BERT-Vignette

Introduction

BERT (Batch-Effect Removal with Trees) offers flexible and efficient batch effect correction of omics data, while providing maximum tolerance to missing values. Tested on multiple datasets from proteomic analyses, BERT offered a typical 5-10x runtime improvement over existing methods, while retaining more numeric values and preserving batch effect reduction quality.

As such, BERT is a valuable preprocessing tool for data analysis workflows, in particular for proteomic data. By providing BERT via Bioconductor, we make this tool available to a wider research community. An accompanying research paper is currently under preparation and will be made public soon.

BERT addresses the same fundamental data integration challenges than the [HarmonizR][https://github.com/HSU-HPC/HarmonizR] package, which is released on Bioconductor in November 2023. However, various algorithmic modications and optimizations of BERT provide better execution time and better data coverage than HarmonizR. Moreover, BERT offers a more user-friendly design and a less error-prone input format.

Please note that our package BERT is neither affiliated with nor related to Bidirectional Encoder Representations from Transformers as published by Google.

Please report any questions and issues in the GitHub forum, the BioConductor forum or directly contact the authors,

Installation

Please download and install a current version of R (Windows binaries). You might want to consider installing a development environment as well, e.g. RStudio. Finally, BERT can be installed via Bioconductor using

if (!require("BiocManager", quietly = TRUE)){
    install.packages("BiocManager")
}
BiocManager::install("BERT")

which will install all required dependencies. To install the development version of BERT, you can use devtools as follows

devtools::install_github("HSU-HPC/BERT")

which may require the manual installation of the dependencies sva and limma.

if (!require("BiocManager", quietly = TRUE)){
    install.packages("BiocManager")
}
BiocManager::install("sva")
BiocManager::install("limma")

Data Preparation

As input, BERT requires a dataframe1 with samples in rows and features in columns. For each sample, the respective batch should be indicated by an integer or string in a corresponding column labelled Batch. Missing values should be labelled as NA. A valid example dataframe could look like this:

example = data.frame(feature_1 = stats::rnorm(5), feature_2 = stats::rnorm(5), Batch=c(1,1,2,2,2))
example
#>     feature_1  feature_2 Batch
#> 1  0.04789587  0.6573945     1
#> 2  0.35265690  0.4274894     1
#> 3 -0.70299129 -1.2239033     2
#> 4  1.02591076  1.4831450     2
#> 5 -1.23796128 -0.4928261     2

Note that each batch should contain at least two samples. Optional columns that can be passed are

  • Label A column with integers or strings indicating the (known) class for each sample. NA is not allowed. BERT may use this columns and Batch to compute quality metrics after batch effect correction.

  • Sample A sample name. This column is ignored by BERT and can be used to provide meta-information for further processing.

  • Cov_1, Cov_2, …, Cov_x: One or multiple columns with integers, indicating one or several covariate levels. NA is not allowed. If this(these) column(s) is present, BERT will pass them as covariates to the the underlying batch effect correction method. As an example, this functionality can be used to preserve differences between healthy/tumorous samples, if some of the batches exhibit strongly variable class distributions. Note that BERT requires at least two numeric values per batch and unique covariate level to adjust a feature. Features that don’t satisfy this condition in a specific batch are set to NA for that batch.

  • Reference A column with integers or strings from \(\mathbb{N}_0\) that indicate, whether a sample should be used for “learning” the transformation for batch effect correction or whether the sample should be co-adjusted using the learned transformation from the other samples.NA is not allowed. This feature can be used, if some batches contain unique classes or samples with unknown classes which would prohibit the usage of covariate columns. If the column contains a 0 for a sample, this sample will be co-adjusted. Otherwise, the sample should contain the respective class (encoded as integer or string). Note that BERT requires at least two references of common class per adjustment step and that the Reference column is mutually exclusive with covariate columns.

