Package: RGBM 1.0-11

RGBM: LS-TreeBoost and LAD-TreeBoost for Gene Regulatory Network Reconstruction

Provides an implementation of Regularized LS-TreeBoost & LAD-TreeBoost algorithm for Regulatory Network inference from any type of expression data (Microarray/RNA-seq etc).

Authors:Raghvendra Mall [aut, cre], Khalid Kunji [aut], Melissa O'Neill [ctb]

RGBM_1.0-11.tar.gz
RGBM_1.0-11.zip(r-4.5)RGBM_1.0-11.zip(r-4.4)RGBM_1.0-11.zip(r-4.3)
RGBM_1.0-11.tgz(r-4.4-x86_64)RGBM_1.0-11.tgz(r-4.4-arm64)RGBM_1.0-11.tgz(r-4.3-x86_64)RGBM_1.0-11.tgz(r-4.3-arm64)
RGBM_1.0-11.tar.gz(r-4.5-noble)RGBM_1.0-11.tar.gz(r-4.4-noble)
RGBM_1.0-11.tgz(r-4.4-emscripten)RGBM_1.0-11.tgz(r-4.3-emscripten)
RGBM.pdf |RGBM.html✨
RGBM/json (API)

# Install 'RGBM' in R:
install.packages('RGBM', repos = c('https://raghvendra5688.r-universe.dev', 'https://cloud.r-project.org'))

Peer review:

Uses libs:
  • c++– GNU Standard C++ Library v3

On CRAN:

This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.

1.00 score 5 scripts 676 downloads 1 mentions 25 exports 6 dependencies

Last updated 2 years agofrom:80c5df56a5. Checks:OK: 9. Indexed: yes.

TargetResultDate
Doc / VignettesOKNov 04 2024
R-4.5-win-x86_64OKNov 04 2024
R-4.5-linux-x86_64OKNov 04 2024
R-4.4-win-x86_64OKNov 04 2024
R-4.4-mac-x86_64OKNov 04 2024
R-4.4-mac-aarch64OKNov 04 2024
R-4.3-win-x86_64OKNov 04 2024
R-4.3-mac-x86_64OKNov 04 2024
R-4.3-mac-aarch64OKNov 04 2024

Exports:add_namesapply_row_deviationconsider_previous_informationfirst_GBM_stepGBMGBM.testGBM.trainget_colidsget_filepathsget_ko_experimentsget_tf_indicesnormalize_matrix_colwisenull_model_refinement_stepregularized_GBM_stepregulate_regulon_sizeRGBMRGBM.testRGBM.trainsecond_GBM_stepselect_ideal_ktest_regression_stump_Rtrain_regression_stump_Rtransform_importance_to_weightsv2lz_score_effect

Dependencies:codetoolsdoParallelforeachiteratorsplyrRcpp

Readme and manuals

Help Manual

Help pageTopics
Add row and column names to the adjacency matrix Aadd_names
Apply row-wise deviation on the inferred GRNapply_row_deviation
Remember the intermediate inferred GRN while generating the final inferred GRNconsider_previous_information
Perform either LS-Boost or LAD-Boost ('GBM') on expression matrix E followed by the 'null_model_refinement_step'first_GBM_step
Calculate Gene Regulatory Network from Expression data using either LS-TreeBoost or LAD-TreeBoostGBM
Test GBM predictorGBM.test
Train GBM predictorGBM.train
Get the indices of recitifed list of Tfs for individual target geneget_colids
Generate filepaths to maintain adjacency matrices and imagesget_filepaths
Get indices of experiments where knockout or knockdown happenedget_ko_experiments
Get the indices of all the TFs from the dataget_tf_indices
Column normalize the obtained adjacency matrixnormalize_matrix_colwise
Perform the null model refinement stepnull_model_refinement_step
Perform the regularized GBM modelling once the initial GRN is inferredregularized_GBM_step
Regulate the size of the regulon for each TFregulate_regulon_size
Regularized Gradient Boosting Machine for inferring GRNRGBM
Test rgbm predictorRGBM.test
Train RGBM predictorRGBM.train
Re-iterate through the core GBM model building with optimal set of Tfs for each target genesecond_GBM_step
Identifies the optimal value of k i.e. top k Tfs for each target geneselect_ideal_k
Test the regression modeltest_regression_stump_R
Train the regression stumptrain_regression_stump_R
Log transforms the edge-weights in the inferred GRNtransform_importance_to_weights
Convert adjacency matrix to a list of edgesv2l
Generates a matrix S2 of size Ntfs x Ntargets using the null-mutant zscore algorithm Prill, Robert J., et alz_score_effect