From 7839afabd5393f8a27567f47be951357ca2a0b5e Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Thu, 12 Sep 2024 12:51:12 +0200
Subject: [PATCH 01/19] Merge changes from main into hotfix (#195) (#337)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Sara Monzón <sara.monzon.fdz@gmail.com>
Co-authored-by: Pablo Mata <76519482+Shettland@users.noreply.github.com>
Co-authored-by: Víctor López <98259577+victor5lm@users.noreply.github.com>

From 21eac2f0ad35ca064850e2697f0d353623bd14b2 Mon Sep 17 00:00:00 2001
From: Dani VM <da.valle@isciii.es>
Date: Thu, 12 Sep 2024 13:21:21 +0200
Subject: [PATCH 02/19] fixed path database and update emmtyper params

---
 .../ANALYSIS01_CHARACTERIZATION/04-emmtyper/lablog        | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/bu_isciii/templates/characterization/ANALYSIS/ANALYSIS01_CHARACTERIZATION/04-emmtyper/lablog b/bu_isciii/templates/characterization/ANALYSIS/ANALYSIS01_CHARACTERIZATION/04-emmtyper/lablog
index d5897933..342dcfbd 100644
--- a/bu_isciii/templates/characterization/ANALYSIS/ANALYSIS01_CHARACTERIZATION/04-emmtyper/lablog
+++ b/bu_isciii/templates/characterization/ANALYSIS/ANALYSIS01_CHARACTERIZATION/04-emmtyper/lablog
@@ -53,7 +53,7 @@ cat <<EOF > _01_emmtyper.sbatch
 # create results folder
 mkdir -p 01-typing
 mkdir -p 01-typing/tmps
-blastdb_path=/data/bi/references/cdc_emm_blastdb
+blastdb_path=/data/bi/references/cdc_emm_blastdb/20240509
 
 # Run emmtyper
 singularity exec \\
@@ -63,9 +63,9 @@ singularity exec \\
     /data/bi/pipelines/singularity-images/singularity-emmtyper.0.2.0--py_0 emmtyper \\
     -w blast \\
     --keep \\
-    --blast_db "\${blastdb_path}/cdc_emm_database29042024" \\
-    --percent-identity 95 \\
-    --culling-limit 5 \\
+    --blast_db "\${blastdb_path}/cdc_emm_database" \\
+    --percent-identity 100 \\
+    --culling-limit 5 \
     --output 01-typing/results_emmtyper.out \\
     --output-format verbose \\
     ./fasta_inputs/*.fasta

From 34ac552e868dd7ed0434dcbedfa868f7b655145d Mon Sep 17 00:00:00 2001
From: Dani VM <da.valle@isciii.es>
Date: Thu, 12 Sep 2024 13:31:09 +0200
Subject: [PATCH 03/19] update changelog #339

---
 CHANGELOG.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 4ee3575e..35bd7363 100755
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,8 +9,11 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 ### Credits
 
 Code contributions to the new version:
+- [Daniel Valle](https://github.com/Daniel-VM)
+
 
 ### Template fixes and updates
+- Fixed path to blast database and update Emmtyper params [#339](https://github.com/BU-ISCIII/buisciii-tools/pull/339)
 
 ### Modules
 

From 3a5b57116bc1be78fe8269fc71a9ec90f56e992c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergio=20Olmos=20Pi=C3=B1ero?=
 <103578874+OPSergio@users.noreply.github.com>
Date: Thu, 19 Sep 2024 16:20:00 +0200
Subject: [PATCH 04/19] update sarek version in exomeeb (#341)

* update sarek version in exomeeb

* Updated sarek version (v3.4.4) in ExomeEB-ExomeTrio-WGSTrio templates

* Current version Nextflow
---
 CHANGELOG.md                                                  | 2 +-
 bu_isciii/templates/exomeeb/ANALYSIS/ANALYSIS01_EXOME/lablog  | 4 ++--
 .../templates/exometrio/ANALYSIS/ANALYSIS01_EXOME/lablog      | 2 +-
 bu_isciii/templates/wgstrio/ANALYSIS/ANALYSIS01_GENOME/lablog | 4 ++--
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 35bd7363..c899f7d9 100755
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -14,7 +14,7 @@ Code contributions to the new version:
 
 ### Template fixes and updates
 - Fixed path to blast database and update Emmtyper params [#339](https://github.com/BU-ISCIII/buisciii-tools/pull/339)
-
+- Updated sarek version (v3.4.4) in ExomeEB-ExomeTrio-WGSTrio templates [#341] (https://github.com/BU-ISCIII/buisciii-tools/pull/341)
 ### Modules
 
