The 2-Wasserstein distance \(W\) is a metric to describe the distance between two distributions, representing e.g. two different conditions \(A\) and \(B\).
For continuous distributions, it is given by
\[W := W(F_A, F_B) = \bigg( \int_0^1 \big|F_A^{-1}(u) - F_B^{-1}(u) \big|^2 du \bigg)^\frac{1}{2},\]
where \(F_A\) and \(F_B\) are the corresponding cumulative distribution functions (CDFs) and \(F_A^{-1}\) and \(F_B^{-1}\) the respective quantile functions.
We specifically consider the squared 2-Wasserstein distance \(d := W^2\) which offers the following decomposition into location, size, and shape terms: \[d := d(F_A, F_B) = \int_0^1 \big|F^{-1}(u) - F^{-1}(u) \big|^2 du = \underbrace{\big(\mu_A - \mu_B\big)^2}_{\text{location}} + \underbrace{\big(\sigma_A - \sigma_B\big)^2}_{\text{size}} + \underbrace{2\sigma_A \sigma_B \big(1 - \rho^{A,B}\big)}_{\text{shape}},\]
where \(\mu_A\) and \(\mu_B\) are the respective means, \(\sigma_A\) and \(\sigma_B\) are the respective standard deviations, and \(\rho^{A,B}\) is the Pearson correlation of the points in the quantile-quantile plot of \(F_A\) and \(F_B\).
In case the distributions \(F_A\) and \(F_B\) are not explicitly given and information is only availbale in the form of samples from \(F_A\) and \(F_B\), respectively, we use the corresponding empirical CDFs \(\hat{F}_A\) and \(\hat{F}_B\). Then, the 2-Wasserstein distance is computed by
\[d(\hat{F}_A, \hat{F}_B) \approx \frac{1}{K} \sum_{k=1}^K \big(Q_A^{\alpha_k} - Q_B^{\alpha_k} \big) \approx \big(\hat{\mu}_A - \hat{\mu}_B\big)^2 + \big(\hat{\sigma}_A - \hat{\sigma}_B\big)^2 + 2\hat{\sigma}_A \hat{\sigma}_B \big(1 - \hat{\rho}^{A,B}\big).\]
Here, \(Q_A\) and \(Q_B\) denote equidistant quantiles of \(F_A\) and \(F_B\), respectively, at the levels \(\alpha_k := \frac{k-0.5}{K}, k = 1, \dots , K\), where we use \(K:=1000\) in our implementation. Moreover, \(\hat{\mu}_A, \hat{\mu}_B, \hat{\sigma}_A, \hat{\sigma}_B\) and \(\hat{\rho}_{A,B}\) denote the empirical versions of the corresponding quantities.
The waddR package offers three functions to compute the
2-Wasserstein distance in two-sample settings.
We will use samples from normal distributions to illustrate them.
The first function, wasserstein_metric, offers a faster
reimplementation in C++ of the wasserstein1d function from
the R package transport, which is able to compute general
\(p\)-Wasserstein distances. For \(p=2\), we obtain the 2-Wasserstein distance
\(W\).
The corresponding value of the squared 2-Wasserstein distance \(d\) is then computed as:
The second function, squared_wass_approx, computes the
squared 2-Wasserstein distance by calculating the mean squared
difference of the equidistant quantiles (first approximation in the
previous formula). This function is currently used to compute the
2-Wasserstein distances in the testing procedures.
The third function, squared_wass_decomp, approximates
the squared 2-Wasserstein distance using the location, size, and shape
terms from the above decomposition (second apporximation in the previous
formula). It also returns the respective decomposition values.
squared_wass_decomp(x,y)
#> $distance
#> [1] 4.180458
#>
#> $location
#> [1] 4.114983
#>
#> $size
#> [1] 0.002307
#>
#> $shape
#> [1] 0.06316766In the considered example, the decomposition results suggest that the two distributions differ with respect to location (mean), but not in terms of size and shape, thus confirming the underlying normal model.
The waddR package
Two-sample tests to check for differences between two distributions
Detection of differential gene expression distributions in scRNAseq data
sessionInfo()
#> R Under development (unstable) (2024-10-21 r87258)
#> Platform: x86_64-pc-linux-gnu
#> Running under: Ubuntu 24.04.1 LTS
#>
#> Matrix products: default
#> BLAS: /home/biocbuild/bbs-3.21-bioc/R/lib/libRblas.so
#> LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.12.0
#>
#> locale:
#> [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
#> [3] LC_TIME=en_GB LC_COLLATE=C
#> [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
#> [7] LC_PAPER=en_US.UTF-8 LC_NAME=C
#> [9] LC_ADDRESS=C LC_TELEPHONE=C
#> [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
#>
#> time zone: America/New_York
#> tzcode source: system (glibc)
#>
#> attached base packages:
#> [1] stats graphics grDevices utils datasets methods base
#>
#> other attached packages:
#> [1] waddR_1.21.0
#>
#> loaded via a namespace (and not attached):
#> [1] SummarizedExperiment_1.37.0 xfun_0.48
#> [3] bslib_0.8.0 Biobase_2.67.0
#> [5] lattice_0.22-6 vctrs_0.6.5
#> [7] tools_4.5.0 generics_0.1.3
#> [9] stats4_4.5.0 curl_5.2.3
#> [11] parallel_4.5.0 tibble_3.2.1
#> [13] fansi_1.0.6 RSQLite_2.3.7
#> [15] blob_1.2.4 pkgconfig_2.0.3
#> [17] Matrix_1.7-1 arm_1.14-4
#> [19] dbplyr_2.5.0 S4Vectors_0.45.0
#> [21] lifecycle_1.0.4 GenomeInfoDbData_1.2.13
#> [23] compiler_4.5.0 codetools_0.2-20
#> [25] eva_0.2.6 GenomeInfoDb_1.43.0
#> [27] htmltools_0.5.8.1 sass_0.4.9
#> [29] yaml_2.3.10 nloptr_2.1.1
#> [31] pillar_1.9.0 crayon_1.5.3
#> [33] jquerylib_0.1.4 MASS_7.3-61
#> [35] BiocParallel_1.41.0 SingleCellExperiment_1.29.0
#> [37] DelayedArray_0.33.0 cachem_1.1.0
#> [39] boot_1.3-31 abind_1.4-8
#> [41] nlme_3.1-166 tidyselect_1.2.1
#> [43] digest_0.6.37 purrr_1.0.2
#> [45] dplyr_1.1.4 splines_4.5.0
#> [47] fastmap_1.2.0 grid_4.5.0
#> [49] SparseArray_1.7.0 cli_3.6.3
#> [51] magrittr_2.0.3 S4Arrays_1.7.0
#> [53] utf8_1.2.4 withr_3.0.2
#> [55] filelock_1.0.3 UCSC.utils_1.3.0
#> [57] bit64_4.5.2 rmarkdown_2.28
#> [59] XVector_0.47.0 httr_1.4.7
#> [61] matrixStats_1.4.1 lme4_1.1-35.5
#> [63] bit_4.5.0 coda_0.19-4.1
#> [65] memoise_2.0.1 evaluate_1.0.1
#> [67] knitr_1.48 GenomicRanges_1.59.0
#> [69] IRanges_2.41.0 BiocFileCache_2.15.0
#> [71] rlang_1.1.4 Rcpp_1.0.13
#> [73] glue_1.8.0 DBI_1.2.3
#> [75] BiocGenerics_0.53.0 minqa_1.2.8
#> [77] jsonlite_1.8.9 R6_2.5.1
#> [79] MatrixGenerics_1.19.0 zlibbioc_1.53.0