diff --git a/01_ap-ms.ipynb b/01_ap-ms.ipynb
index a878f40..6aff5ad 100644
--- a/01_ap-ms.ipynb
+++ b/01_ap-ms.ipynb
@@ -10,7 +10,7 @@
     "This Jupyter notebok is part of a book chapter demonstrating the data analysis for mass spectrometry-based analysis of mitochondrial protein translocation mutants and interactome studies.\n",
     "Data analysis relies on the autoprot software available at https://github.com/ag-warscheid/autoprot.\n",
     "\n",
-    "Authors: Julian Bender, Chair of biochemistry II, Warscheid Lab, University of Würzburg"
+    "Author: Julian Bender, Warscheid Lab, Chair of Biochemistry II, University of Würzburg"
    ]
   },
   {
@@ -2287,7 +2287,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 1400x300 with 4 Axes>"
       ]
@@ -2306,16 +2306,16 @@
     "        kind=\"scatter\",\n",
     "        ax=ax,\n",
     "        x=ratio,\n",
-    "        y=\"Intensity\",\n",
+    "        y=\"Intensity L\",\n",
     "        color=\"grey\",\n",
     "        logy=True,\n",
     "    )\n",
     "    pg[pg[\"Gene names\"].str.contains(\"TMEM256\", na=False)].plot(\n",
-    "        kind=\"scatter\", ax=ax, x=ratio, y=\"Intensity\", color=\"red\", logy=True\n",
+    "        kind=\"scatter\", ax=ax, x=ratio, y=\"Intensity L\", color=\"red\", logy=True\n",
     "    )\n",
     "\n",
     "    pg[pg[\"Gene names\"].str.contains(\"TIMM50\", na=False)].plot(\n",
-    "        kind=\"scatter\", ax=ax, x=ratio, y=\"Intensity\", color=\"blue\", logy=True\n",
+    "        kind=\"scatter\", ax=ax, x=ratio, y=\"Intensity L\", color=\"blue\", logy=True\n",
     "    )\n",
     "\n",
     "    ymin, ymax = ax.get_ylim()\n",
@@ -2420,6 +2420,7 @@
    "id": "c7667c7f-7d33-46ac-acad-142def672d56",
    "metadata": {},
    "source": [
+    "### Cyclic LOESS normalisation \n",
     "In addition to median normalisation, the data sometimes requires additional normalisation to produce meaningful results. In this case, the two replicates with the label switch are visually different from the other two replicates which is an effect we are not interested in investigating in the study.\n",
     "To reduce the labeling-bias, we use a smoothing normalisation, cyclic LOESS (local weighted smooting, see https://towardsdatascience.com/loess-373d43b03564 for an introduction). We employ the LOESS normalisation implemented in the R package limma (https://www.rdocumentation.org/packages/limma/versions/3.28.14/topics/normalizeCyclicLoess)."
    ]
@@ -2483,7 +2484,7 @@
     "Here we want ot focus on more recent linear models for statistical analyiss.\n",
     "### Linear models\n",
     "In contrast to conventional t-tests, linear models take global patterns into account and can include information for example about label-switches.\n",
-    "As we are only testing the deviation from a ratio of zweo (i.e. from no effect) and we have previously normalised the ratios, we can use a linear fit as the model rendering the result very similar to a t-test."
+    "As we have previously normalised the ratios, we can use a linear fit as the model rendering the result very similar to a t-test."
    ]
   },
   {
@@ -2491,10 +2492,6 @@
    "execution_count": 10,
    "id": "d8815059-ea59-437c-9f30-3b5fdb6bfbcd",
    "metadata": {
-    "collapsed": true,
-    "jupyter": {
-     "outputs_hidden": true
-    },
     "tags": []
    },
    "outputs": [
@@ -2502,215 +2499,12 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "LIMMA: Assuming a one sample test\n",
-      "  coef\n",
-      "1    1\n",
-      "2    1\n",
-      "3    1\n",
-      "4    1\n",
-      "\n",
-      "Loading required package: rrcovNA\n",
-      "Loading required package: rrcov\n",
-      "Loading required package: robustbase\n",
-      "Scalable Robust Estimators with High Breakdown Point (version 1.7-2)\n",
-      "\n",
-      "Scalable Robust Estimators with High Breakdown Point for\n",
-      "Incomplete Data (version 0.4-15)\n",
-      "\n",
-      "Loading required package: tidyverse\n",
-      "── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──\n",
-      "✔ ggplot2 3.4.0     ✔ purrr   1.0.1\n",
-      "✔ tibble  3.1.8     ✔ dplyr   1.1.0\n",
-      "✔ tidyr   1.3.0     ✔ stringr 1.5.0\n",
-      "✔ readr   2.1.3     ✔ forcats 1.0.0\n",
-      "── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──\n",
-      "✖ dplyr::filter() masks stats::filter()\n",
-      "✖ dplyr::lag()    masks stats::lag()\n",
-      "Loading required package: BiocManager\n",
-      "Bioconductor version '3.16' is out-of-date; the current release version '3.18'\n",
-      "  is available with R version '4.3'; see https://bioconductor.org/install\n",
-      "Loading required package: devtools\n",
-      "Loading required package: usethis\n",
-      "\n",
-      "Attaching package: ‘devtools’\n",
-      "\n",
-      "The following object is masked from ‘package:BiocManager’:\n",
-      "\n",
-      "    install\n",
-      "\n",
-      "Loading required package: limma\n",
-      "Loading required package: vsn\n",
-      "Loading required package: Biobase\n",
-      "Loading required package: BiocGenerics\n",
-      "\n",
-      "Attaching package: ‘BiocGenerics’\n",
-      "\n",
-      "The following object is masked from ‘package:limma’:\n",
-      "\n",
-      "    plotMA\n",
-      "\n",
-      "The following objects are masked from ‘package:dplyr’:\n",
-      "\n",
-      "    combine, intersect, setdiff, union\n",
-      "\n",
-      "The following objects are masked from ‘package:stats’:\n",
-      "\n",
-      "    IQR, mad, sd, var, xtabs\n",
-      "\n",
-      "The following objects are masked from ‘package:base’:\n",
-      "\n",
-      "    anyDuplicated, aperm, append, as.data.frame, basename, cbind,\n",
-      "    colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,\n",
-      "    get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,\n",
-      "    match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,\n",
-      "    Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,\n",
-      "    table, tapply, union, unique, unsplit, which.max, which.min\n",
-      "\n",
-      "Welcome to Bioconductor\n",
-      "\n",
-      "    Vignettes contain introductory material; view with\n",
-      "    'browseVignettes()'. To cite Bioconductor, see\n",
-      "    'citation(\"Biobase\")', and for packages 'citation(\"pkgname\")'.\n",
-      "\n",
-      "\n",
-      "Attaching package: ‘Biobase’\n",
-      "\n",
-      "The following object is masked from ‘package:robustbase’:\n",
-      "\n",
-      "    rowMedians\n",
-      "\n",
-      "Loading required package: RankProd\n",
-      "Loading required package: Rmpfr\n",
-      "Loading required package: gmp\n",
-      "\n",
-      "Attaching package: ‘gmp’\n",
-      "\n",
-      "The following objects are masked from ‘package:base’:\n",
-      "\n",
-      "    %*%, apply, crossprod, matrix, tcrossprod\n",
-      "\n",
-      "C code of R package 'Rmpfr': GMP using 64 bits per limb\n",
-      "\n",
-      "\n",
-      "Attaching package: ‘Rmpfr’\n",
-      "\n",
-      "The following object is masked from ‘package:gmp’:\n",
-      "\n",
-      "    outer\n",
-      "\n",
-      "The following objects are masked from ‘package:BiocGenerics’:\n",
-      "\n",
-      "    cbind, pmax, pmin, rbind\n",
-      "\n",
-      "The following objects are masked from ‘package:stats’:\n",
-      "\n",
-      "    dbinom, dgamma, dnbinom, dnorm, dpois, dt, pnorm\n",
-      "\n",
-      "The following objects are masked from ‘package:base’:\n",
-      "\n",
-      "    cbind, pmax, pmin, rbind\n",
-      "\n",
-      "Loading required package: pcaMethods\n",
-      "\n",
-      "Attaching package: ‘pcaMethods’\n",
-      "\n",
-      "The following object is masked from ‘package:stats’:\n",
-      "\n",
-      "    loadings\n",
-      "\n",
-      "Loading required package: impute\n",
-      "Loading required package: SummarizedExperiment\n",
-      "Loading required package: MatrixGenerics\n",
-      "Loading required package: matrixStats\n",
-      "\n",
-      "Attaching package: ‘matrixStats’\n",
-      "\n",
-      "The following objects are masked from ‘package:Biobase’:\n",
-      "\n",
-      "    anyMissing, rowMedians\n",
-      "\n",
-      "The following object is masked from ‘package:dplyr’:\n",
-      "\n",
-      "    count\n",
-      "\n",
-      "The following objects are masked from ‘package:robustbase’:\n",
-      "\n",
-      "    colMedians, rowMedians\n",
-      "\n",
-      "\n",
-      "Attaching package: ‘MatrixGenerics’\n",
-      "\n",
-      "The following objects are masked from ‘package:matrixStats’:\n",
-      "\n",
-      "    colAlls, colAnyNAs, colAnys, colAvgsPerRowSet, colCollapse,\n",
-      "    colCounts, colCummaxs, colCummins, colCumprods, colCumsums,\n",
-      "    colDiffs, colIQRDiffs, colIQRs, colLogSumExps, colMadDiffs,\n",
-      "    colMads, colMaxs, colMeans2, colMedians, colMins, colOrderStats,\n",
-      "    colProds, colQuantiles, colRanges, colRanks, colSdDiffs, colSds,\n",
-      "    colSums2, colTabulates, colVarDiffs, colVars, colWeightedMads,\n",
-      "    colWeightedMeans, colWeightedMedians, colWeightedSds,\n",
-      "    colWeightedVars, rowAlls, rowAnyNAs, rowAnys, rowAvgsPerColSet,\n",
-      "    rowCollapse, rowCounts, rowCummaxs, rowCummins, rowCumprods,\n",
-      "    rowCumsums, rowDiffs, rowIQRDiffs, rowIQRs, rowLogSumExps,\n",
-      "    rowMadDiffs, rowMads, rowMaxs, rowMeans2, rowMedians, rowMins,\n",
-      "    rowOrderStats, rowProds, rowQuantiles, rowRanges, rowRanks,\n",
-      "    rowSdDiffs, rowSds, rowSums2, rowTabulates, rowVarDiffs, rowVars,\n",
-      "    rowWeightedMads, rowWeightedMeans, rowWeightedMedians,\n",
-      "    rowWeightedSds, rowWeightedVars\n",
-      "\n",
-      "The following object is masked from ‘package:Biobase’:\n",
-      "\n",
-      "    rowMedians\n",
-      "\n",
-      "The following objects are masked from ‘package:robustbase’:\n",
-      "\n",
-      "    colMedians, rowMedians\n",
-      "\n",
-      "Loading required package: GenomicRanges\n",
-      "Loading required package: stats4\n",
-      "Loading required package: S4Vectors\n",
-      "\n",
-      "Attaching package: ‘S4Vectors’\n",
-      "\n",
-      "The following objects are masked from ‘package:dplyr’:\n",
-      "\n",
-      "    first, rename\n",
-      "\n",
-      "The following object is masked from ‘package:tidyr’:\n",
-      "\n",
-      "    expand\n",
-      "\n",
-      "The following objects are masked from ‘package:base’:\n",
-      "\n",
-      "    expand.grid, I, unname\n",
-      "\n",
-      "Loading required package: IRanges\n",
-      "\n",
-      "Attaching package: ‘IRanges’\n",
-      "\n",
-      "The following objects are masked from ‘package:dplyr’:\n",
-      "\n",
-      "    collapse, desc, slice\n",
-      "\n",
-      "The following object is masked from ‘package:purrr’:\n",
-      "\n",
-      "    reduce\n",
-      "\n",
-      "Loading required package: GenomeInfoDb\n",
-      "Loading required package: imputation\n",
-      "Loading required package: DMwR\n",
-      "Loading required package: lattice\n",
-      "Loading required package: grid\n",
-      "Registered S3 method overwritten by 'quantmod':\n",
-      "  method            from\n",
-      "  as.zoo.data.frame zoo \n",
-      "Loading required package: DIMAR\n",
-      "\n"
+      "LIMMA: Assuming a one sample test\n"
      ]
     }
    ],
    "source": [
-    "pg = ana.limma(pg, loess_cols, cond=\"_limma\", print_r=True)"
+    "pg = ana.limma(pg, loess_cols, cond=\"_limma\")"
    ]
   },
   {
diff --git a/02_importomics.ipynb b/02_importomics.ipynb
new file mode 100644
index 0000000..7ddee70
--- /dev/null
+++ b/02_importomics.ipynb
@@ -0,0 +1,2920 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "8f09d882-4572-4106-b9c8-fe3470a5f943",
+   "metadata": {},
+   "source": [
+    "# TOMM40 importomics\n",
+    "\n",
+    "This Jupyter notebok is part of a book chapter demonstrating the data analysis for mass spectrometry-based analysis of mitochondrial protein translocation mutants and interactome studies.\n",
+    "Data analysis relies on the autoprot software available at https://github.com/ag-warscheid/autoprot.\n",
+    "\n",
+    "Author: Julian Bender, Warscheid Lab, Chair of Biochemistry II, University of Würzburg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "eda00bc5-738a-45b7-923d-98f70dd0cef1",
+   "metadata": {
+    "collapsed": true,
+    "jupyter": {
+     "outputs_hidden": true
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/opt/tljh/user/envs/autoprot/lib/python3.10/site-packages/_distutils_hack/__init__.py:33: UserWarning: Setuptools is replacing distutils.\n",
+      "  warnings.warn(\"Setuptools is replacing distutils.\")\n",
+      "Loading required package: rrcovNA\n",
+      "Loading required package: rrcov\n",
+      "Loading required package: robustbase\n",
+      "Scalable Robust Estimators with High Breakdown Point (version 1.7-2)\n",
+      "\n",
+      "Scalable Robust Estimators with High Breakdown Point for\n",
+      "Incomplete Data (version 0.4-15)\n",
+      "\n",
+      "Loading required package: tidyverse\n",
+      "── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──\n",
+      "✔ ggplot2 3.4.0     ✔ purrr   1.0.1\n",
+      "✔ tibble  3.1.8     ✔ dplyr   1.1.0\n",
+      "✔ tidyr   1.3.0     ✔ stringr 1.5.0\n",
+      "✔ readr   2.1.3     ✔ forcats 1.0.0\n",
+      "── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──\n",
+      "✖ dplyr::filter() masks stats::filter()\n",
+      "✖ dplyr::lag()    masks stats::lag()\n",
+      "Loading required package: BiocManager\n",
+      "Bioconductor version '3.16' is out-of-date; the current release version '3.18'\n",
+      "  is available with R version '4.3'; see https://bioconductor.org/install\n",
+      "Loading required package: devtools\n",
+      "Loading required package: usethis\n",
+      "\n",
+      "Attaching package: ‘devtools’\n",
