knitr::opts_chunk$set( fig.width = 6, fig.height = 4,out.width = '49%',fig.align = 'center', collapse = TRUE, comment = "#>" ) suppressMessages(library(xnet))
Networks exist in all forms and shapes.
xnet is a simple, but powerful package to predict edges in networks in a supervised fashion. For example:
The two sets can contain the same types nodes (e.g. protein interaction networks) or different nodes (e.g. goods bought by clients in a recommender system). When the two sets are the same, we call this a homogeneous network. A network between two different sets of nodes is called a heterogeneous network.
The interactions are presented in a adjacency matrix, noted Y. The rows of Y represent one set of nodes, the columns the second. Interactions can be measured on a continuous scale, indicating how strong each interaction is. Often the adjacency matrix only contains a few values: 1 for interaction, 0 for no interaction and possibly -1 for an inverse interaction.
Two-step kernel ridge regression ( function
tskrr() ) predicts the values
in the adjacency matrix based on similarities within the node sets,
calculated by using some form of a kernel function. This function takes
two nodes as input, and outputs a measure of similarity with specific
mathematical properties. The resulting kernel matrix has to be positive
definite for the method to work. In the package, these matrices are noted
K for the rows and - if applicable - G for the columns of Y.
We refer to the kernlab for a collection of different kernel functions.
For the illustrations, we use two different datasets.
The example dataset
proteinInteraction originates from a publication
by Yamanishi et al (2004).
It contains data on interaction between a subset of 769 proteins, and
consists of two objects:
proteinInteractionwhere 1 indicates an interaction between proteins
Kmat_y2h_scdescribing the similarity between the proteins.
drugtarget serves as an example of a heterogeneous network
and comes from a publication of Yamanishi et al (2008). In order to get
a correct kernel matrix, we recalculated the kernel matrices as explained
in the vignette Preparation of the example data.
The dataset exists of three objects
The adjacency matrix indicates which protein targets interact with which drugs, and the purpose is to predict new drug-target interactions.
To fit a two-step kernel ridge regression, you use the function
tskrr(). This function needs to get some tuning parameter(s)
lambda. You can choose to set 1 lambda for tuning K
and G using the same lambda value, or you can specify
a different lambda for K and G.
data(drugtarget) drugmodel <- tskrr(y = drugTargetInteraction, k = targetSim, g = drugSim, lambda = c(0.01,0.1)) drugmodel
For homogeneous networks you use the same function, but you don't specify the G matrix. You also need only a single lambda:
data(proteinInteraction) proteinmodel <- tskrr(proteinInteraction, k = Kmat_y2h_sc, lambda = 0.01) proteinmodel
The model output itself tells you only little, apart from the dimensions, the lambdas used and the labels found in the data. That information can be extracted using a number of convenient functions.
lambda(drugmodel) # extract lambda values lambda(proteinmodel) dim(drugmodel) # extract the dimensions protlabels <- labels(proteinmodel) str(protlabels)
lambdareturns a vector with the lambda values used.
dimreturns the dimensions.
labelsreturns a list with two elements,
g, containing the labels for the rows resp. the columns.
You can also use the functions
colnames() to extract
predict() can be used to extract the
fitted values. The latter also allows you to specify new kernel matrices
to predict for new nodes in the network. To obtain the residuals, you can
use the function
residuals(). This is shown further in the document.
The most significant contribution of this package, are the various
shortcuts for leave-one-out cross-validation (LOO-CV) described in
the paper by Stock et al, 2018.
Generally LOO-CV removes a value, refits the model and predicts the
removed value based on this refit model. In this package you do this
using the function
loo(). The paper describes a number
of different settings, which can be passed to the argument
For some networks, only information of interactions is available, so a 0
does not necessarily indicate "no interaction". It just indicates
"no knowledge" for an interaction. In those cases it makes more sense
to calculate the LOO values by replacing the interaction by 0 instead
of removing it. This can be done by setting
replaceby0 = TRUE.
loo_drugs_interaction <- loo(drugmodel, exclusion = "interaction", replaceby0 = TRUE) loo_protein_both <- loo(proteinmodel, exclusion = "both")
In both cases the result is a matrix with the LOO values.
There are several functions that allow to use the LOO values instead
of predictions for model tuning and validation. For example, you can
calculate residuals based on LOO values directly using the
loo_resid <- residuals(drugmodel, method = "loo", exclusion = "interaction", replaceby0 = TRUE) all.equal(loo_resid, response(drugmodel) - loo_drugs_interaction )
Every other function that can use LOO values instead of predictions will
have the same two arguments
The function provides a
plot() function for looking at the model output.
This function can show you the fitted values, LOO values or the
residuals. It also lets you construct dendrograms based on distances
computed using the K and G matrices, so you have both the predictions
and the similarity information on the nodes in one plot.
plot(drugmodel, main = "Drug Target interaction")
To plot LOO values, you set the argument
which. As the protein model
is pretty extensive, we can remove the dendrogram and select a number
of proteins we want to inspect closer.
plot(proteinmodel, dendro = "none", main = "Protein interaction - LOO", which = "loo", exclusion = "both", rows = rownames(proteinmodel)[10:20], cols = colnames(proteinmodel)[30:35])
If the colors don't suit you, you can set both the breaks used for the color code and the color code itself.
plot(drugmodel, which = "residuals", col = rainbow(20), breaks = seq(-1,1,by=0.1))
In most cases you don't know how to set the
lambda values for optimal
predictions. In order to find the best
lambda values, the function
tune() allows you to do a grid search. This grid search can be
done in a number of ways:
Tuning minimizes a loss function. Two loss functions are provided, i.e.
one based on mean squared error (
loss_mse) and one based on the area
under the curve (
loss_auc). But you can provide your own loss function
too, if needed.
