diff --git a/Data_submission/libtype_info.yaml b/Data_submission/libtype_info.yaml
index 7d48c1a2972d89b502da530b8a1d6bf46aa3e566..c6a01f758291e462ccadab1cd2da2054efb0d3b4 100644
--- a/Data_submission/libtype_info.yaml
+++ b/Data_submission/libtype_info.yaml
@@ -16,14 +16,14 @@ sRNA-IP-seq:
default_wildcards:
norm: non_structural
orientation: all
- read_type: all_siRNA
+ read_type: si_22GRNA
rule: make_normalized_bigwig
snakefile: /pasteur/homes/bli/src/bioinfo_utils/sRNA-seq/sRNA-seq.snakefile
sRNA-seq:
default_wildcards:
norm: non_structural
orientation: all
- read_type: all_siRNA
+ read_type: si_22GRNA
rule: make_normalized_bigwig
snakefile: /pasteur/homes/bli/src/bioinfo_utils/sRNA-seq/sRNA-seq.snakefile
diff --git a/small_RNA-seq/small_RNA-seq.snakefile b/small_RNA-seq/small_RNA-seq.snakefile
index 5246e24f7ad96e823275d28c7bf98b5d1a0c4145..9e5d124e994b4d9a42723231d93a411433d19ef7 100644
--- a/small_RNA-seq/small_RNA-seq.snakefile
+++ b/small_RNA-seq/small_RNA-seq.snakefile
@@ -2157,6 +2157,10 @@ rule compute_RPM_folds:
logfile.write("Computing counts per million non-structural mappers\n")
RPM = 1000000 * counts_data / norm
logfile.write("Computing RPM log2 fold changes\n")
+ # Maybe not a very sensible way to compute the mean folds: it pairs replicates, but the pairing is arbitrary
+ # TODO: Should we compute the fold of the means instead?
+ # -> No: the pairing is not necessarily arbitrary.
+ # The condition pairs may come from the same biological line, for instance.
# Add 0.25 as RPM "pseudo-count" (edgeR does this ? https://www.biostars.org/p/102568/#102604)
lfc = np.log2(pd.DataFrame(
{f"log2({cond}_{rep}/{ref}_{rep})" : (RPM[f"{cond}_{rep}"] + 0.25) / (RPM[f"{ref}_{rep}"] + 0.25) for rep in REPS}))
@@ -3761,6 +3765,7 @@ def set_id_lists(wildcards):
rule make_gene_list_lfc_boxplots:
+ """Note: This rule may not work properly if some gene lists contain duplicate entries."""
input:
data = source_fold_data,
output:
diff --git a/small_RNA-seq/small_RNA_nomenclature/small_RNAs.tex b/small_RNA-seq/small_RNA_nomenclature/small_RNAs.tex
index 962600439736d1b71f09b89948a79213e64a44dc..632f457e1e721fb796cda5c930a7fff6ed366cbf 100644
--- a/small_RNA-seq/small_RNA_nomenclature/small_RNAs.tex
+++ b/small_RNA-seq/small_RNA_nomenclature/small_RNAs.tex
@@ -1,5 +1,6 @@
\documentclass[beamer]{standalone}
%\documentclass[landscape]{article}
+\usepackage[T1]{fontenc}
\usepackage{adjustbox}
\usepackage{tikz}
% to have [below=of x]
@@ -13,10 +14,11 @@
\newcommand*{\yMax}{1}%
% https://fr.sharelatex.com/blog/2013/08/29/tikz-series-pt3.html
-\tikzstyle{reads} = [rectangle, rounded corners, text width=3cm, minimum height=1cm,text centered, draw=black, fill=red!30]
-\tikzstyle{virt} = [rectangle, rounded corners, text width=3cm, minimum height=1cm,text centered, draw=gray, fill=red!10]
-\tikzstyle{bam} = [rectangle, rounded corners, text width=3cm, minimum height=1cm,text centered, draw=black, fill=blue!30]
-\tikzstyle{process} = [rectangle, text width=3cm, minimum height=1cm, text centered, draw=black, fill=orange!30]
+\tikzstyle{reads} = [rectangle, rounded corners, text width=3.5cm, minimum height=1cm,text centered, draw=black, fill=red!30]
+\tikzstyle{biotyped_reads} = [rectangle, rounded corners, text width=3.5cm, minimum height=0.625cm,text centered, draw=black, fill=red!30]
+\tikzstyle{virt} = [rectangle, rounded corners, text width=3.5cm, minimum height=1cm,text centered, draw=gray, fill=red!10]
+\tikzstyle{bam} = [rectangle, rounded corners, text width=3.5cm, minimum height=1cm,text centered, draw=black, fill=blue!30]
