Obtaining the original data | Processing the drug similarities | Obtaining the data | Calculating the similarities
Package: xnet 0.1.11
Joris Meys
xnet: Two-Step Kernel Ridge Regression for Network Predictions
Fit a two-step kernel ridge regression model for predicting edges in networks, and carry out cross-validation using shortcuts for swift and accurate performance assessment (Stock et al, 2018 <doi:10.1093/bib/bby095> ).
Authors:
xnet_0.1.11.tar.gz
xnet_0.1.11.zip(r-4.7)xnet_0.1.11.zip(r-4.6)xnet_0.1.11.zip(r-4.5)
xnet_0.1.11.tgz(r-4.6-any)xnet_0.1.11.tgz(r-4.5-any)
xnet_0.1.11.tar.gz(r-4.7-any)xnet_0.1.11.tar.gz(r-4.6-any)
xnet_0.1.11.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
xnet/json (API)
| # Install 'xnet' in R: |
| install.packages('xnet', repos = c('https://centerforstatistics-ugent.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/centerforstatistics-ugent/xnet/issues
Datasets:
- drugSim - Drug target interactions for neural receptors
- drugTargetInteraction - Drug target interactions for neural receptors
- Kmat_y2h_sc - Protein interaction for yeast
- proteinInteraction - Protein interaction for yeast
- targetSim - Drug target interactions for neural receptors
Last updated from:4093905ae8. Checks:9 OK. Indexed: yes.
| Target | Result | Time | Files | Syslog |
|---|---|---|---|---|
| linux-devel-x86_64 | OK | 146 | ||
| source / vignettes | OK | 191 | ||
| linux-release-x86_64 | OK | 155 | ||
| macos-release-arm64 | OK | 194 | ||
| macos-oldrel-arm64 | OK | 211 | ||
| windows-devel | OK | 110 | ||
| windows-release | OK | 146 | ||
| windows-oldrel | OK | 144 | ||
| wasm-release | OK | 116 |
Exports:alphacolMeanscolnamescreate_grideigen2hateigen2mapeigen2matrixfittedget_eigenget_gridget_kernelget_kernelmatrixget_loo_funget_loss_valueshas_imputed_valueshatimpute_tskrrimpute_tskrr.fitis_heterogeneousis_homogeneousis_imputedis_symmetricis_tunedlabelslambdalinear_filterloolossloss_aucloss_msematch_labelsmeanna_removedpermtestpermutationsplot_gridpredictresidualsresponserowMeansrownamessymmetrytest_symmetrytskrrtskrr.fittuneupdatevalid_dimensionsweightswhich_imputed
Dependencies:
Preparation of the example data
Last update: 2019-12-17
Started: 2018-09-17
A short introduction to cross-network analysis with xnet
Concepts and terms used in the package. | Notation and naming of networks in the package | Data in the package | Homogeneous networks | Heterogeneous networks | Fitting a two-step kernel ridge regression | Heterogeneous network | Homogeneous network | Extracting parameters from a trained model. | Information on the fit of the model | Performing leave-one-out cross-validation | Settings for LOO | Use LOO in other functions | Looking at model output | Tuning a model to find the best lambda. | Predicting new values | Predict for new K-nodes | Predict for new G-nodes | Predict for new K and G nodes | Impute new values based on a tskrr model
Last update: 2019-12-17
Started: 2019-04-04
S4 class structure of the xnet package
Virtual classes | Actual classes | Inheritance from tskrr | Slots defined by tskrrHomogeneous | Slots defined by tskrrHeterogeneous | Inheritance from tskrrTune | Inheritance from tskrrImpute
Last update: 2019-12-13
Started: 2019-03-28
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| Two-step kernel ridge regression for network analysis | xnet-package xnet |
| Getters for linearFilter objects | alpha alpha,linearFilter-method colMeans,linearFilter-method getters_linearFilter mean,linearFilter-method mean.linearFilter na_removed na_removed,linearFilter-method rowMeans,linearFilter-method |
| convert tskrr models | as_tskrr as_tskrr,tskrr-method as_tskrr,tskrrImpute-method as_tskrr,tskrrTune-method as_tuned as_tuned,tskrrHeterogeneous-method as_tuned,tskrrHomogeneous-method |
| Create a grid of values for tuning tskrr | create_grid |
| Get the dimensions of a tskrr object | dim,tskrr-method dim.tskrr |
