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 -0.64048327 0.87912077 1
#> 2 0.06306675 -0.47444107 1
#> 3 1.02200446 1.20098913 2
#> 4 2.22581307 -0.04099324 2
#> 5 -0.50398460 -0.51587480 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)
#> 2024-11-20 16:10:51.089882 INFO::Formatting Data.
#> 2024-11-20 16:10:51.101841 INFO::Replacing NaNs with NAs.
#> 2024-11-20 16:10:51.113592 INFO::Removing potential empty rows and columns
#> 2024-11-20 16:10:51.408854 INFO::Found 600 missing values.
#> 2024-11-20 16:10:51.421264 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2024-11-20 16:10:51.421969 INFO::Done
#> 2024-11-20 16:10:51.422501 INFO::Acquiring quality metrics before batch effect correction.
#> 2024-11-20 16:10:51.435038 INFO::Starting hierarchical adjustment
#> 2024-11-20 16:10:51.435899 INFO::Found 10 batches.
#> 2024-11-20 16:10:51.436399 INFO::Cores argument is not defined or BPPARAM has been specified. Argument corereduction will not be used.
#> 2024-11-20 16:10:53.447504 INFO::Using default BPPARAM
#> 2024-11-20 16:10:53.448152 INFO::Processing subtree level 1
#> 2024-11-20 16:10:55.297838 INFO::Processing subtree level 2
#> 2024-11-20 16:10:57.155137 INFO::Adjusting the last 1 batches sequentially
#> 2024-11-20 16:10:57.158134 INFO::Done
#> 2024-11-20 16:10:57.15922 INFO::Acquiring quality metrics after batch effect correction.
#> 2024-11-20 16:10:57.167275 INFO::ASW Batch was 0.439530632420615 prior to batch effect correction and is now -0.117449053152003 .
#> 2024-11-20 16:10:57.168355 INFO::ASW Label was 0.343371671377448 prior to batch effect correction and is now 0.842145500448068 .
#> 2024-11-20 16:10:57.170113 INFO::Total function execution time is 6.10676050186157 s and adjustment time is 5.72243881225586 s ( 93.71 )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")
#> 2024-11-20 16:10:57.255226 INFO::Formatting Data.
#> 2024-11-20 16:10:57.256293 INFO::Replacing NaNs with NAs.
#> 2024-11-20 16:10:57.257858 INFO::Removing potential empty rows and columns
#> 2024-11-20 16:10:57.261107 INFO::Found 2700 missing values.
#> 2024-11-20 16:10:57.293606 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2024-11-20 16:10:57.294423 INFO::Done
#> 2024-11-20 16:10:57.29499 INFO::Acquiring quality metrics before batch effect correction.
#> 2024-11-20 16:10:57.308435 INFO::Starting hierarchical adjustment
#> 2024-11-20 16:10:57.309258 INFO::Found 20 batches.
#> 2024-11-20 16:10:57.309812 INFO::Cores argument is not defined or BPPARAM has been specified. Argument corereduction will not be used.
#> 2024-11-20 16:10:57.310456 INFO::Using default BPPARAM
#> 2024-11-20 16:10:57.310976 INFO::Processing subtree level 1
#> 2024-11-20 16:10:57.749719 INFO::Processing subtree level 2
#> 2024-11-20 16:10:58.145457 INFO::Processing subtree level 3
#> 2024-11-20 16:10:58.575355 INFO::Adjusting the last 1 batches sequentially
#> 2024-11-20 16:10:58.577849 INFO::Done
#> 2024-11-20 16:10:58.578707 INFO::Acquiring quality metrics after batch effect correction.
#> 2024-11-20 16:10:58.593593 INFO::ASW Batch was 0.530161831267214 prior to batch effect correction and is now -0.114500688995732 .
#> 2024-11-20 16:10:58.594578 INFO::ASW Label was 0.272556270248704 prior to batch effect correction and is now 0.734193437388363 .