+\tikzstyle{process} = [rectangle, text width=3.5cm, minimum height=1cm, text centered, draw=black, fill=orange!30]
\tikzstyle{arrow} = [thick,->,>=stealth]
\begin{document}
@@ -77,68 +79,91 @@
\pause{}
\node[process, right= of unmapped] (annotate) {annotate};
-\node[reads, above right= of annotate] (all_si) {all\_si};
-\node[reads, below right= of all_si] (mi) {mi};
-\node[reads, below= of mi] (pi) {pi};
+\node[reads, above right= of selected_on] (all_si) {all\_si};
+%\node[reads, above right= of annotate] (all_si) {all\_si};
+\node[right= 1cm and 5.5cm of annotate] (pimi) {};
+%\node[biotyped_reads, below right=1cm and 2cm of all_si] (mi) {mi};
+\node[biotyped_reads, right= of pimi] (mi) {mi};
+\node[biotyped_reads, below= of mi] (pi) {pi};
\draw[arrow] (selected_on) -- (annotate);
-\draw[arrow] (annotate) -- node[pos=0.825,sloped] {sense} (mi);
-\draw[arrow] (annotate) -- node[pos=0.75,sloped] {sense} (pi);
-\draw[arrow] (annotate) -- node[pos=0.825,sloped] {22G-26G} node[pos=0.5,sloped,below] {22G(U*)} (all_si);
-\pause{}
-
-\node[virt, above= of all_si] (other_all_si) {not antisense or\\no annotation};
-\node[reads, right= of all_si] (simrep_si) {\{simrep/satel\}\_si};
-\node[reads, above= of simrep_si] (pseu_si) {\{te,pseu\}\_si};
-\node[reads, above= of pseu_si] (prot_si) {prot\_si};
-\draw[arrow] (all_si) -- node[pos=0.75,sloped] {antisense} (prot_si);
-\draw[arrow] (all_si) -- node[pos=0.75,sloped] {antisense} (pseu_si);
-\draw[arrow] (all_si) -- node[pos=0.5,sloped] {antisense} (simrep_si);
-\draw[arrow] (all_si) -- (other_all_si);
-\pause{}
-
-\node[reads, right= of pseu_si] (si) {si};
+\draw[arrow] (annotate) -- node[pos=0.75,sloped] {sense} (mi);
+\draw[arrow] (annotate) -- node[pos=0.625,sloped] {sense} (pi);
+%\draw[arrow] (annotate) -- node[pos=0.825,sloped] {22G-26G} node[pos=0.5,sloped,below] {22G(U*)} (all_si);
+\draw[arrow] (annotate) -- node[pos=0.625,sloped,below] {not mi or pi} (all_si);
+\pause{}
+
+%\node[virt, above= of all_si] (other_all_si) {not antisense or\\no annotation};
+%\node[reads, right= of all_si] (simrep_si) {\{simrep|satel\}\_si\_\{22G|26G\}};
+\node[biotyped_reads, right=1cm and 2cm of all_si] (pseu_si) {pseu\_si\_\{22G|26G\}};
+\node[biotyped_reads, below=0.5cm and 1.5cm of pseu_si] (satel_si) {satel\_si\_\{22G|26G\}};
+\node[biotyped_reads, below=0.5cm and 1.5cm of satel_si] (simrep_si) {simrep\_si\_\{22G|26G\}};
+\node[biotyped_reads, above=0.5cm and 1.5cm of pseu_si] (prot_si) {prot\_si\_\{22G|26G\}};
+\node[biotyped_reads, above=0.5cm and 1.5cm of prot_si] (te_si) {te\_si\_\{22G|26G\}};
+%\node[biotyped_reads, right=1cm and 2cm of all_si] (simrep_si) {simrep\_si\_\{22G|26G\}};
+%\node[biotyped_reads, above=0.5cm and 1.5cm of simrep_si] (satel_si) {satel\_si\_\{22G|26G\}};
+%\node[biotyped_reads, above=0.5cm and 1.5cm of satel_si] (pseu_si) {pseu\_si\_\{22G|26G\}};
+%\node[biotyped_reads, above=0.5cm and 1.5cm of pseu_si] (prot_si) {prot\_si\_\{22G|26G\}};
+%\node[biotyped_reads, above=0.5cm and 1.5cm of prot_si] (te_si) {te\_si\_\{22G|26G\}};
+\draw[arrow,blue] (all_si) -- node[pos=0.75,sloped] {antisense 22G|26G} (te_si);
+\draw[arrow,blue] (all_si) -- node[pos=0.5,sloped,below] {\dots{}} (prot_si);
+\draw[arrow,blue] (all_si) -- node[pos=0.5,sloped,below] {\dots{}} (pseu_si);
+\draw[arrow,blue] (all_si) -- node[pos=0.5,sloped,below] {\dots{}} (satel_si);
+\draw[arrow,blue] (all_si) -- node[pos=0.5,sloped,below] {\dots{}} (simrep_si);
+%\draw[arrow] (all_si) -- (other_all_si);
+\pause{}
+
+\node[reads, right= of satel_si] (si) {si\_\{22G|26G\}};
+\draw[arrow] (te_si) -- (si);
\draw[arrow] (prot_si) -- (si);
