MOFA+: downstream analysis in R
2020-11-03
1 Introduction
In the MOFA2 R package we provide a wide range of downstream analysis to visualise and interpret the model output. Here we provide a brief description of the main functionalities. This vignette is made of simulated data and we do not highlight biologically relevant results. Please see our tutorials for real use cases.
2 Load libraries
library(ggplot2)
library(MOFA2)3 Load trained model
filepath <- system.file("extdata", "model.hdf5", package = "MOFA2")
model <- load_model(filepath)3.1 Overview of data
The function plot_data_overview can be used to obtain an overview of the input data.
It shows how many views (rows) and how many groups (columns) exist, what are
their corresponding dimensionalities and how many missing information they have (grey bars).
plot_data_overview(model)
4 Add metadata to the model
The metadata is stored as a data.frame object in model@samples_metadata,
and it requires at least the column sample.
The column group is required only if you are doing multi-group inference.
The number of rows must match the total number of samples
in the model (sum(model@dimensions$N)).
Let’s add some artificial metadata…
Nsamples = sum(get_dimensions(model)[["N"]])
sample_metadata <- data.frame(
sample = samples_names(model)[[1]],
condition = sample(c("A","B"), size = Nsamples, replace = TRUE),
age = sample(1:100, size = Nsamples, replace = TRUE)
)
samples_metadata(model) <- sample_metadata
head(samples_metadata(model), n=3)## sample condition age group
## 1 sample_0_group_1 B 94 single_group
## 2 sample_1_group_1 B 35 single_group
## 3 sample_2_group_1 B 53 single_group5 Variance decomposition
The first step in the MOFA analysis is to quantify the amount
of variance explained (\(R^2\)) by each factor in each data modality.
The variance explained estimates are stored in the hdf5 file and
loaded in model@cache[["variance_explained"]]:
# Total variance explained per view
head(get_variance_explained(model)$r2_total[[1]])## view_0 view_1
## 76.20973 76.97777# Variance explained for every factor in per view
head(get_variance_explained(model)$r2_per_factor[[1]])## view_0 view_1
## Factor1 19.20399955 19.41070871
## Factor2 15.47560732 17.94710458
## Factor3 16.47469843 16.48996544
## Factor4 13.42094721 11.09844071
## Factor5 11.76334520 11.82572116
## Factor6 0.03885712 0.07087386Variance explained estimates can be plotted using plot_variance_explained(model, ...). Options:
- factors: character vector with a factor name(s), or numeric vector with the index(es) of the factor(s). Default is “all”.
- x: character specifying the dimension for the x-axis (“view”, “factor”, or “group”).
- y: character specifying the dimension for the y-axis (“view”, “factor”, or “group”).
- split_by: character specifying the dimension to be faceted (“view”, “factor”, or “group”).
- plot_total: logical value to indicate if to plot the total variance explained (for the variable in the x-axis)
In this case we have 5 active factors that explain a large amount of variation in both data modalities.
plot_variance_explained(model, x="view", y="factor")
The model explains ~70% of the variance in both data modalities.
plot_variance_explained(model, x="view", y="factor", plot_total = TRUE)[[2]]
6 Visualisation of Factors
The MOFA factors capture the global sources of variability in the data. Mathematically, each factor ordinates cells along a one-dimensional axis centered at zero. The value per se is not important, only the relative positioning of samples matters. Samples with different signs manifest opposite “effects” along the inferred axis of variation, with higher absolute value indicating a stronger effect. Note that the interpretation of factors is analogous to the interpretation of the principal components in PCA.