#> 2024-11-20 16:10:58.595809 INFO::Total function execution time is 1.340656042099 s and adjustment time is 1.26873183250427 s ( 94.64 )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)
#> 2024-11-20 16:10:58.647211 INFO::Formatting Data.
#> 2024-11-20 16:10:58.648206 INFO::Replacing NaNs with NAs.
#> 2024-11-20 16:10:58.649665 INFO::Removing potential empty rows and columns
#> 2024-11-20 16:10:58.652762 INFO::Found 2700 missing values.
#> 2024-11-20 16:10:58.680861 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2024-11-20 16:10:58.681537 INFO::Done
#> 2024-11-20 16:10:58.682052 INFO::Acquiring quality metrics before batch effect correction.
#> 2024-11-20 16:10:58.695376 INFO::Starting hierarchical adjustment
#> 2024-11-20 16:10:58.696219 INFO::Found 20 batches.
#> 2024-11-20 16:10:59.361443 INFO::Set up parallel execution backend with 2 workers
#> 2024-11-20 16:10:59.362583 INFO::Processing subtree level 1 with 20 batches using 2 cores.
#> 2024-11-20 16:11:01.879291 INFO::Adjusting the last 2 batches sequentially
#> 2024-11-20 16:11:01.880572 INFO::Adjusting sequential tree level 1 with 2 batches
#> 2024-11-20 16:11:03.431611 INFO::Done
#> 2024-11-20 16:11:03.432265 INFO::Acquiring quality metrics after batch effect correction.
#> 2024-11-20 16:11:03.441074 INFO::ASW Batch was 0.446504307708352 prior to batch effect correction and is now -0.118437336836096 .
#> 2024-11-20 16:11:03.441738 INFO::ASW Label was 0.335225425613738 prior to batch effect correction and is now 0.831783014463786 .
#> 2024-11-20 16:11:03.442485 INFO::Total function execution time is 4.79541110992432 s and adjustment time is 4.73518681526184 s ( 98.74 )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")
#> 2024-11-20 16:11:03.49871 INFO::Formatting Data.
#> 2024-11-20 16:11:03.499397 INFO::Recognized SummarizedExperiment
#> 2024-11-20 16:11:03.499882 INFO::Typecasting input to dataframe.
#> 2024-11-20 16:11:03.532182 INFO::Replacing NaNs with NAs.
#> 2024-11-20 16:11:03.533346 INFO::Removing potential empty rows and columns
#> 2024-11-20 16:11:03.536495 INFO::Found 0 missing values.
#> 2024-11-20 16:11:03.542491 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2024-11-20 16:11:03.543044 INFO::Done
#> 2024-11-20 16:11:03.543543 INFO::Acquiring quality metrics before batch effect correction.
#> 2024-11-20 16:11:03.547225 INFO::Starting hierarchical adjustment
#> 2024-11-20 16:11:03.547914 INFO::Found 2 batches.
#> 2024-11-20 16:11:03.548429 INFO::Cores argument is not defined or BPPARAM has been specified. Argument corereduction will not be used.
#> 2024-11-20 16:11:03.548965 INFO::Using default BPPARAM
#> 2024-11-20 16:11:03.549446 INFO::Adjusting the last 2 batches sequentially
#> 2024-11-20 16:11:03.550342 INFO::Adjusting sequential tree level 1 with 2 batches
#> 2024-11-20 16:11:03.593367 INFO::Done
#> 2024-11-20 16:11:03.593992 INFO::Acquiring quality metrics after batch effect correction.
#> 2024-11-20 16:11:03.597704 INFO::ASW Batch was -0.0134533442499793 prior to batch effect correction and is now -0.0977562308552735 .
#> 2024-11-20 16:11:03.598294 INFO::ASW Label was 1.20261345789379e-05 prior to batch effect correction and is now 0.0157039840603292 .
