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,
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")As input, BERT requires a dataframe1 Matrices and SummarizedExperiments work as well, but will automatically be converted to dataframes. 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 1.04207307 0.65475974 1
#> 2 -0.86999443 0.08049844 1
#> 3 0.05389955 -1.50491086 2
#> 4 0.43347620 -1.03206268 2
#> 5 -0.33828837 -1.10961855 2Note 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)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 In particular, the row and column names are in the same order and the optional columns are preserved..
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)
#> 2024-05-01 17:14:27.826117 INFO::Formatting Data.
#> 2024-05-01 17:14:27.842824 INFO::Replacing NaNs with NAs.
#> 2024-05-01 17:14:27.858719 INFO::Removing potential empty rows and columns
#> 2024-05-01 17:14:28.286564 INFO::Found 600 missing values.
#> 2024-05-01 17:14:28.302244 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2024-05-01 17:14:28.303382 INFO::Done
#> 2024-05-01 17:14:28.304337 INFO::Acquiring quality metrics before batch effect correction.
#> 2024-05-01 17:14:28.323735 INFO::Starting hierarchical adjustment
#> 2024-05-01 17:14:28.325187 INFO::Found 10 batches.
#> 2024-05-01 17:14:28.326087 INFO::Cores argument is not defined or BPPARAM has been specified. Argument corereduction will not be used.
#> 2024-05-01 17:14:29.697437 INFO::Using default BPPARAM
#> 2024-05-01 17:14:29.698981 INFO::Processing subtree level 1
#> 2024-05-01 17:14:40.391652 INFO::Processing subtree level 2
#> 2024-05-01 17:14:51.554033 INFO::Adjusting the last 1 batches sequentially
#> 2024-05-01 17:14:51.556447 INFO::Done
#> 2024-05-01 17:14:51.55776 INFO::Acquiring quality metrics after batch effect correction.
#> 2024-05-01 17:14:51.565372 INFO::ASW Batch was 0.405484564571412 prior to batch effect correction and is now -0.146022392489083 .
#> 2024-05-01 17:14:51.566739 INFO::ASW Label was 0.393962045305071 prior to batch effect correction and is now 0.852379545280748 .
#> 2024-05-01 17:14:51.568424 INFO::Total function execution time is 23.8421139717102 s and adjustment time is 23.2315909862518 s ( 97.44 )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 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..
Finally, BERT prints the total function execution time (including the computation time for the quality metrics).
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 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.
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.
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 silentlyBERT 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.
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.
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")
#> 2024-05-01 17:14:51.692 INFO::Formatting Data.
#> 2024-05-01 17:14:51.693265 INFO::Replacing NaNs with NAs.
#> 2024-05-01 17:14:51.694656 INFO::Removing potential empty rows and columns
#> 2024-05-01 17:14:51.69707 INFO::Found 2700 missing values.
#> 2024-05-01 17:14:51.71756 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2024-05-01 17:14:51.71856 INFO::Done
#> 2024-05-01 17:14:51.71932 INFO::Acquiring quality metrics before batch effect correction.
#> 2024-05-01 17:14:51.737089 INFO::Starting hierarchical adjustment
#> 2024-05-01 17:14:51.738301 INFO::Found 20 batches.
#> 2024-05-01 17:14:51.739104 INFO::Cores argument is not defined or BPPARAM has been specified. Argument corereduction will not be used.
#> 2024-05-01 17:14:51.739972 INFO::Using default BPPARAM
#> 2024-05-01 17:14:51.740722 INFO::Processing subtree level 1
#> 2024-05-01 17:14:54.805861 INFO::Processing subtree level 2
#> 2024-05-01 17:14:58.066547 INFO::Processing subtree level 3
#> 2024-05-01 17:15:00.946562 INFO::Adjusting the last 1 batches sequentially
#> 2024-05-01 17:15:00.949111 INFO::Done
#> 2024-05-01 17:15:00.950567 INFO::Acquiring quality metrics after batch effect correction.
#> 2024-05-01 17:15:00.973566 INFO::ASW Batch was 0.534515236583742 prior to batch effect correction and is now -0.123968141924083 .