+      "\n",
+      "The following object is masked from ‘package:BiocManager’:\n",
+      "\n",
+      "    install\n",
+      "\n",
+      "Loading required package: limma\n",
+      "Loading required package: vsn\n",
+      "Loading required package: Biobase\n",
+      "Loading required package: BiocGenerics\n",
+      "\n",
+      "Attaching package: ‘BiocGenerics’\n",
+      "\n",
+      "The following object is masked from ‘package:limma’:\n",
+      "\n",
+      "    plotMA\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    combine, intersect, setdiff, union\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    IQR, mad, sd, var, xtabs\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    anyDuplicated, aperm, append, as.data.frame, basename, cbind,\n",
+      "    colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,\n",
+      "    get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,\n",
+      "    match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,\n",
+      "    Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,\n",
+      "    table, tapply, union, unique, unsplit, which.max, which.min\n",
+      "\n",
+      "Welcome to Bioconductor\n",
+      "\n",
+      "    Vignettes contain introductory material; view with\n",
+      "    'browseVignettes()'. To cite Bioconductor, see\n",
+      "    'citation(\"Biobase\")', and for packages 'citation(\"pkgname\")'.\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Biobase’\n",
+      "\n",
+      "The following object is masked from ‘package:robustbase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "Loading required package: RankProd\n",
+      "Loading required package: Rmpfr\n",
+      "Loading required package: gmp\n",
+      "\n",
+      "Attaching package: ‘gmp’\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    %*%, apply, crossprod, matrix, tcrossprod\n",
+      "\n",
+      "C code of R package 'Rmpfr': GMP using 64 bits per limb\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Rmpfr’\n",
+      "\n",
+      "The following object is masked from ‘package:gmp’:\n",
+      "\n",
+      "    outer\n",
+      "\n",
+      "The following objects are masked from ‘package:BiocGenerics’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    dbinom, dgamma, dnbinom, dnorm, dpois, dt, pnorm\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "Loading required package: pcaMethods\n",
+      "\n",
+      "Attaching package: ‘pcaMethods’\n",
+      "\n",
+      "The following object is masked from ‘package:stats’:\n",
+      "\n",
+      "    loadings\n",
+      "\n",
+      "Loading required package: impute\n",
+      "Loading required package: SummarizedExperiment\n",
+      "Loading required package: MatrixGenerics\n",
+      "Loading required package: matrixStats\n",
+      "\n",
+      "Attaching package: ‘matrixStats’\n",
+      "\n",
+      "The following objects are masked from ‘package:Biobase’:\n",
+      "\n",
+      "    anyMissing, rowMedians\n",
+      "\n",
+      "The following object is masked from ‘package:dplyr’:\n",
+      "\n",
+      "    count\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘MatrixGenerics’\n",
+      "\n",
+      "The following objects are masked from ‘package:matrixStats’:\n",
+      "\n",
+      "    colAlls, colAnyNAs, colAnys, colAvgsPerRowSet, colCollapse,\n",
+      "    colCounts, colCummaxs, colCummins, colCumprods, colCumsums,\n",
+      "    colDiffs, colIQRDiffs, colIQRs, colLogSumExps, colMadDiffs,\n",
+      "    colMads, colMaxs, colMeans2, colMedians, colMins, colOrderStats,\n",
+      "    colProds, colQuantiles, colRanges, colRanks, colSdDiffs, colSds,\n",
+      "    colSums2, colTabulates, colVarDiffs, colVars, colWeightedMads,\n",
+      "    colWeightedMeans, colWeightedMedians, colWeightedSds,\n",
+      "    colWeightedVars, rowAlls, rowAnyNAs, rowAnys, rowAvgsPerColSet,\n",
+      "    rowCollapse, rowCounts, rowCummaxs, rowCummins, rowCumprods,\n",
+      "    rowCumsums, rowDiffs, rowIQRDiffs, rowIQRs, rowLogSumExps,\n",
+      "    rowMadDiffs, rowMads, rowMaxs, rowMeans2, rowMedians, rowMins,\n",
+      "    rowOrderStats, rowProds, rowQuantiles, rowRanges, rowRanks,\n",
+      "    rowSdDiffs, rowSds, rowSums2, rowTabulates, rowVarDiffs, rowVars,\n",
+      "    rowWeightedMads, rowWeightedMeans, rowWeightedMedians,\n",
+      "    rowWeightedSds, rowWeightedVars\n",
+      "\n",
+      "The following object is masked from ‘package:Biobase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "Loading required package: GenomicRanges\n",
+      "Loading required package: stats4\n",
+      "Loading required package: S4Vectors\n",
+      "\n",
+      "Attaching package: ‘S4Vectors’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    first, rename\n",
+      "\n",
+      "The following object is masked from ‘package:tidyr’:\n",
+      "\n",
+      "    expand\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    expand.grid, I, unname\n",
+      "\n",
+      "Loading required package: IRanges\n",
+      "\n",
+      "Attaching package: ‘IRanges’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    collapse, desc, slice\n",
+      "\n",
+      "The following object is masked from ‘package:purrr’:\n",
+      "\n",
+      "    reduce\n",
+      "\n",
+      "Loading required package: GenomeInfoDb\n",
+      "Loading required package: imputation\n",
+      "Loading required package: DMwR\n",
+      "Loading required package: lattice\n",
+      "Loading required package: grid\n",
+      "Registered S3 method overwritten by 'quantmod':\n",
+      "  method            from\n",
+      "  as.zoo.data.frame zoo \n",
+      "Loading required package: DIMAR\n",
+      "Loading required package: rrcovNA\n",
+      "Loading required package: rrcov\n",
+      "Loading required package: robustbase\n",
+      "Scalable Robust Estimators with High Breakdown Point (version 1.7-2)\n",
+      "\n",
+      "Scalable Robust Estimators with High Breakdown Point for\n",
+      "Incomplete Data (version 0.4-15)\n",
+      "\n",
+      "Loading required package: tidyverse\n",
+      "── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──\n",
+      "✔ ggplot2 3.4.0     ✔ purrr   1.0.1\n",
+      "✔ tibble  3.1.8     ✔ dplyr   1.1.0\n",
+      "✔ tidyr   1.3.0     ✔ stringr 1.5.0\n",
+      "✔ readr   2.1.3     ✔ forcats 1.0.0\n",
+      "── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──\n",
+      "✖ dplyr::filter() masks stats::filter()\n",
+      "✖ dplyr::lag()    masks stats::lag()\n",
+      "Loading required package: BiocManager\n",
+      "Bioconductor version '3.16' is out-of-date; the current release version '3.18'\n",
+      "  is available with R version '4.3'; see https://bioconductor.org/install\n",
+      "Loading required package: devtools\n",
+      "Loading required package: usethis\n",
+      "\n",
+      "Attaching package: ‘devtools’\n",
+      "\n",
+      "The following object is masked from ‘package:BiocManager’:\n",
+      "\n",
+      "    install\n",
+      "\n",
+      "Loading required package: limma\n",
+      "Loading required package: vsn\n",
+      "Loading required package: Biobase\n",
+      "Loading required package: BiocGenerics\n",
+      "\n",
+      "Attaching package: ‘BiocGenerics’\n",
+      "\n",
+      "The following object is masked from ‘package:limma’:\n",
+      "\n",
+      "    plotMA\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    combine, intersect, setdiff, union\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    IQR, mad, sd, var, xtabs\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    anyDuplicated, aperm, append, as.data.frame, basename, cbind,\n",
+      "    colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,\n",
+      "    get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,\n",
+      "    match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,\n",
+      "    Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,\n",
+      "    table, tapply, union, unique, unsplit, which.max, which.min\n",
+      "\n",
+      "Welcome to Bioconductor\n",
+      "\n",
+      "    Vignettes contain introductory material; view with\n",
+      "    'browseVignettes()'. To cite Bioconductor, see\n",
+      "    'citation(\"Biobase\")', and for packages 'citation(\"pkgname\")'.\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Biobase’\n",
+      "\n",
+      "The following object is masked from ‘package:robustbase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "Loading required package: RankProd\n",
+      "Loading required package: Rmpfr\n",
+      "Loading required package: gmp\n",
+      "\n",
+      "Attaching package: ‘gmp’\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    %*%, apply, crossprod, matrix, tcrossprod\n",
+      "\n",
+      "C code of R package 'Rmpfr': GMP using 64 bits per limb\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Rmpfr’\n",
+      "\n",
+      "The following object is masked from ‘package:gmp’:\n",
+      "\n",
+      "    outer\n",
+      "\n",
+      "The following objects are masked from ‘package:BiocGenerics’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    dbinom, dgamma, dnbinom, dnorm, dpois, dt, pnorm\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "Loading required package: pcaMethods\n",
+      "\n",
+      "Attaching package: ‘pcaMethods’\n",
+      "\n",
+      "The following object is masked from ‘package:stats’:\n",
+      "\n",
+      "    loadings\n",
+      "\n",
+      "Loading required package: impute\n",
+      "Loading required package: SummarizedExperiment\n",
+      "Loading required package: MatrixGenerics\n",
+      "Loading required package: matrixStats\n",
+      "\n",
+      "Attaching package: ‘matrixStats’\n",
+      "\n",
+      "The following objects are masked from ‘package:Biobase’:\n",
+      "\n",
+      "    anyMissing, rowMedians\n",
+      "\n",
+      "The following object is masked from ‘package:dplyr’:\n",
+      "\n",
+      "    count\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘MatrixGenerics’\n",
+      "\n",
+      "The following objects are masked from ‘package:matrixStats’:\n",
+      "\n",
+      "    colAlls, colAnyNAs, colAnys, colAvgsPerRowSet, colCollapse,\n",
+      "    colCounts, colCummaxs, colCummins, colCumprods, colCumsums,\n",
+      "    colDiffs, colIQRDiffs, colIQRs, colLogSumExps, colMadDiffs,\n",
+      "    colMads, colMaxs, colMeans2, colMedians, colMins, colOrderStats,\n",
+      "    colProds, colQuantiles, colRanges, colRanks, colSdDiffs, colSds,\n",
+      "    colSums2, colTabulates, colVarDiffs, colVars, colWeightedMads,\n",
+      "    colWeightedMeans, colWeightedMedians, colWeightedSds,\n",
+      "    colWeightedVars, rowAlls, rowAnyNAs, rowAnys, rowAvgsPerColSet,\n",
+      "    rowCollapse, rowCounts, rowCummaxs, rowCummins, rowCumprods,\n",
+      "    rowCumsums, rowDiffs, rowIQRDiffs, rowIQRs, rowLogSumExps,\n",
+      "    rowMadDiffs, rowMads, rowMaxs, rowMeans2, rowMedians, rowMins,\n",
+      "    rowOrderStats, rowProds, rowQuantiles, rowRanges, rowRanks,\n",
+      "    rowSdDiffs, rowSds, rowSums2, rowTabulates, rowVarDiffs, rowVars,\n",
+      "    rowWeightedMads, rowWeightedMeans, rowWeightedMedians,\n",
+      "    rowWeightedSds, rowWeightedVars\n",
+      "\n",
+      "The following object is masked from ‘package:Biobase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "Loading required package: GenomicRanges\n",
+      "Loading required package: stats4\n",
+      "Loading required package: S4Vectors\n",
+      "\n",
+      "Attaching package: ‘S4Vectors’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    first, rename\n",
+      "\n",
+      "The following object is masked from ‘package:tidyr’:\n",
+      "\n",
+      "    expand\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    expand.grid, I, unname\n",
+      "\n",
+      "Loading required package: IRanges\n",
+      "\n",
+      "Attaching package: ‘IRanges’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    collapse, desc, slice\n",
+      "\n",
+      "The following object is masked from ‘package:purrr’:\n",
+      "\n",
+      "    reduce\n",
+      "\n",
+      "Loading required package: GenomeInfoDb\n",
+      "Loading required package: imputation\n",
+      "Loading required package: DMwR\n",
+      "Loading required package: lattice\n",
+      "Loading required package: grid\n",
+      "Registered S3 method overwritten by 'quantmod':\n",
+      "  method            from\n",
+      "  as.zoo.data.frame zoo \n",
+      "Loading required package: DIMAR\n",
+      "Loading required package: rrcovNA\n",
+      "Loading required package: rrcov\n",
+      "Loading required package: robustbase\n",
+      "Scalable Robust Estimators with High Breakdown Point (version 1.7-2)\n",
+      "\n",
+      "Scalable Robust Estimators with High Breakdown Point for\n",
+      "Incomplete Data (version 0.4-15)\n",
+      "\n",
+      "Loading required package: tidyverse\n",
+      "── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──\n",
+      "✔ ggplot2 3.4.0     ✔ purrr   1.0.1\n",
+      "✔ tibble  3.1.8     ✔ dplyr   1.1.0\n",
+      "✔ tidyr   1.3.0     ✔ stringr 1.5.0\n",
+      "✔ readr   2.1.3     ✔ forcats 1.0.0\n",
+      "── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──\n",
+      "✖ dplyr::filter() masks stats::filter()\n",
+      "✖ dplyr::lag()    masks stats::lag()\n",
+      "Loading required package: BiocManager\n",
+      "Bioconductor version '3.16' is out-of-date; the current release version '3.18'\n",
+      "  is available with R version '4.3'; see https://bioconductor.org/install\n",
+      "Loading required package: devtools\n",
+      "Loading required package: usethis\n",
+      "\n",
+      "Attaching package: ‘devtools’\n",
+      "\n",
+      "The following object is masked from ‘package:BiocManager’:\n",
+      "\n",
+      "    install\n",
+      "\n",
