diff --git a/README.md b/README.md
index bf6b6492b6b8865056e26c0e15454954b7c1cfc6..8798226532ada23fbcd0d3c029098173d857673a 100644
--- a/README.md
+++ b/README.md
@@ -20,11 +20,11 @@ Installation and Quick Start
The following quick start briefly summarizes the necessary steps to use our pipeline:
-1. Install the necessary tools (Snakemake, samtools, and bedtools). We recommend installing them via conda, in which case the installation is as easy as
+1. Install the necessary tools (Snakemake, samtools, bedtools, and Subread). We recommend installing them via conda, in which case the installation is as easy as
- ``conda install -c bioconda snakemake bedtools samtools``
+ ``conda install -c bioconda snakemake bedtools samtools subread``
- If conda is not yet installed, follow the [installation instructions](https://conda.io/docs/user-guide/install/index.html). If you want to install the tools manually and outside of the conda framework, see the following instructions for each of the tools: [snakemake](http://snakemake.readthedocs.io/en/stable/getting_started/installation.html), [samtools](http://www.htslib.org/download/), [bedtools](http://bedtools.readthedocs.io/en/latest/content/installation.html).
+ If conda is not yet installed, follow the [installation instructions](https://conda.io/docs/user-guide/install/index.html). If you want to install the tools manually and outside of the conda framework, see the following instructions for each of the tools: [snakemake](http://snakemake.readthedocs.io/en/stable/getting_started/installation.html), [samtools](http://www.htslib.org/download/), [bedtools](http://bedtools.readthedocs.io/en/latest/content/installation.html), [Subread](http://subread.sourceforge.net/).
2. Clone the Git repository:
``git clone https://git.embl.de/grp-zaugg/diffTF``
diff --git a/src/R/4.summary1.R b/src/R/4.summary1.R
index a5f946d8f6de645021818e9ac67d72c5d7171bfb..3c8324fb1fe6562f535c0e6c19666b4bd4c9b909 100755
--- a/src/R/4.summary1.R
+++ b/src/R/4.summary1.R
@@ -154,65 +154,16 @@ mode_peaks = mlv(round(peaks.df$D2_l2FC, 2), method = "mfv", na.rm = TRUE)
summary.df = summary.df %>%
dplyr::mutate(
- pvalue_adj = p.adjust(pvalue_raw, method = "fdr"),
+ adj_pvalue = p.adjust(Ttest_pval, method = "fdr"),
Diff_mean = Mean_l2FC - mean (peaks.df$D2_l2FC, na.rm = TRUE),
- Diff_median = Median_l2FC - median(peaks.df$D2_l2FC, na.rm = TRUE),
+ DiffMedian = Median_l2FC - median(peaks.df$D2_l2FC, na.rm = TRUE),
Diff_mode = Mode_l2FC - mode_peaks[[1]],
Diff_skew = Modeskewness - mode_peaks[[2]]) %>%
na.omit(summary.df)
-# Loop through summary files and use the TFBS_num column
-
-
-
-
-# Automatically calculate the significance thresholds
-# Reverse Ivans heuristic approach earlier
-# TODO: Old code, how to make this up to date?
-# threshold1 = par.l$FDR_threshold / nTF
-# min_T_stat = qt(threshold1/2, median(summary.df$TFBS_num), lower.tail = FALSE)
-#
-#
-#
-# # Filter rows
-# plot_thr.df = summary.df %>%
-# filter(Diff_mean > par.l$plot_min_diffMean | Diff_mean < -par.l$plot_min_diffMean) %>%
-# filter(abs(T_statistic) > min_T_stat)
-#
-#
-#
-# TF_volcano = ggplot() +
-# geom_point(aes(x = summary.df$Diff_mean,
-# y = abs(summary.df$T_statistic),
-# label = summary.df$TF),size = 1) +
-# geom_vline(xintercept = 0, size = 0.7,
-# linetype = "longdash", color = "blue") +
-# geom_hline(yintercept = min_T_stat, size = 0.7,
-# linetype = "longdash", color = "red") +
-# geom_text_repel(aes(x = plot_thr.df$Diff_mean,
-# y = abs(plot_thr.df$T_statistic),
-# label = plot_thr.df$TF),size = 2.5,
-# segment.size = 0.5,box.padding = unit(0.05,"lines")) +
-# ylab("Absolute T-statistic") +
-# xlab(paste0("Mean(TF distr) - mean(peaks)")) +
-# theme(axis.text.x = element_text(face = "bold", color = "black", size = 20),
-# axis.text.y = element_text(face = "bold", color = "black", size = 20),
-# axis.title.x = element_text(face = "bold", colour = "black", size = 24,margin = margin(25,0,0,0)),
-# axis.title.y = element_text(face = "bold", colour = "black", size = 24,margin = margin(0,25,0,0)),
-# axis.line.x = element_line(color = "black"), axis.line.y = element_line(color = "black"),
-# panel.grid.major = element_blank(),
-# panel.grid.minor = element_blank(),
-# panel.border = element_blank(),
-# panel.background = element_blank(),
-# legend.position = c(0.1,0.9),
-# legend.justification = "center",
-# legend.title = element_blank())
-#
-# ggsave(plot = TF_volcano, filename = par.l$file_output_volcanoPlot, width = 12, height = 8, useDingbats = FALSE, dpi = 600)
-
-
-write_tsv(summary.df, par.l$file_output_table) # TODO: check the dec = "." parameter
+
+write_tsv(summary.df, par.l$file_output_table)
.printExecutionTime(start.time)
diff --git a/src/R/7.summaryFinal.R b/src/R/7.summaryFinal.R
index 93af655e67024ae24f28c52ab80dbc94bb2b3bea..ee2e0b1dc6daec59b9836d804f117fb17b5e4d8b 100755
--- a/src/R/7.summaryFinal.R
+++ b/src/R/7.summaryFinal.R
@@ -453,12 +453,19 @@ if (par.l$plotRNASeqClassification) {
}
# Filter by rowMeans to eliminate rows with an sd of 0
- rowMeans1 = rowMeans(expressed.TF.counts.df)
- rowsToDelete = which(rowMeans1 < 1)
+ # rowMeans1 = rowMeans(expressed.TF.counts.df)
+ # rowsToDelete = which(rowMeans1 < 1)
+ # if (length(rowsToDelete) > 0) {
+ # expressed.TF.counts.df = expressed.TF.counts.df[-rowsToDelete,]
+ # flog.info(paste0("Removed ", length(rowsToDelete), " TFs out of ", nrow(expressed.TF.counts.df), " because they had a row mean of < 1."))
+ # }
+ rowSds = rowSds(expressed.TF.counts.df)
+ rowsToDelete = which(rowSds == 0)
if (length(rowsToDelete) > 0) {
- expressed.TF.counts.df = expressed.TF.counts.df[-rowsToDelete,]
- flog.info(paste0("Removed ", length(rowsToDelete), " TFs out of ", nrow(expressed.TF.counts.df), " because they had a row mean of < 1."))
+ expressed.TF.counts.df = expressed.TF.counts.df[-rowsToDelete,]
+ flog.info(paste0("Removed ", length(rowsToDelete), " TFs out of ", nrow(expressed.TF.counts.df), " because they had a standard deviation of 0."))
}
+
rowMeans2 = rowMeans(peak.counts)
rowsToDelete = which(rowMeans2 == 0)
if (length(rowsToDelete) > 0) {