| drug target interactions for neural receptors | drugSim drugtarget drugTargetInteraction targetSim |
| Calculate the hat matrix from an eigen decomposition | eigen2hat eigen2map eigen2matrix |
| extract the predictions | fitted,linearFilter-method fitted,tskrr-method fitted.linearFilter fitted.tskrr |
| Retrieve a loo function | get_loo_fun get_loo_fun,character-method get_loo_fun,linearFilter-method get_loo_fun,tskrrHeterogeneous-method get_loo_fun,tskrrHomogeneous-method get_loo_fun,tskrrTune-method |
| Getters for tskrrImpute objects | has_imputed_values is_imputed which_imputed |
| Return the hat matrix of a tskrr model | hat hat,tskrrHeterogeneous-method hat,tskrrHomogeneous-method |
| Impute missing values in a label matrix | impute_tskrr |
| Impute values based on a two-step kernel ridge regression | impute_tskrr.fit |
| Test symmetry of a matrix | is_symmetric |
| Getters for tskrrTune objects | get_grid get_loss_values has_onedim is_tuned |
| Extract labels from a tskrr object | colnames,tskrr-method dimnames,tskrr-method dimnames.tskrr labels,tskrr-method labels.tskrr rownames,tskrr-method |
| Fit a linear filter over a label matrix | linear_filter |
| Class linearFilter | linearFilter linearFilter-class |
| Leave-one-out cross-validation for tskrr | loo loo,linearFilter-method loo,tskrrHeterogeneous-method loo,tskrrHomogeneous-method |
| Leave-one-out cross-validation for two-step kernel ridge regression | loo.b loo.c loo.e.skew loo.e.sym loo.e0.skew loo.e0.sym loo.i loo.i.lf loo.i0 loo.i0.lf loo.r loo.v loo_internal |
| Calculate or extract the loss of a tskrr model | loss loss,permtest-method loss,tskrr-method loss,tskrrTune-method |
| loss functions | loss_auc loss_functions loss_mse |
| Reorder the label matrix | match_labels |
| Calculate the relative importance of the edges | permtest permtest,tskrrHeterogeneous-method permtest,tskrrHomogeneous-method permtest,tskrrTune-method print.permtest |
| Class permtest | permtest-class |
| Getters for permtest objects | Extract-permtest permutations [,permtest-method |
| Plot the grid of a tuned tskrr model | plot_grid |
| plot a heatmap of the predictions from a tskrr model | plot.tskrr |
| predict method for tskrr fits | predict,tskrr-method predict.tskrr |
| Protein interaction for yeast | Kmat_y2h_sc proteinInteraction |
| calculate residuals from a tskrr model | residuals residuals,tskrr-method residuals.tskrr |
| Getters for tskrr objects | get_eigen get_kernel get_kernelmatrix has_hat is_heterogeneous is_homogeneous is_tskrr lambda lambda,tskrrHeterogeneous-method lambda,tskrrHomogeneous-method response response,tskrr-method symmetry |
| test the symmetry of a matrix | test_symmetry |
| Fitting a two step kernel ridge regression | tskrr |
| Class tskrr | tskrr-class |
| Carry out a two-step kernel ridge regression | tskrr.fit |
| Class tskrrHeterogeneous | tskrrHeterogeneous tskrrHeterogeneous-class |
| Class tskrrHomogeneous | tskrrHomogeneous tskrrHomogeneous-class |
| Class tskrrImpute | tskrrImpute tskrrImpute-class |
| Class tskrrImputeHeterogeneous | tskrrImputeHeterogeneous tskrrImputeHeterogeneous-class |
| Class tskrrImputeHomogeneous | tskrrImputeHomogeneous tskrrImputeHomogeneous-class |
| Class tskrrTune | tskrrTune tskrrTune-class |
| Class tskrrTuneHeterogeneous | tskrrTuneHeterogeneous tskrrTuneHeterogeneous-class |
| Class tskrrTuneHomogeneous | tskrrTuneHomogeneous tskrrTuneHomogeneous-class |
| tune the lambda parameters for a tskrr | tune tune,matrix-method tune,tskrrHeterogeneous-method tune,tskrrHomogeneous-method |
| Update a tskrr object with a new lambda | update update,tskrrHeterogeneous-method update,tskrrHomogeneous-method |
| Functions to check matrices | is_square valid_dimensions |
| Test the correctness of the labels. | valid_labels |
| Extract weights from a tskrr model | weights weights,tskrrHeterogeneous-method weights,tskrrHomogeneous-method |