Note that BERT tries to find all metadata information for a SummarizedExperiment, including the mandatory batch information, using colData. For instance, a valid SummarizedExperiment might be defined as

nrows <- 200
ncols <- 8
expr_values <- matrix(runif(nrows * ncols, 1, 1e4), nrows)
# colData also takes all other metadata information, such as Label, Sample,
# Covariables etc.
colData <- data.frame(Batch=c(1,1,1,1,2,2,2,2), Reference=c(1,1,0,0,1,1,0,0))
dataset_raw = SummarizedExperiment::SummarizedExperiment(assays=list(expr=expr_values), colData=colData)

Basic Usage

BERT can be invoked by importing the BERT library and calling the BERT function. The batch effect corrected data is returned as a dataframe that mirrors the input dataframe2.

library(BERT)
# generate test data with 10% missing values as provided by the BERT library
dataset_raw <- generate_dataset(features=60, batches=10, samplesperbatch=10, mvstmt=0.1, classes=2)
# apply BERT
dataset_adjusted <- BERT(dataset_raw)
#> 2026-06-20 06:35:41.678057 INFO::Formatting Data.
#> 2026-06-20 06:35:41.685407 INFO::Replacing NaNs with NAs.
#> 2026-06-20 06:35:41.692287 INFO::Removing potential empty rows and columns
#> 2026-06-20 06:35:41.887066 INFO::Found  600  missing values.
#> 2026-06-20 06:35:41.901888 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2026-06-20 06:35:41.902689 INFO::Done
#> 2026-06-20 06:35:41.903418 INFO::Acquiring quality metrics before batch effect correction.
#> 2026-06-20 06:35:41.915107 INFO::Starting hierarchical adjustment
#> 2026-06-20 06:35:41.915862 INFO::Found  10  batches.
#> 2026-06-20 06:35:41.916353 INFO::Cores argument is not defined or BPPARAM has been specified. Argument corereduction will not be used.
#> 2026-06-20 06:35:43.807084 INFO::Using default BPPARAM
#> 2026-06-20 06:35:43.807659 INFO::Processing subtree level 1
#> 2026-06-20 06:35:45.244742 INFO::Processing subtree level 2
#> 2026-06-20 06:35:46.716643 INFO::Adjusting the last 1 batches sequentially
#> 2026-06-20 06:35:46.718109 INFO::Done
#> 2026-06-20 06:35:46.718597 INFO::Acquiring quality metrics after batch effect correction.
#> 2026-06-20 06:35:46.722492 INFO::ASW Batch was 0.490144784268985 prior to batch effect correction and is now -0.0933372395878012 .
#> 2026-06-20 06:35:46.722952 INFO::ASW Label was 0.331046731333715 prior to batch effect correction and is now 0.798859904174277 .
#> 2026-06-20 06:35:46.723778 INFO::Total function execution time is  5.46212434768677  s and adjustment time is  4.80248665809631 s ( 87.92 )

BERT uses the logging library to convey live information to the user during the adjustment procedure. The algorithm first verifies the shape and suitability of the input dataframe (lines 1-6) before continuing with the actual batch effect correction (lines 8-14). BERT measure batch effects before and after the correction step by means of the average silhouette score (ASW) with respect to batch and labels (lines 7 and 15). The ASW Label should increase in a successful batch effect correction, whereas low values (\(\leq 0\)) are desireable for the ASW Batch3. Finally, BERT prints the total function execution time (including the computation time for the quality metrics).

Advanced Options

Parameters

BERT offers a large number of parameters to customize the batch effect adjustment. The full function call, including all defaults is

BERT(data, cores = NULL, combatmode = 1, corereduction=2, stopParBatches=2, backend="default", method="ComBat", qualitycontrol=TRUE, verify=TRUE, labelname="Label", batchname="Batch", referencename="Reference", samplename="Sample", covariatename=NULL, BPPARAM=NULL, assayname=NULL)

In the following, we list the respective meaning of each parameter: - data: The input dataframe/matrix/SummarizedExperiment to adjust. See Data Preparation for detailed formatting instructions. - data The data for batch-effect correction. Must contain at least two samples per batch and 2 features.

  • cores: BERT uses BiocParallel for parallelization. If the user specifies a value cores, BERT internally creates and uses a new instance of BiocParallelParam, which is however not exhibited to the user. Setting this parameter can speed up the batch effect adjustment considerably, in particular for large datasets and on unix-based operating systems. A value between \(2\) and \(4\) is a reasonable choice for typical commodity hardware. Multi-node computations are not supported as of now. If, however, cores is not specified, BERT will default to BiocParallel::bpparam(), which may have been set by the user or the system. Additionally, the user can directly specify a specific instance of BiocParallelParam to be used via the BPPARAM argument.
  • combatmode An integer that encodes the parameters to use for ComBat.
Value par.prior mean.only
1 TRUE FALSE
2 TRUE TRUE
3 FALSE FALSE
4 FALSE TRUE

The value of this parameter will be ignored, if method!="ComBat".