#> 2024-05-01 17:15:00.975183 INFO::ASW Label was 0.243681519953329 prior to batch effect correction and is now 0.841527175152726 .
#> 2024-05-01 17:15:00.976964 INFO::Total function execution time is 9.28506112098694 s and adjustment time is 9.21096706390381 s ( 99.2 )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)
#> 2024-05-01 17:15:01.078979 INFO::Formatting Data.
#> 2024-05-01 17:15:01.080548 INFO::Replacing NaNs with NAs.
#> 2024-05-01 17:15:01.082891 INFO::Removing potential empty rows and columns
#> 2024-05-01 17:15:01.086205 INFO::Found 2700 missing values.
#> 2024-05-01 17:15:01.121354 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2024-05-01 17:15:01.122933 INFO::Done
#> 2024-05-01 17:15:01.124266 INFO::Acquiring quality metrics before batch effect correction.
#> 2024-05-01 17:15:01.14845 INFO::Starting hierarchical adjustment
#> 2024-05-01 17:15:01.149744 INFO::Found 20 batches.
#> 2024-05-01 17:15:01.785913 INFO::Set up parallel execution backend with 2 workers
#> 2024-05-01 17:15:01.787507 INFO::Processing subtree level 1 with 20 batches using 2 cores.
#> 2024-05-01 17:15:13.093277 INFO::Adjusting the last 2 batches sequentially
#> 2024-05-01 17:15:13.095594 INFO::Adjusting sequential tree level 1 with 2 batches
#> 2024-05-01 17:15:15.812512 INFO::Done
#> 2024-05-01 17:15:15.814099 INFO::Acquiring quality metrics after batch effect correction.
#> 2024-05-01 17:15:15.83802 INFO::ASW Batch was 0.433090888781601 prior to batch effect correction and is now -0.189465842270365 .
#> 2024-05-01 17:15:15.839667 INFO::ASW Label was 0.344549028354408 prior to batch effect correction and is now 0.858178405120114 .
#> 2024-05-01 17:15:15.841429 INFO::Total function execution time is 14.7625441551208 s and adjustment time is 14.6622939109802 s ( 99.32 )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")
#> 2024-05-01 17:15:15.98115 INFO::Formatting Data.
#> 2024-05-01 17:15:15.982744 INFO::Recognized SummarizedExperiment
#> 2024-05-01 17:15:15.984133 INFO::Typecasting input to dataframe.
#> 2024-05-01 17:15:16.041396 INFO::Replacing NaNs with NAs.
#> 2024-05-01 17:15:16.043819 INFO::Removing potential empty rows and columns
#> 2024-05-01 17:15:16.049385 INFO::Found 0 missing values.
#> 2024-05-01 17:15:16.059285 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2024-05-01 17:15:16.060902 INFO::Done
#> 2024-05-01 17:15:16.062322 INFO::Acquiring quality metrics before batch effect correction.
#> 2024-05-01 17:15:16.070019 INFO::Starting hierarchical adjustment
#> 2024-05-01 17:15:16.071797 INFO::Found 2 batches.
#> 2024-05-01 17:15:16.0732 INFO::Cores argument is not defined or BPPARAM has been specified. Argument corereduction will not be used.
#> 2024-05-01 17:15:16.074649 INFO::Using default BPPARAM
#> 2024-05-01 17:15:16.075988 INFO::Adjusting the last 2 batches sequentially
#> 2024-05-01 17:15:16.078166 INFO::Adjusting sequential tree level 1 with 2 batches
#> 2024-05-01 17:15:16.149296 INFO::Done
#> 2024-05-01 17:15:16.150844 INFO::Acquiring quality metrics after batch effect correction.
#> 2024-05-01 17:15:16.158368 INFO::ASW Batch was -0.00937773162761619 prior to batch effect correction and is now -0.0907385128473714 .
#> 2024-05-01 17:15:16.159901 INFO::ASW Label was -0.0123721839321117 prior to batch effect correction and is now 8.05109511998613e-05 .
