Package: fuseMLR 0.0.1

Cesaire J. K. Fouodo

fuseMLR: Fusing Machine Learning in R

Recent technological advances have enable the simultaneous collection of multi-omics data i.e., different types or modalities of molecular data, presenting challenges for integrative prediction modeling due to the heterogeneous, high-dimensional nature and possible missing modalities of some individuals. We introduce this package for late integrative prediction modeling, enabling modality-specific variable selection and prediction modeling, followed by the aggregation of the modality-specific predictions to train a final meta-model. This package facilitates conducting late integration predictive modeling in a systematic, structured, and reproducible way.

Authors:Cesaire J. K. Fouodo [aut, cre]

fuseMLR_0.0.1.tar.gz
fuseMLR_0.0.1.zip(r-4.5)fuseMLR_0.0.1.zip(r-4.4)fuseMLR_0.0.1.zip(r-4.3)
fuseMLR_0.0.1.tgz(r-4.4-any)fuseMLR_0.0.1.tgz(r-4.3-any)
fuseMLR_0.0.1.tar.gz(r-4.5-noble)fuseMLR_0.0.1.tar.gz(r-4.4-noble)
fuseMLR_0.0.1.tgz(r-4.4-emscripten)fuseMLR_0.0.1.tgz(r-4.3-emscripten)
fuseMLR.pdf |fuseMLR.html
fuseMLR/json (API)

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

Peer review:

Bug tracker:https://github.com/imbs-hl/fusemlr/issues

Datasets:
  • multi_omics - Simulated multiomics data for 70 training participants and 23 testing participants, each with an effect size of 20 on each layer. Each layer includes 50 participants for training and 20 for testing. Participants do not perfectly overlap across layers. The simulation is based on the R package 'interSIM'.

On CRAN:

5.60 score 4 stars 3 scripts 31 exports 2 dependencies

Last updated 12 days agofrom:9869b24595. Checks:OK: 7. Indexed: yes.

TargetResultDate
Doc / VignettesOKDec 18 2024
R-4.5-winOKDec 18 2024
R-4.5-linuxOKDec 18 2024
R-4.4-winOKDec 18 2024
R-4.4-macOKDec 18 2024
R-4.3-winOKDec 18 2024
R-4.3-macOKDec 18 2024

Exports:bestLayerLearnercobracreateTestingcreateTestLayercreateTrainingcreateTrainLayercreateTrainMetaLayerDataextractDataextractModelfusemlrHashTableLrnerModelPredictDataPredictingPredictLayerPredictMetaLayerTargetTestDataTestingTestLayerTestMetaLayerTrainDataTrainingTrainLayerTrainMetaLayerupsetplotVarSelvarSelectionweightedMeanLearner

Dependencies:digestR6

How does fuseMLR work?

Rendered fromfuseMLR.Rmdusingknitr::rmarkdownon Dec 18 2024.

Last update: 2024-12-13
Started: 2024-12-09

Readme and manuals

Help Manual

Help pageTopics
The best layer-specific model is used as meta model.bestLayerLearner
Cobra Meta Learnercobra
Create COBRA PredictionscreateCobraPred
Create DifferencecreateDif
Create LosscreateLoss
createTestingcreateTesting
createTestLayercreateTestLayer
createTrainingcreateTraining
createTrainLayercreateTrainLayer
createTrainMetaLayercreateTrainMetaLayer
Create weights for COBRA PredictionscreateWeights
Abstract class DataData
extractDataextractData
extractModelextractModel
fusemlrfusemlr
Class HashTableHashTable
Lrner ClassLrner
Model ClassModel
Simulated multiomics data for 70 training participants and 23 testing participants, each with an effect size of 20 on each layer. Each layer includes 50 participants for training and 20 for testing. Participants do not perfectly overlap across layers. The simulation is based on the R package 'interSIM'.multi_omics
Best specific Learner prediction.predict.bestLayerLearner
Predict Using COBRA objectpredict.cobra
predict.Trainingpredict.Training
Weighted mean prediction.predict.weightedMeanLearner
PredictData ClassPredictData
Predicting ClassPredicting
PredictLayer ClassPredictLayer
PredictMetaLayer ClassPredictMetaLayer
Testing object Summariessummary.Testing
Training object Summariessummary.Training
Target ClassTarget
TestData ClassTestData
Testing ClassTesting
TestLayer ClassTestLayer
TestMetaLayer ClassTestMetaLayer
TrainData ClassTrainData
Training ClassTraining
TrainLayer ClassTrainLayer
TrainMetaLayer ClassTrainMetaLayer
upsetplotupsetplot
Varsel ClassVarSel
varSelectionvarSelection
The weighted mean meta-learnerweightedMeanLearner