Package {strollur}

Type:	Package
Title:	Store and Transfer Amplicon Sequence Data
Version:	0.1.4
Date:	2026-10-16
Maintainer:	Pat Schloss <pschloss@umich.edu>
Description:	Stores the data associated with your amplicon sequence analysis. This includes nucleotide sequences, abundance, sample and treatment assignments, taxonomic classifications, asv, otu and phylotype clusters, metadata, trees and various reports. It is designed to facilitate data analysis across multiple R packages with utility functions to read / write from 'mothur', 'qiime2', 'dada2', and 'phyloseq'.
URL:	https://github.com/mothur/strollur, https://mothur.org/strollur/
BugReports:	https://github.com/mothur/strollur/issues
License:	GPL (≥ 3)
Imports:	Rcpp, cli, methods, microseq, R.utils, R6, waldo, readr, ape, dplyr, tidyr, yaml, rbiom (≥ 3.1.0), stats, utils
LinkingTo:	Rcpp, cli, Rcereal
Depends:	R (≥ 4.2.0)
Suggests:	knitr, rmarkdown, testthat (≥ 3.0.0), xml2, phyloseq, ggplot2, phylotypr, rhdf5, h5lite, pak
Config/testthat/edition:	3
Encoding:	UTF-8
VignetteBuilder:	knitr
Config/roxygen2/version:	8.1.0
NeedsCompilation:	yes
Packaged:	2026-10-16 17:34:22 UTC; swestcot
Author:	Sarah Westcott [aut], Gregory Johnson [aut], Pat Schloss [cph, cre]
Repository:	CRAN
Date/Publication:	2026-10-19 13:10:02 UTC

strollur: Store and Transfer Amplicon Sequence Data

Description

Stores the data associated with your amplicon sequence analysis. This includes nucleotide sequences, abundance, sample and treatment assignments, taxonomic classifications, asv, otu and phylotype clusters, metadata, trees and various reports. It is designed to facilitate data analysis across multiple R packages with utility functions to read / write from 'mothur', 'qiime2', 'dada2', and 'phyloseq'.

Author(s)

Maintainer: Pat Schloss pschloss@umich.edu (ORCID) [copyright holder]

Authors:

• Sarah Westcott swestcot@umich.edu (ORCID)

• Gregory Johnson grejoh@umich.edu (ORCID)

See Also

Useful links:

• https://github.com/mothur/strollur

• https://mothur.org/strollur/

• Report bugs at https://github.com/mothur/strollur/issues

Get the abundance data for sequences, bins, samples, and treatments in a strollur object

Description

Get the abundance data for sequences, bins, samples, and treatments in a strollur object

Usage

abundance(data, type = "sequence", bin_type = "otu", by_sample = FALSE)

Arguments

Value

data.frame

Examples

miseq <- strollur::miseq_sop_example()

# To the total abundance for each sequence
strollur::abundance(data = miseq, type = "sequence")

# To the total abundance for each sequence parsed by sample
strollur::abundance(data = miseq, type = "sequence", by_sample = TRUE)

# To the total abundance for each "otu" bin
strollur::abundance(data = miseq, type = "bin", bin_type = "otu")

# To the total abundance for each "otu" bin parsed by sample
strollur::abundance(data = miseq, type = "bin",
                     bin_type = "otu", by_sample = TRUE)

# To the total abundance for each "asv" bin
strollur::abundance(data = miseq, type = "bin", bin_type = "asv")

# To the total abundance for each "asv" bin parsed by sample
strollur::abundance(data = miseq, type = "bin",
                     bin_type = "asv", by_sample = TRUE)

# To the total abundance for each sample
strollur::abundance(data = miseq, type = "sample")

# To the total abundance for each treatment
strollur::abundance(data = miseq, type = "treatment")

Add sequences, reports, trees or resource references to a strollur object

Description

Add sequences, reports, trees or resource references to a strollur object

Usage

add(
  data,
  table,
  type = "sequence",
  report_type = NULL,
  table_names = list(sequence_name = "sequence_name", sequence = "sequence", comment =
    "comment", quality_score = "quality_score", reference_vendor = "vendor",
    reference_name = "name", reference_version = "version", reference_usage = "usage",
    reference_note = "note", reference_method_url = "method_url",
    reference_documentation_url = "documentation_url", reference_parameter = "parameter",
    reference_citation = "citation"),
  reference = NULL,
  verbose = TRUE
)

Arguments

Value

an updated strollur object

Examples

# Create a new empty strollur object named 'example_dataset'
data <- strollur::new_dataset(dataset_name = "example_dataset")

# Read FASTA data into data.frame
fasta_data <-
  strollur::read_fasta(fasta = strollur_example("final.fasta.gz"))

# Add FASTA sequence data
strollur::add(data = data, table = fasta_data, type = "sequence")

# To add FASTA data with a resource reference

# Create a new empty strollur object named 'example_dataset'
data <- strollur::new_dataset(dataset_name = "example_dataset")

# Create a resource reference for the FASTA data silva_resource <-
silva_resource <- strollur::new_reference(
  vendor = "SILVA", name =
    "silva.bacteria.fasta", version = "1.38.1",
  usage = "alignment of sequences",
  note = "reference trimmed to V4 region", method_url =
    "https://mothur.org/blog/2024/SILVA-v138_2-reference-files/",
  documentation_url = "https://mothur.org/wiki/silva_reference_files/"
)

# Add FASTA data with a resource reference

strollur::add(
  data,
  table = fasta_data,
  type = "sequence",
  reference = silva_resource
)

# Create a new empty strollur object named 'example_dataset'
data <- strollur::new_dataset(dataset_name = "example_dataset")

# Read FASTQ data into data.frame
fastq_data <-
  strollur::read_fastq(fastq = strollur_example("tiny.fastq.gz"))

# Add FASTQ sequence data
strollur::add(data = data, table = fastq_data, type = "fastq")

# Add contigs assembly report with a 'sequence_name' column named 'Name'

contigs_report <- readRDS(strollur_example("miseq_contigs_report.rds"))

strollur::add(
  data,
  table = contigs_report, type = "report",
  report_type = "contigs_report", list(sequence_name = "Name")
)

# To add metadata related to your study

metadata <- readRDS(strollur_example("miseq_metadata.rds"))

strollur::add(data,
  table = metadata,
  type = "report", report_type = "metadata"
)

# To add a tree relating to your sequences

tree <- ape::read.tree(strollur_example("final.phylip.tre.gz"))

strollur::add(data, table = tree, type = "sequence_tree")

# To add a tree relating to your samples
data <- strollur::new_dataset(dataset_name = "example_dataset")

df <- strollur::read_mothur_shared(strollur_example("final.opti_mcc.shared"))
tree <- ape::read.tree(strollur_example("final.opti_mcc.jclass.ave.tre"))

strollur::assign(data, table = df, type = "bin", bin_type = "otu")
strollur::add(data, table = tree, type = "sample_tree")

Assign sequence abundances, sequence classifications, bins, bin representative sequences, bin classifications, sample distances or treatments to a strollur object

Description

Assign sequence abundances, sequence classifications, bins, bin representative sequences, bin classifications, sample distances or treatments to a strollur object

Usage

assign(
  data,
  table,
  type = "bin",
  bin_type = "otu",
  table_names = list(sequence_name = "sequence_name", quality_score = "quality_score",
    abundance = "abundance", sample = "sample", treatment = "treatment", taxonomy =
    "taxonomy", level = "level", confidence = "confidence", bin_name = "bin_name"),
  reference = NULL,
  verbose = TRUE
)

Arguments

Value

an updated strollur object

See Also

taxonomy_table_format

Examples

# Assign sequence classifications

# create a new empty strollur object named 'example_dataset'
data <- strollur::new_dataset(dataset_name = "example_dataset")

sequence_classifications <- strollur::read_mothur_taxonomy(strollur_example(
  "final.taxonomy.gz"
))

strollur::assign(
  data,
  table = sequence_classifications, type = "sequence_taxonomy"
)

# Assigning bins

# read mothur's otu list file into data.frame
otu_data <- strollur::read_mothur_list(list = strollur_example(
  "final.opti_mcc.list.gz"
))

# read mothur's asv list file into data.frame
asv_data <- strollur::read_mothur_list(list = strollur_example(
  "final.asv.list.gz"
))

# read mothur's phylotype list file into data.frame
phylo_data <- strollur::read_mothur_list(list = strollur_example(
  "final.tx.list.gz"
))

# read otu bin representative sequences into a data.frame
bin_reps <- readRDS(strollur_example("miseq_representative_sequences.rds"))

# assign 'otu' bins using sequence names
strollur::assign(data, table = otu_data, bin_type = "otu")

# assign 'asv' bins using sequence names
strollur::assign(data, table = asv_data, bin_type = "asv")

# assign 'phylotype' bins using sequence names
strollur::assign(data, table = phylo_data, bin_type = "phylotype")

# assign 'otu' bin representative sequences
strollur::assign(data, table = bin_reps, type = "bin_representative")

# To assign abundance only bins

# create a new empty strollur object named 'example_dataset'
data <- strollur::new_dataset(dataset_name = "example_dataset")

# read mothur's shared file
otu_data <-
  strollur::read_mothur_shared(strollur_example("final.opti_mcc.shared"))

# assign abundance only otus parsed by sample
strollur::assign(data, table = otu_data, bin_type = "otu")

# Assigning bin classifications

# read bin taxonomies
otu_data <- strollur::read_mothur_cons_taxonomy(strollur_example(
  "final.cons.taxonomy"
))

# assign otu consensus taxonomies
strollur::assign(
  data,
  table = otu_data,
  type = "bin_taxonomy", bin_type = "otu"
)

# Assign treatments

sample_assignments <- readRDS(strollur_example("miseq_sample_design.rds"))

strollur::assign(data, table = sample_assignments, type = "treatment")

# Assign sample distances

dist_file <- strollur_example("final.opti_mcc.jclass.0.03.column.dist")
sample_dists <- readr::read_table(dist_file,
  col_names = FALSE,
  show_col_types = FALSE
)
strollur::assign(data, table = sample_dists, type = "sample_distance")

Clear data from a strollur object

Description

Clear data from a strollur object

Usage

clear(data)

Arguments

Value

an updated strollur object

Examples

data <- miseq_sop_example()
clear(data)

Create a new strollur object from an existing dataset.

Description

Create a new strollur object from an existing dataset.

Usage

copy_dataset(data)

Arguments

Value

a strollur object

See Also

The 'new' method in the strollur object

Examples

miseq <- strollur::miseq_sop_example()

# to create a new dataset that is a copy of miseq

data <- strollur::copy_dataset(miseq)

Find the number of sequences, samples, treatments or bins of a given type in a strollur object

Description

Find the number of sequences, samples, treatments or bins of a given type in a strollur object

Usage

count(
  data,
  type = "sequence",
  bin_type = "otu",
  samples = NULL,
  distinct = FALSE
)

Arguments

Value

double

Examples

miseq <- strollur::miseq_sop_example()

# To get the total number of sequences
strollur::count(data = miseq, type = "sequence")

# To get number of unique sequences
strollur::count(data = miseq, type = "sequence", distinct = TRUE)

# To get number of unique sequences from samples 'F3D0' and 'F3D1'
# Note these sequences will be present in both samples but may be
# be present in other samples as well
strollur::count(data = miseq, type = "sequence", samples = c("F3D0", "F3D1"))

# To get number of unique sequences exclusive to samples 'F3D0' and 'F3D1'
# Note sequences are present in both samples and NOT present in any other
# samples.
strollur::count(
  data = miseq, type = "sequence", samples = c("F3D0", "F3D1"),
  distinct = TRUE
)

# To get the number of samples in the dataset
strollur::count(data = miseq, type = "sample")

# To get the number of treatments in the dataset
strollur::count(data = miseq, type = "treatment")

# To get the number of "otu" bins in the dataset
strollur::count(data = miseq, type = "bin", bin_type = "otu")

# To get the number of "asv" bins in the dataset
strollur::count(data = miseq, type = "bin", bin_type = "asv")

# To get the number of "phylotype" bins in the dataset
strollur::count(data = miseq, type = "bin", bin_type = "phylotype")

# To get number of "otu" bins from samples 'F3D0' and 'F3D1'
# Note these bins will have sequences from both samples but there may be
# other samples present as well
strollur::count(
  data = miseq,
  type = "bin", bin_type = "otu", samples = c("F3D0", "F3D1")
)

# To get number of "otu" bins unique to samples 'F3D0' and 'F3D1'
# Note these bins will have sequences from both samples and NO other samples
# will be present in the bins.
strollur::count(
  data = miseq, type = "bin", bin_type = "otu",
  samples = c("F3D0", "F3D1"), distinct = TRUE
)

Create a human readable table containing all data from a strollur object.

Description

Export all data from a strollur object.

Usage

export_dataset(data)

Arguments

Value

list, containing the data in the strollur::strollur object

Examples

dataset <- strollur::new_dataset("my_dataset")
strollur::export_dataset(dataset)

Get bin table types of a strollur object

Description

Get bin table types of a strollur object

Usage

get_bin_types(data)

Arguments

Value

vector of strings

Examples

data <- miseq_sop_example()
get_bin_types(data)

Determine if a given sample is in a strollur object

Description

Determine if a given sample is in a strollur object

Usage

has_sample(data, sample)

Arguments

Value

boolean indicating whether the dataset has a given sample

Examples

data <- miseq_sop_example()
has_sample(data, "F3D0")
has_sample(data, "not a valid sample")

Determine if a strollur object contains sequence nucleotide strings.

