Package: BERT 1.3.6

Yannis Schumann

BERT: High Performance Data Integration for Large-Scale Analyses of Incomplete Omic Profiles Using Batch-Effect Reduction Trees (BERT)

Provides efficient batch-effect adjustment of data with missing values. BERT orders all batch effect correction to a tree of pairwise computations. BERT allows parallelization over sub-trees.

Authors:Yannis Schumann [aut, cre], Simon Schlumbohm [aut]

BERT_1.3.6.tar.gz
BERT_1.3.6.zip(r-4.5)BERT_1.3.6.zip(r-4.4)BERT_1.3.6.zip(r-4.3)
BERT_1.3.6.tgz(r-4.5-any)BERT_1.3.6.tgz(r-4.4-any)BERT_1.3.6.tgz(r-4.3-any)
BERT_1.3.6.tar.gz(r-4.5-noble)BERT_1.3.6.tar.gz(r-4.4-noble)
BERT_1.3.6.tgz(r-4.4-emscripten)BERT_1.3.6.tgz(r-4.3-emscripten)
BERT.pdf |BERT.html✨
BERT/json (API)
NEWS

# Install 'BERT' in R:

install.packages('BERT', repos = c('https://bioc.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/hsu-hpc/bert/issues

On BioConductor:BERT-1.3.3(bioc 3.21)BERT-1.2.0(bioc 3.20)

batcheffect preprocessing experimentaldesign qualitycontrol batch-effect bioconductor-package bioinformatics data-integration data-science

5.40 score 2 stars 18 scripts 124 downloads 5 exports 91 dependencies

Last updated 22 days agofrom:f785e17081. Checks:8 OK. Indexed: yes.

Target	Result	Latest binary
Doc / Vignettes	OK	Jan 29 2025
R-4.5-win	OK	Jan 29 2025
R-4.5-mac	OK	Jan 29 2025
R-4.5-linux	OK	Jan 29 2025
R-4.4-win	OK	Jan 29 2025
R-4.4-mac	OK	Jan 29 2025
R-4.3-win	OK	Jan 29 2025
R-4.3-mac	OK	Jan 29 2025

Exports:BERT compute_asw count_existing generate_data_covariables generate_dataset

Dependencies:abind annotate AnnotationDbi askpass BH Biobase BiocGenerics BiocParallel Biostrings bit bit64 blob cachem cli cluster codetools comprehenr cpp11 crayon curl DBI DelayedArray dplyr edgeR fansi fastmap foreach formatR futile.logger futile.options genefilter generics GenomeInfoDb GenomeInfoDbData GenomicRanges glue hms httr invgamma IRanges iterators janitor jsonlite KEGGREST lambda.r lattice lifecycle limma locfit logging lubridate magrittr Matrix MatrixGenerics matrixStats memoise mgcv mime nlme openssl pillar pkgconfig plogr png purrr R6 rlang RSQLite S4Arrays S4Vectors snakecase snow SparseArray statmod stringi stringr SummarizedExperiment survival sva sys tibble tidyr tidyselect timechange UCSC.utils utf8 vctrs withr XML xtable XVector

BERT-Vignette

Rendered fromBERT-Vignette.Rmdusingknitr::rmarkdownon Jan 29 2025.

Last update: 2025-01-22
Started: 2023-05-30

Citation

Development and contributors

Readme and manuals

Help Manual

Help page	Topics
Adjust two batches to each other.	adjust_node
Adjust a hierarchy level sequentially.	adjustment_step
Adjust data using the BERT algorithm.	BERT
Chunks data into n segments with (close-to) equivalent number of batches and stores them in temporary RDS files	chunk_data
Compute the average silhouette width (ASW) for the dataset with respect to both label and batch.	compute_asw
Count the number of numeric features in this dataset. Columns labeled "Batch", "Sample" or "Label" will be ignored.	count_existing
Format the data as expected by BERT.	format_DF
Generate dataset with batch-effects and 2 classes with a specified imbalance.	generate_data_covariables
Generate dataset with batch-effects and biological labels using a simple LS model	generate_dataset
Check, which features contain enough numeric data to be adjusted (at least 2 numeric values)	get_adjustable_features
Check, which features contain enough numeric data to be adjusted (at least 2 numeric values per batch and covariate level)	get_adjustable_features_with_mod
Identifies the adjustable features using only the references. Similar to the function in adjust_features.R but with different arguments	identify_adjustableFeatures_refs
Identifies the references to use for this specific batch effect adjustment	identify_references
Ordinal encoding of a vector.	ordinal_encode
Adjusts all chunks of data (in parallel) as far as possible.	parallel_bert
A method to remove batch effects estimated from a subset (references) per batch only. Source code is heavily based on limma::removeBatchEffects by Gordon Smyth and Carolyn de Graaf	removeBatchEffectRefs
Replaces missing values (NaN) by NA, this appears to be faster	replace_missing
Strip column labelled Cov_1 from dataframe.	strip_Covariable
Verifies that the input to BERT is valid.	validate_bert_input
Validate the user input to the function generate_dataset. Raises an error if and only if the input is malformatted.	validate_input_generate_dataset
Verify that the Reference column of the data contains only zeros and ones (if it is present at all)	verify_references