diff --git a/README.md b/README.md index 970c428b..4c43e240 100644 --- a/README.md +++ b/README.md @@ -249,10 +249,20 @@ Thank you for using `mixOmics`! ## What’s New -#### Septermber 2020 - -- New biplot now available for `pca` family. See the examples in [this - issue](https://github.com/mixOmicsTeam/mixOmics/issues/90) +#### July 2021 + +- `tune.spls` now able to tune the selected variables on both `X` and + `Y`. See `?tune.spls` +- new function `impute.nipals` to impute missing values using the + nipals algorithm +- new function `tune.spca` to tune the number of selected variables + for pca components +- `circosPlot` now has methods for `block.spls` objects. It can now + handle similar feature names across blocks. It is also much more + customisable. See advanced arguments in `?circosPlot` +- new `biplot` function for `pca` and `pls` objects. See + `?mixOmics::biplot` +- `plotDiablo` now takes `col.per.group` (see \#119) #### April 2020 @@ -272,21 +282,3 @@ Thank you for using `mixOmics`! - `perf.block.splsda` now supports calculation of combined AUC - `block.splsda` bug which could drop some classes with `near.zero.variance=TRUE` now fixed - -#### November 2019 - -- Parallel computing improved for `tune` and `perf` functions, and - even more on Unix-like systems - -- Fixed margin error problem with `plotLoadings`. See the example in - [this issue](https://github.com/mixOmicsTeam/mixOmics/issues/45) - -- `cim` bug which overestimated correlations for single component now - fixed - -- `perf.sgccda` now supports calculation of average combined AUC - -#### September 2019 - -- You can now customise `auroc` plots in version 6.8.3. See example - [here](https://github.com/mixOmicsTeam/mixOmics/issues/35) diff --git a/inst/README-WhatsNew.Rmd b/inst/README-WhatsNew.Rmd index 52462c67..f83f8552 100644 --- a/inst/README-WhatsNew.Rmd +++ b/inst/README-WhatsNew.Rmd @@ -17,9 +17,14 @@ opts_chunk$set( echo = TRUE, eval = FALSE, warning = FALSE, message = FALSE) ## What's New -#### Septermber 2020 +#### July 2021 -* New biplot now available for `pca` family. See the examples in [this issue](https://github.com/mixOmicsTeam/mixOmics/issues/90) +* `tune.spls` now able to tune the selected variables on both `X` and `Y`. See `?tune.spls` +* new function `impute.nipals` to impute missing values using the nipals algorithm +* new function `tune.spca` to tune the number of selected variables for pca components +* `circosPlot` now has methods for `block.spls` objects. It can now handle similar feature names across blocks. It is also much more customisable. See advanced arguments in `?circosPlot` +* new `biplot` function for `pca` and `pls` objects. See `?mixOmics::biplot` +* `plotDiablo` now takes `col.per.group` (see #119) #### April 2020 @@ -28,86 +33,9 @@ opts_chunk$set( echo = TRUE, eval = FALSE, warning = FALSE, message = FALSE) #### March 2020 * `plotIndiv` now supports (weighted) consensus plots for block analyses. See the example in [this issue](https://github.com/mixOmicsTeam/mixOmics/issues/57) - * `plotIndiv(..., ind.names=FALSE)` [warning issue](https://github.com/mixOmicsTeam/mixOmics/issues/59) now fixed #### January 2020 * `perf.block.splsda` now supports calculation of combined AUC * `block.splsda` bug which could drop some classes with `near.zero.variance=TRUE` now fixed - -#### November 2019 - -* Parallel computing improved for `tune` and `perf` functions, and even more on Unix-like systems -```{r, eval=FALSE, echo=FALSE} -library(mixOmics) -require(microbenchmark) -require(parallel) -data(nutrimouse) -nrep <- 25 -folds <- 2 -Y = nutrimouse$diet -data = list(gene = nutrimouse$gene, lipid = nutrimouse$lipid) -design = matrix(c(0,1,1,1,0,1,1,1,0), ncol = 3, nrow = 3, byrow = TRUE) - -nutrimouse.sgccda <- block.splsda(X=data, - Y = Y, - design = design, - keepX = list(gene=c(10,10), lipid=c(15,15)), - ncomp = 2, - scheme = "horst") -microbenchmark::microbenchmark( - serial = perf(nutrimouse.sgccda, folds = folds, nrepeat = nrep), - parallel = perf(nutrimouse.sgccda, folds = folds, nrepeat = nrep, cpus = parallel::detectCores()), times = 2 -) -#> Unit: seconds -#> expr min lq mean median uq max neval -#> serial 10.09760 10.09760 12.130116 12.130116 14.162629 14.162629 2 -#> parallel 5.62336 5.62336 5.756024 5.756024 5.888689 5.888689 2 -``` -* Fixed margin error problem with `plotLoadings`. See the example in [this issue](https://github.com/mixOmicsTeam/mixOmics/issues/45) - -* `cim` bug which overestimated correlations for single component now fixed - -* `perf.sgccda` now supports calculation of average combined AUC -```{r, eval=FALSE, echo=FALSE} -library(mixOmics) -data(nutrimouse) -nrep <- 4 -folds <- 4 -Y = nutrimouse$diet -data = list(gene = nutrimouse$gene, lipid = nutrimouse$lipid) -design = matrix(c(0,1,1,1,0,1,1,1,0), ncol = 3, nrow = 3, byrow = TRUE) -set.seed(42) -nutrimouse.sgccda <- block.splsda(X=data, - Y = Y, - design = design, - keepX = list(gene=c(10,10), lipid=c(15,15)), - ncomp = 2) - -perf.res <- perf(nutrimouse.sgccda, folds = folds, nrepeat = nrep, - auc = TRUE, cpus = parallel::detectCores()) - -perf.res$auc -#> $comp1 -#> AUC p-value -#> coc vs Other(s) 0.8769531 0.2125844 -#> fish vs Other(s) 0.6914062 0.4333581 -#> lin vs Other(s) 0.5449219 0.5615303 -#> ref vs Other(s) 0.5000000 0.5086909 -#> sun vs Other(s) 0.6640625 0.4005816 -#> -#> $comp2 -#> AUC p-value -#> coc vs Other(s) 0.9179688 0.1401584 -#> fish vs Other(s) 0.8164062 0.2083663 -#> lin vs Other(s) 0.7089844 0.3245500 -#> ref vs Other(s) 0.5800781 0.4885250 -#> sun vs Other(s) 0.9238281 0.1132753 -``` - -#### September 2019 - -* You can now customise `auroc` plots in version 6.8.3. See example [here](https://github.com/mixOmicsTeam/mixOmics/issues/35) - -