Homogeneous networks have a single lambda value, and should hence only search in a single dimension. The following code tests 20 lambda values between 0.001 and 10.
proteintuned <- tune(proteinmodel, lim = c(0.001,10), ngrid = 20, fun = loss_auc) proteintuned
The returned object is a again a model object with the model fitted using the best lambda value. It also contains extra information on the settings of the tuning. You can extract the grid values as follows:
This returns a list with one or two elements, each element containing the grid values for the respective kernel matrix.
You can also create a plot to visually inspect the tuning:
This object is also a tskrr model, so all the functions used above can be used here as well. For example, we can use the same code as before to inspect the LOO values of this tuned model:
plot(proteintuned, dendro = "none", main = "Protein interaction - LOO", which = "loo", exclusion = "both", rows = rownames(proteinmodel)[10:20], cols = colnames(proteinmodel)[30:35])
For heterogeneous networks, the tuning works the same way. Standard, the
tune() performs a two-dimensional grid search. To do a
one-dimensional grid search (i.e. use the same lambda for K and
G), you set the argument
onedim = TRUE.
drugtuned1d <- tune(drugmodel, lim = c(0.001,10), ngrid = 20, fun = loss_auc, onedim = TRUE) plot_grid(drugtuned1d, main = "1D search")
When performing a two-dimensional grid search, you can specify different limits and grid values or lambda values for both dimensions. You do this by passing a list with two elements for the respective arguments.
drugtuned2d <- tune(drugmodel, lim = list(k = c(0.001,10), g = c(0.0001,10)), ngrid = list(k = 20, g = 10), fun = loss_auc)
will give you a heatmap indicating where the optimal lambda values are
plot_grid(drugtuned2d, main = "2D search")
As before, you can use the function
lambda() to get to the best
A one-dimensional grid search give might yield quite different optimal
lambda values. To get more information on the loss values,
get_loss_values() can be used. This allows you to examine the actual
improvement for every lambda value. The output is always a matrix, and
in the case of a 1D search it's a matrix with one column. Combining
these values with the lambda grid, shows that the the difference between
a lambda value of around 0.20 and around 0.34 is very small. This is
also obvious from the grid plots shown above.
cbind( loss = get_loss_values(drugtuned1d)[,1], lambda = get_grid(drugtuned1d)$k )[10:15,]
In order to predict new values, you need information on the outcome of the kernel functions for the combination of the new values and those used to train the model. Depending on which information you have, you can do different predictions. To illustrate this, we split up the data for the drugsmodel.
idk_test <- c(5,10,15,20,25) idg_test <- c(2,4,6,8,10) drugInteraction_train <- drugTargetInteraction[-idk_test, -idg_test] target_train <- targetSim[-idk_test, -idk_test] drug_train <- drugSim[-idg_test, -idg_test] target_test <- targetSim[idk_test, -idk_test] drug_test <- drugSim[idg_test, -idg_test]
So the following drugs and targets are removed from the training data and will be used for predictions later:
We can now train the data using
tune() just like we would use
trained <- tune(drugInteraction_train, k = target_train, g = drug_train, ngrid = 30)
In order to predict the interaction between new targets and the drugs
in the model, we need to pass the kernel values for the similarities
between the new targets and the ones in the model. The
function will select the correct G matrix for calculating the
Newtargets <- predict(trained, k = target_test) Newtargets[, 1:5]
If you want to predict for new drugs, you need the kernel values for the similarities between new drugs and the drugs trained in the model.
Newdrugs <- predict(trained, g = drug_test) Newdrugs[1:5, ]
You can combine both kernel matrices used above to get predictions about the interaction between new drugs and new targets:
Newdrugtarget <- predict(trained, k=target_test, g=drug_test) Newdrugtarget
Sometimes you have missing values in a adjacency matrix. These missing values can be imputed based on a simple algorithm:
Apart from the usual arguments of
tskrr, you can give additional
parameters to the function
impute_tskrr. The most important ones are
niter: the maximum number of iterations
tol: the tolerance, i.e. the minimal sum of squared differences between iteration steps to keep the algorithm going
verbose: setting this to 1 or 2 gives additional info on the algorithm performance.
So let's construct a dataset with missing values:
drugTargetMissing <- drugTargetInteraction idmissing <- c(10,20,30,40,50,60) drugTargetMissing[idmissing] <- NA
Now we can try to impute these values. The outcome is again a tskrr model.
imputed <- impute_tskrr(drugTargetMissing, k = targetSim, g = drugSim, verbose = TRUE) plot(imputed, dendro = "none")
To extract information on the imputation, you have a few convenience functions to your disposal:
has_imputed_values()tells you whether the model contains imputed values
is_imputed()returns a logical matrix where
TRUEindicates an imputed value
which_imputed()returns an integer vector with the positions of the imputed values. Note that these positions are vector positions, i.e. they give the position in a single dimension (according to how a matrix is stored internally in R.)
has_imputed_values(imputed) which_imputed(imputed) # Extract only the imputed values id <- is_imputed(imputed) predict(imputed)[id]
You can use this information to plot the imputed values in context:
rowid <- rowSums(id) > 0 colid <- colSums(id) > 0 plot(imputed, rows = rowid, cols = colid)
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.