#> 2024-05-01 17:15:16.161675 INFO::Total function execution time is 0.180484056472778 s and adjustment time is 0.0777251720428467 s ( 43.06 )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)
#> 2024-05-01 17:15:16.271181 INFO::Formatting Data.
#> 2024-05-01 17:15:16.272912 INFO::Replacing NaNs with NAs.
#> 2024-05-01 17:15:16.275111 INFO::Removing potential empty rows and columns
#> 2024-05-01 17:15:16.278411 INFO::Found 1350 missing values.
#> 2024-05-01 17:15:16.280423 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.
#> 2024-05-01 17:15:16.307741 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2024-05-01 17:15:16.309318 INFO::Done
#> 2024-05-01 17:15:16.310757 INFO::Acquiring quality metrics before batch effect correction.
#> 2024-05-01 17:15:16.321526 INFO::Starting hierarchical adjustment
#> 2024-05-01 17:15:16.323332 INFO::Found 5 batches.
#> 2024-05-01 17:15:16.324763 INFO::Cores argument is not defined or BPPARAM has been specified. Argument corereduction will not be used.
#> 2024-05-01 17:15:16.326212 INFO::Using default BPPARAM
#> 2024-05-01 17:15:16.32754 INFO::Processing subtree level 1
#> 2024-05-01 17:15:27.85168 INFO::Adjusting the last 2 batches sequentially
#> 2024-05-01 17:15:27.85314 INFO::Adjusting sequential tree level 1 with 2 batches
#> 2024-05-01 17:15:27.89331 INFO::Done
#> 2024-05-01 17:15:27.894248 INFO::Acquiring quality metrics after batch effect correction.
#> 2024-05-01 17:15:27.900909 INFO::ASW Batch was 0.492773245691086 prior to batch effect correction and is now -0.0377157224767566 .
#> 2024-05-01 17:15:27.90184 INFO::ASW Label was 0.40854766060101 prior to batch effect correction and is now 0.895560693013661 .
#> 2024-05-01 17:15:27.902846 INFO::Total function execution time is 11.6318850517273 s and adjustment time is 11.5702688694 s ( 99.47 )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")
#> 2024-05-01 17:15:27.988924 INFO::Formatting Data.
#> 2024-05-01 17:15:27.989977 INFO::Replacing NaNs with NAs.
#> 2024-05-01 17:15:27.991105 INFO::Removing potential empty rows and columns
#> 2024-05-01 17:15:27.992257 INFO::Found 60 missing values.
#> 2024-05-01 17:15:27.995519 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2024-05-01 17:15:27.996276 INFO::Done
#> 2024-05-01 17:15:27.996994 INFO::Acquiring quality metrics before batch effect correction.
#> 2024-05-01 17:15:28.000168 INFO::Starting hierarchical adjustment
#> 2024-05-01 17:15:28.001117 INFO::Found 4 batches.
#> 2024-05-01 17:15:28.002047 INFO::Cores argument is not defined or BPPARAM has been specified. Argument corereduction will not be used.
#> 2024-05-01 17:15:28.003078 INFO::Using default BPPARAM
#> 2024-05-01 17:15:28.004348 INFO::Processing subtree level 1
#> 2024-05-01 17:15:31.15695 INFO::Adjusting the last 2 batches sequentially
#> 2024-05-01 17:15:31.159157 INFO::Adjusting sequential tree level 1 with 2 batches
#> 2024-05-01 17:15:31.188231 INFO::Done
#> 2024-05-01 17:15:31.18977 INFO::Acquiring quality metrics after batch effect correction.
#> 2024-05-01 17:15:31.195133 INFO::ASW Batch was 0.440355021914032 prior to batch effect correction and is now -0.087480278736629 .
#> 2024-05-01 17:15:31.196572 INFO::ASW Label was 0.373906827748893 prior to batch effect correction and is now 0.919791677398366 .
#> 2024-05-01 17:15:31.198147 INFO::Total function execution time is 3.20925521850586 s and adjustment time is 3.18718004226685 s ( 99.31 )Issues can be reported in the GitHub forum, the BioConductor forum or directly to the authors.