+      "Loading required package: limma\n",
+      "Loading required package: vsn\n",
+      "Loading required package: Biobase\n",
+      "Loading required package: BiocGenerics\n",
+      "\n",
+      "Attaching package: ‘BiocGenerics’\n",
+      "\n",
+      "The following object is masked from ‘package:limma’:\n",
+      "\n",
+      "    plotMA\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    combine, intersect, setdiff, union\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    IQR, mad, sd, var, xtabs\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    anyDuplicated, aperm, append, as.data.frame, basename, cbind,\n",
+      "    colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,\n",
+      "    get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,\n",
+      "    match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,\n",
+      "    Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,\n",
+      "    table, tapply, union, unique, unsplit, which.max, which.min\n",
+      "\n",
+      "Welcome to Bioconductor\n",
+      "\n",
+      "    Vignettes contain introductory material; view with\n",
+      "    'browseVignettes()'. To cite Bioconductor, see\n",
+      "    'citation(\"Biobase\")', and for packages 'citation(\"pkgname\")'.\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Biobase’\n",
+      "\n",
+      "The following object is masked from ‘package:robustbase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "Loading required package: RankProd\n",
+      "Loading required package: Rmpfr\n",
+      "Loading required package: gmp\n",
+      "\n",
+      "Attaching package: ‘gmp’\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    %*%, apply, crossprod, matrix, tcrossprod\n",
+      "\n",
+      "C code of R package 'Rmpfr': GMP using 64 bits per limb\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Rmpfr’\n",
+      "\n",
+      "The following object is masked from ‘package:gmp’:\n",
+      "\n",
+      "    outer\n",
+      "\n",
+      "The following objects are masked from ‘package:BiocGenerics’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    dbinom, dgamma, dnbinom, dnorm, dpois, dt, pnorm\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "Loading required package: pcaMethods\n",
+      "\n",
+      "Attaching package: ‘pcaMethods’\n",
+      "\n",
+      "The following object is masked from ‘package:stats’:\n",
+      "\n",
+      "    loadings\n",
+      "\n",
+      "Loading required package: impute\n",
+      "Loading required package: SummarizedExperiment\n",
+      "Loading required package: MatrixGenerics\n",
+      "Loading required package: matrixStats\n",
+      "\n",
+      "Attaching package: ‘matrixStats’\n",
+      "\n",
+      "The following objects are masked from ‘package:Biobase’:\n",
+      "\n",
+      "    anyMissing, rowMedians\n",
+      "\n",
+      "The following object is masked from ‘package:dplyr’:\n",
+      "\n",
+      "    count\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘MatrixGenerics’\n",
+      "\n",
+      "The following objects are masked from ‘package:matrixStats’:\n",
+      "\n",
+      "    colAlls, colAnyNAs, colAnys, colAvgsPerRowSet, colCollapse,\n",
+      "    colCounts, colCummaxs, colCummins, colCumprods, colCumsums,\n",
+      "    colDiffs, colIQRDiffs, colIQRs, colLogSumExps, colMadDiffs,\n",
+      "    colMads, colMaxs, colMeans2, colMedians, colMins, colOrderStats,\n",
+      "    colProds, colQuantiles, colRanges, colRanks, colSdDiffs, colSds,\n",
+      "    colSums2, colTabulates, colVarDiffs, colVars, colWeightedMads,\n",
+      "    colWeightedMeans, colWeightedMedians, colWeightedSds,\n",
+      "    colWeightedVars, rowAlls, rowAnyNAs, rowAnys, rowAvgsPerColSet,\n",
+      "    rowCollapse, rowCounts, rowCummaxs, rowCummins, rowCumprods,\n",
+      "    rowCumsums, rowDiffs, rowIQRDiffs, rowIQRs, rowLogSumExps,\n",
+      "    rowMadDiffs, rowMads, rowMaxs, rowMeans2, rowMedians, rowMins,\n",
+      "    rowOrderStats, rowProds, rowQuantiles, rowRanges, rowRanks,\n",
+      "    rowSdDiffs, rowSds, rowSums2, rowTabulates, rowVarDiffs, rowVars,\n",
+      "    rowWeightedMads, rowWeightedMeans, rowWeightedMedians,\n",
+      "    rowWeightedSds, rowWeightedVars\n",
+      "\n",
+      "The following object is masked from ‘package:Biobase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "Loading required package: GenomicRanges\n",
+      "Loading required package: stats4\n",
+      "Loading required package: S4Vectors\n",
+      "\n",
+      "Attaching package: ‘S4Vectors’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    first, rename\n",
+      "\n",
+      "The following object is masked from ‘package:tidyr’:\n",
+      "\n",
+      "    expand\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    expand.grid, I, unname\n",
+      "\n",
+      "Loading required package: IRanges\n",
+      "\n",
+      "Attaching package: ‘IRanges’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    collapse, desc, slice\n",
+      "\n",
+      "The following object is masked from ‘package:purrr’:\n",
+      "\n",
+      "    reduce\n",
+      "\n",
+      "Loading required package: GenomeInfoDb\n",
+      "Loading required package: imputation\n",
+      "Loading required package: DMwR\n",
+      "Loading required package: lattice\n",
+      "Loading required package: grid\n",
+      "Registered S3 method overwritten by 'quantmod':\n",
+      "  method            from\n",
+      "  as.zoo.data.frame zoo \n",
+      "Loading required package: DIMAR\n",
+      "Loading required package: rrcovNA\n",
+      "Loading required package: rrcov\n",
+      "Loading required package: robustbase\n",
+      "Scalable Robust Estimators with High Breakdown Point (version 1.7-2)\n",
+      "\n",
+      "Scalable Robust Estimators with High Breakdown Point for\n",
+      "Incomplete Data (version 0.4-15)\n",
+      "\n",
+      "Loading required package: tidyverse\n",
+      "── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──\n",
+      "✔ ggplot2 3.4.0     ✔ purrr   1.0.1\n",
+      "✔ tibble  3.1.8     ✔ dplyr   1.1.0\n",
+      "✔ tidyr   1.3.0     ✔ stringr 1.5.0\n",
+      "✔ readr   2.1.3     ✔ forcats 1.0.0\n",
+      "── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──\n",
+      "✖ dplyr::filter() masks stats::filter()\n",
+      "✖ dplyr::lag()    masks stats::lag()\n",
+      "Loading required package: BiocManager\n",
+      "Bioconductor version '3.16' is out-of-date; the current release version '3.18'\n",
+      "  is available with R version '4.3'; see https://bioconductor.org/install\n",
+      "Loading required package: devtools\n",
+      "Loading required package: usethis\n",
+      "\n",
+      "Attaching package: ‘devtools’\n",
+      "\n",
+      "The following object is masked from ‘package:BiocManager’:\n",
+      "\n",
+      "    install\n",
+      "\n",
+      "Loading required package: limma\n",
+      "Loading required package: vsn\n",
+      "Loading required package: Biobase\n",
+      "Loading required package: BiocGenerics\n",
+      "\n",
+      "Attaching package: ‘BiocGenerics’\n",
+      "\n",
+      "The following object is masked from ‘package:limma’:\n",
+      "\n",
+      "    plotMA\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    combine, intersect, setdiff, union\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    IQR, mad, sd, var, xtabs\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    anyDuplicated, aperm, append, as.data.frame, basename, cbind,\n",
+      "    colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,\n",
+      "    get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,\n",
+      "    match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,\n",
+      "    Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,\n",
+      "    table, tapply, union, unique, unsplit, which.max, which.min\n",
+      "\n",
+      "Welcome to Bioconductor\n",
+      "\n",
+      "    Vignettes contain introductory material; view with\n",
+      "    'browseVignettes()'. To cite Bioconductor, see\n",
+      "    'citation(\"Biobase\")', and for packages 'citation(\"pkgname\")'.\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Biobase’\n",
+      "\n",
+      "The following object is masked from ‘package:robustbase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "Loading required package: RankProd\n",
+      "Loading required package: Rmpfr\n",
+      "Loading required package: gmp\n",
+      "\n",
+      "Attaching package: ‘gmp’\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    %*%, apply, crossprod, matrix, tcrossprod\n",
+      "\n",
+      "C code of R package 'Rmpfr': GMP using 64 bits per limb\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Rmpfr’\n",
+      "\n",
+      "The following object is masked from ‘package:gmp’:\n",
+      "\n",
+      "    outer\n",
+      "\n",
+      "The following objects are masked from ‘package:BiocGenerics’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    dbinom, dgamma, dnbinom, dnorm, dpois, dt, pnorm\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "Loading required package: pcaMethods\n",
+      "\n",
+      "Attaching package: ‘pcaMethods’\n",
+      "\n",
+      "The following object is masked from ‘package:stats’:\n",
+      "\n",
+      "    loadings\n",
+      "\n",
+      "Loading required package: impute\n",
+      "Loading required package: SummarizedExperiment\n",
+      "Loading required package: MatrixGenerics\n",
+      "Loading required package: matrixStats\n",
+      "\n",
+      "Attaching package: ‘matrixStats’\n",
+      "\n",
+      "The following objects are masked from ‘package:Biobase’:\n",
+      "\n",
+      "    anyMissing, rowMedians\n",
+      "\n",
+      "The following object is masked from ‘package:dplyr’:\n",
+      "\n",
+      "    count\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘MatrixGenerics’\n",
+      "\n",
+      "The following objects are masked from ‘package:matrixStats’:\n",
+      "\n",
+      "    colAlls, colAnyNAs, colAnys, colAvgsPerRowSet, colCollapse,\n",
+      "    colCounts, colCummaxs, colCummins, colCumprods, colCumsums,\n",
+      "    colDiffs, colIQRDiffs, colIQRs, colLogSumExps, colMadDiffs,\n",
+      "    colMads, colMaxs, colMeans2, colMedians, colMins, colOrderStats,\n",
+      "    colProds, colQuantiles, colRanges, colRanks, colSdDiffs, colSds,\n",
+      "    colSums2, colTabulates, colVarDiffs, colVars, colWeightedMads,\n",
+      "    colWeightedMeans, colWeightedMedians, colWeightedSds,\n",
+      "    colWeightedVars, rowAlls, rowAnyNAs, rowAnys, rowAvgsPerColSet,\n",
+      "    rowCollapse, rowCounts, rowCummaxs, rowCummins, rowCumprods,\n",
+      "    rowCumsums, rowDiffs, rowIQRDiffs, rowIQRs, rowLogSumExps,\n",
+      "    rowMadDiffs, rowMads, rowMaxs, rowMeans2, rowMedians, rowMins,\n",
+      "    rowOrderStats, rowProds, rowQuantiles, rowRanges, rowRanks,\n",
+      "    rowSdDiffs, rowSds, rowSums2, rowTabulates, rowVarDiffs, rowVars,\n",
+      "    rowWeightedMads, rowWeightedMeans, rowWeightedMedians,\n",
+      "    rowWeightedSds, rowWeightedVars\n",
+      "\n",
+      "The following object is masked from ‘package:Biobase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "Loading required package: GenomicRanges\n",
+      "Loading required package: stats4\n",
+      "Loading required package: S4Vectors\n",
+      "\n",
+      "Attaching package: ‘S4Vectors’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    first, rename\n",
+      "\n",
+      "The following object is masked from ‘package:tidyr’:\n",
+      "\n",
+      "    expand\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    expand.grid, I, unname\n",
+      "\n",
+      "Loading required package: IRanges\n",
+      "\n",
+      "Attaching package: ‘IRanges’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    collapse, desc, slice\n",
+      "\n",
+      "The following object is masked from ‘package:purrr’:\n",
+      "\n",
+      "    reduce\n",
+      "\n",
+      "Loading required package: GenomeInfoDb\n",
+      "Loading required package: imputation\n",
+      "Loading required package: DMwR\n",
+      "Loading required package: lattice\n",
+      "Loading required package: grid\n",
+      "Registered S3 method overwritten by 'quantmod':\n",
+      "  method            from\n",
+      "  as.zoo.data.frame zoo \n",
+      "Loading required package: DIMAR\n",
+      "Loading required package: rrcovNA\n",
+      "Loading required package: rrcov\n",
+      "Loading required package: robustbase\n",
+      "Scalable Robust Estimators with High Breakdown Point (version 1.7-2)\n",
+      "\n",
+      "Scalable Robust Estimators with High Breakdown Point for\n",
+      "Incomplete Data (version 0.4-15)\n",
+      "\n",
+      "Loading required package: tidyverse\n",
+      "── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──\n",
+      "✔ ggplot2 3.4.0     ✔ purrr   1.0.1\n",
+      "✔ tibble  3.1.8     ✔ dplyr   1.1.0\n",
+      "✔ tidyr   1.3.0     ✔ stringr 1.5.0\n",
+      "✔ readr   2.1.3     ✔ forcats 1.0.0\n",
+      "── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──\n",
+      "✖ dplyr::filter() masks stats::filter()\n",
+      "✖ dplyr::lag()    masks stats::lag()\n",
+      "Loading required package: BiocManager\n",
+      "Bioconductor version '3.16' is out-of-date; the current release version '3.18'\n",
+      "  is available with R version '4.3'; see https://bioconductor.org/install\n",
+      "Loading required package: devtools\n",
+      "Loading required package: usethis\n",
+      "\n",
+      "Attaching package: ‘devtools’\n",
+      "\n",
+      "The following object is masked from ‘package:BiocManager’:\n",
+      "\n",
+      "    install\n",
+      "\n",
+      "Loading required package: limma\n",
+      "Loading required package: vsn\n",
+      "Loading required package: Biobase\n",
+      "Loading required package: BiocGenerics\n",