Description

Determine if a strollur object contains sequence nucleotide strings.

Usage

has_sequence_strings(data)

Arguments

Value

boolean indicating whether the dataset has sequence nucleotide strings.

Examples

data <- miseq_sop_example()
has_sequence_strings(data)

Create a strollur object from the exported table of a strollur object

Description

The import_dataset function will create a strollur object from the exported table of a strollur object object.

Usage

import_dataset(table)

Arguments

Value

a strollur object

See Also

export_dataset()

Examples

miseq <- strollur::miseq_sop_example()
data <- strollur::import_dataset(strollur::export_dataset(miseq))
data

Determine if a strollur object contains aligned sequences.

Description

Determine if a strollur object contains aligned sequences.

Usage

is_aligned(data)

Arguments

Value

Boolean

Examples

dataset <- miseq_sop_example()
is_aligned(dataset)

Determine if two strollur objects are equal.

Description

Determine if two strollur objects are equal.

Usage

is_equal(data, data2)

Arguments

Value

a logical

Examples

miseq <- strollur::miseq_sop_example()

data <- strollur::copy_dataset(miseq)

strollur::is_equal(miseq, data)

Load a strollur object from a file.

Description

The load_dataset function will create a strollur object from an RDS file.

Usage

load_dataset(file)

Arguments

Value

a strollur object

See Also

save_dataset()

Examples

data <- strollur::load_dataset(strollur_example("miseq_sop.rds"))
data

Create a strollur object using the analysis files from the MiSeq_SOP example.

Description

The miseq_sop_example function will create strollur object using the analysis files from the MiSeq_SOP example.

Usage

miseq_sop_example()

Value

A strollur::strollur object

Examples

miseq <- strollur::miseq_sop_example()

Get the names of various data in a strollur object

Description

Get the names of names sequences, bins, samples, treatments, and reports data in a strollur object

Usage

names(
  data,
  type = "sequence",
  bin_type = "otu",
  samples = NULL,
  distinct = FALSE
)

Arguments

Value

vector of strings, containing the names requested

Examples

miseq <- strollur::miseq_sop_example()

# To get the name of the dataset
strollur::names(data = miseq, type = "dataset")

# To get the names of the sequences
strollur::names(data = miseq, type = "sequence")

# To get the names of the sequences present sample 'F3D0'
strollur::names(data = miseq, type = "sequence", samples = c("F3D0"))

#' # To get the names of the sequences unique to sample 'F3D0'
strollur::names(data = miseq, type = "sequence",
                samples = c("F3D0"), distinct = TRUE)

# To get the names of the samples
strollur::names(data = miseq, type = "sample")

# To get the names of the treatments
strollur::names(data = miseq, type = "treatment")

# To get the names of the bins
strollur::names(data = miseq, type = "bin")

# To get the names of the bins that are unique to 'F3D0'
strollur::names(data = miseq, type = "bin",
                samples = c("F3D0"), distinct = TRUE)

# To get the names of the bins that include sequences from 'F3D0'
strollur::names(data = miseq, type = "bin",
                samples = c("F3D0"), distinct = FALSE)

# To get the names of the reports
strollur::names(data = miseq, type = "report")

Create a new strollur object

Description

Create a new strollur object

Usage

new_dataset(dataset_name = "")

Arguments

Value

a strollur object

See Also

The 'new' method in the strollur object

Examples

data <- strollur::new_dataset()

# to create a new dataset named "soil", run the following:

data <- strollur::new_dataset(dataset_name = "soil")

Create a resource reference for your strollur object to aid in reproducibility.

Description

Create a resource reference for your strollur object to aid in reproducibility.

Usage

new_reference(
  name,
  vendor = "",
  version = "",
  usage = "",
  note = "",
  documentation_url = "",
  method_url = "",
  parameter = "",
  citation = ""
)

Arguments

Value

a list

Examples

silva_resource <- strollur::new_reference(
  vendor = "SILVA", name =
    "silva.bacteria.fasta", version = "1.38.1",
  usage = "alignment of sequences",
  note = "alignment reference trimmed to V4 region", documentation_url =
    "https://mothur.org/wiki/silva_reference_files/", method_url =
    "https://mothur.org/blog/2024/SILVA-v138_2-reference-files/"
)

phylotypr_resource <- strollur::new_reference(
  vendor = "Schloss Lab - University of
Michigan", name = "R phylotypr package", version = "0.1.1", usage =
    "classification of sequences",
  note = "classification using Bayesian method",
  parameter = "kmer_size = 8, num_bootstraps = 100, min_confidence = 80",
  documentation_url = "https://mothur.org/phylotypr/", method_url =
    "doi:10.1128/mra.01144-24",
  citation = "@article{doi:10.1128/AEM.00062-07,
author = {Qiong Wang and George M. Garrity and James M. Tiedje and James R.
Cole}, title = {Naïve Bayesian Classifier for Rapid Assignment of rRNA
Sequences into the New Bacterial Taxonomy}, journal = {Applied and
Environmental Microbiology}, volume = {73}, number = {16}, pages =
{5261-5267}, year = {2007}, doi = {10.1128/AEM.00062-07}, URL =
{https://journals.asm.org/doi/abs/10.1128/aem.00062-07}, eprint =
{https://journals.asm.org/doi/pdf/10.1128/aem.00062-07}}"
)

Create a strollur object from a biom formatted file.

Description

The read_biom function reads a biom formatted file and creates a strollur::strollur object.

Usage

read_biom(biom)

Arguments

Value

A strollur object

Examples

if (requireNamespace("h5lite", quietly = TRUE)) {
  data <- strollur::read_biom(biom = strollur_example("miseq_sop.otu.biom"))
  data
} else {
  message(paste(
    "To use this functionality you have to install the",
    "h5lite package."
  ))
}

Create a strollur object from dada2 outputs

Description

This function reads a dada2 sequence table and creates a strollur::strollur object. The dada2 sequence table is a 2D matrix containing the abundance counts by sample for each ASV. The sample names are stored as row names and the sequence nucleotide strings are stored as column names.

To generate the dada2 sequence table from your own files you can follow this dada2 tutorial.

Usage

read_dada2(sequence_table, dataset_name = "")

Arguments

Value

A strollur::strollur object

References

Callahan,B.J., McMurdie,P.J., Rosen,M.J., Han,A.W., Johnson,A.J.A. and Holmes,S.P. (2016), DADA2: High-resolution sample inference from Illumina amplicon data. Nature Methods 13:581-583. https://doi.org/10.1038/nmeth.3869

Examples

seqtab <- readRDS(strollur_example("dada2.rds"))
dim(seqtab)

data <- strollur::read_dada2(sequence_table = seqtab,
                               dataset_name = "dada2 example")

Read a FASTA formatted sequence file

Description

Read a FASTA formatted sequence file

Usage

read_fasta(fasta)

Arguments

Value

A data.frame containing the FASTA sequence data

Examples

fasta_data <- strollur::read_fasta(strollur_example("final.fasta.gz"))

# fasta_data is a data.frame.
# To access the names of the sequences in the file, run the following:

fasta_data$sequence_name

# To access the sequences in the file, run the following:

fasta_data$sequence

Read a FASTQ formatted file

Description

Read a FASTQ formatted file

Usage

read_fastq(fastq, path = NULL, format = "illumina1.8+")

Arguments

Value

A data.frame containing the FASTQ sequence data

Examples

fastq_data <- strollur::read_fastq(strollur_example("tiny.fastq.gz"))

# fastq_data is a data.frame.
# To access the names of the sequences in the file, run the following:

fastq_data$sequence_name

# To access the sequences in the file, run the following:

fastq_data$sequence

# To access the quality scores in the file, run the following:

fastq_data$quality_score

Create a strollur object from mothur outputs

Description

The read_mothur function reads various file types created by mothur, and creates a strollur::strollur object.

To generate the various input files you can follow Pat's Miseq example analysis.

Usage

read_mothur(
  fasta = NULL,
  count = NULL,
  taxonomy = NULL,
  otu_list = NULL,
  asv_list = NULL,
  phylo_list = NULL,
  design = NULL,
  cons_taxonomy = NULL,
  otu_shared = NULL,
  asv_shared = NULL,
  phylo_shared = NULL,
  sample_tree = NULL,
  sequence_tree = NULL,
  sample_distance = NULL,
  dataset_name = ""
)

Arguments

Value

A strollur object

Note

• consensus taxonomy, The strollur::strollur object will generate consensus taxonomies for you based on the sequence taxonomy assignment. You only need to provide the ".cons.taxonomy" file if you are not providing sequence taxonomy assignments.

• shared / rabund file, The strollur::strollur object will generate shared and rabund data for you based on the otu assignment in the list file and the count data. You only need to provide the ".shared" file if you are not providing the list and count files.

References

Schloss,P.D., Westcott,S.L., Ryabin,T., Hall,J.R., Hartmann,M., Hollister,E.B., Lesniewski,R.A., Oakley,B.B., Parks,D.H., Robinson,C.J., Sahl,J.W., Stres,B., Thallinger,G.G., Van Horn,D.J. and Weber,C.F. (2009), Introducing mothur: Open-source, platform-independent, community-supported software for describing and comparing microbial communities. Applied and Environmental Microbiology 75:7537-7541. https://doi.org/10.1128/AEM.01541-09

Examples

# For dataset's including sequence data:

data <- strollur::read_mothur(
  fasta = strollur_example("final.fasta.gz"),
  count = strollur_example("final.count_table.gz"),
  taxonomy = strollur_example("final.taxonomy.gz"),
  design = strollur_example("mouse.time.design"),
  otu_list = strollur_example("final.opti_mcc.list.gz"),
  asv_list = strollur_example("final.asv.list.gz"),
  phylo_list = strollur_example("final.tx.list.gz"),
  sample_tree = strollur_example("final.opti_mcc.jclass.ave.tre"),
  sample_distance = strollur_example(
    "final.opti_mcc.jclass.0.03.column.dist"
  ),
  dataset_name = "miseq_sop"
)

# For dataset's with only otu data:

data <- strollur::read_mothur(
  otu_shared = strollur_example("final.opti_mcc.shared"),
  cons_taxonomy = strollur_example(
    "final.cons.taxonomy"
  ),
  design = strollur_example("mouse.time.design"),
  sample_tree = strollur_example("final.opti_mcc.jclass.ave.tre"),
  dataset_name = "miseq_sop"
)

Read a mothur formatted cons_taxonomy file

Description

Read a mothur formatted cons_taxonomy file

Usage

read_mothur_cons_taxonomy(taxonomy)

Arguments

Value

A data.frame containing the bin names, bin abundances and bin taxonomies.

Examples

# You can add the otu assignments and bin taxonomies to the your data set
# using the following:

# read mothur's consensus taxonomy file into a data.frame
otu_data <- strollur::read_mothur_cons_taxonomy(strollur_example(
  "final.cons.taxonomy"
))

data <- strollur::new_dataset()

# assign abundance only 'otu' bins
strollur::assign(data = data, table = otu_data,
                 type = "bin", bin_type = "otu")

# assign consensus taxonomies to 'otu' bins
strollur::assign(
  data = data, table = otu_data,
  type = "bin_taxonomy", bin_type = "otu"
)

Read a mothur formatted count file

Description

Read a mothur formatted count file

Usage

read_mothur_count(filename)

Arguments

Value

data.frame

Examples

# mothur count file
# Representative_Sequence     total   sample2	sample3	sample4
# seq1	1150	250	400	500
# seq2	115	25	40	50
# seq3	50	25	25	0
# seq4	4	0	0	4

# returns
# sequence_name   sample abundance
# <char>  <char>     <int>
#  1:   seq1 sample2       250
#  2:   seq1 sample3       400
#  3:   seq1 sample4       500
#  4:   seq2 sample2        25
#  5:   seq2 sample3        40
#  6:   seq2 sample4        50
#  7:   seq3 sample2        25
#  8:   seq3 sample3        25
#  9:   seq4 sample4         4

# read a count file with samples
sample_table <-
      strollur::read_mothur_count(strollur_example("final.count_table.gz"))

# You can add your sequence abundance data to your `strollur` object as
# follows:

# create a new empty `strollur::strollur` object
data <- strollur::new_dataset()

# assign sequence abundances parsed by sample
strollur::assign(data, table = sample_table, type = "sequence_abundance")

# print summary of data
data

Read a mothur formatted list file

Description

Read a mothur formatted list file

Usage

read_mothur_list(list)

Arguments

Value

A data.frame containing the sequence otu assignments

Examples

# You can add your otu assignments to the your data set using the following:

# read mothur's list file into data.frame
otu_data <-
     strollur::read_mothur_list(strollur_example("final.opti_mcc.list.gz"))

# create a new empty `strollur::strollur` object
data <- strollur::new_dataset()

# assign sequences to 'otu' bins
strollur::assign(data = data, table = otu_data,
                 type = "bin", bin_type = "otu")

Read a mothur formatted oligos file

Description

Read a mothur formatted oligos file

Usage

read_mothur_oligos(oligos)

Arguments

Value

A data.frame containing the oligos data.