6.1 Visualisation of factors one at a time
Factors can be plotted using plot_factor (for beeswarm plots of individual factors) or
plot_factors (for scatter plots of factor combinations).
plot_factor(model,
factor = 1:3,
color_by = "age",
shape_by = "condition"
)
Adding more options
p <- plot_factor(model,
factors = c(1,2,3),
color_by = "condition",
dot_size = 3, # change dot size
dodge = TRUE, # dodge points with different colors
legend = FALSE, # remove legend
add_violin = TRUE, # add violin plots,
violin_alpha = 0.25 # transparency of violin plots
)
# The output of plot_factor is a ggplot2 object that we can edit
p <- p +
scale_color_manual(values=c("A"="black", "B"="red")) +
scale_fill_manual(values=c("A"="black", "B"="red"))
print(p)
6.2 Visualisation of combinations of factors
Scatter plots
plot_factors(model,
factors = 1:3,
color_by = "condition"
)
7 Visualisation of feature weights
The weights provide a score for how strong each feature relates to each factor. Features with no association with the factor have values close to zero, while features with strong association with the factor have large absolute values. The sign of the weight indicates the direction of the effect: a positive weight indicates that the feature has higher levels in the cells with positive factor values, and vice versa.
Weights can be plotted using plot_weights or plot_top_weights
plot_weights(model,
view = "view_0",
factor = 1,
nfeatures = 10, # Number of features to highlight
scale = TRUE, # Scale weights from -1 to 1
abs = FALSE # Take the absolute value?
)
plot_top_weights(model,
view = "view_0",
factor = 1,
nfeatures = 10
)
8 Visualisation of covariation patterns in the input data
Instead of looking at weights, it is useful to observe the coordinated heterogeneity
that MOFA captures in the original data.
This can be done using the plot_data_heatmap and plot_data_scatter function.
8.1 Heatmaps
Heatmap of observations. Top features are selected by its weight in the selected factor. By default, samples are ordered according to their corresponding factor value.
plot_data_heatmap(model,
view = "view_1", # view of interest
factor = 1, # factor of interest
features = 20, # number of features to plot (they are selected by weight)
# extra arguments that are passed to the `pheatmap` function
cluster_rows = TRUE, cluster_cols = FALSE,
show_rownames = TRUE, show_colnames = FALSE
)
8.2 Scatter plots
Scatter plots of observations vs factor values. It is useful to add a linear regression estimate to visualise if the relationship between (top) features and factor values is linear.
plot_data_scatter(model,
view = "view_1", # view of interest
factor = 1, # factor of interest
features = 5, # number of features to plot (they are selected by weight)
add_lm = TRUE, # add linear regression
color_by = "condition"
)
8.3 Non-linear dimensionality reduction
The MOFA factors are linear (as in Principal Component analysis), so each one captures limited amount of information, but they can be used as input to other methods that learn compact nonlinear manifolds, e.g. t-SNE or UMAP.
Run UMAP or t-SNE
set.seed(42)
model <- run_umap(model)
model <- run_tsne(model)Plot (nothing too interesting in this simulated data set)
plot_dimred(model,
method = "TSNE", # method can be either "TSNE" or "UMAP"
color_by = "condition",
dot_size = 5
)
9 Other functionalities
9.1 Renaming dimensions
The user can rename the dimensions of the model
views_names(model) <- c("Transcriptomics", "Proteomics")
factors_names(model) <- paste("Factor", 1:get_dimensions(model)$K, sep=" ")views_names(model)## [1] "Transcriptomics" "Proteomics"9.2 Extracting data for downstream analysis
The user can extract the feature weights, the data and the factors to generate their own plots.