+      "\n",
+      "Attaching package: ‘BiocGenerics’\n",
+      "\n",
+      "The following object is masked from ‘package:limma’:\n",
+      "\n",
+      "    plotMA\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    combine, intersect, setdiff, union\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    IQR, mad, sd, var, xtabs\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    anyDuplicated, aperm, append, as.data.frame, basename, cbind,\n",
+      "    colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,\n",
+      "    get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,\n",
+      "    match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,\n",
+      "    Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,\n",
+      "    table, tapply, union, unique, unsplit, which.max, which.min\n",
+      "\n",
+      "Welcome to Bioconductor\n",
+      "\n",
+      "    Vignettes contain introductory material; view with\n",
+      "    'browseVignettes()'. To cite Bioconductor, see\n",
+      "    'citation(\"Biobase\")', and for packages 'citation(\"pkgname\")'.\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Biobase’\n",
+      "\n",
+      "The following object is masked from ‘package:robustbase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "Loading required package: RankProd\n",
+      "Loading required package: Rmpfr\n",
+      "Loading required package: gmp\n",
+      "\n",
+      "Attaching package: ‘gmp’\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    %*%, apply, crossprod, matrix, tcrossprod\n",
+      "\n",
+      "C code of R package 'Rmpfr': GMP using 64 bits per limb\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Rmpfr’\n",
+      "\n",
+      "The following object is masked from ‘package:gmp’:\n",
+      "\n",
+      "    outer\n",
+      "\n",
+      "The following objects are masked from ‘package:BiocGenerics’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    dbinom, dgamma, dnbinom, dnorm, dpois, dt, pnorm\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "Loading required package: pcaMethods\n",
+      "\n",
+      "Attaching package: ‘pcaMethods’\n",
+      "\n",
+      "The following object is masked from ‘package:stats’:\n",
+      "\n",
+      "    loadings\n",
+      "\n",
+      "Loading required package: impute\n",
+      "Loading required package: SummarizedExperiment\n",
+      "Loading required package: MatrixGenerics\n",
+      "Loading required package: matrixStats\n",
+      "\n",
+      "Attaching package: ‘matrixStats’\n",
+      "\n",
+      "The following objects are masked from ‘package:Biobase’:\n",
+      "\n",
+      "    anyMissing, rowMedians\n",
+      "\n",
+      "The following object is masked from ‘package:dplyr’:\n",
+      "\n",
+      "    count\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘MatrixGenerics’\n",
+      "\n",
+      "The following objects are masked from ‘package:matrixStats’:\n",
+      "\n",
+      "    colAlls, colAnyNAs, colAnys, colAvgsPerRowSet, colCollapse,\n",
+      "    colCounts, colCummaxs, colCummins, colCumprods, colCumsums,\n",
+      "    colDiffs, colIQRDiffs, colIQRs, colLogSumExps, colMadDiffs,\n",
+      "    colMads, colMaxs, colMeans2, colMedians, colMins, colOrderStats,\n",
+      "    colProds, colQuantiles, colRanges, colRanks, colSdDiffs, colSds,\n",
+      "    colSums2, colTabulates, colVarDiffs, colVars, colWeightedMads,\n",
+      "    colWeightedMeans, colWeightedMedians, colWeightedSds,\n",
+      "    colWeightedVars, rowAlls, rowAnyNAs, rowAnys, rowAvgsPerColSet,\n",
+      "    rowCollapse, rowCounts, rowCummaxs, rowCummins, rowCumprods,\n",
+      "    rowCumsums, rowDiffs, rowIQRDiffs, rowIQRs, rowLogSumExps,\n",
+      "    rowMadDiffs, rowMads, rowMaxs, rowMeans2, rowMedians, rowMins,\n",
+      "    rowOrderStats, rowProds, rowQuantiles, rowRanges, rowRanks,\n",
+      "    rowSdDiffs, rowSds, rowSums2, rowTabulates, rowVarDiffs, rowVars,\n",
+      "    rowWeightedMads, rowWeightedMeans, rowWeightedMedians,\n",
+      "    rowWeightedSds, rowWeightedVars\n",
+      "\n",
+      "The following object is masked from ‘package:Biobase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "Loading required package: GenomicRanges\n",
+      "Loading required package: stats4\n",
+      "Loading required package: S4Vectors\n",
+      "\n",
+      "Attaching package: ‘S4Vectors’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    first, rename\n",
+      "\n",
+      "The following object is masked from ‘package:tidyr’:\n",
+      "\n",
+      "    expand\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    expand.grid, I, unname\n",
+      "\n",
+      "Loading required package: IRanges\n",
+      "\n",
+      "Attaching package: ‘IRanges’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    collapse, desc, slice\n",
+      "\n",
+      "The following object is masked from ‘package:purrr’:\n",
+      "\n",
+      "    reduce\n",
+      "\n",
+      "Loading required package: GenomeInfoDb\n",
+      "Loading required package: imputation\n",
+      "Loading required package: DMwR\n",
+      "Loading required package: lattice\n",
+      "Loading required package: grid\n",
+      "Registered S3 method overwritten by 'quantmod':\n",
+      "  method            from\n",
+      "  as.zoo.data.frame zoo \n",
+      "Loading required package: DIMAR\n",
+      "Loading required package: rrcovNA\n",
+      "Loading required package: rrcov\n",
+      "Loading required package: robustbase\n",
+      "Scalable Robust Estimators with High Breakdown Point (version 1.7-2)\n",
+      "\n",
+      "Scalable Robust Estimators with High Breakdown Point for\n",
+      "Incomplete Data (version 0.4-15)\n",
+      "\n",
+      "Loading required package: tidyverse\n",
+      "── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──\n",
+      "✔ ggplot2 3.4.0     ✔ purrr   1.0.1\n",
+      "✔ tibble  3.1.8     ✔ dplyr   1.1.0\n",
+      "✔ tidyr   1.3.0     ✔ stringr 1.5.0\n",
+      "✔ readr   2.1.3     ✔ forcats 1.0.0\n",
+      "── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──\n",
+      "✖ dplyr::filter() masks stats::filter()\n",
+      "✖ dplyr::lag()    masks stats::lag()\n",
+      "Loading required package: BiocManager\n",
+      "Bioconductor version '3.16' is out-of-date; the current release version '3.18'\n",
+      "  is available with R version '4.3'; see https://bioconductor.org/install\n",
+      "Loading required package: devtools\n",
+      "Loading required package: usethis\n",
+      "\n",
+      "Attaching package: ‘devtools’\n",
+      "\n",
+      "The following object is masked from ‘package:BiocManager’:\n",
+      "\n",
+      "    install\n",
+      "\n",
+      "Loading required package: limma\n",
+      "Loading required package: vsn\n",
+      "Loading required package: Biobase\n",
+      "Loading required package: BiocGenerics\n",
+      "\n",
+      "Attaching package: ‘BiocGenerics’\n",
+      "\n",
+      "The following object is masked from ‘package:limma’:\n",
+      "\n",
+      "    plotMA\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    combine, intersect, setdiff, union\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    IQR, mad, sd, var, xtabs\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    anyDuplicated, aperm, append, as.data.frame, basename, cbind,\n",
+      "    colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,\n",
+      "    get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,\n",
+      "    match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,\n",
+      "    Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,\n",
+      "    table, tapply, union, unique, unsplit, which.max, which.min\n",
+      "\n",
+      "Welcome to Bioconductor\n",
+      "\n",
+      "    Vignettes contain introductory material; view with\n",
+      "    'browseVignettes()'. To cite Bioconductor, see\n",
+      "    'citation(\"Biobase\")', and for packages 'citation(\"pkgname\")'.\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Biobase’\n",
+      "\n",
+      "The following object is masked from ‘package:robustbase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "Loading required package: RankProd\n",
+      "Loading required package: Rmpfr\n",
+      "Loading required package: gmp\n",
+      "\n",
+      "Attaching package: ‘gmp’\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    %*%, apply, crossprod, matrix, tcrossprod\n",
+      "\n",
+      "C code of R package 'Rmpfr': GMP using 64 bits per limb\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Rmpfr’\n",
+      "\n",
+      "The following object is masked from ‘package:gmp’:\n",
+      "\n",
+      "    outer\n",
+      "\n",
+      "The following objects are masked from ‘package:BiocGenerics’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    dbinom, dgamma, dnbinom, dnorm, dpois, dt, pnorm\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "Loading required package: pcaMethods\n",
+      "\n",
+      "Attaching package: ‘pcaMethods’\n",
+      "\n",
+      "The following object is masked from ‘package:stats’:\n",
+      "\n",
+      "    loadings\n",
+      "\n",
+      "Loading required package: impute\n",
+      "Loading required package: SummarizedExperiment\n",
+      "Loading required package: MatrixGenerics\n",
+      "Loading required package: matrixStats\n",
+      "\n",
+      "Attaching package: ‘matrixStats’\n",
+      "\n",
+      "The following objects are masked from ‘package:Biobase’:\n",
+      "\n",
+      "    anyMissing, rowMedians\n",
+      "\n",
+      "The following object is masked from ‘package:dplyr’:\n",
+      "\n",
+      "    count\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘MatrixGenerics’\n",
+      "\n",
+      "The following objects are masked from ‘package:matrixStats’:\n",
+      "\n",
+      "    colAlls, colAnyNAs, colAnys, colAvgsPerRowSet, colCollapse,\n",
+      "    colCounts, colCummaxs, colCummins, colCumprods, colCumsums,\n",
+      "    colDiffs, colIQRDiffs, colIQRs, colLogSumExps, colMadDiffs,\n",
+      "    colMads, colMaxs, colMeans2, colMedians, colMins, colOrderStats,\n",
+      "    colProds, colQuantiles, colRanges, colRanks, colSdDiffs, colSds,\n",
+      "    colSums2, colTabulates, colVarDiffs, colVars, colWeightedMads,\n",
+      "    colWeightedMeans, colWeightedMedians, colWeightedSds,\n",
+      "    colWeightedVars, rowAlls, rowAnyNAs, rowAnys, rowAvgsPerColSet,\n",
+      "    rowCollapse, rowCounts, rowCummaxs, rowCummins, rowCumprods,\n",
+      "    rowCumsums, rowDiffs, rowIQRDiffs, rowIQRs, rowLogSumExps,\n",
+      "    rowMadDiffs, rowMads, rowMaxs, rowMeans2, rowMedians, rowMins,\n",
+      "    rowOrderStats, rowProds, rowQuantiles, rowRanges, rowRanks,\n",
+      "    rowSdDiffs, rowSds, rowSums2, rowTabulates, rowVarDiffs, rowVars,\n",
+      "    rowWeightedMads, rowWeightedMeans, rowWeightedMedians,\n",
+      "    rowWeightedSds, rowWeightedVars\n",
+      "\n",
+      "The following object is masked from ‘package:Biobase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "Loading required package: GenomicRanges\n",
+      "Loading required package: stats4\n",
+      "Loading required package: S4Vectors\n",
+      "\n",
+      "Attaching package: ‘S4Vectors’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    first, rename\n",
+      "\n",
+      "The following object is masked from ‘package:tidyr’:\n",
+      "\n",
+      "    expand\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    expand.grid, I, unname\n",
+      "\n",
+      "Loading required package: IRanges\n",
+      "\n",
+      "Attaching package: ‘IRanges’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    collapse, desc, slice\n",
+      "\n",
+      "The following object is masked from ‘package:purrr’:\n",
+      "\n",
+      "    reduce\n",
+      "\n",
+      "Loading required package: GenomeInfoDb\n",
+      "Loading required package: imputation\n",
+      "Loading required package: DMwR\n",
+      "Loading required package: lattice\n",
+      "Loading required package: grid\n",
+      "Registered S3 method overwritten by 'quantmod':\n",
+      "  method            from\n",
+      "  as.zoo.data.frame zoo \n",
+      "Loading required package: DIMAR\n",
+      "Loading required package: rrcovNA\n",
+      "Loading required package: rrcov\n",
+      "Loading required package: robustbase\n",
+      "Scalable Robust Estimators with High Breakdown Point (version 1.7-2)\n",
+      "\n",
+      "Scalable Robust Estimators with High Breakdown Point for\n",
+      "Incomplete Data (version 0.4-15)\n",
+      "\n",
+      "Loading required package: tidyverse\n",
+      "── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──\n",
+      "✔ ggplot2 3.4.0     ✔ purrr   1.0.1\n",
+      "✔ tibble  3.1.8     ✔ dplyr   1.1.0\n",
+      "✔ tidyr   1.3.0     ✔ stringr 1.5.0\n",
+      "✔ readr   2.1.3     ✔ forcats 1.0.0\n",
+      "── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──\n",
+      "✖ dplyr::filter() masks stats::filter()\n",
+      "✖ dplyr::lag()    masks stats::lag()\n",
+      "Loading required package: BiocManager\n",
+      "Bioconductor version '3.16' is out-of-date; the current release version '3.18'\n",
+      "  is available with R version '4.3'; see https://bioconductor.org/install\n",
+      "Loading required package: devtools\n",
+      "Loading required package: usethis\n",
+      "\n",
+      "Attaching package: ‘devtools’\n",
+      "\n",
+      "The following object is masked from ‘package:BiocManager’:\n",
+      "\n",
+      "    install\n",
+      "\n",
+      "Loading required package: limma\n",
+      "Loading required package: vsn\n",
+      "Loading required package: Biobase\n",
+      "Loading required package: BiocGenerics\n",
+      "\n",
+      "Attaching package: ‘BiocGenerics’\n",
+      "\n",
+      "The following object is masked from ‘package:limma’:\n",
+      "\n",