Examples

oligos <-
     strollur::read_mothur_oligos(strollur_example("paired_read.oligos"))

# Create a new dataset and add your oligos data

data <- strollur::new_dataset() |>
  strollur::add(
    table = oligos,
    type = "report",
    report_type = "oligos"
  )

Read a mothur formatted rabund file

Description

Read a mothur formatted rabund file

Usage

read_mothur_rabund(rabund)

Arguments

Value

A data.frame containing the sequence otu assignments

Examples

# You can add your otu assignments to the your data set using the following:

# read rabund file into data.frame
otu_data <- strollur::read_mothur_rabund(
  rabund =
    strollur_example("final.opti_mcc.rabund")
)

data <- strollur::new_dataset()

# assign abundance only 'otu' bins
strollur::assign(data = data, table = otu_data,
                 type = "bin", bin_type = "otu")

Read a mothur formatted shared file

Description

Read a mothur formatted shared file

Usage

read_mothur_shared(shared)

Arguments

Value

A data.frame containing the sequence otu assignments

Examples

# You can add your otu assignments to the your data set using the following:

# read mothur shared file into data.frame
otu_data <-
     strollur::read_mothur_shared(strollur_example("final.opti_mcc.shared"))

# create a new empty `strollur::strollur` object
data <- strollur::new_dataset()

# assign abundance only 'otu' bins parsed by sample
strollur::assign(data = data, table = otu_data,
                  type = "bin", bin_type = "otu")

Read a mothur formatted taxonomy file

Description

Read a mothur formatted taxonomy file

Usage

read_mothur_taxonomy(taxonomy)

Arguments

Value

A data.frame containing the sequences names and sequences taxonomies.

Examples

# You can add the sequences and their taxonomies to the your data set
# using the following:

# read mothur's taxonomy file into a data.frame
classification_data <- strollur::read_mothur_taxonomy(strollur_example(
  "final.taxonomy.gz"
))

# create a new empty `strollur::strollur` object
data <- strollur::new_dataset()

# assign sequence classifications
strollur::assign(data = data, table = classification_data,
                 type = "sequence_taxonomy")

Create a strollur object from a phyloseq object

Description

The strollur::read_phyloseq() function reads phyloseq objects created from the phyloseq package (https://www.bioconductor.org/packages/release/bioc/html/phyloseq.html) and converts it into a strollur object.

Usage

read_phyloseq(phyloseq_object, treatment_column_name = NULL, dataset_name = "")

Arguments

Value

a strollur object

References

McMurdie,P.J. and Holmes,S. (2013), phyloseq: An R Package for Reproducible Interactive Analysis and Graphics of Microbiome Census Data. PLoS ONE 8:e61217. https://doi.org/10.1371/journal.pone.0061217

Examples

miseq <- strollur::miseq_sop_example()

if (requireNamespace("phyloseq", quietly = TRUE)) {
  phylo_obj <- strollur::write_phyloseq(miseq)
  miseq_re_read <- strollur::read_phyloseq(phylo_obj)
} else {
  message(paste(
    "To use this functionality you have to install the",
    "phyloseq package."
  ))
}

Create a strollur object from a qiime2 outputs

Description

The read_qiime2 function reads various types of .qza files created by qiime2, and creates a strollur::strollur object.

Usage

read_qiime2(
  qza,
  metadata = NULL,
  dataset_name = "",
  dir_path = NULL,
  remove_unpacked_artifacts = TRUE
)

Arguments

Value

a strollur object

References

Bolyen,E., Rideout,J.R., Dillon,M.R. et al. (2019), Reproducible, interactive, scalable and extensible microbiome data science using QIIME 2. Bioinformatics 37:852-857. https://doi.org/10.1038/s41587-019-0209-9

Examples

# Using the example files from moving-pictures, we add FASTA data, assign
# taxonomy and abundance for features, and add a newick tree and
# metadata.

qza_files <- c(
  strollur_example("rep_seqs.qza"),
  strollur_example("table.qza"),
  strollur_example("taxonomy.qza"),
  strollur_example("rooted-tree.qza")
)

if (requireNamespace("h5lite", quietly = TRUE)) {
  data <- strollur::read_qiime2(
    qza = qza_files,
    metadata = strollur_example("sample_metadata.tsv"),
    dataset_name = "qiime2_moving_pictures"
  )
  data
} else {
  message(paste(
    "To use this functionality you have to install the",
    "h5lite package."
  ))
}

Read a qiime2 qza containing bin data

Description

Read a qiime2 qza containing bin data

Usage

read_qiime2_feature_table(
  qza,
  dir_path = NULL,
  remove_unpacked_artifacts = TRUE
)

Arguments

Value

A list containing artifact

Examples

if (requireNamespace("h5lite", quietly = TRUE)) {
  artifact <-
       strollur::read_qiime2_feature_table(strollur_example("table.qza"))

  # access the bin assignment table

  artifact$data

  # to create a `strollur::strollur` object with your data

  data <- strollur::new_dataset("my_data")

  strollur::assign(data = data, table = artifact$data, type = "bin")
  data
} else {
  message(paste(
    "To use this functionality you have to install the",
    "h5lite package."
  ))
}

Read a qiime2 .tsv table containing metadata.

Description

Read a qiime2 .tsv table containing metadata.

Usage

read_qiime2_metadata(metadata)

Arguments

Value

A data.frame containing metadata

Examples

metadata <- strollur::read_qiime2_metadata(strollur_example(
  "sample_metadata.tsv"
))

Read a qiime2 qza containing taxonomy data

Description

Read a qiime2 qza containing taxonomy data

Usage

read_qiime2_taxonomy(qza, dir_path = NULL, remove_unpacked_artifacts = TRUE)

Arguments

Value

A list containing artifact

Examples

artifact <- strollur::read_qiime2_taxonomy(strollur_example(
  "taxonomy.qza"
))

# access the taxonomy table

artifact$data

Read a file containing sequence quality scores

Description

Read a file containing sequence quality scores

Usage

read_quality(quality, path = NULL)

Arguments

Value

A data.frame containing the quality score sequence data

Examples

quality_data <- strollur::read_quality(strollur_example("tiny.qual"))

# quality_data is a data.frame.
# To access the names of the sequences in the file, run the following:

quality_data$sequence_name

# To access the quality scores in the file, run the following:

quality_data$quality_score

remove_file

Description

Remove file, if it exists

Usage

remove_file(filename)

Arguments

Get a data.frame containing the given report in a strollur object

Description

Get a data.frame containing the report or the phylo tree requested. Reports include FASTA format, FASTQ format, sequences reports, sequence quality data, sequence_bin_assignments, sequence_taxonomy, sequence_tree, bin_taxonomy, bin_representatives, sample_assignments, sample distances, sample_tree, references, custom reports, sequence_scrap, and bin_scrap in a strollur object.

Usage

report(data, type = "sequence", bin_type = "otu")

Arguments

Value

data.frame or tree

Examples

miseq <- strollur::miseq_sop_example()

# To get the FASTA data

strollur::report(data = miseq, type = "fasta") |> head(n = 5)

# To get a report about the FASTA data

strollur::report(data = miseq, type = "sequence") |> head(n = 5)

# To get the sequence bin assignments

strollur::report(data = miseq,
                 type = "sequence_bin_assignment", bin_type = "otu") |>
  head(n = 5)

# To get the sample treatment assignments

strollur::report(data = miseq, type = "sample_assignment")

# To get a report about sequence classifications

strollur::report(data = miseq, type = "sequence_taxonomy") |> head(n = 10)

# To get a report about bin classifications for 'otu' data

strollur::report(data = miseq,
                 type = "bin_taxonomy", bin_type = "otu") |> head(n = 10)

# To get the 'otu' bin representative sequences

strollur::report(
  data = miseq, type = "bin_representative",
  bin_type = "otu"
) |> head(n = 5)

# To get a report about the sequences removed during your analysis:

strollur::report(data = miseq, type = "sequence_scrap")

# To get a report about the "otu" bins removed during your analysis:

strollur::report(data = miseq, type = "bin_scrap", bin_type = "otu")

# To get the metadata associated with your data:

metadata <- strollur::report(data = miseq, type = "metadata")

# To get the resource references associated with your data:

references <- strollur::report(data = miseq, type = "resource_reference")

# To get our custom report containing the contigs assembly data:

strollur::report(data = miseq, type = "contigs_report") |> head(n = 10)

# To get the tree that relates your sequences:

sequence_tree <- strollur::report(data = miseq, type = "sequence_tree")

# To get the tree that relates your samples:

sample_tree <- strollur::report(data = miseq, type = "sample_tree")

# To get the distances between your samples:

sample_dists <- strollur::report(data = miseq, type = "sample_distance")

Save the strollur object to file.

Description

The save_dataset function will save the strollur object to file.

Usage

save_dataset(data, file)

Arguments

Value

A file containing the strollur::strollur object

See Also

load_dataset()

Examples

data <- strollur::read_mothur(
  fasta = strollur_example("final.fasta.gz"),
  count = strollur_example("final.count_table.gz"),
  taxonomy = strollur_example("final.taxonomy.gz"),
  design = strollur_example("mouse.time.design"),
  otu_list = strollur_example("final.opti_mcc.list.gz"),
  dataset_name = "miseq_sop"
)

file_name <- file.path(tempdir(), "miseq_sop.rds")
strollur::save_dataset(data, file = file_name)

sort_dataframe

Description

Sort dataframe

Usage

sort_dataframe(data, order, named_col)

Arguments

Value

sorted data.frame

Examples

# sort results alphabetically

miseq <- strollur::miseq_sop_example()

sequence_names <- strollur::names(miseq)

fasta <- strollur::report(miseq, type = fasta)

sorted_fasta <- strollur::sort_dataframe(fasta,
  order = sort(sequence_names),
  named_col = "sequence_name"
)

The strollur::strollur object

Description

strollur::strollur is an R6 class that stores nucleotide sequences, abundance, sample and treatment assignments, taxonomic classifications, trees, asv / otu clusters and various reports. It is designed to facilitate data analysis across multiple R packages.

Public fields

Methods

Public methods

• strollur$new()

• strollur$print()

• strollur$abundance()

• strollur$add()

• strollur$alignment_length()

• strollur$assign()

• strollur$clear()

• strollur$count()

• strollur$get_bin_types()

• strollur$get_version()

• strollur$has_bin_taxonomy()

• strollur$has_sequence_taxonomy()

• strollur$is_equal()

• strollur$names()

• strollur$rename()

• strollur$report()

• strollur$summary()

• strollur$clone()

strollur$new()

Create a new strollur::strollur object

Usage

strollur$new(name = "", dataset = NULL)

Arguments

Returns

A new strollur::strollur object.

Examples

# to create an empty strollur object, run the following:

data <- strollur::strollur$new("soil")

strollur$print()

Print a summary of the strollur::strollur object

Usage

strollur$print()

Returns

No return value, called for side effects.

Examples

miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))
miseq

strollur$abundance()

Get the abundance data for sequences, bins, samples, and treatments.

Usage

strollur$abundance(type = "sequence", bin_type = "otu", by_sample = FALSE)

Arguments

Returns

data.frame

Examples

miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))

# To the total abundance for each sequence
miseq$abundance(type = "sequence") |> head(n = 5)

# To the total abundance for each sequence parsed by sample
miseq$abundance(type = "sequence", by_sample = TRUE) |> head(n = 5)

# To the total abundance for each "otu" bin
miseq$abundance(type = "bin", bin_type = "otu") |> head(n = 5)

# To the total abundance for each "otu" bin parsed by sample
miseq$abundance(type = "bin", bin_type = "otu", by_sample = TRUE) |>
head(n = 5)

# To the total abundance for each "asv" bin
miseq$abundance(type = "bin", bin_type = "asv") |> head(n = 5)

# To the total abundance for each "asv" bin parsed by sample
miseq$abundance(type = "bin", bin_type = "asv", by_sample = TRUE) |>
head(n = 5)

# To the total abundance for each sample
miseq$abundance(type = "sample") |> head(n = 5)

# To the total abundance for each treatment
miseq$abundance(type = "treatment")

strollur$add()

Add sequences, reports, trees or resource references

Usage

strollur$add(
  table,
  type = "sequence",
  report_type = NULL,
  table_names = list(sequence_name = "sequence_name", sequence = "sequence", comment =
    "comment", quality_score = "quality_score", reference_vendor = "vendor",
    reference_name = "name", reference_version = "version", reference_usage = "usage",
    reference_note = "note", reference_method_url = "method_url",
    reference_documentation_url = "documentation_url", reference_parameter = "parameter",
    reference_citation = "citation"),
  reference = NULL,
  verbose = TRUE
)

Arguments

Returns

Updated strollur::strollur object

Examples

fasta_data <- strollur::read_fasta(fasta =
strollur_example("final.fasta.gz"))
contigs_report <- readRDS(strollur_example("miseq_contigs_report.rds"))

# Create a new empty `strollur::strollur` object named 'example_dataset'
data <- strollur::strollur$new(name = "example_dataset")

data$add(table = fasta_data, type = "sequence")
data$add(
  table = contigs_report, type = "report",
  report_type = "contigs_report", list(sequence_name = "Name")
)

# To add metadata related to your study

metadata <- readRDS(strollur_example("miseq_metadata.rds"))

data$add(table = metadata, type = "report", report_type = "metadata")

# To add a tree relating to your sequences

tree <- ape::read.tree(strollur_example("final.phylip.tre.gz"))

data$add(table = tree, type = "sequence_tree")

# To add a tree relating to your samples
data <- strollur::strollur$new(name = "example_dataset")

df <-
strollur::read_mothur_shared(strollur_example("final.opti_mcc.shared"))
data$assign(table = df, type = "bin", bin_type = "otu")

tree <- ape::read.tree(strollur_example("final.opti_mcc.jclass.ave.tre"))

data$add(table = tree, type = "sample_tree")

# Create a new empty `strollur::strollur` object named 'example_dataset'
data <- strollur::strollur$new(name = "example_dataset")

# Read FASTQ data into data.frame
fastq_data <-
    strollur::read_fastq(fastq = strollur_example("tiny.fastq.gz"))

# Add FASTQ sequence data
data$add(table = fastq_data, type = "fastq")

strollur$alignment_length()

Get length of alignment

Usage

strollur$alignment_length()

Returns

Integer containing the length of the aligned sequences or -1 if unaligned.