  • corereduction Positive integer indicating the factor by which the number of processes should be reduced, once no further adjustment is possible for the current number of batches.4 This parameter is used only, if the user specified a custom value for parameter cores.

  • stopParBatches Positive integer indicating the minimum number of batches required at a hierarchy level to proceed with parallelized adjustment. If the number of batches is smaller, adjustment will be performed sequentially to avoid communication overheads.

  • backend: The backend to use for inter-process communication. Possible choices are default and file, where the former refers to the default communication backend of the requested parallelization mode and the latter will create temporary .rds files for data communication. ‘default’ is usually faster for small to medium sized datasets.

  • method: The method to use for the underlying batch effect correction steps. Should be either ComBat, limma for limma::removeBatchEffects or ref for adjustment using specified references (cf. Data Preparation). The underlying batch effect adjustment method for ref is a modified version of the limma method.

  • qualitycontrol: A boolean to (de)activate the ASW computation. Deactivating the ASW computations accelerates the computations.

  • verify: A boolean to (de)activate the initial format check of the input data. Deactivating this verification step accelerates the computations.

  • labelname: A string containing the name of the column to use as class labels. The default is “Label”.

  • batchname: A string containing the name of the column to use as batch labels. The default is “Batch”.

  • referencename: A string containing the name of the column to use as reference labels. The default is “Reference”.

  • covariatename: A vector containing the names of columns with categorical covariables.The default is NULL, in which case all column names are matched agains the pattern “Cov”.

  • BPPARAM: An instance of BiocParallelParam that will be used for parallelization. The default is null, in which case the value of cores determines the behaviour of BERT.

  • assayname: If the user chooses to pass a SummarizedExperiment object, they need to specify the name of the assay that they want to apply BERT to here. BERT then returns the input SummarizedExperiment with an additional assay labeled assayname_BERTcorrected.

Verbosity

BERT utilizes the logging package for output. The user can easily specify the verbosity of BERT by setting the global logging level in the script. For instance

logging::setLevel("WARN") # set level to warn and upwards
result <- BERT(data,cores = 1) # BERT executes silently

Choosing the Optimal Number of Cores

BERT exhibits a large number of parameters for parallelisation as to provide users with maximum flexibility. For typical scenarios, however, the default parameters are well suited. For very large experiments (\(>15\) batches), we recommend to increase the number of cores (a reasonable value is \(4\) but larger values may be possible on your hardware). Most users should leave all parameters to their respective default.

Examples

In the following, we present simple cookbook examples for BERT usage. Note that ASWs (and runtime) will most likely differ on your machine, since the data generating process involves multiple random choices.

Sequential Adjustment with limma

Here, BERT uses limma as underlying batch effect correction algorithm (method='limma') and performs all computations on a single process (cores parameter is left on default).

# import BERT
library(BERT)
# generate data with 30 batches, 60 features, 15 samples per batch, 15% missing values and 2 classes
dataset_raw <- generate_dataset(features=60, batches=20, samplesperbatch=15, mvstmt=0.15, classes=2)
# BERT
dataset_adjusted <- BERT(dataset_raw, method="limma")
#> 2026-06-20 06:35:46.770774 INFO::Formatting Data.
#> 2026-06-20 06:35:46.771459 INFO::Replacing NaNs with NAs.
#> 2026-06-20 06:35:46.7723 INFO::Removing potential empty rows and columns
#> 2026-06-20 06:35:46.774204 INFO::Found  2700  missing values.
#> 2026-06-20 06:35:46.793914 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2026-06-20 06:35:46.794581 INFO::Done
#> 2026-06-20 06:35:46.794978 INFO::Acquiring quality metrics before batch effect correction.
#> 2026-06-20 06:35:46.803636 INFO::Starting hierarchical adjustment
#> 2026-06-20 06:35:46.804227 INFO::Found  20  batches.
#> 2026-06-20 06:35:46.804621 INFO::Cores argument is not defined or BPPARAM has been specified. Argument corereduction will not be used.
#> 2026-06-20 06:35:46.80508 INFO::Using default BPPARAM
#> 2026-06-20 06:35:46.805497 INFO::Processing subtree level 1
#> 2026-06-20 06:35:47.167 INFO::Processing subtree level 2
#> 2026-06-20 06:35:47.497928 INFO::Processing subtree level 3
#> 2026-06-20 06:35:47.845528 INFO::Adjusting the last 1 batches sequentially
#> 2026-06-20 06:35:47.84772 INFO::Done
#> 2026-06-20 06:35:47.848482 INFO::Acquiring quality metrics after batch effect correction.
#> 2026-06-20 06:35:47.859916 INFO::ASW Batch was 0.50833082181358 prior to batch effect correction and is now -0.171432108302738 .
#> 2026-06-20 06:35:47.860571 INFO::ASW Label was 0.263539055474588 prior to batch effect correction and is now 0.842566647569397 .
#> 2026-06-20 06:35:47.861367 INFO::Total function execution time is  1.09063172340393  s and adjustment time is  1.04359459877014 s ( 95.69 )