+      "    plotMA\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    combine, intersect, setdiff, union\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    IQR, mad, sd, var, xtabs\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    anyDuplicated, aperm, append, as.data.frame, basename, cbind,\n",
+      "    colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,\n",
+      "    get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,\n",
+      "    match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,\n",
+      "    Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,\n",
+      "    table, tapply, union, unique, unsplit, which.max, which.min\n",
+      "\n",
+      "Welcome to Bioconductor\n",
+      "\n",
+      "    Vignettes contain introductory material; view with\n",
+      "    'browseVignettes()'. To cite Bioconductor, see\n",
+      "    'citation(\"Biobase\")', and for packages 'citation(\"pkgname\")'.\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Biobase’\n",
+      "\n",
+      "The following object is masked from ‘package:robustbase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "Loading required package: RankProd\n",
+      "Loading required package: Rmpfr\n",
+      "Loading required package: gmp\n",
+      "\n",
+      "Attaching package: ‘gmp’\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    %*%, apply, crossprod, matrix, tcrossprod\n",
+      "\n",
+      "C code of R package 'Rmpfr': GMP using 64 bits per limb\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Rmpfr’\n",
+      "\n",
+      "The following object is masked from ‘package:gmp’:\n",
+      "\n",
+      "    outer\n",
+      "\n",
+      "The following objects are masked from ‘package:BiocGenerics’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    dbinom, dgamma, dnbinom, dnorm, dpois, dt, pnorm\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "Loading required package: pcaMethods\n",
+      "\n",
+      "Attaching package: ‘pcaMethods’\n",
+      "\n",
+      "The following object is masked from ‘package:stats’:\n",
+      "\n",
+      "    loadings\n",
+      "\n",
+      "Loading required package: impute\n",
+      "Loading required package: SummarizedExperiment\n",
+      "Loading required package: MatrixGenerics\n",
+      "Loading required package: matrixStats\n",
+      "\n",
+      "Attaching package: ‘matrixStats’\n",
+      "\n",
+      "The following objects are masked from ‘package:Biobase’:\n",
+      "\n",
+      "    anyMissing, rowMedians\n",
+      "\n",
+      "The following object is masked from ‘package:dplyr’:\n",
+      "\n",
+      "    count\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘MatrixGenerics’\n",
+      "\n",
+      "The following objects are masked from ‘package:matrixStats’:\n",
+      "\n",
+      "    colAlls, colAnyNAs, colAnys, colAvgsPerRowSet, colCollapse,\n",
+      "    colCounts, colCummaxs, colCummins, colCumprods, colCumsums,\n",
+      "    colDiffs, colIQRDiffs, colIQRs, colLogSumExps, colMadDiffs,\n",
+      "    colMads, colMaxs, colMeans2, colMedians, colMins, colOrderStats,\n",
+      "    colProds, colQuantiles, colRanges, colRanks, colSdDiffs, colSds,\n",
+      "    colSums2, colTabulates, colVarDiffs, colVars, colWeightedMads,\n",
+      "    colWeightedMeans, colWeightedMedians, colWeightedSds,\n",
+      "    colWeightedVars, rowAlls, rowAnyNAs, rowAnys, rowAvgsPerColSet,\n",
+      "    rowCollapse, rowCounts, rowCummaxs, rowCummins, rowCumprods,\n",
+      "    rowCumsums, rowDiffs, rowIQRDiffs, rowIQRs, rowLogSumExps,\n",
+      "    rowMadDiffs, rowMads, rowMaxs, rowMeans2, rowMedians, rowMins,\n",
+      "    rowOrderStats, rowProds, rowQuantiles, rowRanges, rowRanks,\n",
+      "    rowSdDiffs, rowSds, rowSums2, rowTabulates, rowVarDiffs, rowVars,\n",
+      "    rowWeightedMads, rowWeightedMeans, rowWeightedMedians,\n",
+      "    rowWeightedSds, rowWeightedVars\n",
+      "\n",
+      "The following object is masked from ‘package:Biobase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "Loading required package: GenomicRanges\n",
+      "Loading required package: stats4\n",
+      "Loading required package: S4Vectors\n",
+      "\n",
+      "Attaching package: ‘S4Vectors’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    first, rename\n",
+      "\n",
+      "The following object is masked from ‘package:tidyr’:\n",
+      "\n",
+      "    expand\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    expand.grid, I, unname\n",
+      "\n",
+      "Loading required package: IRanges\n",
+      "\n",
+      "Attaching package: ‘IRanges’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    collapse, desc, slice\n",
+      "\n",
+      "The following object is masked from ‘package:purrr’:\n",
+      "\n",
+      "    reduce\n",
+      "\n",
+      "Loading required package: GenomeInfoDb\n",
+      "Loading required package: imputation\n",
+      "Loading required package: DMwR\n",
+      "Loading required package: lattice\n",
+      "Loading required package: grid\n",
+      "Registered S3 method overwritten by 'quantmod':\n",
+      "  method            from\n",
+      "  as.zoo.data.frame zoo \n",
+      "Loading required package: DIMAR\n",
+      "Loading required package: rrcovNA\n",
+      "Loading required package: rrcov\n",
+      "Loading required package: robustbase\n",
+      "Scalable Robust Estimators with High Breakdown Point (version 1.7-2)\n",
+      "\n",
+      "Scalable Robust Estimators with High Breakdown Point for\n",
+      "Incomplete Data (version 0.4-15)\n",
+      "\n",
+      "Loading required package: tidyverse\n",
+      "── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──\n",
+      "✔ ggplot2 3.4.0     ✔ purrr   1.0.1\n",
+      "✔ tibble  3.1.8     ✔ dplyr   1.1.0\n",
+      "✔ tidyr   1.3.0     ✔ stringr 1.5.0\n",
+      "✔ readr   2.1.3     ✔ forcats 1.0.0\n",
+      "── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──\n",
+      "✖ dplyr::filter() masks stats::filter()\n",
+      "✖ dplyr::lag()    masks stats::lag()\n",
+      "Loading required package: BiocManager\n",
+      "Bioconductor version '3.16' is out-of-date; the current release version '3.18'\n",
+      "  is available with R version '4.3'; see https://bioconductor.org/install\n",
+      "Loading required package: devtools\n",
+      "Loading required package: usethis\n",
+      "\n",
+      "Attaching package: ‘devtools’\n",
+      "\n",
+      "The following object is masked from ‘package:BiocManager’:\n",
+      "\n",
+      "    install\n",
+      "\n",
+      "Loading required package: limma\n",
+      "Loading required package: vsn\n",
+      "Loading required package: Biobase\n",
+      "Loading required package: BiocGenerics\n",
+      "\n",
+      "Attaching package: ‘BiocGenerics’\n",
+      "\n",
+      "The following object is masked from ‘package:limma’:\n",
+      "\n",
+      "    plotMA\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    combine, intersect, setdiff, union\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    IQR, mad, sd, var, xtabs\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    anyDuplicated, aperm, append, as.data.frame, basename, cbind,\n",
+      "    colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,\n",
+      "    get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,\n",
+      "    match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,\n",
+      "    Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,\n",
+      "    table, tapply, union, unique, unsplit, which.max, which.min\n",
+      "\n",
+      "Welcome to Bioconductor\n",
+      "\n",
+      "    Vignettes contain introductory material; view with\n",
+      "    'browseVignettes()'. To cite Bioconductor, see\n",
+      "    'citation(\"Biobase\")', and for packages 'citation(\"pkgname\")'.\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Biobase’\n",
+      "\n",
+      "The following object is masked from ‘package:robustbase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "Loading required package: RankProd\n",
+      "Loading required package: Rmpfr\n",
+      "Loading required package: gmp\n",
+      "\n",
+      "Attaching package: ‘gmp’\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    %*%, apply, crossprod, matrix, tcrossprod\n",
+      "\n",
+      "C code of R package 'Rmpfr': GMP using 64 bits per limb\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Rmpfr’\n",
+      "\n",
+      "The following object is masked from ‘package:gmp’:\n",
+      "\n",
+      "    outer\n",
+      "\n",
+      "The following objects are masked from ‘package:BiocGenerics’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    dbinom, dgamma, dnbinom, dnorm, dpois, dt, pnorm\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "Loading required package: pcaMethods\n",
+      "\n",
+      "Attaching package: ‘pcaMethods’\n",
+      "\n",
+      "The following object is masked from ‘package:stats’:\n",
+      "\n",
+      "    loadings\n",
+      "\n",
+      "Loading required package: impute\n",
+      "Loading required package: SummarizedExperiment\n",
+      "Loading required package: MatrixGenerics\n",
+      "Loading required package: matrixStats\n",
+      "\n",
+      "Attaching package: ‘matrixStats’\n",
+      "\n",
+      "The following objects are masked from ‘package:Biobase’:\n",
+      "\n",
+      "    anyMissing, rowMedians\n",
+      "\n",
+      "The following object is masked from ‘package:dplyr’:\n",
+      "\n",
+      "    count\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘MatrixGenerics’\n",
+      "\n",
+      "The following objects are masked from ‘package:matrixStats’:\n",
+      "\n",
+      "    colAlls, colAnyNAs, colAnys, colAvgsPerRowSet, colCollapse,\n",
+      "    colCounts, colCummaxs, colCummins, colCumprods, colCumsums,\n",
+      "    colDiffs, colIQRDiffs, colIQRs, colLogSumExps, colMadDiffs,\n",
+      "    colMads, colMaxs, colMeans2, colMedians, colMins, colOrderStats,\n",
+      "    colProds, colQuantiles, colRanges, colRanks, colSdDiffs, colSds,\n",
+      "    colSums2, colTabulates, colVarDiffs, colVars, colWeightedMads,\n",
+      "    colWeightedMeans, colWeightedMedians, colWeightedSds,\n",
+      "    colWeightedVars, rowAlls, rowAnyNAs, rowAnys, rowAvgsPerColSet,\n",
+      "    rowCollapse, rowCounts, rowCummaxs, rowCummins, rowCumprods,\n",
+      "    rowCumsums, rowDiffs, rowIQRDiffs, rowIQRs, rowLogSumExps,\n",
+      "    rowMadDiffs, rowMads, rowMaxs, rowMeans2, rowMedians, rowMins,\n",
+      "    rowOrderStats, rowProds, rowQuantiles, rowRanges, rowRanks,\n",
+      "    rowSdDiffs, rowSds, rowSums2, rowTabulates, rowVarDiffs, rowVars,\n",
+      "    rowWeightedMads, rowWeightedMeans, rowWeightedMedians,\n",
+      "    rowWeightedSds, rowWeightedVars\n",
+      "\n",
+      "The following object is masked from ‘package:Biobase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "Loading required package: GenomicRanges\n",
+      "Loading required package: stats4\n",
+      "Loading required package: S4Vectors\n",
+      "\n",
+      "Attaching package: ‘S4Vectors’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    first, rename\n",
+      "\n",
+      "The following object is masked from ‘package:tidyr’:\n",
+      "\n",
+      "    expand\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    expand.grid, I, unname\n",
+      "\n",
+      "Loading required package: IRanges\n",
+      "\n",
+      "Attaching package: ‘IRanges’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    collapse, desc, slice\n",
+      "\n",
+      "The following object is masked from ‘package:purrr’:\n",
+      "\n",
+      "    reduce\n",
+      "\n",
+      "Loading required package: GenomeInfoDb\n",
+      "Loading required package: imputation\n",
+      "Loading required package: DMwR\n",
+      "Loading required package: lattice\n",
+      "Loading required package: grid\n",
+      "Registered S3 method overwritten by 'quantmod':\n",
+      "  method            from\n",
+      "  as.zoo.data.frame zoo \n",
+      "Loading required package: DIMAR\n",
+      "Loading required package: rrcovNA\n",
+      "Loading required package: rrcov\n",
+      "Loading required package: robustbase\n",
+      "Scalable Robust Estimators with High Breakdown Point (version 1.7-2)\n",
+      "\n",
+      "Scalable Robust Estimators with High Breakdown Point for\n",
+      "Incomplete Data (version 0.4-15)\n",
+      "\n",
+      "Loading required package: tidyverse\n",
+      "── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──\n",
+      "✔ ggplot2 3.4.0     ✔ purrr   1.0.1\n",
+      "✔ tibble  3.1.8     ✔ dplyr   1.1.0\n",
+      "✔ tidyr   1.3.0     ✔ stringr 1.5.0\n",
+      "✔ readr   2.1.3     ✔ forcats 1.0.0\n",
+      "── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──\n",
+      "✖ dplyr::filter() masks stats::filter()\n",
+      "✖ dplyr::lag()    masks stats::lag()\n",
+      "Loading required package: BiocManager\n",
+      "Bioconductor version '3.16' is out-of-date; the current release version '3.18'\n",
+      "  is available with R version '4.3'; see https://bioconductor.org/install\n",
+      "Loading required package: devtools\n",
+      "Loading required package: usethis\n",
+      "\n",
+      "Attaching package: ‘devtools’\n",
+      "\n",
+      "The following object is masked from ‘package:BiocManager’:\n",
+      "\n",
+      "    install\n",
+      "\n",
+      "Loading required package: limma\n",
+      "Loading required package: vsn\n",
+      "Loading required package: Biobase\n",
+      "Loading required package: BiocGenerics\n",
+      "\n",
+      "Attaching package: ‘BiocGenerics’\n",
+      "\n",
+      "The following object is masked from ‘package:limma’:\n",
+      "\n",