Examples

data <- strollur::miseq_sop_example()
data$alignment_length()

strollur$assign()

Assign sequence abundances, sequence classifications, bins, bin representative sequences, sequence quality data, bin classifications, sample distances or treatments.

Usage

strollur$assign(
  table,
  type = "bin",
  bin_type = "otu",
  table_names = list(sequence_name = "sequence_name", quality_score = "quality_score",
    abundance = "abundance", sample = "sample", treatment = "treatment", taxonomy =
    "taxonomy", level = "level", confidence = "confidence", bin_name = "bin_name"),
  reference = NULL,
  verbose = TRUE
)

Arguments

Returns

Updated strollur::strollur object

Examples

# create a new empty strollur object named 'example_dataset'

data <- strollur::strollur$new(name = "example_dataset")

# Assign sequence abundances

abundance_by_sample <- strollur::read_mothur_count(strollur_example(
  "final.count_table.gz"
))

data$assign(table = abundance_by_sample, type = "sequence_abundance")

# Assign sequence classifications

sequence_classifications <-
strollur::read_mothur_taxonomy(strollur_example( "final.taxonomy.gz" ))

data$assign(table = sequence_classifications, type = "sequence_taxonomy")

# Assigning bins

# read mothur's otu list file into data.frame
otu_data <- strollur::read_mothur_list(list = strollur_example(
  "final.opti_mcc.list.gz"
))

# read mothur's asv list file into data.frame
asv_data <- strollur::read_mothur_list(list = strollur_example(
  "final.asv.list.gz"
))

# read mothur's phylotype list file into data.frame
phylo_data <- strollur::read_mothur_list(list = strollur_example(
  "final.tx.list.gz"
))

# read otu bin representative sequences into a data.frame
bin_reps <- readRDS(strollur_example(
                        "miseq_representative_sequences.rds"))

# assign 'otu' bins using sequence names
data$assign(table = otu_data, bin_type = "otu")

# assign 'asv' bins using sequence names
data$assign(table = asv_data, bin_type = "asv")

# assign 'phylotype' bins using sequence names
data$assign(table = phylo_data, bin_type = "phylotype")

# assign 'otu' bin representative sequences
data$assign(table = bin_reps, type = "bin_representative")

# To assign abundance only bins

# create a new empty strollur object named 'example_dataset'
data <- strollur::strollur$new(name = "example_dataset")

# read mothur's shared file
otu_data <-
strollur::read_mothur_shared(strollur_example("final.opti_mcc.shared"))

# assign abundance only otus parsed by sample
data$assign(table = otu_data, bin_type = "otu")

# Assigning bin classifications

# read bin taxonomies
otu_data <- strollur::read_mothur_cons_taxonomy(strollur_example(
  "final.cons.taxonomy"
))

# assign otu consensus taxonomies
data$assign(
  table = otu_data,
  type = "bin_taxonomy", bin_type = "otu"
)

# Assign treatments

sample_assignments <- readRDS(
   strollur_example("miseq_sample_design.rds"))

data$assign(table = sample_assignments, type = "treatment")

# Assign sample distances

dist_file <- strollur_example("final.opti_mcc.jclass.0.03.column.dist")
sample_dists <- readr::read_table(dist_file,
                                  col_names = FALSE,
                                  show_col_types = FALSE)
data$assign(table = sample_dists, type = "sample_distance")

strollur$clear()

Clear data from datasest

Usage

strollur$clear()

Returns

Updated strollur::strollur object

Examples

miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))
miseq
miseq$clear()
miseq

strollur$count()

Find the number of sequences, samples, treatments or bins of a given type

Usage

strollur$count(
  type = "sequence",
  bin_type = "otu",
  samples = NULL,
  distinct = FALSE
)

Arguments

Returns

double

Examples

miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))

# To get the total number of sequences
miseq$count(type = "sequence")

# To get number of unique sequences
miseq$count(type = "sequence", distinct = TRUE)

# To get number of unique sequences from samples 'F3D0' and 'F3D1'
# Note these sequences will be present in both samples but may be
# be present in other samples as well
miseq$count(type = "sequence", samples = c("F3D0", "F3D1"))

# To get number of unique sequences exclusive to samples 'F3D0' and
# 'F3D1'. Note sequences are present in both samples and NOT present in
# any other samples.

miseq$count(type = "sequence",
            samples = c("F3D0", "F3D1"), distinct = TRUE )

# To get the number of samples in the dataset
miseq$count(type = "sample")

# To get the number of treatments in the dataset
miseq$count(type = "treatment")

# To get the number of "otu" bins in the dataset
miseq$count(type = "bin", bin_type = "otu")

# To get the number of "asv" bins in the dataset
miseq$count(type = "bin", bin_type = "asv")

# To get the number of "phylotype" bins in the dataset
miseq$count(type = "bin", bin_type = "phylotype")

# To get number of "otu" bins from samples 'F3D0' and 'F3D1'
# Note these bins will have sequences from both samples but there may be
# other samples present as well
miseq$count(
  type = "bin", bin_type = "otu", samples = c("F3D0", "F3D1")
)

# To get number of "otu" bins unique to samples 'F3D0' and 'F3D1'
# Note these bins will have sequences from both samples and NO other
# samples will be present in the bins.

miseq$count(
  type = "bin", bin_type = "otu",
  samples = c("F3D0", "F3D1"), distinct = TRUE
)

strollur$get_bin_types()

Get bin table types

Usage

strollur$get_bin_types()

Returns

vector of strings

Examples

data <- strollur::miseq_sop_example()
data$get_bin_types()

strollur$get_version()

Get the version of the strollur object

Usage

strollur$get_version()

Returns

a string

Examples

data <- strollur::strollur$new("test")

data$get_version()

strollur$has_bin_taxonomy()

Determine if your dataset contains bin classifications

Usage

strollur$has_bin_taxonomy(bin_type = "otu")

Arguments

Returns

a logical

Examples

miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))

miseq$has_bin_taxonomy(bin_type = "otu")

strollur$has_sequence_taxonomy()

Determine if your dataset contains sequence classifications

Usage

strollur$has_sequence_taxonomy()

Returns

a logical

Examples

miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))

miseq$has_sequence_taxonomy()

strollur$is_equal()

Determine if two strollur objects are equal.

Usage

strollur$is_equal(data)

Arguments

Returns

a logical

Examples

miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))

data <- strollur::copy_dataset(miseq)

miseq$is_equal(data)

strollur$names()

Get the names of a given type of data

Usage

strollur$names(
  type = "sequence",
  bin_type = "otu",
  samples = NULL,
  distinct = FALSE
)

Arguments

Returns

vector of strings, containing the names requested

Examples

miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))

# To get the name of the dataset
miseq$names(type = "dataset")

# To get the names of the sequences
miseq$names(type = "sequence")

# To get the names of the sequences present sample 'F3D0'
miseq$names(type = "sequence", samples = c("F3D0"))

#' # To get the names of the sequences unique to sample 'F3D0'
miseq$names(type = "sequence", samples = c("F3D0"), distinct = TRUE)

# To get the names of the samples
miseq$names(type = "sample")

# To get the names of the treatments
miseq$names(type = "treatment")

# To get the names of the bins
miseq$names(type = "bin")

# To get the names of the bins that are unique to 'F3D0'
miseq$names(type = "bin", samples = c("F3D0"), distinct = TRUE)

# To get the names of the bins that include sequences from 'F3D0'
miseq$names(type = "bin", samples = c("F3D0"), distinct = FALSE)

# To get the names of the reports
miseq$names(type = "report")

strollur$rename()

Rename your strollur object.

Usage

strollur$rename(name)

Arguments

Returns

Updated strollur::strollur object

Examples

data <- strollur::strollur$new("old_name")
data

data$rename("new_name")
data

strollur$report()

Get a data.frame containing the given report, or the phylo tree requested.

Usage

strollur$report(type = "sequence", bin_type = "otu")

Arguments

Returns

data.frame or tree

Examples

miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))

# To get the FASTA data

miseq$report(type = "fasta") |> head(n = 5)

# To get a report about the FASTA data

miseq$report(type = "sequence") |> head(n = 5)

# To get the sequence bin assignments

miseq$report(type = "sequence_bin_assignment", bin_type = "otu") |>
head(n = 5)

# To get the sample treatment assignments

miseq$report(type = "sample_assignment") |> head(n = 5)

# To get a report about sequence classifications

miseq$report(type = "sequence_taxonomy") |> head(n = 5)

# To get a report about bin classifications for 'otu' data

miseq$report(type = "bin_taxonomy", bin_type = "otu") |> head(n = 5)

# To get the 'otu' bin representative sequences

miseq$report(type = "bin_representative", bin_type = "otu") |>
head(n = 5)

# To get a report about the sequences removed during your analysis:

miseq$report(type = "sequence_scrap")

# To get a report about the "otu" bins removed during your analysis:

miseq$report(type = "bin_scrap", bin_type = "otu")

# To get the metadata associated with your data:

metadata <- miseq$report(type = "metadata") |> head(n = 5)

# To get the resource references associated with your data:

references <- miseq$report(type = "resource_reference")

# To get our custom report containing the contigs assembly data:

miseq$report(type = "contigs_report") |> head(n = 5)

# To get the tree that relates your sequences:

sequence_tree <- miseq$report(type = "sequence_tree")

# To get the tree that relates your sequences:

sample_tree <- miseq$report(type = "sample_tree")

# To get the distances between your samples:

sample_dists <- miseq$report(type = "sample_distance")

strollur$summary()

Summarize the sequences data, custom reports, and scrapped data

Usage

strollur$summary(type = "sequence", report_type = NULL, verbose = TRUE)

Arguments

Returns

data.frame Get summary of the sequence reports

Examples

miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))

# To get the summary of your FASTA data
miseq$summary(type = "sequence")

# summarize contigs_report
miseq$summary(type = "report", report_type = "contigs_report")

# remove sample 'F3D0' to produce a scrap report
strollur::xdev_remove_samples(data = miseq, samples = c("F3D0"))

# summarize scrapped data -
# sequences and bins scrapped by removing the sample "F3D0"
miseq$summary(type = "scrap")

strollur$clone()

The objects of this class are cloneable with this method.