\draw[arrow] (pseu_si) -- (si);
+\draw[arrow] (satel_si) -- (si);
\draw[arrow] (simrep_si) -- (si);
\pause{}
\node[process, right= of nomap] (annotateU) {annotate};
\node[reads, right= of annotateU] (all_siu) {all\_siu};
\draw[arrow] (nomap_on) -- (annotateU);
-\draw[arrow] (annotateU) -- node[pos=0.5,sloped] {22G(U*)} node[pos=0.5,sloped,below] {22G-26G} (all_siu);
-\pause{}
-
-\node[virt, below= of all_siu] (other_all_siu) {not antisense or\\no annotation};
-\node[reads, right= of all_siu] (prot_siu) {prot\_siu};
-\node[reads, below= of prot_siu] (pseu_siu) {\{te,pseu\}\_siu};
-\node[reads, below= of pseu_siu] (simrep_siu) {\{simrep/satel\}\_siu};
-\draw[arrow] (all_siu) -- node[pos=0.5,sloped] {antisense} (prot_siu);
-\draw[arrow] (all_siu) -- node[pos=0.25,sloped] {antisense} (pseu_siu);
-\draw[arrow] (all_siu) -- node[pos=0.66,sloped,below] {antisense} (simrep_siu);
-\draw[arrow] (all_siu) -- (other_all_siu);
-\pause{}
-
-\node[reads, right= of pseu_siu] (siu) {siu};
+%\draw[arrow] (annotateU) -- node[pos=0.5,sloped] {22G(U*)} node[pos=0.5,sloped,below] {22G-26G} (all_siu);
+\draw[arrow] (annotateU) -- (all_siu);
+\pause{}
+
+%\node[virt, below= of all_siu] (other_all_siu) {not antisense or\\no annotation};
+\node[biotyped_reads, right=1cm and 2cm of all_siu] (te_siu) {te\_siu\_\{22G|26G\}};
+\node[biotyped_reads, below=0.5cm and 1.5cm of te_siu] (prot_siu) {prot\_siu\_\{22G|26G\}};
+\node[biotyped_reads, below=0.5cm and 1.5cm of prot_siu] (pseu_siu) {pseu\_siu\_\{22G|26G\}};
+\node[biotyped_reads, below=0.5cm and 1.5cm of pseu_siu] (satel_siu) {satel\_siu\_\{22G|26G\}};
+\node[biotyped_reads, below=0.5cm and 1.5cm of satel_siu] (simrep_siu) {simrep\_siu\_\{22G|26G\}};
+\draw[arrow,blue] (all_siu) -- node[pos=0.5,sloped] {antisense} node[pos=0.5,sloped,below] {22G|26G} (te_siu);
+\draw[arrow,blue] (all_siu) -- node[pos=0.5,sloped,below] {\dots{}} (prot_siu);
+\draw[arrow,blue] (all_siu) -- node[pos=0.5,sloped,below] {\dots{}} (pseu_siu);
+\draw[arrow,blue] (all_siu) -- node[pos=0.5,sloped,below] {\dots{}} (satel_siu);
+\draw[arrow,blue] (all_siu) -- node[pos=0.5,sloped,below] {\dots{}} (simrep_siu);
+%\draw[arrow] (all_siu) -- (other_all_siu);
+\pause{}
+
+\node[reads, right= of pseu_siu] (siu) {siu\_\{22G|26G\}};
+\draw[arrow] (te_siu) -- (siu);
\draw[arrow] (prot_siu) -- (siu);
\draw[arrow] (pseu_siu) -- (siu);
+\draw[arrow] (satel_siu) -- (siu);
\draw[arrow] (simrep_siu) -- (siu);
\pause{}
-\node[reads, below right= of si] (sisiu) {sisiu};
+\node[reads, below right= of si] (sisiu) {sisiu\_\{22G|26G\}};
\draw[arrow] (si) -- (sisiu);
\draw[arrow] (siu) -- (sisiu);
\pause{}
-\node[reads, right= of mi] (pisimi) {pisimi};
-\draw[arrow] (sisiu) -- (pisimi);
-\draw[arrow] (mi) -- (pisimi);
-\draw[arrow] (pi) -- (pisimi);
+\node[reads, right= of mi] (pimi22G) {pimi22G};
+\draw[arrow] (si) -- node[pos=0.4,sloped,below] {22G} (pimi22G);
+\draw[arrow] (mi) -- (pimi22G);
+\draw[arrow] (pi) -- (pimi22G);
\pause{}
\node[process, above right= of si] (deseq) {DESeq2};
\draw[arrow] (sisiu) -- (deseq);
\draw[arrow] (prot_si) -- (deseq);
-\draw[arrow] (pisimi) -- (deseq);
+\draw[arrow] (pimi22G) -- (deseq);
\pause{}
\node[reads, above= of all_siu] (all_sisiu) {all\_sisiu};
@@ -172,9 +197,9 @@
\draw[arrow] (count_filesU) -- (norm);
\pause{}
-\node[process, below= of pisimi] (RPKM_fold) {RPKM folds};
+\node[process, below= of pimi22G] (RPKM_fold) {RPKM folds};
\draw[arrow] (norm) -- (RPKM_fold);
-\draw[arrow] (pisimi) -- (RPKM_fold);
+\draw[arrow] (pimi22G) -- (RPKM_fold);
\pause{}
\node[process, above right= of prot_si] (remap_small) {remap};