#> 2024-11-20 16:11:03.599021 INFO::Total function execution time is 0.100292205810547 s and adjustment time is 0.0455722808837891 s ( 45.44 )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)
#> 2024-11-20 16:11:03.634217 INFO::Formatting Data.
#> 2024-11-20 16:11:03.634945 INFO::Replacing NaNs with NAs.
#> 2024-11-20 16:11:03.635846 INFO::Removing potential empty rows and columns
#> 2024-11-20 16:11:03.637605 INFO::Found 1350 missing values.
#> 2024-11-20 16:11:03.638442 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.
#> 2024-11-20 16:11:03.666929 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2024-11-20 16:11:03.667596 INFO::Done
#> 2024-11-20 16:11:03.668068 INFO::Acquiring quality metrics before batch effect correction.
#> 2024-11-20 16:11:03.672478 INFO::Starting hierarchical adjustment
#> 2024-11-20 16:11:03.673154 INFO::Found 5 batches.
#> 2024-11-20 16:11:03.673638 INFO::Cores argument is not defined or BPPARAM has been specified. Argument corereduction will not be used.
#> 2024-11-20 16:11:03.674152 INFO::Using default BPPARAM
#> 2024-11-20 16:11:03.674613 INFO::Processing subtree level 1
#> 2024-11-20 16:11:03.898976 INFO::Adjusting the last 2 batches sequentially
#> 2024-11-20 16:11:03.900907 INFO::Adjusting sequential tree level 1 with 2 batches
#> 2024-11-20 16:11:03.965262 INFO::Done
#> 2024-11-20 16:11:03.966014 INFO::Acquiring quality metrics after batch effect correction.
#> 2024-11-20 16:11:03.971526 INFO::ASW Batch was 0.492773245691086 prior to batch effect correction and is now -0.0377157224767566 .
#> 2024-11-20 16:11:03.972221 INFO::ASW Label was 0.40854766060101 prior to batch effect correction and is now 0.895560693013661 .
#> 2024-11-20 16:11:03.973179 INFO::Total function execution time is 0.338994979858398 s and adjustment time is 0.292189598083496 s ( 86.19 )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")
#> 2024-11-20 16:11:04.026954 INFO::Formatting Data.
#> 2024-11-20 16:11:04.027805 INFO::Replacing NaNs with NAs.
#> 2024-11-20 16:11:04.028798 INFO::Removing potential empty rows and columns
#> 2024-11-20 16:11:04.029894 INFO::Found 60 missing values.
#> 2024-11-20 16:11:04.034318 INFO::Introduced 0 missing values due to singular proteins at batch/covariate level.
#> 2024-11-20 16:11:04.034947 INFO::Done
#> 2024-11-20 16:11:04.035527 INFO::Acquiring quality metrics before batch effect correction.
#> 2024-11-20 16:11:04.038707 INFO::Starting hierarchical adjustment
#> 2024-11-20 16:11:04.039522 INFO::Found 4 batches.
#> 2024-11-20 16:11:04.040098 INFO::Cores argument is not defined or BPPARAM has been specified. Argument corereduction will not be used.
#> 2024-11-20 16:11:04.040786 INFO::Using default BPPARAM
#> 2024-11-20 16:11:04.041358 INFO::Processing subtree level 1
#> 2024-11-20 16:11:04.141865 INFO::Adjusting the last 2 batches sequentially
#> 2024-11-20 16:11:04.143577 INFO::Adjusting sequential tree level 1 with 2 batches
#> 2024-11-20 16:11:04.164537 INFO::Done
#> 2024-11-20 16:11:04.165242 INFO::Acquiring quality metrics after batch effect correction.
#> 2024-11-20 16:11:04.168413 INFO::ASW Batch was 0.440355021914032 prior to batch effect correction and is now -0.087480278736629 .
#> 2024-11-20 16:11:04.169055 INFO::ASW Label was 0.373906827748893 prior to batch effect correction and is now 0.919791677398366 .