Usage

strollur$clone(deep = FALSE)

Arguments

Author(s)

Sarah Westcott, swestcot@umich.edu

See Also

taxonomy_table_format

Examples

## ------------------------------------------------
## Method `strollur$new()`
## ------------------------------------------------


# to create an empty strollur object, run the following:

data <- strollur::strollur$new("soil")


## ------------------------------------------------
## Method `strollur$print()`
## ------------------------------------------------

miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))
miseq


## ------------------------------------------------
## Method `strollur$abundance()`
## ------------------------------------------------


miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))

# To the total abundance for each sequence
miseq$abundance(type = "sequence") |> head(n = 5)

# To the total abundance for each sequence parsed by sample
miseq$abundance(type = "sequence", by_sample = TRUE) |> head(n = 5)

# To the total abundance for each "otu" bin
miseq$abundance(type = "bin", bin_type = "otu") |> head(n = 5)

# To the total abundance for each "otu" bin parsed by sample
miseq$abundance(type = "bin", bin_type = "otu", by_sample = TRUE) |>
head(n = 5)

# To the total abundance for each "asv" bin
miseq$abundance(type = "bin", bin_type = "asv") |> head(n = 5)

# To the total abundance for each "asv" bin parsed by sample
miseq$abundance(type = "bin", bin_type = "asv", by_sample = TRUE) |>
head(n = 5)

# To the total abundance for each sample
miseq$abundance(type = "sample") |> head(n = 5)

# To the total abundance for each treatment
miseq$abundance(type = "treatment")


## ------------------------------------------------
## Method `strollur$add()`
## ------------------------------------------------


fasta_data <- strollur::read_fasta(fasta =
strollur_example("final.fasta.gz"))
contigs_report <- readRDS(strollur_example("miseq_contigs_report.rds"))

# Create a new empty `strollur::strollur` object named 'example_dataset'
data <- strollur::strollur$new(name = "example_dataset")

data$add(table = fasta_data, type = "sequence")
data$add(
  table = contigs_report, type = "report",
  report_type = "contigs_report", list(sequence_name = "Name")
)

# To add metadata related to your study

metadata <- readRDS(strollur_example("miseq_metadata.rds"))

data$add(table = metadata, type = "report", report_type = "metadata")

# To add a tree relating to your sequences

tree <- ape::read.tree(strollur_example("final.phylip.tre.gz"))

data$add(table = tree, type = "sequence_tree")

# To add a tree relating to your samples
data <- strollur::strollur$new(name = "example_dataset")

df <-
strollur::read_mothur_shared(strollur_example("final.opti_mcc.shared"))
data$assign(table = df, type = "bin", bin_type = "otu")

tree <- ape::read.tree(strollur_example("final.opti_mcc.jclass.ave.tre"))

data$add(table = tree, type = "sample_tree")

# Create a new empty `strollur::strollur` object named 'example_dataset'
data <- strollur::strollur$new(name = "example_dataset")

# Read FASTQ data into data.frame
fastq_data <-
    strollur::read_fastq(fastq = strollur_example("tiny.fastq.gz"))

# Add FASTQ sequence data
data$add(table = fastq_data, type = "fastq")


## ------------------------------------------------
## Method `strollur$alignment_length()`
## ------------------------------------------------


data <- strollur::miseq_sop_example()
data$alignment_length()


## ------------------------------------------------
## Method `strollur$assign()`
## ------------------------------------------------


# create a new empty strollur object named 'example_dataset'

data <- strollur::strollur$new(name = "example_dataset")

# Assign sequence abundances

abundance_by_sample <- strollur::read_mothur_count(strollur_example(
  "final.count_table.gz"
))

data$assign(table = abundance_by_sample, type = "sequence_abundance")

# Assign sequence classifications

sequence_classifications <-
strollur::read_mothur_taxonomy(strollur_example( "final.taxonomy.gz" ))

data$assign(table = sequence_classifications, type = "sequence_taxonomy")

# Assigning bins

# read mothur's otu list file into data.frame
otu_data <- strollur::read_mothur_list(list = strollur_example(
  "final.opti_mcc.list.gz"
))

# read mothur's asv list file into data.frame
asv_data <- strollur::read_mothur_list(list = strollur_example(
  "final.asv.list.gz"
))

# read mothur's phylotype list file into data.frame
phylo_data <- strollur::read_mothur_list(list = strollur_example(
  "final.tx.list.gz"
))

# read otu bin representative sequences into a data.frame
bin_reps <- readRDS(strollur_example(
                        "miseq_representative_sequences.rds"))

# assign 'otu' bins using sequence names
data$assign(table = otu_data, bin_type = "otu")

# assign 'asv' bins using sequence names
data$assign(table = asv_data, bin_type = "asv")

# assign 'phylotype' bins using sequence names
data$assign(table = phylo_data, bin_type = "phylotype")

# assign 'otu' bin representative sequences
data$assign(table = bin_reps, type = "bin_representative")

# To assign abundance only bins

# create a new empty strollur object named 'example_dataset'
data <- strollur::strollur$new(name = "example_dataset")

# read mothur's shared file
otu_data <-
strollur::read_mothur_shared(strollur_example("final.opti_mcc.shared"))

# assign abundance only otus parsed by sample
data$assign(table = otu_data, bin_type = "otu")

# Assigning bin classifications

# read bin taxonomies
otu_data <- strollur::read_mothur_cons_taxonomy(strollur_example(
  "final.cons.taxonomy"
))

# assign otu consensus taxonomies
data$assign(
  table = otu_data,
  type = "bin_taxonomy", bin_type = "otu"
)

# Assign treatments

sample_assignments <- readRDS(
   strollur_example("miseq_sample_design.rds"))

data$assign(table = sample_assignments, type = "treatment")

# Assign sample distances

dist_file <- strollur_example("final.opti_mcc.jclass.0.03.column.dist")
sample_dists <- readr::read_table(dist_file,
                                  col_names = FALSE,
                                  show_col_types = FALSE)
data$assign(table = sample_dists, type = "sample_distance")


## ------------------------------------------------
## Method `strollur$clear()`
## ------------------------------------------------

miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))
miseq
miseq$clear()
miseq

## ------------------------------------------------
## Method `strollur$count()`
## ------------------------------------------------


miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))

# To get the total number of sequences
miseq$count(type = "sequence")

# To get number of unique sequences
miseq$count(type = "sequence", distinct = TRUE)

# To get number of unique sequences from samples 'F3D0' and 'F3D1'
# Note these sequences will be present in both samples but may be
# be present in other samples as well
miseq$count(type = "sequence", samples = c("F3D0", "F3D1"))

# To get number of unique sequences exclusive to samples 'F3D0' and
# 'F3D1'. Note sequences are present in both samples and NOT present in
# any other samples.

miseq$count(type = "sequence",
            samples = c("F3D0", "F3D1"), distinct = TRUE )

# To get the number of samples in the dataset
miseq$count(type = "sample")

# To get the number of treatments in the dataset
miseq$count(type = "treatment")

# To get the number of "otu" bins in the dataset
miseq$count(type = "bin", bin_type = "otu")

# To get the number of "asv" bins in the dataset
miseq$count(type = "bin", bin_type = "asv")

# To get the number of "phylotype" bins in the dataset
miseq$count(type = "bin", bin_type = "phylotype")

# To get number of "otu" bins from samples 'F3D0' and 'F3D1'
# Note these bins will have sequences from both samples but there may be
# other samples present as well
miseq$count(
  type = "bin", bin_type = "otu", samples = c("F3D0", "F3D1")
)

# To get number of "otu" bins unique to samples 'F3D0' and 'F3D1'
# Note these bins will have sequences from both samples and NO other
# samples will be present in the bins.

miseq$count(
  type = "bin", bin_type = "otu",
  samples = c("F3D0", "F3D1"), distinct = TRUE
)


## ------------------------------------------------
## Method `strollur$get_bin_types()`
## ------------------------------------------------


data <- strollur::miseq_sop_example()
data$get_bin_types()


## ------------------------------------------------
## Method `strollur$get_version()`
## ------------------------------------------------


data <- strollur::strollur$new("test")

data$get_version()


## ------------------------------------------------
## Method `strollur$has_bin_taxonomy()`
## ------------------------------------------------


miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))

miseq$has_bin_taxonomy(bin_type = "otu")


## ------------------------------------------------
## Method `strollur$has_sequence_taxonomy()`
## ------------------------------------------------


miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))

miseq$has_sequence_taxonomy()


## ------------------------------------------------
## Method `strollur$is_equal()`
## ------------------------------------------------


miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))

data <- strollur::copy_dataset(miseq)

miseq$is_equal(data)


## ------------------------------------------------
## Method `strollur$names()`
## ------------------------------------------------


miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))

# To get the name of the dataset
miseq$names(type = "dataset")

# To get the names of the sequences
miseq$names(type = "sequence")

# To get the names of the sequences present sample 'F3D0'
miseq$names(type = "sequence", samples = c("F3D0"))

#' # To get the names of the sequences unique to sample 'F3D0'
miseq$names(type = "sequence", samples = c("F3D0"), distinct = TRUE)

# To get the names of the samples
miseq$names(type = "sample")

# To get the names of the treatments
miseq$names(type = "treatment")

# To get the names of the bins
miseq$names(type = "bin")

# To get the names of the bins that are unique to 'F3D0'
miseq$names(type = "bin", samples = c("F3D0"), distinct = TRUE)

# To get the names of the bins that include sequences from 'F3D0'
miseq$names(type = "bin", samples = c("F3D0"), distinct = FALSE)

# To get the names of the reports
miseq$names(type = "report")


## ------------------------------------------------
## Method `strollur$rename()`
## ------------------------------------------------


data <- strollur::strollur$new("old_name")
data

data$rename("new_name")
data


## ------------------------------------------------
## Method `strollur$report()`
## ------------------------------------------------


miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))

# To get the FASTA data

miseq$report(type = "fasta") |> head(n = 5)

# To get a report about the FASTA data

miseq$report(type = "sequence") |> head(n = 5)

# To get the sequence bin assignments

miseq$report(type = "sequence_bin_assignment", bin_type = "otu") |>
head(n = 5)

# To get the sample treatment assignments

miseq$report(type = "sample_assignment") |> head(n = 5)

# To get a report about sequence classifications

miseq$report(type = "sequence_taxonomy") |> head(n = 5)

# To get a report about bin classifications for 'otu' data

miseq$report(type = "bin_taxonomy", bin_type = "otu") |> head(n = 5)

# To get the 'otu' bin representative sequences

miseq$report(type = "bin_representative", bin_type = "otu") |>
head(n = 5)

# To get a report about the sequences removed during your analysis:

miseq$report(type = "sequence_scrap")

# To get a report about the "otu" bins removed during your analysis:

miseq$report(type = "bin_scrap", bin_type = "otu")

# To get the metadata associated with your data:

metadata <- miseq$report(type = "metadata") |> head(n = 5)

# To get the resource references associated with your data:

references <- miseq$report(type = "resource_reference")

# To get our custom report containing the contigs assembly data:

miseq$report(type = "contigs_report") |> head(n = 5)

# To get the tree that relates your sequences:

sequence_tree <- miseq$report(type = "sequence_tree")

# To get the tree that relates your sequences:

sample_tree <- miseq$report(type = "sample_tree")

# To get the distances between your samples:

sample_dists <- miseq$report(type = "sample_distance")


## ------------------------------------------------
## Method `strollur$summary()`
## ------------------------------------------------


miseq <- strollur::load_dataset(strollur_example("miseq_sop.rds"))

# To get the summary of your FASTA data
miseq$summary(type = "sequence")

# summarize contigs_report
miseq$summary(type = "report", report_type = "contigs_report")

# remove sample 'F3D0' to produce a scrap report
strollur::xdev_remove_samples(data = miseq, samples = c("F3D0"))

# summarize scrapped data -
# sequences and bins scrapped by removing the sample "F3D0"
miseq$summary(type = "scrap")

strollur_example

Description

strollur comes bundled with some example files in its inst/extdata directory. This function make them easy to access them.

Usage

strollur_example(file = NULL)

Arguments

Details

Get path to strollur example

Value

string, Full path to example files

Examples

strollur::strollur_example()
strollur::strollur_example("final.fasta.gz")

Summarize the sequences data, custom reports, and scrapped data in a strollur object

Description

Summarize the sequences data, custom reports, and scrapped data in a strollur object

Usage

summary(data, type = "sequence", report_type = NULL, verbose = TRUE)

Arguments

Value

data.frame

Examples

miseq <- strollur::miseq_sop_example()

# To get the summary of your FASTA data
strollur::summary(data = miseq, type = "sequence")

# summarize contigs_report
strollur::summary(data = miseq,
                  type = "report", report_type = "contigs_report")

# remove sample 'F3D0' to produce a scrap report
strollur::xdev_remove_samples(data = miseq, samples = c("F3D0"))

# summarize FASTA data after removal of sample F3D0
strollur::summary(data = miseq, type = "sequence")

# summarize scrapped data -
# sequences and bins scrapped by removing the sample "F3D0"
strollur::summary(data = miseq, type = "scrap")

taxonomy_table_format

Description

strollur accepts two formats for classification data: full or tidy.

Details

The full taxonomy table is a data.frame with two columns: sequence_name or bin_name, and taxonomy. The taxonomy column contains the full classification string.

The full taxonomy table format:

sequence_name
M00967_43_000000000-A3JHG_1_1102_26308_14496
M00967_43_000000000-A3JHG_1_1103_22654_26891

taxonomy
Bacteria(100);"Bacteroidetes"(100);"Bacteroidia"(100);"Bacteroidales"(100);
Bacteria(100);Firmicutes(99);Clostridia(99);Clostridiales(99);

The tidy taxonomy table is a data.frame with 4 columns: sequence_name or bin_name, taxonomy, level, and confidence. For example:

The tidy taxonomy table format:

sequence_name                                    taxonomy
M00967_43_000000000-A3JHG_1_1102_26308_14496     Bacteria
M00967_43_000000000-A3JHG_1_1102_26308_14496     "Bacteroidetes"
M00967_43_000000000-A3JHG_1_1102_26308_14496     "Bacteroidia"
M00967_43_000000000-A3JHG_1_1102_26308_14496     "Bacteroidales"
M00967_43_000000000-A3JHG_1_1103_22654_26891     Bacteria
M00967_43_000000000-A3JHG_1_1103_22654_26891     Firmicutes
M00967_43_000000000-A3JHG_1_1103_22654_26891     Clostridia
M00967_43_000000000-A3JHG_1_1103_22654_26891     Clostridiales

level    confidence
1        100
2        100
3        100
4        100
1        100
2        99
3        99
4        99

The unpack_qiime2_artifact function reads .qza files created by qiime2, and returns the artifact.

Description

The unpack_qiime2_artifact function reads .qza files created by qiime2, and returns the artifact.