Extract factors
# "factors" is a list of matrices, one matrix per group with dimensions (nsamples, nfactors)
factors <- get_factors(model, factors = "all")
lapply(factors,dim)## $single_group
## [1] 100 10Extract weights
# "weights" is a list of matrices, one matrix per view with dimensions (nfeatures, nfactors)
weights <- get_weights(model, views = "all", factors = "all")
lapply(weights,dim)## $Transcriptomics
## [1] 1000 10
##
## $Proteomics
## [1] 1000 10Extract data
# "data" is a nested list of matrices, one matrix per view and group with dimensions (nfeatures, nsamples)
data <- get_data(model)
lapply(data, function(x) lapply(x, dim))[[1]]## $single_group
## [1] 1000 100For convenience, the user can extract the data in long data.frame format:
factors <- get_factors(model, as.data.frame = TRUE)
head(factors, n=3)## sample factor value group
## 1 sample_0_group_1 Factor 1 -2.0102648 single_group
## 2 sample_1_group_1 Factor 1 0.2251219 single_group
## 3 sample_2_group_1 Factor 1 -0.2968025 single_groupweights <- get_weights(model, as.data.frame = TRUE)
head(weights, n=3)## feature factor value view
## 1 feature_0_view_0 Factor 1 -0.002225892 Transcriptomics
## 2 feature_1_view_0 Factor 1 -0.353517945 Transcriptomics
## 3 feature_2_view_0 Factor 1 0.016938729 Transcriptomicsdata <- get_data(model, as.data.frame = TRUE)
head(data, n=3)## view group feature sample value
## 1 Transcriptomics single_group feature_0_view_0 sample_0_group_1 2.08
## 2 Transcriptomics single_group feature_1_view_0 sample_0_group_1 1.10
## 3 Transcriptomics single_group feature_2_view_0 sample_0_group_1 -2.50Session Info
sessionInfo()## R version 4.0.3 (2020-10-10)
## Platform: x86_64-w64-mingw32/x64 (64-bit)
## Running under: Windows Server 2012 R2 x64 (build 9600)
##
## Matrix products: default
##
## locale:
## [1] LC_COLLATE=C
## [2] LC_CTYPE=English_United States.1252
## [3] LC_MONETARY=English_United States.1252
## [4] LC_NUMERIC=C
## [5] LC_TIME=English_United States.1252
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] MOFA2_1.0.1 ggplot2_3.3.2 BiocStyle_2.18.0
##
## loaded via a namespace (and not attached):
## [1] nlme_3.1-150 matrixStats_0.57.0 filelock_1.0.2
## [4] RColorBrewer_1.1-2 tools_4.0.3 backports_1.2.0
## [7] R6_2.5.0 HDF5Array_1.18.0 uwot_0.1.8
## [10] BiocGenerics_0.36.0 mgcv_1.8-33 colorspace_1.4-1
## [13] rhdf5filters_1.2.0 withr_2.3.0 tidyselect_1.1.0
## [16] GGally_2.0.0 curl_4.3 compiler_4.0.3
## [19] basilisk.utils_1.2.0 DelayedArray_0.16.0 labeling_0.4.2
## [22] bookdown_0.21 scales_1.1.1 rappdirs_0.3.1
## [25] stringr_1.4.0 digest_0.6.27 foreign_0.8-80
## [28] rmarkdown_2.5 basilisk_1.2.0 rio_0.5.16
## [31] pkgconfig_2.0.3 htmltools_0.5.0 MatrixGenerics_1.2.0
## [34] rlang_0.4.8 readxl_1.3.1 FNN_1.1.3
## [37] farver_2.0.3 generics_0.1.0 jsonlite_1.7.1
## [40] dplyr_1.0.2 zip_2.1.1 car_3.0-10
## [43] magrittr_1.5 Matrix_1.2-18 Rcpp_1.0.5
## [46] munsell_0.5.0 S4Vectors_0.28.0 Rhdf5lib_1.12.0
## [49] abind_1.4-5 reticulate_1.18 lifecycle_0.2.0
## [52] stringi_1.5.3 yaml_2.2.1 carData_3.0-4
## [55] rhdf5_2.34.0 Rtsne_0.15 plyr_1.8.6
## [58] grid_4.0.3 parallel_4.0.3 ggrepel_0.8.2
## [61] forcats_0.5.0 crayon_1.3.4 lattice_0.20-41
## [64] haven_2.3.1 cowplot_1.1.0 splines_4.0.3
## [67] hms_0.5.3 magick_2.5.0 knitr_1.30
## [70] pillar_1.4.6 ggpubr_0.4.0 ggsignif_0.6.0
## [73] reshape2_1.4.4 stats4_4.0.3 glue_1.4.2
## [76] evaluate_0.14 data.table_1.13.2 BiocManager_1.30.10
## [79] vctrs_0.3.4 cellranger_1.1.0 gtable_0.3.0
## [82] purrr_0.3.4 tidyr_1.1.2 reshape_0.8.8
## [85] xfun_0.19 openxlsx_4.2.3 broom_0.7.2
## [88] RSpectra_0.16-0 rstatix_0.6.0 tibble_3.0.4
## [91] pheatmap_1.0.12 IRanges_2.24.0 corrplot_0.84
## [94] ellipsis_0.3.1