+      "    plotMA\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    combine, intersect, setdiff, union\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    IQR, mad, sd, var, xtabs\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    anyDuplicated, aperm, append, as.data.frame, basename, cbind,\n",
+      "    colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,\n",
+      "    get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,\n",
+      "    match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,\n",
+      "    Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,\n",
+      "    table, tapply, union, unique, unsplit, which.max, which.min\n",
+      "\n",
+      "Welcome to Bioconductor\n",
+      "\n",
+      "    Vignettes contain introductory material; view with\n",
+      "    'browseVignettes()'. To cite Bioconductor, see\n",
+      "    'citation(\"Biobase\")', and for packages 'citation(\"pkgname\")'.\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Biobase’\n",
+      "\n",
+      "The following object is masked from ‘package:robustbase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "Loading required package: RankProd\n",
+      "Loading required package: Rmpfr\n",
+      "Loading required package: gmp\n",
+      "\n",
+      "Attaching package: ‘gmp’\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    %*%, apply, crossprod, matrix, tcrossprod\n",
+      "\n",
+      "C code of R package 'Rmpfr': GMP using 64 bits per limb\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Rmpfr’\n",
+      "\n",
+      "The following object is masked from ‘package:gmp’:\n",
+      "\n",
+      "    outer\n",
+      "\n",
+      "The following objects are masked from ‘package:BiocGenerics’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    dbinom, dgamma, dnbinom, dnorm, dpois, dt, pnorm\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "Loading required package: pcaMethods\n",
+      "\n",
+      "Attaching package: ‘pcaMethods’\n",
+      "\n",
+      "The following object is masked from ‘package:stats’:\n",
+      "\n",
+      "    loadings\n",
+      "\n",
+      "Loading required package: impute\n",
+      "Loading required package: SummarizedExperiment\n",
+      "Loading required package: MatrixGenerics\n",
+      "Loading required package: matrixStats\n",
+      "\n",
+      "Attaching package: ‘matrixStats’\n",
+      "\n",
+      "The following objects are masked from ‘package:Biobase’:\n",
+      "\n",
+      "    anyMissing, rowMedians\n",
+      "\n",
+      "The following object is masked from ‘package:dplyr’:\n",
+      "\n",
+      "    count\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘MatrixGenerics’\n",
+      "\n",
+      "The following objects are masked from ‘package:matrixStats’:\n",
+      "\n",
+      "    colAlls, colAnyNAs, colAnys, colAvgsPerRowSet, colCollapse,\n",
+      "    colCounts, colCummaxs, colCummins, colCumprods, colCumsums,\n",
+      "    colDiffs, colIQRDiffs, colIQRs, colLogSumExps, colMadDiffs,\n",
+      "    colMads, colMaxs, colMeans2, colMedians, colMins, colOrderStats,\n",
+      "    colProds, colQuantiles, colRanges, colRanks, colSdDiffs, colSds,\n",
+      "    colSums2, colTabulates, colVarDiffs, colVars, colWeightedMads,\n",
+      "    colWeightedMeans, colWeightedMedians, colWeightedSds,\n",
+      "    colWeightedVars, rowAlls, rowAnyNAs, rowAnys, rowAvgsPerColSet,\n",
+      "    rowCollapse, rowCounts, rowCummaxs, rowCummins, rowCumprods,\n",
+      "    rowCumsums, rowDiffs, rowIQRDiffs, rowIQRs, rowLogSumExps,\n",
+      "    rowMadDiffs, rowMads, rowMaxs, rowMeans2, rowMedians, rowMins,\n",
+      "    rowOrderStats, rowProds, rowQuantiles, rowRanges, rowRanks,\n",
+      "    rowSdDiffs, rowSds, rowSums2, rowTabulates, rowVarDiffs, rowVars,\n",
+      "    rowWeightedMads, rowWeightedMeans, rowWeightedMedians,\n",
+      "    rowWeightedSds, rowWeightedVars\n",
+      "\n",
+      "The following object is masked from ‘package:Biobase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "Loading required package: GenomicRanges\n",
+      "Loading required package: stats4\n",
+      "Loading required package: S4Vectors\n",
+      "\n",
+      "Attaching package: ‘S4Vectors’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    first, rename\n",
+      "\n",
+      "The following object is masked from ‘package:tidyr’:\n",
+      "\n",
+      "    expand\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    expand.grid, I, unname\n",
+      "\n",
+      "Loading required package: IRanges\n",
+      "\n",
+      "Attaching package: ‘IRanges’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    collapse, desc, slice\n",
+      "\n",
+      "The following object is masked from ‘package:purrr’:\n",
+      "\n",
+      "    reduce\n",
+      "\n",
+      "Loading required package: GenomeInfoDb\n",
+      "Loading required package: imputation\n",
+      "Loading required package: DMwR\n",
+      "Loading required package: lattice\n",
+      "Loading required package: grid\n",
+      "Registered S3 method overwritten by 'quantmod':\n",
+      "  method            from\n",
+      "  as.zoo.data.frame zoo \n",
+      "Loading required package: DIMAR\n",
+      "Loading required package: rrcovNA\n",
+      "Loading required package: rrcov\n",
+      "Loading required package: robustbase\n",
+      "Scalable Robust Estimators with High Breakdown Point (version 1.7-2)\n",
+      "\n",
+      "Scalable Robust Estimators with High Breakdown Point for\n",
+      "Incomplete Data (version 0.4-15)\n",
+      "\n",
+      "Loading required package: tidyverse\n",
+      "── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──\n",
+      "✔ ggplot2 3.4.0     ✔ purrr   1.0.1\n",
+      "✔ tibble  3.1.8     ✔ dplyr   1.1.0\n",
+      "✔ tidyr   1.3.0     ✔ stringr 1.5.0\n",
+      "✔ readr   2.1.3     ✔ forcats 1.0.0\n",
+      "── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──\n",
+      "✖ dplyr::filter() masks stats::filter()\n",
+      "✖ dplyr::lag()    masks stats::lag()\n",
+      "Loading required package: BiocManager\n",
+      "Bioconductor version '3.16' is out-of-date; the current release version '3.18'\n",
+      "  is available with R version '4.3'; see https://bioconductor.org/install\n",
+      "Loading required package: devtools\n",
+      "Loading required package: usethis\n",
+      "\n",
+      "Attaching package: ‘devtools’\n",
+      "\n",
+      "The following object is masked from ‘package:BiocManager’:\n",
+      "\n",
+      "    install\n",
+      "\n",
+      "Loading required package: limma\n",
+      "Loading required package: vsn\n",
+      "Loading required package: Biobase\n",
+      "Loading required package: BiocGenerics\n",
+      "\n",
+      "Attaching package: ‘BiocGenerics’\n",
+      "\n",
+      "The following object is masked from ‘package:limma’:\n",
+      "\n",
+      "    plotMA\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    combine, intersect, setdiff, union\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    IQR, mad, sd, var, xtabs\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    anyDuplicated, aperm, append, as.data.frame, basename, cbind,\n",
+      "    colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,\n",
+      "    get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,\n",
+      "    match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,\n",
+      "    Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,\n",
+      "    table, tapply, union, unique, unsplit, which.max, which.min\n",
+      "\n",
+      "Welcome to Bioconductor\n",
+      "\n",
+      "    Vignettes contain introductory material; view with\n",
+      "    'browseVignettes()'. To cite Bioconductor, see\n",
+      "    'citation(\"Biobase\")', and for packages 'citation(\"pkgname\")'.\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Biobase’\n",
+      "\n",
+      "The following object is masked from ‘package:robustbase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "Loading required package: RankProd\n",
+      "Loading required package: Rmpfr\n",
+      "Loading required package: gmp\n",
+      "\n",
+      "Attaching package: ‘gmp’\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    %*%, apply, crossprod, matrix, tcrossprod\n",
+      "\n",
+      "C code of R package 'Rmpfr': GMP using 64 bits per limb\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Rmpfr’\n",
+      "\n",
+      "The following object is masked from ‘package:gmp’:\n",
+      "\n",
+      "    outer\n",
+      "\n",
+      "The following objects are masked from ‘package:BiocGenerics’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    dbinom, dgamma, dnbinom, dnorm, dpois, dt, pnorm\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "Loading required package: pcaMethods\n",
+      "\n",
+      "Attaching package: ‘pcaMethods’\n",
+      "\n",
+      "The following object is masked from ‘package:stats’:\n",
+      "\n",
+      "    loadings\n",
+      "\n",
+      "Loading required package: impute\n",
+      "Loading required package: SummarizedExperiment\n",
+      "Loading required package: MatrixGenerics\n",
+      "Loading required package: matrixStats\n",
+      "\n",
+      "Attaching package: ‘matrixStats’\n",
+      "\n",
+      "The following objects are masked from ‘package:Biobase’:\n",
+      "\n",
+      "    anyMissing, rowMedians\n",
+      "\n",
+      "The following object is masked from ‘package:dplyr’:\n",
+      "\n",
+      "    count\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘MatrixGenerics’\n",
+      "\n",
+      "The following objects are masked from ‘package:matrixStats’:\n",
+      "\n",
+      "    colAlls, colAnyNAs, colAnys, colAvgsPerRowSet, colCollapse,\n",
+      "    colCounts, colCummaxs, colCummins, colCumprods, colCumsums,\n",
+      "    colDiffs, colIQRDiffs, colIQRs, colLogSumExps, colMadDiffs,\n",
+      "    colMads, colMaxs, colMeans2, colMedians, colMins, colOrderStats,\n",
+      "    colProds, colQuantiles, colRanges, colRanks, colSdDiffs, colSds,\n",
+      "    colSums2, colTabulates, colVarDiffs, colVars, colWeightedMads,\n",
+      "    colWeightedMeans, colWeightedMedians, colWeightedSds,\n",
+      "    colWeightedVars, rowAlls, rowAnyNAs, rowAnys, rowAvgsPerColSet,\n",
+      "    rowCollapse, rowCounts, rowCummaxs, rowCummins, rowCumprods,\n",
+      "    rowCumsums, rowDiffs, rowIQRDiffs, rowIQRs, rowLogSumExps,\n",
+      "    rowMadDiffs, rowMads, rowMaxs, rowMeans2, rowMedians, rowMins,\n",
+      "    rowOrderStats, rowProds, rowQuantiles, rowRanges, rowRanks,\n",
+      "    rowSdDiffs, rowSds, rowSums2, rowTabulates, rowVarDiffs, rowVars,\n",
+      "    rowWeightedMads, rowWeightedMeans, rowWeightedMedians,\n",
+      "    rowWeightedSds, rowWeightedVars\n",
+      "\n",
+      "The following object is masked from ‘package:Biobase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "Loading required package: GenomicRanges\n",
+      "Loading required package: stats4\n",
+      "Loading required package: S4Vectors\n",
+      "\n",
+      "Attaching package: ‘S4Vectors’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    first, rename\n",
+      "\n",
+      "The following object is masked from ‘package:tidyr’:\n",
+      "\n",
+      "    expand\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    expand.grid, I, unname\n",
+      "\n",
+      "Loading required package: IRanges\n",
+      "\n",
+      "Attaching package: ‘IRanges’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    collapse, desc, slice\n",
+      "\n",
+      "The following object is masked from ‘package:purrr’:\n",
+      "\n",
+      "    reduce\n",
+      "\n",
+      "Loading required package: GenomeInfoDb\n",
+      "Loading required package: imputation\n",
+      "Loading required package: DMwR\n",
+      "Loading required package: lattice\n",
+      "Loading required package: grid\n",
+      "Registered S3 method overwritten by 'quantmod':\n",
+      "  method            from\n",
+      "  as.zoo.data.frame zoo \n",
+      "Loading required package: DIMAR\n",
+      "Loading required package: rrcovNA\n",
+      "Loading required package: rrcov\n",
+      "Loading required package: robustbase\n",
+      "Scalable Robust Estimators with High Breakdown Point (version 1.7-2)\n",
+      "\n",
+      "Scalable Robust Estimators with High Breakdown Point for\n",
+      "Incomplete Data (version 0.4-15)\n",
+      "\n",
+      "Loading required package: tidyverse\n",
+      "── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──\n",
+      "✔ ggplot2 3.4.0     ✔ purrr   1.0.1\n",
+      "✔ tibble  3.1.8     ✔ dplyr   1.1.0\n",
+      "✔ tidyr   1.3.0     ✔ stringr 1.5.0\n",
+      "✔ readr   2.1.3     ✔ forcats 1.0.0\n",
+      "── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──\n",
+      "✖ dplyr::filter() masks stats::filter()\n",
+      "✖ dplyr::lag()    masks stats::lag()\n",
+      "Loading required package: BiocManager\n",
+      "Bioconductor version '3.16' is out-of-date; the current release version '3.18'\n",
+      "  is available with R version '4.3'; see https://bioconductor.org/install\n",
+      "Loading required package: devtools\n",
+      "Loading required package: usethis\n",
+      "\n",
+      "Attaching package: ‘devtools’\n",
+      "\n",
+      "The following object is masked from ‘package:BiocManager’:\n",
+      "\n",
+      "    install\n",
+      "\n",
+      "Loading required package: limma\n",
+      "Loading required package: vsn\n",
+      "Loading required package: Biobase\n",
+      "Loading required package: BiocGenerics\n",
+      "\n",
+      "Attaching package: ‘BiocGenerics’\n",
+      "\n",
+      "The following object is masked from ‘package:limma’:\n",
+      "\n",
+      "    plotMA\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    combine, intersect, setdiff, union\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    IQR, mad, sd, var, xtabs\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    anyDuplicated, aperm, append, as.data.frame, basename, cbind,\n",