Usage

unpack_qiime2_artifact(qza, dir_path = NULL)

Arguments

Value

A unpacked qza artifact

Examples

# Using the example files from moving-pictures

artifact <- strollur::unpack_qiime2_artifact(
  qza = strollur_example("table.qza"),
  dir_path = tempdir()
)

Write a BIOM formatted file containing a strollur object's data.

Description

Write a BIOM formatted file containing your strollur::strollur objects data.

Usage

write_biom(
  data,
  file_root = NULL,
  path = NULL,
  taxonomy = TRUE,
  sequence = TRUE
)

Arguments

Value

vector of BIOM file names. One for each bin type.

Examples

if (requireNamespace("h5lite", quietly = TRUE)) {
  miseq <- strollur::miseq_sop_example()
  strollur::write_biom(miseq, tempfile())
} else {
  message(paste(
    "To use this functionality you have to install the",
    "h5lite package."
  ))
}

Write a FASTA formatted sequence file

Description

Write a FASTA formatted sequence file

Usage

write_fasta(data, filename = NULL, degap = FALSE)

Arguments

Value

name of FASTA file

Examples

miseq <- strollur::miseq_sop_example()
strollur::write_fasta(miseq, tempfile())

Write a FASTQ formatted file

Description

Write a FASTQ formatted file

Usage

write_fastq(data, filename = NULL)

Arguments

Value

name of FASTQ file

Examples

table <- strollur::read_fastq(strollur_example("tiny.fastq.gz"))

# Create `strollur::strollur` object
data <- strollur::new_dataset("example")

# Add FASTQ data `strollur::strollur` object
strollur::add(data, table, type = "fastq")

# Write `strollur::strollur` objects FASTQ data to file
strollur::write_fastq(data, tempfile())

Write the various file types from your strollur object for use with mothur.

Description

The write_mothur function will write various file types for use with mothur.

Usage

write_mothur(data, dir_path = NULL, compress = TRUE, tags = NULL)

Arguments

Value

a vector of file names

References

Schloss,P.D., Westcott,S.L., Ryabin,T., Hall,J.R., Hartmann,M., Hollister,E.B., Lesniewski,R.A., Oakley,B.B., Parks,D.H., Robinson,C.J., Sahl,J.W., Stres,B., Thallinger,G.G., Van Horn,D.J. and Weber,C.F. (2009), Introducing mothur: Open-source, platform-independent, community-supported software for describing and comparing microbial communities. Applied and Environmental Microbiology 75:7537-7541. https://doi.org/10.1128/AEM.01541-09

Examples

miseq <- strollur::miseq_sop_example()
files <- strollur::write_mothur(miseq, tempdir(), compress = FALSE)

Write a mothur formatted cons_taxonomy file

Description

Write a mothur formatted cons_taxonomy file

Usage

write_mothur_cons_taxonomy(data, file_root = NULL)

Arguments

Value

vector containing the names of the files created

Examples

miseq <- strollur::miseq_sop_example()
strollur::write_mothur_cons_taxonomy(miseq, tempfile())

Write a mothur formatted count file

Description

Write a mothur formatted count file

Usage

write_mothur_count(data, filename = NULL)

Arguments

Value

name of count file

Examples

miseq <- strollur::miseq_sop_example()
strollur::write_mothur_count(miseq, tempfile())

Write a mothur formatted design file

Description

Write a mothur formatted design file

Usage

write_mothur_design(data, filename = NULL)

Arguments

Value

name of design file

Examples

miseq <- strollur::miseq_sop_example()
strollur::write_mothur_design(miseq, tempfile())

Write mothur formatted list files

Description

Write mothur formatted list files

Usage

write_mothur_list(data, file_root = NULL)

Arguments

Value

vector containing the names of the files created

Examples

miseq <- strollur::miseq_sop_example()
strollur::write_mothur_list(miseq, tempfile())

Write mothur formatted rabund files

Description

Write mothur formatted rabund files

Usage

write_mothur_rabund(data, file_root = NULL)

Arguments

Value

vector containing the names of the files created

Examples

miseq <- strollur::miseq_sop_example()
strollur::write_mothur_rabund(miseq, tempfile())

Write mothur formatted shared files

Description

Write mothur formatted shared files

Usage

write_mothur_shared(data, file_root = NULL)

Arguments

Value

vector containing the names of the files created

Examples

miseq <- strollur::miseq_sop_example()
strollur::write_mothur_shared(miseq, tempfile())

Create a phyloseq object from your strollur object

Description

The strollur::write_phyloseq() function will take any strollur object and return it as a phyloseq object.

Usage

write_phyloseq(data)

Arguments

Value

returns a phyloseq object.

References

McMurdie,P.J. and Holmes,S. (2013), phyloseq: An R Package for Reproducible Interactive Analysis and Graphics of Microbiome Census Data. PLoS ONE 8:e61217. https://doi.org/10.1371/journal.pone.0061217

Examples

miseq <- strollur::miseq_sop_example()
if (requireNamespace("phyloseq", quietly = TRUE)) {
  phylo_obj <- strollur::write_phyloseq(miseq)
} else {
  message(paste(
    "To use this functionality you have to install the",
    "phyloseq package."
  ))
}

Write a file containing sequence quality scores

Description

Write a file containing sequence quality scores

Usage

write_quality(data, filename = NULL)

Arguments

Value

name of sequence quality file

Examples

table <- strollur::read_fastq(strollur_example("tiny.fastq.gz"))

# Create `strollur::strollur` object
data <- strollur::new_dataset("example")

# Add FASTQ data `strollur::strollur` object
strollur::add(data, table, type = "fastq")

# Write `strollur::strollur` objects sequence quality data to file
strollur::write_quality(data, tempfile())

Write a 2 column taxonomy file

Description

Write a 2 column taxonomy file

Usage

write_taxonomy(data, filename = NULL)

Arguments

Value

name of taxonomy file

Examples

miseq <- strollur::miseq_sop_example()
strollur::write_taxonomy(miseq, tempfile())

Get a data.frame containing the requested abundance data

Description

Get a table containing the requested abundance data in a strollur object

Usage

xdev_abundance(data, type = "sequence", bin_type = "otu", by_sample = FALSE)

Arguments

Value

data.frame

Examples

miseq <- strollur::miseq_sop_example()

# To the total abundance for each sequence
strollur::xdev_abundance(data = miseq, type = "sequence")

# To the total abundance for each sequence parsed by sample
strollur::xdev_abundance(data = miseq, type = "sequence",
                           by_sample = TRUE)

# To the total abundance for each "otu" bin
strollur::xdev_abundance(data = miseq, type = "bin",
                           bin_type = "otu")

# To the total abundance for each "otu" bin parsed by sample
strollur::xdev_abundance(data = miseq, type = "bin",
                           bin_type = "otu", by_sample = TRUE)

# To the total abundance for each "asv" bin
strollur::xdev_abundance(data = miseq, type = "bin",
                           bin_type = "asv")

# To the total abundance for each "asv" bin parsed by sample
strollur::xdev_abundance(data = miseq, type = "bin",
                           bin_type = "asv", by_sample = TRUE)

# To the total abundance of each sample
strollur::xdev_abundance(data = miseq, type = "sample")

# To the total abundance of each treatment
strollur::xdev_abundance(data = miseq, type = "treatment")

Add resource references to a strollur object to aid in reproducibility

Description

Add resource references to a strollur object

Usage

xdev_add_references(
  data,
  table,
  name = "name",
  vendor = "vendor",
  version = "version",
  usage = "usage",
  note = "note",
  method_url = "method_url",
  documentation_url = "documentation_url",
  parameter = "parameter",
  citation = "citation",
  verbose = TRUE
)

Arguments

Value

an updated strollur object

Examples

data <- strollur::new_dataset("just for fun")
reference_table <- readr::read_csv(strollur_example("references.csv"),
                             col_names = TRUE, show_col_types = FALSE)
strollur::xdev_add_references(data, reference_table)

Add a report to a strollur object

Description

Add a report to a strollur object

Usage

xdev_add_report(
  data,
  table,
  reference = NULL,
  type = "report",
  sequence_name = "none",
  verbose = TRUE
)

Arguments

Value

an updated strollur object

Examples

# To add a custom report including your contigs assembly data

data <- strollur::new_dataset("just for fun")
contigs_report <- readRDS(strollur_example("miseq_contigs_report.rds"))

strollur::xdev_add_report(data,
                            table = contigs_report,
                            type = "contigs_report",
                            sequence_name = "Name")

# To add metadata related to your study

metadata <- readRDS(strollur_example("miseq_metadata.rds"))

strollur::xdev_add_report(data,
                            table = metadata,
                            type = "metadata")

Add FASTQ data to a strollur object

Description

Add FASTQ data to a strollur object.

Usage

xdev_add_sequence_fastq_scores(
  data,
  table,
  reference = NULL,
  sequence_name = "sequence_name",
  sequence = "sequence",
  quality_score = "quality_score",
  verbose = TRUE
)

Arguments

Value

an updated strollur object

Examples

table <- strollur::read_fastq(strollur_example("tiny.fastq.gz"))
data <- strollur::new_dataset("example")
strollur::xdev_add_sequence_fastq_scores(data, table)
data

Add sequence data to a strollur object

Description

Add sequence data to a strollur object

Usage

xdev_add_sequences(
  data,
  table,
  reference = NULL,
  sequence_name = "sequence_name",
  sequence = "sequence",
  comment = "comment",
  verbose = TRUE
)

Arguments

Value

an updated strollur object

Examples

 data <- strollur::new_dataset("miseq_sop")
 fasta_data <- strollur::read_fasta(strollur_example("final.fasta.gz"))
 strollur::xdev_add_sequences(data, fasta_data)

# With the additional parameters to add information about the reference

 data <- strollur::new_dataset("miseq_sop")
 fasta_data <- strollur::read_fasta(strollur_example("final.fasta.gz"))

 strollur::xdev_add_sequences(data, fasta_data,
               new_reference("silva.bacteria.fasta",
               "1.38.1",
               "alignment by mothur2 v1.0 using default options",
               "https://mothur.org/wiki/silva_reference_files/"))

# You can also add references using the `strollur::xdev_add_references`
# function.

Assign representative sequences to bins

Description

Assign representative sequences to bins.

Usage

xdev_assign_bin_representative_sequences(
  data,
  table,
  bin_type = "otu",
  reference = NULL,
  bin_name = "bin_name",
  sequence_name = "sequence_name",
  verbose = TRUE
)

Arguments

Value

an updated strollur object

Examples

  miseq <- strollur::miseq_sop_example()

  bin_reps <- readRDS(strollur_example(
         "miseq_representative_sequences.rds"))

  strollur::xdev_assign_bin_representative_sequences(miseq,
                          table = bin_reps, bin_type = "otu")

Assign bin classifications to a strollur object

Description

Assign bin classifications to a strollur object

Note, if you assign sequence taxonomies and assign bins, strollur will find the concensus taxonomy for each bin for you.

Usage

xdev_assign_bin_taxonomy(
  data,
  table,
  bin_type = "otu",
  reference = NULL,
  bin_name = "bin_name",
  taxonomy = "taxonomy",
  verbose = TRUE
)

Arguments

Value

an updated strollur object

Examples

otu_data <- strollur::read_mothur_cons_taxonomy(strollur_example(
                        "final.cons.taxonomy"))

data <- strollur::new_dataset(dataset_name = "my_dataset")

# assign otu abundances
strollur::xdev_assign_bins(data,
                             table = otu_data,
                             bin_type = "otu")

# assign otu classifications
strollur::xdev_assign_bin_taxonomy(data,
                                     table = otu_data,
                                     bin_type = "otu")

Assign bin classifications to a strollur object

Description

Assign bin classifications to a strollur object

Usage

xdev_assign_bin_taxonomy_tidy(
  data,
  table,
  bin_type = "otu",
  reference = NULL,
  bin_name = "bin_name",
  level = "level",
  taxonomy = "taxonomy",
  confidence = "confidence",
  verbose = TRUE
)

Arguments

Value

an updated strollur object

Examples

bin_classifications <- readRDS(strollur_example("miseq_tidy_bin_taxonomy.rds"))
str(bin_classifications)

data <- strollur::read_mothur(otu_shared =
                                strollur_example("final.opti_mcc.shared"))

xdev_assign_bin_taxonomy_tidy(data, bin_classifications)

# With the reference parameter you can add information about the reference
# you used to classify your bins. You can also add references using the
# 'strollur::xdev_add_references' function.

reference <- new_reference("trainset9_032012.pds.zip", "9_032012",
              "classification_otu by mothur2 v1.0.0 using default options",
               "",
"https://mothur.s3.us-east-2.amazonaws.com/wiki/trainset9_032012.pds.zip")

xdev_assign_bin_taxonomy_tidy(data, bin_classifications,
                                 reference = reference)

Add bin assignments to a strollur object

Description

Add bin assignments to a strollur object

Usage

xdev_assign_bins(
  data,
  table,
  bin_type = "otu",
  reference = NULL,
  bin_name = "bin_name",
  abundance = "abundance",
  sample = "sample",
  sequence_name = "sequence_name",
  verbose = TRUE
)