Parallel Batch Effect Correction with ComBat

Here, BERT uses ComBat as underlying batch effect correction algorithm (method is left on default) and performs all computations on a 2 processes (cores=2).

# import BERT
library(BERT)
# generate data with 30 batches, 60 features, 15 samples per batch, 15% missing values and 2 classes
dataset_raw <- generate_dataset(features=60, batches=20, samplesperbatch=15, mvstmt=0.15, classes=2)
# BERT
dataset_adjusted <- BERT(dataset_raw, cores=2)
#> 2026-06-20 06:35:47.899103 INFO::Formatting Data.
#> 2026-06-20 06:35:47.899833 INFO::Replacing NaNs with NAs.
#> 2026-06-20 06:35:47.900699 INFO::Removing potential empty rows and columns
#> 2026-06-20 06:35:47.902553 INFO::Found  2700  missing values.
#> 2026-06-20 06:35:47.923482 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2026-06-20 06:35:47.924108 INFO::Done
#> 2026-06-20 06:35:47.924569 INFO::Acquiring quality metrics before batch effect correction.
#> 2026-06-20 06:35:47.933397 INFO::Starting hierarchical adjustment
#> 2026-06-20 06:35:47.934106 INFO::Found  20  batches.
#> 2026-06-20 06:35:48.689463 INFO::Set up parallel execution backend with 2 workers
#> 2026-06-20 06:35:48.690586 INFO::Processing subtree level 1 with 20 batches using 2 cores.
#> 2026-06-20 06:35:50.841036 INFO::Adjusting the last 2 batches sequentially
#> 2026-06-20 06:35:50.842188 INFO::Adjusting sequential tree level 1 with 2 batches
#> 2026-06-20 06:35:52.012684 INFO::Done
#> 2026-06-20 06:35:52.013245 INFO::Acquiring quality metrics after batch effect correction.
#> 2026-06-20 06:35:52.020715 INFO::ASW Batch was 0.420232881344214 prior to batch effect correction and is now -0.148608304828576 .
#> 2026-06-20 06:35:52.021176 INFO::ASW Label was 0.36216348740398 prior to batch effect correction and is now 0.784651612928491 .
#> 2026-06-20 06:35:52.021685 INFO::Total function execution time is  4.12269568443298  s and adjustment time is  4.07848739624023 s ( 98.93 )

Batch Effect Correction Using SummarizedExperiment

Here, BERT takes the input data using a SummarizedExperiment instead. Batch effect correction is then performed using ComBat as underlying algorithm (method is left on default) and all computations are performed on a single process (cores parameter is left on default).