#> 2024-11-20 16:11:04.169866 INFO::Total function execution time is 0.14298415184021 s and adjustment time is 0.125148773193359 s ( 87.53 )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 Under development (unstable) (2024-10-21 r87258)
#> Platform: x86_64-pc-linux-gnu
#> Running under: Ubuntu 24.04.1 LTS
#>
#> Matrix products: default
#> BLAS: /home/biocbuild/bbs-3.21-bioc/R/lib/libRblas.so
#> LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.12.0
#>
#> locale:
#> [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
#> [3] LC_TIME=en_GB LC_COLLATE=C
#> [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: America/New_York
#> tzcode source: system (glibc)
#>
#> attached base packages:
#> [1] stats graphics grDevices utils datasets methods base
#>
#> other attached packages:
#> [1] BERT_1.3.3 BiocStyle_2.35.0
#>
#> loaded via a namespace (and not attached):
#> [1] tidyselect_1.2.1 blob_1.2.4
#> [3] Biostrings_2.75.1 fastmap_1.2.0
#> [5] janitor_2.2.0 XML_3.99-0.17
#> [7] digest_0.6.37 timechange_0.3.0
#> [9] lifecycle_1.0.4 cluster_2.1.6
#> [11] statmod_1.5.0 survival_3.7-0
#> [13] KEGGREST_1.47.0 invgamma_1.1
#> [15] RSQLite_2.3.8 magrittr_2.0.3
#> [17] genefilter_1.89.0 compiler_4.5.0
#> [19] rlang_1.1.4 sass_0.4.9
#> [21] tools_4.5.0 yaml_2.3.10
#> [23] knitr_1.49 S4Arrays_1.7.1
#> [25] bit_4.5.0 DelayedArray_0.33.2
#> [27] abind_1.4-8 BiocParallel_1.41.0
#> [29] BiocGenerics_0.53.3 grid_4.5.0
#> [31] stats4_4.5.0 xtable_1.8-4
#> [33] edgeR_4.5.0 iterators_1.0.14
#> [35] logging_0.10-108 SummarizedExperiment_1.37.0
#> [37] cli_3.6.3 rmarkdown_2.29
#> [39] crayon_1.5.3 generics_0.1.3
#> [41] httr_1.4.7 DBI_1.2.3
#> [43] cachem_1.1.0 stringr_1.5.1
#> [45] zlibbioc_1.53.0 splines_4.5.0
#> [47] parallel_4.5.0 AnnotationDbi_1.69.0
#> [49] BiocManager_1.30.25 XVector_0.47.0
#> [51] matrixStats_1.4.1 vctrs_0.6.5
#> [53] Matrix_1.7-1 jsonlite_1.8.9
#> [55] sva_3.55.0 bookdown_0.41
#> [57] comprehenr_0.6.10 IRanges_2.41.1
#> [59] S4Vectors_0.45.2 bit64_4.5.2
#> [61] locfit_1.5-9.10 foreach_1.5.2
#> [63] limma_3.63.2 jquerylib_0.1.4
#> [65] annotate_1.85.0 glue_1.8.0
#> [67] codetools_0.2-20 lubridate_1.9.3
#> [69] stringi_1.8.4 GenomeInfoDb_1.43.1
#> [71] GenomicRanges_1.59.1 UCSC.utils_1.3.0
#> [73] htmltools_0.5.8.1 GenomeInfoDbData_1.2.13
#> [75] R6_2.5.1 evaluate_1.0.1
#> [77] lattice_0.22-6 Biobase_2.67.0
#> [79] png_0.1-8 memoise_2.0.1
#> [81] snakecase_0.11.1 bslib_0.8.0
#> [83] SparseArray_1.7.2 nlme_3.1-166
#> [85] mgcv_1.9-1 xfun_0.49
#> [87] MatrixGenerics_1.19.0