Arguments

Value

an updated strollur object

Examples

  # To assign sequences to bins:

  data <- strollur::new_dataset(dataset_name = "miseq_sop")
  otu_data <- strollur::read_mothur_list(
                          list = strollur_example("final.opti_mcc.list.gz"))

  strollur::xdev_assign_bins(data, table = otu_data, bin_type = "otu")

  # To add abundance only bin assignments:

  data <- strollur::new_dataset(dataset_name = "miseq_sop")
  otu_data <- strollur::read_mothur_rabund(
                         rabund = strollur_example("final.opti_mcc.rabund"))

  strollur::xdev_assign_bins(data, table = otu_data, bin_type = "otu")

  # To add abundance bin assignments parsed by sample:

  data <- strollur::new_dataset(dataset_name = "miseq_sop")
  otu_data <- readRDS(strollur_example("miseq_shared_otu.rds"))

  strollur::xdev_assign_bins(data, table = otu_data, bin_type = "otu")

Assign samples distances in a strollur object

Description

Assign samples distances in a strollur object

Usage

xdev_assign_sample_distances(data, table, reference = NULL, verbose = TRUE)

Arguments

Value

an updated strollur object

Examples

shared_file <- strollur_example("final.opti_mcc.shared")
dist_file <- strollur_example("final.opti_mcc.jclass.0.03.column.dist")
reference <- strollur::new_reference(name = "jclass estimator distances",
                                     vendor = "mothur_v1.48.6")

data <- strollur::new_dataset("my_dataset")
df <- read_mothur_shared(shared_file)
xdev_assign_bins(data, table = df, bin_type = "otu")

sample_dists <- readr::read_table(dist_file,
                                  col_names = FALSE,
                                  show_col_types = FALSE)
xdev_assign_sample_distances(data, table = sample_dists,
                             reference = reference)
data

Assign sequence abundance and optionally assign sample and treatment data to a strollur object

Description

Assign sequence abundance and optionally assign sample and treatment data to a strollur object

Usage

xdev_assign_sequence_abundance(
  data,
  table,
  sequence_name = "sequence_name",
  abundance = "abundance",
  sample = "sample",
  treatment = "treatment",
  verbose = TRUE
)

Arguments

Value

an updated strollur object

Examples

data <- strollur::new_dataset("my_dataset")
abundance <- readRDS(strollur_example("miseq_abundance_by_sample.rds"))

strollur::xdev_assign_sequence_abundance(data,
                                           table = abundance)

Add quality data to a strollur object

Description

Add quality data to a strollur object.

Usage

xdev_assign_sequence_quality_scores(
  data,
  table,
  reference = NULL,
  sequence_name = "sequence_name",
  quality_score = "quality_score",
  verbose = TRUE
)

Arguments

Value

an updated strollur object

Examples

qual_table <- strollur::read_quality(strollur_example("tiny.qual"))
fasta_table <- strollur::read_fasta(strollur_example("tiny.fasta"))

data <- strollur::new_dataset("example")
strollur::xdev_add_sequences(data, fasta_table)
strollur::xdev_assign_sequence_quality_scores(data, qual_table)

data

Assign sequence classifications to a strollur object

Description

Assign sequence classifications to a strollur object

Note, if you assign sequence taxonomies and assign bins, strollur will find the consensus taxonomy for each bin for you.

Usage

xdev_assign_sequence_taxonomy(
  data,
  table,
  reference = NULL,
  sequence_name = "sequence_name",
  taxonomy = "taxonomy",
  verbose = TRUE
)

Arguments

Value

an updated strollur object

Examples

taxonomy <- strollur::read_mothur_taxonomy(strollur_example(
                        "final.taxonomy.gz"))

data <- strollur::new_dataset("my_dataset")

strollur::xdev_assign_sequence_taxonomy(data,
                                          table = taxonomy)

# With the reference parameter you can add information about the reference
# you used to classify your sequences. You can also add references using the
# 'strollur::xdev_add_references' function.

reference <- strollur::new_reference("trainset9_032012.pds.zip", "9_032012",
              "classification by mothur2 v1.0 using default options", "",
"https://mothur.s3.us-east-2.amazonaws.com/wiki/trainset9_032012.pds.zip")

strollur::xdev_assign_sequence_taxonomy(data,
                                        table = taxonomy,
                                        reference = reference)

Assign sequence classifications to a strollur object

Description

Assign sequence classifications to a strollur object

Note, if you assign sequence taxonomies and assign bins, strollur will find the consensus taxonomy for each bin for you.

Usage

xdev_assign_sequence_taxonomy_tidy(
  data,
  table,
  reference = NULL,
  sequence_name = "sequence_name",
  level = "level",
  taxonomy = "taxonomy",
  confidence = "confidence",
  verbose = TRUE
)

Arguments

Value

an updated strollur object

Examples

taxonomy <- readRDS(strollur_example("miseq_tidy_taxonomy.rds"))
str(taxonomy)

data <- strollur::new_dataset("my_dataset")

strollur::xdev_assign_sequence_taxonomy_tidy(data,
                                             table = taxonomy)

# With the reference parameter you can add information about the reference
# you used to classify your sequences. You can also add references using the
# 'strollur::xdev_add_references()' function.

reference <- strollur::new_reference("trainset9_032012.pds.zip", "9_032012",
              "classification by mothur2 v1.0 using default options", "",
"https://mothur.s3.us-east-2.amazonaws.com/wiki/trainset9_032012.pds.zip")

strollur::xdev_assign_sequence_taxonomy_tidy(data,
                                               table = taxonomy,
                                               reference = reference)

Assign samples to treatments in a strollur object

Description

Assign samples to treatments in a strollur object

Usage

xdev_assign_treatments(
  data,
  table,
  sample = "sample",
  treatment = "treatment",
  verbose = TRUE
)

Arguments

Value

an updated strollur object

Examples

data <- strollur::new_dataset("my_dataset")
abundance <- readRDS(strollur_example("miseq_abundance_by_sample.rds"))

strollur::xdev_assign_sequence_abundance(data,
                                           table = abundance)

sample_assignments <- readRDS(strollur_example("miseq_sample_design.rds"))

strollur::xdev_assign_treatments(data,
                                   table = sample_assignments)

Find the number of sequences, samples, treatments or bins of a given type in a strollur object

Description

Find the number of sequences, samples, treatments or bins of a given type in a strollur object

Usage

xdev_count(
  data,
  type = "sequence",
  bin_type = "otu",
  samples = NULL,
  distinct = FALSE
)

Arguments

Value

double

Examples

miseq <- strollur::miseq_sop_example()

# To get the total number of sequences
strollur::xdev_count(data = miseq,
                       type = "sequence")

# To get number of unique sequences
strollur::xdev_count(data = miseq,
                       type = "sequence", distinct = TRUE)

# To get number of unique sequences from samples 'F3D0' and 'F3D1'
# Note these sequences will be present in both samples but may be
# be present in other samples as well
strollur::xdev_count(data = miseq,
                       type = "sequence",
                       samples = c("F3D0", "F3D1"))

# To get number of unique sequences exclusive to samples 'F3D0' and 'F3D1'
# Note these sequences are present in both samples and NOT present in
# other samples
strollur::xdev_count(data = miseq,
                       type = "sequence",
                       samples = c("F3D0", "F3D1"),
                       distinct = TRUE)

# To get the number of samples in the dataset
strollur::xdev_count(data = miseq, type = "sample")

# To get the number of treatments in the dataset
strollur::xdev_count(data = miseq, type = "treatment")

# To get the number of "otu" bins in the dataset
strollur::xdev_count(data = miseq,
                       type = "bin",
                       bin_type = "otu")

# To get the number of "asv" bins in the dataset
strollur::xdev_count(data = miseq,
                       type = "bin",
                       bin_type = "asv")

# To get the number of "phylotype" bins in the dataset
strollur::xdev_count(data = miseq,
                       type = "bin",
                       bin_type = "phylotype")

# To get number of bins from samples 'F3D0' and 'F3D1'
# Note these bins will have sequences from both samples but there may be
# other samples present as well
strollur::xdev_count(data = miseq,
                       type = "bin",
                       samples = c("F3D0", "F3D1"))

# To get number of bins unique to samples 'F3D0' and 'F3D1'
# Note these bins will have sequences from both samples and NO other samples
# will be present in the bins.
strollur::xdev_count(data = miseq,
                       type = "bin",
                       samples = c("F3D0", "F3D1"),
                       distinct = TRUE)

Get the sequence abundance data in a strollur object parsed by sample

Description

Get the sequence abundance data in a strollur object parsed by sample

Usage

xdev_get_abundances_by_sample(data, samples = as.character(c()))

Arguments

Value

2D vector of float containing data requested parsed by sample.

Examples

data <- strollur::miseq_sop_example()

# To get the sequence names parsed by sample
abunds <- strollur::xdev_get_abundances_by_sample(data)

Get the alignment length of sequences in your strollur object

Description

Get the alignment length of sequences in your strollur object

Usage

xdev_get_alignment_length(data)

Arguments

Value

Integer containing the length of the alignment or -1 if unaligned.

Examples

 data <- strollur::miseq_sop_example()
 strollur::xdev_get_alignment_length(data)

Get the sequence abundance data in a strollur object parsed by sample

Description

Get the sequence abundance data in a strollur object parsed by sample

Usage

xdev_get_bin_abundances_by_sample(data, bin_type = "otu")

Arguments

Value

2D vector of float containing data requested parsed by sample.

Examples

data <- strollur::miseq_sop_example()

# To get the `otu` bin abundances parsed by sample
otu_abunds <- strollur::xdev_get_bin_abundances_by_sample(data)

Get the requested data in a strollur object parsed by sample

Description

Get the requested data in a strollur object parsed by sample

Usage

xdev_get_by_sample(
  data,
  type = "sequence_name",
  samples = as.character(c()),
  degap = FALSE
)

Arguments

Value

2D vector of strings num_seqs x num_samples containing data requested parsed by sample.

Examples

data <- strollur::miseq_sop_example()

# To get the sequence names parsed by sample
strollur::xdev_get_by_sample(data,
                               type = "sequence_name")

# To get the sequence nucleotide strings parsed by sample
parsed_sequences <- strollur::xdev_get_by_sample(data,
                                         type = "sequence")

Get vector of strings containing the sequences bin data

Description

Get vector of strings containing the sequences bin data

Usage

xdev_get_list_vector(data, type = "otu")

Arguments

Value

vector of strings containing the names of the sequences in each bin separated by commas

Examples

data <- strollur::miseq_sop_example()
strollur::xdev_get_list_vector(data)

Get distances between samples in your 'strollur object

Description

Get distances between samples in your strollur::strollur object

Usage

xdev_get_sample_distances(data)

Arguments

Value

Rcpp::DataFrame with 3 columns (sample1, sample2, distance)

Examples

 data <- strollur::miseq_sop_example()
 strollur::xdev_get_sample_distances(data)

Get the sequence abundance data in a strollur object parsed by sample

Description

Get the sequence abundance data in a strollur object parsed by sample

Usage

xdev_get_sequence_abundances_by_sample(data, samples = as.character(c()))

Arguments

Value

2D vector of float containing data requested parsed by sample.

Examples

data <- strollur::miseq_sop_example()

# To get the sequence names parsed by sample
abunds <- strollur::xdev_get_sequence_abundances_by_sample(data)

Get indexes of sequences parsed by sample

Description

As a developer you may want to process data by sample. To save space you can request the indexes parsed by sample, and then get a single copy of the sequences and sequence names.

Usage

xdev_get_sequence_indexes_by_sample(data, samples = as.character(c()))

Arguments

Value

2D vector of strings indexes for use with xdev_get_sequences and xdev_get_names. requested parsed by sample. (Indexes start at 1)

Examples

data <- strollur::miseq_sop_example()

sequences <- strollur::xdev_get_sequences(data)
names <- strollur::xdev_names(data)

# To get the indexes of the names and sequences by sample
indexes <- strollur::xdev_get_sequence_indexes_by_sample(data)

# First sequence in first sample
names[indexes[[1]][1]]
sequences[indexes[[1]][1]]

Get the nucleotide strings for each sequence in a strollur object

Description

Get the nucleotide strings for each sequence in a strollur object

Usage

xdev_get_sequences(data, sample = "", degap = FALSE)

Arguments

Value

vector of string containing nucleotide strings of the sequences in a strollur object

Examples

 data <- strollur::miseq_sop_example()
 strollur::xdev_get_sequences(data)

Determine if a strollur object has bin taxonomy assignments

Description

Determine if a strollur object has bin taxonomy assignments

Usage

xdev_has_bin_taxonomy(data, type = "otu")

Arguments

Value

boolean

Examples

 data <- strollur::miseq_sop_example()
 strollur::xdev_has_bin_taxonomy(data)

Determine if a strollur object has sequence taxonomy assignments

Description

Determine if a strollur object has sequence taxonomy assignments

Usage

xdev_has_sequence_taxonomy(data)

Arguments

Value

boolean

Examples

 data <- strollur::miseq_sop_example()
 strollur::xdev_has_sequence_taxonomy(data)

Merge bins in your strollur object

Description

Designed with package integration in mind, the merge bins function allows you to merge bins in a strollur object

Usage

xdev_merge_bins(data, bin_names, reason = "merged", bin_type = "otu")

Arguments

Value

an updated strollur object

Examples

 data <- strollur::miseq_sop_example()

 # to merge otu5 and otu6

 bins_to_merge <- c("Otu005", "Otu006")

 strollur::xdev_merge_bins(data,
                             bin_names = bins_to_merge)

 # If you look at the scrap report, you will see Otu006 with the trash code
 # set to "merged".

 strollur::report(data, type = "bin_scrap")

Merge sequences combines the abundances of sequences

Description

Designed with package integration in mind, the merge sequences function allows you to merge sequences in a strollur object.