+      "    colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,\n",
+      "    get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,\n",
+      "    match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,\n",
+      "    Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,\n",
+      "    table, tapply, union, unique, unsplit, which.max, which.min\n",
+      "\n",
+      "Welcome to Bioconductor\n",
+      "\n",
+      "    Vignettes contain introductory material; view with\n",
+      "    'browseVignettes()'. To cite Bioconductor, see\n",
+      "    'citation(\"Biobase\")', and for packages 'citation(\"pkgname\")'.\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Biobase’\n",
+      "\n",
+      "The following object is masked from ‘package:robustbase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "Loading required package: RankProd\n",
+      "Loading required package: Rmpfr\n",
+      "Loading required package: gmp\n",
+      "\n",
+      "Attaching package: ‘gmp’\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    %*%, apply, crossprod, matrix, tcrossprod\n",
+      "\n",
+      "C code of R package 'Rmpfr': GMP using 64 bits per limb\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘Rmpfr’\n",
+      "\n",
+      "The following object is masked from ‘package:gmp’:\n",
+      "\n",
+      "    outer\n",
+      "\n",
+      "The following objects are masked from ‘package:BiocGenerics’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "The following objects are masked from ‘package:stats’:\n",
+      "\n",
+      "    dbinom, dgamma, dnbinom, dnorm, dpois, dt, pnorm\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    cbind, pmax, pmin, rbind\n",
+      "\n",
+      "Loading required package: pcaMethods\n",
+      "\n",
+      "Attaching package: ‘pcaMethods’\n",
+      "\n",
+      "The following object is masked from ‘package:stats’:\n",
+      "\n",
+      "    loadings\n",
+      "\n",
+      "Loading required package: impute\n",
+      "Loading required package: SummarizedExperiment\n",
+      "Loading required package: MatrixGenerics\n",
+      "Loading required package: matrixStats\n",
+      "\n",
+      "Attaching package: ‘matrixStats’\n",
+      "\n",
+      "The following objects are masked from ‘package:Biobase’:\n",
+      "\n",
+      "    anyMissing, rowMedians\n",
+      "\n",
+      "The following object is masked from ‘package:dplyr’:\n",
+      "\n",
+      "    count\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "\n",
+      "Attaching package: ‘MatrixGenerics’\n",
+      "\n",
+      "The following objects are masked from ‘package:matrixStats’:\n",
+      "\n",
+      "    colAlls, colAnyNAs, colAnys, colAvgsPerRowSet, colCollapse,\n",
+      "    colCounts, colCummaxs, colCummins, colCumprods, colCumsums,\n",
+      "    colDiffs, colIQRDiffs, colIQRs, colLogSumExps, colMadDiffs,\n",
+      "    colMads, colMaxs, colMeans2, colMedians, colMins, colOrderStats,\n",
+      "    colProds, colQuantiles, colRanges, colRanks, colSdDiffs, colSds,\n",
+      "    colSums2, colTabulates, colVarDiffs, colVars, colWeightedMads,\n",
+      "    colWeightedMeans, colWeightedMedians, colWeightedSds,\n",
+      "    colWeightedVars, rowAlls, rowAnyNAs, rowAnys, rowAvgsPerColSet,\n",
+      "    rowCollapse, rowCounts, rowCummaxs, rowCummins, rowCumprods,\n",
+      "    rowCumsums, rowDiffs, rowIQRDiffs, rowIQRs, rowLogSumExps,\n",
+      "    rowMadDiffs, rowMads, rowMaxs, rowMeans2, rowMedians, rowMins,\n",
+      "    rowOrderStats, rowProds, rowQuantiles, rowRanges, rowRanks,\n",
+      "    rowSdDiffs, rowSds, rowSums2, rowTabulates, rowVarDiffs, rowVars,\n",
+      "    rowWeightedMads, rowWeightedMeans, rowWeightedMedians,\n",
+      "    rowWeightedSds, rowWeightedVars\n",
+      "\n",
+      "The following object is masked from ‘package:Biobase’:\n",
+      "\n",
+      "    rowMedians\n",
+      "\n",
+      "The following objects are masked from ‘package:robustbase’:\n",
+      "\n",
+      "    colMedians, rowMedians\n",
+      "\n",
+      "Loading required package: GenomicRanges\n",
+      "Loading required package: stats4\n",
+      "Loading required package: S4Vectors\n",
+      "\n",
+      "Attaching package: ‘S4Vectors’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    first, rename\n",
+      "\n",
+      "The following object is masked from ‘package:tidyr’:\n",
+      "\n",
+      "    expand\n",
+      "\n",
+      "The following objects are masked from ‘package:base’:\n",
+      "\n",
+      "    expand.grid, I, unname\n",
+      "\n",
+      "Loading required package: IRanges\n",
+      "\n",
+      "Attaching package: ‘IRanges’\n",
+      "\n",
+      "The following objects are masked from ‘package:dplyr’:\n",
+      "\n",
+      "    collapse, desc, slice\n",
+      "\n",
+      "The following object is masked from ‘package:purrr’:\n",
+      "\n",
+      "    reduce\n",
+      "\n",
+      "Loading required package: GenomeInfoDb\n",
+      "Loading required package: imputation\n",
+      "Loading required package: DMwR\n",
+      "Loading required package: lattice\n",
+      "Loading required package: grid\n",
+      "Registered S3 method overwritten by 'quantmod':\n",
+      "  method            from\n",
+      "  as.zoo.data.frame zoo \n",
+      "Loading required package: DIMAR\n"
+     ]
+    }
+   ],
+   "source": [
+    "import re\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import seaborn as sns\n",
+    "from autoprot_dev import analysis as ana\n",
+    "from autoprot_dev import preprocessing as pp\n",
+    "from autoprot_dev import visualization as vis"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "21051b74-3990-4fe6-840e-dddadb346fe0",
+   "metadata": {},
+   "source": [
+    "## Import and cleaning of data\n",
+    "\n",
+    "The MaxQuant results files are parsed and reverse as well as potential contaminant entries are removed.\n",
+    "The additional column \"Gene names first\" that is eventually added, serves for the annotatin of the final volcano plot."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "310313ba-81e8-467a-b732-98e4614b011d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "12461 rows before filter operation.\n",
+      "12461 rows after filter operation.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# parse the results file\n",
+    "pg = pp.read_csv(\"../MitoCop_main_search_proteinGroups.txt\")\n",
+    "# remove reverse and potential contaminant entries\n",
+    "pg = pp.cleaning(pg, file=\"proteinGroups.txt\")\n",
+    "# generate column for volcano plot annotation\n",
+    "pg[\"Gene names first\"] = pg[\"Gene names\"].str.split(\";\").str[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "02c567e9-ac84-4fbf-8adb-4058104157f0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Ratio H/L TOMM40KD_1',\n",
+       " 'Ratio H/L TOMM40KD_2',\n",
+       " 'Ratio H/L TOMM40KD_3',\n",
+       " 'Ratio H/L TOMM40KD_4']"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# select the ratio columns from the proteinGroups dataframe\n",
+    "ratio_cols = pg.filter(regex=\"Ratio H/L TOMM40\").columns.tolist()\n",
+    "ratio_cols"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "33825857-1221-42ae-b8d2-5cce879b077e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "12461 rows before filter operation.\n",
+      "6693 rows after filter operation.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# filter for at least 2 valid values across 4 replicates\n",
+    "pg = pp.filter_vv(pg, [ratio_cols], n=2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "1aef0dd6-f3d4-4fe2-b4ce-fbb7ffa92c48",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# log transform the ratio columns.\n",
+    "# the invert kwarg indicates which replicates are label switches (i.e. must be multiplied with -1 to get the correct ratio)\n",
+    "pg, log_ratio_cols = pp.log(pg, ratio_cols, invert=(1, 1, -1, -1), return_cols=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6668bb41-662d-48d4-a906-a54e341af96b",
+   "metadata": {},
+   "source": [
+    "As a control for the correct inversion of ratio columns, we plot the ratios of all proteins and highlight the knocked-down protein TOMM40 and its close interactor TIMM21.\n",
+    "The log ratio of these two proteins should be negative if we correctly inverted the ratios."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "6f2114d3-0e84-4dfc-ace2-ecd6427ad5e5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1400x300 with 4 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# figure object for plotting\n",
+    "fig, axs = plt.subplots(nrows=1, ncols=4, figsize=(14, 3), sharey=True, sharex=True)\n",
+    "\n",
+    "# plot every replicate on a separate subplot\n",
+    "for ax, ratio in zip(axs, log_ratio_cols):\n",
+    "    pg.plot(\n",
+    "        kind=\"scatter\",\n",
+    "        ax=ax,\n",
+    "        x=ratio,\n",
+    "        y=\"Intensity L\",\n",
+    "        color=\"grey\",\n",
+    "        alpha=0.2,\n",
+    "        logy=True,\n",
+    "    )\n",
+    "\n",
+    "    pg[pg[\"Gene names\"] == \"TOMM40\"].plot(\n",
+    "        kind=\"scatter\", ax=ax, x=ratio, y=\"Intensity L\", color=\"red\", logy=True\n",
+    "    )\n",
+    "\n",
+    "    pg[pg[\"Gene names\"].str.contains(\"TIMM21\", na=False)].plot(\n",
+    "        kind=\"scatter\", ax=ax, x=ratio, y=\"Intensity L\", color=\"blue\", logy=True\n",
+    "    )\n",
+    "\n",
+    "    ymin, ymax = ax.get_ylim()\n",
+    "    ax.vlines(0, ymin, ymax)\n",
+    "\n",
+    "# nicer figures\n",
+    "plt.tight_layout()\n",
+    "# save the result\n",
+    "plt.savefig(\"importomics_fig1.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1433add8-710f-4994-bc7f-e613cefa17a3",
+   "metadata": {},
+   "source": [
+    "## Normalisation\n",
+    "### Median normalisation\n",
+    "\n",
+    "Differences in sample treatment and/or loading can shift the ratios between replicates in a systematic fashion. This will impair downstream statistical analysis that tests if the separate protein groups behave similarly in all replicates.\n",
+    "Normalisation corrects for these systematic effects by shifting the log ratio distributions.\n",
+    "To account for loading differences, we start with a median normalisation that shifts the medians of the repliates to the median of medians between replicates."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "154be1b7-80c5-4fc2-84d7-09e993572e58",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['log2_Ratio H/L TOMM40KD_1_mnorm',\n",
+       " 'log2_Ratio H/L TOMM40KD_2_mnorm',\n",
+       " 'log2_Ratio L/H TOMM40KD_3_mnorm',\n",
+       " 'log2_Ratio L/H TOMM40KD_4_mnorm']"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# median normalisation\n",
+    "mnorm_cols = []\n",
+    "for col in log_ratio_cols:\n",
+    "    # calculate the correction factor\n",
+    "    median_shift = pg[col].median() - pg[log_ratio_cols].median().median()\n",
+    "    # generate a new column name for the median-corrected ratios\n",
+    "    new_col = col + \"_mnorm\"\n",
+    "    mnorm_cols.append(new_col)\n",
+    "    # apply the correction and store in the new column\n",
+    "    pg[new_col] = pg[col] - median_shift\n",
+    "\n",
+    "mnorm_cols"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "778694c4-a426-42ab-9b44-ce17a540d761",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 700x300 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# visualisation of the effect of median normalisation\n",
+    "fig, axs = plt.subplots(nrows=1, ncols=2, figsize=(7, 3), sharex=True, sharey=True)\n",
+    "\n",
+    "# plot kernel density plots to show the different distributions\n",
+    "pg[log_ratio_cols].plot(kind=\"kde\", ax=axs[0])\n",
+    "pg[mnorm_cols].plot(kind=\"kde\", ax=axs[1])\n",
+    "\n",
+    "# shorten labels\n",
+    "for ax in axs:\n",
+    "    handles, labels = ax.get_legend_handles_labels()\n",
+    "    labels = [x.split(\" \")[-1] for x in labels]\n",
+    "\n",
+    "    ax.legend(handles, labels)\n",
+    "    ax.set_xlabel(\"Log2 ratio tomm40KD/mock\")\n",
+    "    ax.set_xlim((-5, 5))\n",
+    "\n",
+    "# nice figures and save result\n",
+    "plt.tight_layout()\n",
+    "plt.savefig(\"importomics_fig2.pdf\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9de8e4c5-0632-4883-9865-ed2adb78424d",
+   "metadata": {},
+   "source": [
+    "## Statistical analysis\n",
+    "For statistical analysis, conventional t-tests have long been used (and are still used today). The pre-processed, normalised ratio distribution should produce a similar result when analysed with a t-test. Here we want ot focus on more recent linear models for statistical analyiss.\n",
+    "### Linear models\n",
+    "In contrast to conventional t-tests, linear models take global patterns into account and can include information for example about label-switches.\n",
+    "To this end, we generate a custom design file which represents the variable space in which the experimental data points are projected and in which regression is performed.\n",
+    "If the design matrix contains a row of categorial 1s, this row is identical for every condition and hence corresponds to the intercept of the linear regression.\n",
+    "The presence of a label switch can be indicated by values of -1 vs. 1 in the design matrix. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "250927de-8b57-4006-9a77-fb6352282c0b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>treatment</th>\n",
+       "      <th>labelswitch</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1</td>\n",
+       "      <td>-1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1</td>\n",
+       "      <td>-1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   treatment  labelswitch\n",
+       "0          1            1\n",
+       "1          1            1\n",
+       "2          1           -1\n",