nrows <- 200
ncols <- 8
# SummarizedExperiments store samples in columns and features in rows (in contrast to BERT).
# BERT will automatically account for this.
expr_values <- matrix(runif(nrows * ncols, 1, 1e4), nrows)
# colData also takes further metadata information, such as Label, Sample,
# Reference or Covariables
colData <- data.frame("Batch"=c(1,1,1,1,2,2,2,2), "Label"=c(1,2,1,2,1,2,1,2), "Sample"=c(1,2,3,4,5,6,7,8))
dataset_raw = SummarizedExperiment::SummarizedExperiment(assays=list(expr=expr_values), colData=colData)
dataset_adjusted = BERT(dataset_raw, assayname = "expr")
#> 2026-06-20 06:35:52.063276 INFO::Formatting Data.
#> 2026-06-20 06:35:52.063895 INFO::Recognized SummarizedExperiment
#> 2026-06-20 06:35:52.064289 INFO::Typecasting input to dataframe.
#> 2026-06-20 06:35:52.087492 INFO::Replacing NaNs with NAs.
#> 2026-06-20 06:35:52.088419 INFO::Removing potential empty rows and columns
#> 2026-06-20 06:35:52.090671 INFO::Found  0  missing values.
#> 2026-06-20 06:35:52.094868 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2026-06-20 06:35:52.095288 INFO::Done
#> 2026-06-20 06:35:52.095631 INFO::Acquiring quality metrics before batch effect correction.
#> 2026-06-20 06:35:52.098318 INFO::Starting hierarchical adjustment
#> 2026-06-20 06:35:52.098846 INFO::Found  2  batches.
#> 2026-06-20 06:35:52.099236 INFO::Cores argument is not defined or BPPARAM has been specified. Argument corereduction will not be used.
#> 2026-06-20 06:35:52.099631 INFO::Using default BPPARAM
#> 2026-06-20 06:35:52.099961 INFO::Adjusting the last 2 batches sequentially
#> 2026-06-20 06:35:52.100584 INFO::Adjusting sequential tree level 1 with 2 batches
#> 2026-06-20 06:35:52.131718 INFO::Done
#> 2026-06-20 06:35:52.132271 INFO::Acquiring quality metrics after batch effect correction.
#> 2026-06-20 06:35:52.136245 INFO::ASW Batch was -0.0179607556007898 prior to batch effect correction and is now -0.0950371895267438 .
#> 2026-06-20 06:35:52.136844 INFO::ASW Label was -0.0104067978354695 prior to batch effect correction and is now 0.00180655279242062 .
#> 2026-06-20 06:35:52.137454 INFO::Total function execution time is  0.0742099285125732  s and adjustment time is  0.0329740047454834 s ( 44.43 )

BERT with Covariables

BERT can utilize categorical covariables that are specified in columns Cov_1, Cov_2, .... These columns are automatically detected and integrated into the batch effect correction process.

# import BERT
library(BERT)
# set seed for reproducibility
set.seed(1)
# generate data with 5 batches, 60 features, 30 samples per batch, 15% missing values and 2 classes
dataset_raw <- generate_dataset(features=60, batches=5, samplesperbatch=30, mvstmt=0.15, classes=2)
# create covariable column with 2 possible values, e.g. male/female condition
dataset_raw["Cov_1"] = sample(c(1,2), size=dim(dataset_raw)[1], replace=TRUE)
# BERT
dataset_adjusted <- BERT(dataset_raw)
#> 2026-06-20 06:35:52.171277 INFO::Formatting Data.
#> 2026-06-20 06:35:52.171883 INFO::Replacing NaNs with NAs.
#> 2026-06-20 06:35:52.17255 INFO::Removing potential empty rows and columns
#> 2026-06-20 06:35:52.173791 INFO::Found  1350  missing values.
#> 2026-06-20 06:35:52.174387 INFO::BERT requires at least 2 numeric values per batch/covariate level. This may reduce the number of adjustable features considerably, depending on the quantification technique.
#> 2026-06-20 06:35:52.186548 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2026-06-20 06:35:52.187074 INFO::Done
#> 2026-06-20 06:35:52.187461 INFO::Acquiring quality metrics before batch effect correction.
#> 2026-06-20 06:35:52.190855 INFO::Starting hierarchical adjustment
#> 2026-06-20 06:35:52.191356 INFO::Found  5  batches.
#> 2026-06-20 06:35:52.191702 INFO::Cores argument is not defined or BPPARAM has been specified. Argument corereduction will not be used.
#> 2026-06-20 06:35:52.192084 INFO::Using default BPPARAM
#> 2026-06-20 06:35:52.192456 INFO::Processing subtree level 1
#> 2026-06-20 06:35:52.434902 INFO::Adjusting the last 2 batches sequentially
#> 2026-06-20 06:35:52.43697 INFO::Adjusting sequential tree level 1 with 2 batches
#> 2026-06-20 06:35:52.480192 INFO::Done
#> 2026-06-20 06:35:52.480802 INFO::Acquiring quality metrics after batch effect correction.
#> 2026-06-20 06:35:52.485011 INFO::ASW Batch was 0.492773245691086 prior to batch effect correction and is now -0.0377157224767566 .
#> 2026-06-20 06:35:52.485529 INFO::ASW Label was 0.40854766060101 prior to batch effect correction and is now 0.895560693013661 .
#> 2026-06-20 06:35:52.486219 INFO::Total function execution time is  0.315027952194214  s and adjustment time is  0.288861274719238 s ( 91.69 )

BERT with references

In rare cases, class distributions across experiments may be severely skewed. In particular, a batch might contain classes that other batches don’t contain. In these cases, samples of common conditions may serve as references (bridges) between the batches (method="ref"). BERT utilizes those samples as references that have a condition specified in the “Reference” column of the input. All other samples are co-adjusted. Please note, that this strategy implicitly uses limma as underlying batch effect correction algorithm.