Usage

xdev_merge_sequences(data, sequence_names, reason = "merged")

Arguments

Value

an updated strollur object

Examples

sequence_names <- c("seq1", "seq2", "seq3", "seq3",
               "seq4", "seq4", "seq5", "seq6",
               "seq7", "seq8", "seq9", "seq9",
               "seq10", "seq10", "seq10", "seq10")

samples <- c("sample1", "sample2", "sample4", "sample5",
             "sample1", "sample2", "sample1", "sample1",
             "sample2", "sample4", "sample4", "sample5",
             "sample1", "sample3", "sample5", "sample6")

abundances <- c(10, 10, 5, 5, 5, 5,
                10, 10, 10, 10, 5, 5,
                1, 2, 3, 4)

data <- strollur::new_dataset("my_data")


strollur::assign(data,
       table = data.frame(sequence_name = sequence_names,
                          abundance = abundances,
                          sample = samples),
       type = "sequence_abundance")

# For the sake of example let's merge the first 3 sequences.

seqs_to_merge <- c("seq1", "seq2", "seq3")

strollur::xdev_merge_sequences(data,
                                 sequence_names = seqs_to_merge)

# If you look at the scrap report, you will see the second two sequence
# names, listed with the trash code set to "merged".

strollur::report(data,
                   type = "sequence_scrap")

# You can see from the get_num_sequences function that the merged sequence's
# abundances are added to the first sequence.

strollur::count(data,
                  type = "sequence")

Get the names of a given type of data in a strollur object

Description

Get the names of a given type of data in a strollur object

Usage

xdev_names(
  data,
  type = "sequence",
  bin_type = "otu",
  samples = NULL,
  distinct = FALSE
)

Arguments

Value

vector of strings containing the names requested

Examples

miseq <- strollur::miseq_sop_example()

# To get the name of the dataset
strollur::xdev_names(data = miseq,
                       type = "dataset")

# To get the names of the sequences in the dataset
strollur::xdev_names(data = miseq,
                       type = "sequence")

# To get the names of the sequences that are unique to sample 'F3D0'
strollur::xdev_names(data = miseq,
                       type = "sequence",
                       samples = c("F3D0"),
                       distinct = TRUE)

# To get the names of the sequences that include sample 'F3D0'
strollur::xdev_names(data = miseq,
                       type = "sequence",
                       samples = c("F3D0"))

# To get the names of the samples in the dataset
strollur::xdev_names(data = miseq,
                       type = "sample")

# To get the names of the treatments in the dataset
strollur::xdev_names(data = miseq,
                       type = "treatment")

# To get the names of the bins in the dataset
strollur::xdev_names(data = miseq,
                       type = "bin")

# To get the names of the bins in the dataset that are unique to 'F3D0'
strollur::xdev_names(data = miseq,
                       type = "bin",
                       samples = c("F3D0"),
                       distinct = TRUE)

# To get the names of the bins in the dataset that include sequences
# from 'F3D0'
strollur::xdev_names(data = miseq,
                       type = "bin",
                       samples = c("F3D0"),
                       distinct = FALSE)

# To get the names of the reports in the dataset
strollur::xdev_names(data = miseq,
                       type = "report")

Remove bins from a strollur object

Description

Designed with package integration in mind, the remove bins function allows you to remove bins from a strollur object

Usage

xdev_remove_bins(data, bin_names, trash_tags, bin_type = "otu")

Arguments

Value

an updated strollur object

Examples

  data <- strollur::new_dataset(dataset_name = "my_dataset")

  bin_names <- c("bin1", "bin2", "bin3")
  abundances <- c(110, 525, 80)

  strollur::xdev_assign_bins(data,
                   table = data.frame(bin_name = bin_names,
                                      abundance = abundances),
                   bin_type = "otu")

  strollur::count(data,
                    type = "bin",
                    bin_type = "otu")

  bins_to_remove <- c("bin1")
  trash_tag <- c("bad_bin")

  strollur::xdev_remove_bins(data,
                   bin_names = bins_to_remove,
                   trash_tags = trash_tag)

  strollur::count(data,
                    type = "bin",
                    bin_type = "otu")

Remove contaminants from a strollur object

Description

Designed with package integration in mind, the remove lineages function allows you to remove contaminents from a strollur object

Usage

xdev_remove_lineages(data, contaminants, reason = "contaminant")

Arguments

Value

an updated strollur object

Examples

data <- strollur::read_mothur(fasta = strollur_example("final.fasta.gz"),
                       count = strollur_example("final.count_table.gz"),
                       taxonomy = strollur_example("final.taxonomy.gz"),
                       design = strollur_example("mouse.time.design"),
                       otu_list = strollur_example("final.opti_mcc.list.gz"),
                       dataset_name = "miseq_sop")

contaminants <- c("Chloroplast", "Mitochondria", "unknown", "Archaea",
 "Eukaryota")

strollur::xdev_remove_lineages(data, contaminants = contaminants)

Remove samples from a strollur object

Description

Designed with package integration in mind, the remove samples function allows you to remove samples from a strollur object

Usage

xdev_remove_samples(data, samples, reason = "remove_samples")

Arguments

Value

an updated strollur object

Examples

data <- strollur::miseq_sop_example()

strollur::count(data, type = "sample")

# To remove samples 'F3D0' and 'F3D1'

strollur::xdev_remove_samples(data,
                               samples = c("F3D0", "F3D1"))

strollur::count(data, type = "sample")

Remove sequences from a strollur object

Description

Designed with package integration in mind, the remove sequences function allows you to remove sequences from a strollur object

Usage

xdev_remove_sequences(data, sequence_names, trash_tags)

Arguments

Value

an updated strollur object

Examples

data <- strollur::miseq_sop_example()

strollur::count(data, type = "sequence")

# For the sake of example let's remove the first 3 sequences from
# miseq_sop_example:

seqs_to_remove <- c("M00967_43_000000000-A3JHG_1_2101_16474_12783",
                   "M00967_43_000000000-A3JHG_1_1113_12711_3318",
                   "M00967_43_000000000-A3JHG_1_2108_14707_9807")
trash_codes <- c("example", "removing", "sequences")

strollur::xdev_remove_sequences(data,
                                  sequence_names = seqs_to_remove,
                                  trash_tags = trash_codes)

# If you look at the scrap report, you the sequences names, listed with the
# trash codes set to "example", "removing", "sequences".

strollur::report(data, type = "sequence_scrap")

# You can see from the get_num_sequences function that the removed
# sequence's abundances are removed from the dataset.

strollur::count(data, type = "sequence")

Get a data.frame containing the given report in a strollur object

Description

Get a data.frame containing the given report in a strollur object

Usage

xdev_report(data, type = "sequence", bin_type = "otu")

Arguments

Value

data.frame

Examples

# First let's create a dataset from the \href{https://mothur.org/wiki/miseq_sop/}{MiSeq_SOP}

miseq <- strollur::miseq_sop_example()

# To get the FASTA data

fasta <- strollur::xdev_report(miseq, type = "fasta")
head(fasta, n = 10)

# To get a report about the FASTA data

sequence_report <- strollur::xdev_report(miseq,
                                           type = "sequence")
head(sequence_report, n = 10)

# To get the sequence bin assignments

bin_assignments <- strollur::xdev_report(miseq,
                               type = "sequence_bin_assignment",
                               bin_type = "otu")
head(bin_assignments, n = 10)

# To get the sample treatment assignments

strollur::xdev_report(miseq,
                        type = "sample_assignment")

# To get a report about sequence classifications

sequence_taxonomy_report <- strollur::xdev_report(miseq,
                                       type = "sequence_taxonomy")
head(sequence_taxonomy_report, n = 10)

# To get a report about bin classifications for 'otu' data

otu_taxonomy_report <- strollur::xdev_report(miseq,
                                   type = "bin_taxonomy",
                                   bin_type = "otu")
head(otu_taxonomy_report, n = 10)

# To get a report about bin classifications for 'asv' data

asv_taxonomy_report <- strollur::xdev_report(miseq,
                                   type = "bin_taxonomy",
                                   bin_type = "asv")
head(asv_taxonomy_report, n = 10)

# To get a report about bin classifications for 'phylotype' data

phylotype_taxonomy_report <- strollur::xdev_report(miseq,
                                         type = "bin_taxonomy",
                                         bin_type = "phylotype")
head(phylotype_taxonomy_report, n = 10)

# To get the 'otu' bin representative sequences

otu_bin_reps <- strollur::xdev_report(miseq,
                            type = "bin_representative",
                            bin_type = "otu")
head(otu_bin_reps, n = 10)

# To get a report about the sequences removed during your analysis:

scrapped_sequence_report <- strollur::xdev_report(miseq,
                                        type = "sequence_scrap")

# To get a report about the "otu" bins removed during your analysis:

scrapped_otu_report <- strollur::xdev_report(miseq,
                                   type = "bin_scrap",
                                   bin_type = "otu")

# To get a report about the "phylotype" bins removed during your analysis:

scrapped_phylotype_report <- strollur::xdev_report(miseq,
                                         type = "bin_scrap",
                                         bin_type = "phylotype")

# To get the metadata associated with your data:

metadata <- strollur::xdev_report(miseq,
                                     type = "metadata")

# To get the resource references associated with your data:

references <- strollur::xdev_report(miseq,
                                     type = "resource_reference")

# To get our custom report containing the contigs assembly data:

contigs_report <- strollur::xdev_report(miseq,
                                         type = "contigs_report")
head(contigs_report, n = 10)

Set abundances of sequences in a strollur object without sample data

Description

Designed with package integration in mind, the set abundance function allows you to change the abundances of sequences in a strollur object without samples.

Usage

xdev_set_abundance(
  data,
  sequence_names,
  sequence_abundances,
  reason = "update"
)

Arguments

Value

an updated strollur object

Examples

names <- c("seq1", "seq2", "seq3",  "seq4")
abunds <- c(1250, 65, 50, 4)
table <- data.frame(sequence_name = names,
                   abundance = abunds)

data <- strollur::new_dataset(dataset_name = "my_dataset")

strollur::xdev_assign_sequence_abundance(data,
                                         table = table)
strollur::abundance(data, type = "sequence")

seqs_to_update <- c("seq1", "seq3")
new_abunds <- c(1000, 100)

strollur::xdev_set_abundance(data,
                   sequence_names = seqs_to_update,
                   sequence_abundances = new_abunds)

strollur::abundance(data, type = "sequence")

Set abundances of sequences in a strollur object with sample data

Description

Designed with package integration in mind, the set abundances function allows you to change the abundances of sequences in a strollur object with samples.

Usage

xdev_set_abundances(data, sequence_names, abundances, reason = "update")

Arguments

Value

an updated strollur object

Examples

data <- strollur::new_dataset(dataset_name = "my_dataset")

sequence_names <- c("seq1", "seq1", "seq1", "seq2", "seq2", "seq2", "seq3",
                    "seq3", "seq4")
samples <- c("sample2", "sample3", "sample4", "sample2", "sample3",
             "sample4", "sample2", "sample3", "sample4")
abundances <- c(250, 400, 500, 25, 40, 50, 25, 25, 4)
table <- data.frame(sequence_name = sequence_names,
                    abundance = abundances,
                    sample = samples)

strollur::xdev_assign_sequence_abundance(data,
                                           table = table)

seqs_to_update <- c("seq4")
new_abunds <- list(c(20, 10, 4))

strollur::xdev_set_abundances(data,
                    sequence_names = seqs_to_update,
                    abundances = new_abunds)

Set the name of a strollur object

Description

Designed with package integration in mind, set the name of a strollur object.

Usage

xdev_set_dataset_name(data, dataset_name)

Arguments

Value

No return value, called for side effects.

Examples

data <- strollur::new_dataset(dataset_name = "my_dataset")
strollur::xdev_set_dataset_name(data,
                                dataset_name = "new_dataset_name")

Set neucleotide sequence string in a strollur object

Description

Designed with package integration in mind, the set sequences function allows you to change the nucleotide strings of sequences in a strollur object. For example, set_sequences may be used after alignment to overwrite the unaligned sequences with aligned sequences.

Usage

xdev_set_sequences(
  data,
  sequence_names,
  sequences,
  comments = as.character(c())
)

Arguments

Value

an updated strollur object

Examples

data <- strollur::new_dataset(dataset_name = "my_dataset")

strollur::xdev_add_sequences(data,
              table = data.frame(sequence_name = c("seq1", "seq2",
                                                  "seq3", "seq4")))

strollur::xdev_set_sequences(data,
                   sequence_names = c("seq1", "seq2","seq3", "seq4"),
                   sequences = c("ATTGC", "ACTGC", "AGTGC", "TTTGC"))