This code is published under the GPLv3.0 License and is available for non-commercial academic purposes.
Please cite our manuscript, if you use BERT for your research: Yannis Schumann, Simon Schlumbohm et al., BERT - Batch Effect Reduction Trees with Missing Value Tolerance, 2023
sessionInfo()
#> R version 4.4.0 beta (2024-04-15 r86425 ucrt)
#> Platform: x86_64-w64-mingw32/x64
#> Running under: Windows Server 2022 x64 (build 20348)
#>
#> Matrix products: default
#>
#>
#> locale:
#> [1] LC_COLLATE=C
#> [2] LC_CTYPE=English_United States.utf8
#> [3] LC_MONETARY=English_United States.utf8
#> [4] LC_NUMERIC=C
#> [5] LC_TIME=English_United States.utf8
#>
#> time zone: America/New_York
#> tzcode source: internal
#>
#> attached base packages:
#> [1] stats graphics grDevices utils datasets methods base
#>
#> other attached packages:
#> [1] BERT_1.0.0 BiocStyle_2.32.0
#>
#> loaded via a namespace (and not attached):
#> [1] tidyselect_1.2.1 blob_1.2.4
#> [3] Biostrings_2.72.0 fastmap_1.1.1
#> [5] janitor_2.2.0 XML_3.99-0.16.1
#> [7] digest_0.6.35 timechange_0.3.0
#> [9] lifecycle_1.0.4 cluster_2.1.6
#> [11] statmod_1.5.0 survival_3.6-4
#> [13] KEGGREST_1.44.0 invgamma_1.1
#> [15] RSQLite_2.3.6 magrittr_2.0.3
#> [17] genefilter_1.86.0 compiler_4.4.0
#> [19] rlang_1.1.3 sass_0.4.9
#> [21] tools_4.4.0 yaml_2.3.8
#> [23] knitr_1.46 S4Arrays_1.4.0
#> [25] bit_4.0.5 DelayedArray_0.30.0
#> [27] abind_1.4-5 BiocParallel_1.38.0
#> [29] BiocGenerics_0.50.0 grid_4.4.0
#> [31] stats4_4.4.0 xtable_1.8-4
#> [33] edgeR_4.2.0 iterators_1.0.14
#> [35] logging_0.10-108 SummarizedExperiment_1.34.0
#> [37] cli_3.6.2 rmarkdown_2.26
#> [39] crayon_1.5.2 generics_0.1.3
#> [41] httr_1.4.7 DBI_1.2.2
#> [43] cachem_1.0.8 stringr_1.5.1
#> [45] zlibbioc_1.50.0 splines_4.4.0
#> [47] parallel_4.4.0 AnnotationDbi_1.66.0
#> [49] BiocManager_1.30.22 XVector_0.44.0
#> [51] matrixStats_1.3.0 vctrs_0.6.5
#> [53] Matrix_1.7-0 jsonlite_1.8.8
#> [55] sva_3.52.0 bookdown_0.39
#> [57] comprehenr_0.6.10 IRanges_2.38.0
#> [59] S4Vectors_0.42.0 bit64_4.0.5
#> [61] locfit_1.5-9.9 foreach_1.5.2
#> [63] limma_3.60.0 jquerylib_0.1.4
#> [65] snow_0.4-4 annotate_1.82.0
#> [67] glue_1.7.0 codetools_0.2-20
#> [69] lubridate_1.9.3 stringi_1.8.3
#> [71] GenomeInfoDb_1.40.0 GenomicRanges_1.56.0
#> [73] UCSC.utils_1.0.0 htmltools_0.5.8.1
#> [75] GenomeInfoDbData_1.2.12 R6_2.5.1
#> [77] evaluate_0.23 lattice_0.22-6
#> [79] Biobase_2.64.0 png_0.1-8
#> [81] memoise_2.0.1 snakecase_0.11.1
#> [83] bslib_0.7.0 Rcpp_1.0.12
#> [85] SparseArray_1.4.0 nlme_3.1-164
#> [87] mgcv_1.9-1 xfun_0.43
#> [89] MatrixGenerics_1.16.0