# import BERT
library(BERT)
# generate data with 4 batches, 6 features, 15 samples per batch, 15% missing values and 2 classes
dataset_raw <- generate_dataset(features=6, batches=4, samplesperbatch=15, mvstmt=0.15, classes=2)
# create reference column with default value 0.  The 0 indicates, that the respective sample should be co-adjusted only.
dataset_raw[, "Reference"] <- 0
# randomly select 2 references per batch and class - in practice, this choice will be determined by external requirements (e.g. class known for only these samples)
batches <- unique(dataset_raw$Batch) # all the batches
for(b in batches){ # iterate over all batches
    # references from class 1
    ref_idx = sample(which((dataset_raw$Batch==b)&(dataset_raw$Label==1)), size=2, replace=FALSE)
    dataset_raw[ref_idx, "Reference"] <- 1
    # references from class 2
    ref_idx = sample(which((dataset_raw$Batch==b)&(dataset_raw$Label==2)), size=2, replace=FALSE)
    dataset_raw[ref_idx, "Reference"] <- 2
}
# BERT
dataset_adjusted <- BERT(dataset_raw, method="ref")
#> 2026-06-20 06:35:52.569422 INFO::Formatting Data.
#> 2026-06-20 06:35:52.570069 INFO::Replacing NaNs with NAs.
#> 2026-06-20 06:35:52.570765 INFO::Removing potential empty rows and columns
#> 2026-06-20 06:35:52.571507 INFO::Found  60  missing values.
#> 2026-06-20 06:35:52.574253 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2026-06-20 06:35:52.574647 INFO::Done
#> 2026-06-20 06:35:52.575021 INFO::Acquiring quality metrics before batch effect correction.
#> 2026-06-20 06:35:52.577234 INFO::Starting hierarchical adjustment
#> 2026-06-20 06:35:52.577751 INFO::Found  4  batches.
#> 2026-06-20 06:35:52.578155 INFO::Cores argument is not defined or BPPARAM has been specified. Argument corereduction will not be used.
#> 2026-06-20 06:35:52.578598 INFO::Using default BPPARAM
#> 2026-06-20 06:35:52.579006 INFO::Processing subtree level 1
#> 2026-06-20 06:35:52.669201 INFO::Adjusting the last 2 batches sequentially
#> 2026-06-20 06:35:52.67132 INFO::Adjusting sequential tree level 1 with 2 batches
#> 2026-06-20 06:35:52.694206 INFO::Done
#> 2026-06-20 06:35:52.694856 INFO::Acquiring quality metrics after batch effect correction.
#> 2026-06-20 06:35:52.697627 INFO::ASW Batch was 0.440355021914032 prior to batch effect correction and is now -0.087480278736629 .
#> 2026-06-20 06:35:52.69815 INFO::ASW Label was 0.373906827748893 prior to batch effect correction and is now 0.919791677398366 .
#> 2026-06-20 06:35:52.698759 INFO::Total function execution time is  0.129416942596436  s and adjustment time is  0.116477966308594 s ( 90 )

Issues

Issues can be reported in the GitHub forum, the BioConductor forum or directly to the authors.

License

This code is published under the GPLv3.0 License and is available for non-commercial academic purposes.

