampleID) %>% distinct() %>%
group_by(ExtractID) %>% mutate(n_16s_extract = n_distinct(SequenceID)) %>% ungroup() %>%
group_by(SampleID) %>% mutate(n_16s_sample = n_distinct(SequenceID)) %>% ungroup() %>% select(-SequenceID)samplesheet <- compilation %>%
filter(steps_remaining == "sample extracted and sequenced") %>%
mutate(barcode = if_else(LibraryBarcode < 10,
str_glue("barcode0", "{LibraryBarcode}"),
str_glue("barcode" , "{LibraryBarcode}"))) %>%
select(flow_cell_id = FlowCellSerial,
experiment_id = protocol_group_id,
kit = LibPrepKit,
barcode,
alias = SequenceID,
seqrun = LibraryCode)
write.table(samplesheet,
sample_sheets$compilations[[paste0(params$sampleset)]],
row.names = F,
quote = F,
sep = ",")samplesheet.nested <- samplesheet %>% nest(.by = seqrun) %>%
deframe()Now you should proceed to the Read Processing workflow to begin basecalling the sequencing run.