+       "3          1           -1"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "custom_design = pd.DataFrame({\"treatment\": [1, 1, 1, 1], \"labelswitch\": [1, 1, -1, -1]})\n",
+    "\n",
+    "custom_design.to_csv(\"custom_design.tsv\", sep=\"\\t\", index=False)\n",
+    "\n",
+    "custom_design"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "209636ec-aa09-4032-a2c0-07fb202eeed0",
+   "metadata": {},
+   "source": [
+    "Extracting the coefficient corresponding to each column in the design matrix (i.e. treatment of labelswitch) extracts the corresponding P values."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "8db91841-2c0d-4c2a-bdb9-57f63026ebd7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "LIMMA: Assuming a custom design test with:\n",
+      "Design specified at custom_design.tsv\n",
+      "Columns: log2_Ratio H/L TOMM40KD_1_mnorm\n",
+      "\tlog2_Ratio H/L TOMM40KD_2_mnorm\n",
+      "\tlog2_Ratio L/H TOMM40KD_3_mnorm\n",
+      "\tlog2_Ratio L/H TOMM40KD_4_mnorm\n",
+      "Using design matrix:\n",
+      "\n",
+      "|    |   treatment |   labelswitch |\n",
+      "|---:|------------:|--------------:|\n",
+      "|  0 |           1 |             1 |\n",
+      "|  1 |           1 |             1 |\n",
+      "|  2 |           1 |            -1 |\n",
+      "|  3 |           1 |            -1 |\n",
+      "LIMMA: Assuming a custom design test with:\n",
+      "Design specified at custom_design.tsv\n",
+      "Columns: log2_Ratio H/L TOMM40KD_1_mnorm\n",
+      "\tlog2_Ratio H/L TOMM40KD_2_mnorm\n",
+      "\tlog2_Ratio L/H TOMM40KD_3_mnorm\n",
+      "\tlog2_Ratio L/H TOMM40KD_4_mnorm\n",
+      "Using design matrix:\n",
+      "\n",
+      "|    |   treatment |   labelswitch |\n",
+      "|---:|------------:|--------------:|\n",
+      "|  0 |           1 |             1 |\n",
+      "|  1 |           1 |             1 |\n",
+      "|  2 |           1 |            -1 |\n",
+      "|  3 |           1 |            -1 |\n"
+     ]
+    }
+   ],
+   "source": [
+    "pg = ana.limma(\n",
+    "    pg, mnorm_cols, custom_design=\"custom_design.tsv\", coef=\"treatment\", cond=\"_limma\"\n",
+    ")\n",
+    "\n",
+    "pg = ana.limma(\n",
+    "    pg,\n",
+    "    mnorm_cols,\n",
+    "    custom_design=\"custom_design.tsv\",\n",
+    "    coef=\"labelswitch\",\n",
+    "    cond=\"_limma_ls\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "64109a67-5094-4a70-941b-4e04b1909ef0",
+   "metadata": {},
+   "source": [
+    "Here we plot the P values as histogram. The values corresponding to the label switch are all very high indicating that the label switch had only a minor effect on the total outcome of the experiment.\n",
+    "In contrast, the P values for the intercept coefficient (treatment) are very small, indicating that the overall ratios are significantly different from zero."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "14a8b765-d4ee-4b07-a074-3216257c4acc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 640x480 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "pg.filter(regex=\"adj\\.P\\.\").plot(kind=\"hist\", subplots=True)\n",
+    "\n",
+    "plt.savefig(\"importomics_fig3.pdf\")\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "801439be-892f-47f8-b895-0c299bdaf821",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## Visualisation\n",
+    "\n",
+    "The most common visulisation for quantitiatve AP-MS results is a volcano plot that depicts the average enrichment on the x-axis vs. the statistical significance of the enrichment on the y-axis. Protein groups falling into the upper right quadrant are significantly enriched and are promising targets for biological validation\n",
+    "\n",
+    "### Volcano plot"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "93a3d518-2ee6-4089-826d-d89290c2c960",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "No kwargs provided for highlights. Using default values.\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1400x300 with 3 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "fig, axs = plt.subplots(nrows=1, ncols=3, figsize=(14, 3), sharex=True)\n",
+    "\n",
+    "highlight_bait = pg[pg[\"Gene names\"].str.contains(\"TOMM40\", na=False)].index\n",
+    "kwargs_bait = {\"color\": \"red\"}\n",
+    "\n",
+    "highlight_tomm = pg[pg[\"Gene names\"].str.contains(\"TOMM\", na=False)].index\n",
+    "kwargs_tomm = {\"color\": \"blue\"}\n",
+    "\n",
+    "highlight_micos = pg[\n",
+    "    pg[\"Gene names\"].str.match(\".*MTX2.*|.*MTX1.*|.*SAMM50.*|.*MTX3.*\", na=False)\n",
+    "].index\n",
+    "\n",
+    "highlight_timm23 = pg[\n",
+    "    pg[\"Gene names\"].str.match(\n",
+    "        \".*TIMM21.*|.*DNAJC19.*|.*TIMM17A.*|.*ROMO1.*|.*TIMM50.*|.*HSP70.*|.*TIMM17B.*|.*GRPEL1.*|.*TIMM44.*|.*TIMM23.*|.*GRPEL2\",\n",
+    "        na=False,\n",
+    "    )\n",
+    "].index\n",
+    "\n",
+    "axs[0].set_xlim(-5, 4)\n",
+    "axs[0].set_title(\"TOMM\")\n",
+    "\n",
+    "# this wrapper function produces the actual volcano plot\n",
+    "vis.volcano(\n",
+    "    pg,\n",
+    "    log_fc_colname=\"logFC_limma\",  # colname from which the x values are taken\n",
+    "    p_colname=\"adj.P.Val_limma\",  # same for the y values\n",
+    "    log_fc_thresh=1,  # a threshold of 4-fold enrichment is typically chosen\n",
+    "    kwargs_both_sig={\"color\": \"lightgrey\", \"edgecolor\": \"none\"},\n",
+    "    kwargs_p_sig={\"color\": \"lightgrey\", \"edgecolor\": \"none\"},\n",
+    "    kwargs_log_fc_sig={\"color\": \"lightgrey\", \"edgecolor\": \"none\"},\n",
+    "    show_legend=False,\n",
+    "    ax=axs[0],\n",
+    "    show_caption=False,\n",
+    "    annotate=\"highlight\",\n",
+    "    highlight=[highlight_tomm, highlight_bait],\n",
+    "    kwargs_highlight=[kwargs_tomm, kwargs_bait],\n",
+    ")\n",
+    "\n",
+    "axs[0].set_xlabel(\"Mean log2 KD/mock\")\n",
+    "axs[1].set_title(\"MICOS\")\n",
+    "\n",
+    "# MICOS\n",
+    "vis.volcano(\n",
+    "    pg,\n",
+    "    log_fc_colname=\"logFC_limma\",  # colname from which the x values are taken\n",
+    "    p_colname=\"adj.P.Val_limma\",  # same for the y values\n",
+    "    log_fc_thresh=1,  # a threshold of 4-fold enrichment is typically chosen\n",
+    "    kwargs_both_sig={\"color\": \"lightgrey\", \"edgecolor\": \"none\"},\n",
+    "    kwargs_p_sig={\"color\": \"lightgrey\", \"edgecolor\": \"none\"},\n",
+    "    kwargs_log_fc_sig={\"color\": \"lightgrey\", \"edgecolor\": \"none\"},\n",
+    "    show_legend=False,\n",
+    "    ax=axs[1],\n",
+    "    show_caption=False,\n",
+    "    annotate=\"highlight\",\n",
+    "    highlight=highlight_micos,\n",
+    ")\n",
+    "\n",
+    "axs[1].set_xlabel(\"Mean log2 KD/mock\")\n",
+    "axs[2].set_title(\"TIMM23\")\n",
+    "\n",
+    "# TIMM23\n",
+    "vis.volcano(\n",
+    "    pg,\n",
+    "    log_fc_colname=\"logFC_limma\",  # colname from which the x values are taken\n",
+    "    p_colname=\"adj.P.Val_limma\",  # same for the y values\n",
+    "    log_fc_thresh=1,  # a threshold of 4-fold enrichment is typically chosen\n",
+    "    kwargs_both_sig={\"color\": \"lightgrey\", \"edgecolor\": \"none\"},\n",
+    "    kwargs_p_sig={\"color\": \"lightgrey\", \"edgecolor\": \"none\"},\n",
+    "    kwargs_log_fc_sig={\"color\": \"lightgrey\", \"edgecolor\": \"none\"},\n",
+    "    show_legend=False,\n",
+    "    ax=axs[2],\n",
+    "    show_caption=False,\n",
+    "    annotate=\"highlight\",\n",
+    "    highlight=highlight_timm23,\n",
+    "    kwargs_highlight={\"color\": \"red\"},\n",
+    ")\n",
+    "\n",
+    "axs[2].set_xlabel(\"Mean log2 KD/mock\")\n",
+    "\n",
+    "plt.tight_layout()\n",
+    "\n",
+    "plt.savefig(\"importomics_fig4.pdf\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "36d57703-cf68-4da9-8dd9-f6ca4e514950",
+   "metadata": {},
+   "source": [
+    "## Functional analysis\n",
+    "As the effect of TOMM40-KD is hampering the import of mitochondrial proteins, this section showcases how significantly (in this case) depleted proteins can be functionally annotated.\n",
+    "Therefore we compare these genes with all genes identified in the analysis. **Important**: When performing functional annotation on enriched samples, never use the total proteome as reference but the enriched subset.\n",
+    "\n",
+    "We use the GProfiler API to perform the enrichment analysis (https://biit.cs.ut.ee/gprofiler/gost) completely from Python. The resulting table contains the significantly enriched terms from several sources which we filter and display as bar plots."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "f1327ada-1f2e-40cc-b17d-262ddcb14004",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# extract the genes significantly downregulated after TOMM40 KD\n",
+    "signficantly_downregulated = (\n",
+    "    pg.loc[\n",
+    "        (pg[\"adj.P.Val_limma\"] < 0.05) & (pg[\"logFC_limma\"] < -1), \"Gene names first\"\n",
+    "    ]\n",
+    "    .dropna()\n",
+    "    .index\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "f9d9d4e7-4ea5-4d52-b457-4a456775d016",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# perform GO\n",
+    "go_annot = ana.go_analysis(\n",
+    "    pg.loc[signficantly_downregulated, \"Gene names first\"].tolist(),\n",
+    "    organism=\"hsapiens\",\n",
+    "    background=pg[\"Gene names first\"].dropna().tolist(),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "71bf36c9-1543-4add-9b29-9bdf3819b70f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "go_annot[\"-log10 P Value\"] = go_annot[\"p_value\"].apply(lambda x: -np.log10(x))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "89377514-6074-4ef7-bc18-f5c59a241b36",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1400x300 with 3 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "fig, axs = plt.subplots(nrows=1, ncols=3, figsize=(14, 3))\n",
+    "\n",
+    "axs[0].set_xlim(-5, 4)\n",
+    "\n",
+    "# this wrapper function produces the actual volcano plot\n",
+    "vis.volcano(\n",
+    "    pg,\n",
+    "    log_fc_colname=\"logFC_limma\",  # colname from which the x values are taken\n",
+    "    p_colname=\"adj.P.Val_limma\",  # same for the y values\n",
+    "    log_fc_thresh=1,  # a threshold of 4-fold enrichment is typically chosen\n",
+    "    kwargs_both_sig={\"color\": \"lightgrey\", \"edgecolor\": \"none\"},\n",
+    "    kwargs_p_sig={\"color\": \"lightgrey\", \"edgecolor\": \"none\"},\n",
+    "    kwargs_log_fc_sig={\"color\": \"lightgrey\", \"edgecolor\": \"none\"},\n",
+    "    show_legend=False,\n",
+    "    show_caption=False,\n",
+    "    annotate=None,\n",
+    "    highlight=signficantly_downregulated,\n",
+    "    kwargs_highlight={\"color\": \"lightblue\"},\n",
+    "    ax=axs[0],\n",
+    ")\n",
+    "\n",
+    "sns.barplot(\n",
+    "    data=go_annot[go_annot[\"source\"] == \"GO:MF\"].head(10),\n",
+    "    x=\"-log10 P Value\",\n",
+    "    y=\"name\",\n",
+    "    color=\"lightblue\",\n",
+    "    ax=axs[1],\n",
+    ")\n",
+    "\n",
+    "axs[1].bar_label(axs[1].containers[0], fmt=\"%.2f\", padding=2)\n",
+    "axs[1].set_ylabel(None)\n",
+    "axs[1].set_title(\"GO:MF\")\n",
+    "axs[1].yaxis.set_tick_params(labelsize=6)\n",
+    "axs[1].yaxis.set_ticklabels(\n",
+    "    [\n",
+    "        re.sub(\"(.{50})\", \"\\\\1\\n\", label.get_text(), 0, re.DOTALL)\n",
+    "        for label in axs[1].yaxis.get_ticklabels()\n",
+    "    ]\n",
+    ")\n",
+    "sns.despine(ax=axs[1])\n",
+    "\n",
+    "sns.barplot(\n",
+    "    data=go_annot[go_annot[\"source\"] == \"GO:CC\"].head(10),\n",
+    "    x=\"-log10 P Value\",\n",
+    "    y=\"name\",\n",
+    "    color=\"lightblue\",\n",
+    "    ax=axs[2],\n",
+    ")\n",
+    "\n",
+    "axs[2].bar_label(axs[2].containers[0], fmt=\"%.2f\", padding=2)\n",
+    "axs[2].set_ylabel(None)\n",
+    "axs[2].set_title(\"GO:CC\")\n",
+    "\n",
+    "axs[2].yaxis.set_tick_params(labelsize=6)\n",
+    "axs[2].yaxis.set_ticklabels(\n",
+    "    [\n",
+    "        re.sub(\"(.{50})\", \"\\\\1\\n\", label.get_text(), 0, re.DOTALL)\n",
+    "        for label in axs[2].yaxis.get_ticklabels()\n",
+    "    ]\n",
+    ")\n",
+    "sns.despine(ax=axs[2])\n",
+    "\n",
+    "plt.tight_layout()\n",
+    "plt.savefig(\"importomics_fig5.pdf\")\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "python3 (autoprot)",
+   "language": "python",
+   "name": "conda-env-autoprot-py"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.9"
+  },
+  "toc-autonumbering": true
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/apms_fig1.pdf b/apms_fig1.pdf
index f1873af..ae4e510 100644
Binary files a/apms_fig1.pdf and b/apms_fig1.pdf differ
diff --git a/apms_fig2.pdf b/apms_fig2.pdf
index a1b04db..ee1071d 100644
Binary files a/apms_fig2.pdf and b/apms_fig2.pdf differ
diff --git a/apms_fig3.pdf b/apms_fig3.pdf
index 5a27094..c22f1bf 100644
Binary files a/apms_fig3.pdf and b/apms_fig3.pdf differ
diff --git a/apms_fig4.pdf b/apms_fig4.pdf
index e997a45..cfcf9bd 100644
Binary files a/apms_fig4.pdf and b/apms_fig4.pdf differ
diff --git a/custom_design.tsv b/custom_design.tsv
new file mode 100644
index 0000000..88f0b88
--- /dev/null
+++ b/custom_design.tsv
@@ -0,0 +1,5 @@
+treatment	labelswitch
+1	1
+1	1
+1	-1
+1	-1
diff --git a/importomics_fig1.pdf b/importomics_fig1.pdf
new file mode 100644
index 0000000..8920553
Binary files /dev/null and b/importomics_fig1.pdf differ
diff --git a/importomics_fig2.pdf b/importomics_fig2.pdf
new file mode 100644
index 0000000..32d5f66
Binary files /dev/null and b/importomics_fig2.pdf differ
diff --git a/importomics_fig3.pdf b/importomics_fig3.pdf
new file mode 100644
index 0000000..7abc16b
Binary files /dev/null and b/importomics_fig3.pdf differ
diff --git a/importomics_fig4.pdf b/importomics_fig4.pdf
new file mode 100644
index 0000000..90cd397
Binary files /dev/null and b/importomics_fig4.pdf differ
diff --git a/importomics_fig5.pdf b/importomics_fig5.pdf
new file mode 100644
index 0000000..719aab7
Binary files /dev/null and b/importomics_fig5.pdf differ