Reference

Please cite our manuscript, if you use BERT for your research: Schumann Y, Gocke A, Neumann J (2024). Computational Methods for Data Integration and Imputation of Missing Values in Omics Datasets. PROTEOMICS. ISSN 1615-9861, doi:10.1002/pmic.202400100

Session Info

sessionInfo()
#> R version 4.6.0 (2026-04-24)
#> Platform: x86_64-pc-linux-gnu
#> Running under: Ubuntu 24.04.4 LTS
#> 
#> Matrix products: default
#> BLAS:   /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3 
#> LAPACK: /usr/lib/x86_64-linux-gnu/openblas-pthread/libopenblasp-r0.3.26.so;  LAPACK version 3.12.0
#> 
#> locale:
#>  [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
#>  [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
#>  [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
#>  [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
#>  [9] LC_ADDRESS=C               LC_TELEPHONE=C            
#> [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       
#> 
#> time zone: Etc/UTC
#> tzcode source: system (glibc)
#> 
#> attached base packages:
#> [1] stats     graphics  grDevices utils     datasets  methods   base     
#> 
#> other attached packages:
#> [1] BERT_1.9.0       BiocStyle_2.41.0
#> 
#> loaded via a namespace (and not attached):
#>  [1] tidyselect_1.2.1            blob_1.3.0                 
#>  [3] Biostrings_2.81.3           fastmap_1.2.0              
#>  [5] janitor_2.2.1               XML_3.99-0.23              
#>  [7] digest_0.6.39               timechange_0.4.0           
#>  [9] lifecycle_1.0.5             cluster_2.1.8.2            
#> [11] survival_3.8-6              statmod_1.5.2              
#> [13] KEGGREST_1.53.4             invgamma_1.2               
#> [15] RSQLite_3.53.2              magrittr_2.0.5             
#> [17] genefilter_1.95.0           compiler_4.6.0             
#> [19] rlang_1.2.0                 sass_0.4.10                
#> [21] tools_4.6.0                 yaml_2.3.12                
#> [23] knitr_1.51                  S4Arrays_1.13.0            
#> [25] bit_4.6.0                   DelayedArray_0.39.3        
#> [27] abind_1.4-8                 BiocParallel_1.47.0        
#> [29] BiocGenerics_0.59.7         sys_3.4.3                  
#> [31] grid_4.6.0                  stats4_4.6.0               
#> [33] xtable_1.8-8                edgeR_4.11.1               
#> [35] iterators_1.0.14            logging_0.10-111           
#> [37] SummarizedExperiment_1.43.0 cli_3.6.6                  
#> [39] rmarkdown_2.31              crayon_1.5.3               
#> [41] generics_0.1.4              otel_0.2.0                 
#> [43] httr_1.4.8                  DBI_1.3.0                  
#> [45] cachem_1.1.0                stringr_1.6.0              
#> [47] splines_4.6.0               parallel_4.6.0             
#> [49] AnnotationDbi_1.75.0        BiocManager_1.30.27        
#> [51] XVector_0.53.0              matrixStats_1.5.0          
#> [53] vctrs_0.7.3                 Matrix_1.7-5               
#> [55] jsonlite_2.0.0              sva_3.61.0                 
#> [57] comprehenr_0.6.10           IRanges_2.47.2             
#> [59] S4Vectors_0.51.3            bit64_4.8.2                
#> [61] maketools_1.3.2             locfit_1.5-9.12            
#> [63] foreach_1.5.2               limma_3.69.2               
#> [65] jquerylib_0.1.4             annotate_1.91.0            
#> [67] glue_1.8.1                  codetools_0.2-20           
#> [69] lubridate_1.9.5             stringi_1.8.7              
#> [71] GenomicRanges_1.65.0        htmltools_0.5.9            
#> [73] Seqinfo_1.3.0               R6_2.6.1                   
#> [75] evaluate_1.0.5              lattice_0.22-9             
#> [77] Biobase_2.73.1              png_0.1-9                  
#> [79] memoise_2.0.1               snakecase_0.11.1           
#> [81] bslib_0.11.0                SparseArray_1.13.2         
#> [83] nlme_3.1-169                mgcv_1.9-4                 
#> [85] xfun_0.58                   MatrixGenerics_1.25.0      
#> [87] buildtools_1.0.0

  1. Matrices and SummarizedExperiments work as well, but will automatically be converted to dataframes.↩︎

  2. In particular, the row and column names are in the same order and the optional columns are preserved.↩︎

  3. The optimum of ASW Label is 1, which is typically however not achieved on real-world datasets. Also, the optimum of ASW Batch can vary, depending on the class distributions of the batches.↩︎

  4. E.g. consider a BERT call with 8 batches and 8 processes. Further adjustment is not possible with this number of processes, since batches are always processed in pairs. With corereduction=2, the number of processes for the following adjustment steps would be set to \(8/2=4\), which is the maximum number of usable processes for this example.↩︎