 #### Added enhancements
diff --git a/bu_isciii/templates/exomeeb/ANALYSIS/ANALYSIS01_EXOME/lablog b/bu_isciii/templates/exomeeb/ANALYSIS/ANALYSIS01_EXOME/lablog
index 22502631..edc5cd0e 100755
--- a/bu_isciii/templates/exomeeb/ANALYSIS/ANALYSIS01_EXOME/lablog
+++ b/bu_isciii/templates/exomeeb/ANALYSIS/ANALYSIS01_EXOME/lablog
@@ -1,4 +1,4 @@
-# module load Nextflow/22.10.1 singularity
+# module load Nextflow singularity
 
 ln -s ../00-reads/ .
 ln -s ../samples_id.txt .
@@ -28,7 +28,7 @@ cat <<EOF > sarek.sbatch
 
 export NXF_OPTS="-Xms500M -Xmx4G"
 
-nextflow run /data/bi/pipelines/nf-core-sarek/nf-core-sarek-3.4.2/workflow/main.nf \\
+nextflow run /data/bi/pipelines/nf-core-sarek/nf-core-sarek_3.4.4/3_4_4/main.nf \\
 	-c ../../DOC/hpc_slurm_sarek.config \\
 	--input 'samplesheet.csv' \\
 	--outdir 01-sarek \\
diff --git a/bu_isciii/templates/exometrio/ANALYSIS/ANALYSIS01_EXOME/lablog b/bu_isciii/templates/exometrio/ANALYSIS/ANALYSIS01_EXOME/lablog
index 179c7493..a7081ffe 100755
--- a/bu_isciii/templates/exometrio/ANALYSIS/ANALYSIS01_EXOME/lablog
+++ b/bu_isciii/templates/exometrio/ANALYSIS/ANALYSIS01_EXOME/lablog
@@ -42,7 +42,7 @@ cat <<EOF > sarek.sbatch
 
 export NXF_OPTS="-Xms500M -Xmx4G"
 
-nextflow run /data/bi/pipelines/nf-core-sarek/nf-core-sarek-3.4.2/workflow/main.nf \\
+nextflow run /data/bi/pipelines/nf-core-sarek/nf-core-sarek_3.4.4/3_4_4/main.nf \\
           -c ../../DOC/hpc_slurm_sarek.config \\
           --input 'samplesheet.csv' \\
           --outdir 01-sarek \\
diff --git a/bu_isciii/templates/wgstrio/ANALYSIS/ANALYSIS01_GENOME/lablog b/bu_isciii/templates/wgstrio/ANALYSIS/ANALYSIS01_GENOME/lablog
index cb6d1330..14528c4f 100755
--- a/bu_isciii/templates/wgstrio/ANALYSIS/ANALYSIS01_GENOME/lablog
+++ b/bu_isciii/templates/wgstrio/ANALYSIS/ANALYSIS01_GENOME/lablog
@@ -1,4 +1,4 @@
-# module load Nextflow/22.10.1 singularity
+# module load Nextflow singularity
 
 ln -s ../00-reads/ .
 ln -s ../samples_id.txt .
@@ -44,7 +44,7 @@ cat <<EOF > sarek.sbatch
 
 export NXF_OPTS="-Xms500M -Xmx4G"
 
-nextflow run /data/bi/pipelines/nf-core-sarek/nf-core-sarek-3.4.2/workflow/main.nf \\
+nextflow run /data/bi/pipelines/nf-core-sarek/nf-core-sarek_3.4.4/3_4_4/main.nf \\
           -c ../../DOC/hpc_slurm_sarek.config \\
           --input 'samplesheet.csv' \\
           --outdir 01-sarek \\

From 84809b103c073cd2cf4bdfb5d7d53cebdde00605 Mon Sep 17 00:00:00 2001
From: svarona <sarai.var.fer@gmail.com>
Date: Fri, 30 Aug 2024 08:57:56 +0200
Subject: [PATCH 05/19] Created code to generate amended consensus without
 ambiguities but masked

---
 bu_isciii/templates/IRMA/DOC/irma_config.sh | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/bu_isciii/templates/IRMA/DOC/irma_config.sh b/bu_isciii/templates/IRMA/DOC/irma_config.sh
index 145da9b3..bcaba2ab 100644
--- a/bu_isciii/templates/IRMA/DOC/irma_config.sh
+++ b/bu_isciii/templates/IRMA/DOC/irma_config.sh
@@ -5,3 +5,7 @@ MATCH_PROC=8		# grid maximum processes for the MATCH
 SORT_PROC=8		# currently not used
 ALIGN_PROC=8		# grid maximum processes for the rough align
 ASSEM_PROC=8		# grid maximum processes for assembly
+
+### AMENDED CONSENSUS ###
+MIN_AMBIG=0.75          # Sets ambiguities to off
+MIN_CONS_SUPPORT=9      # Mask low coverage <= 9 (10 is ok)

From bd85c054d67ec400f562d03b7c4f75b386fedfc6 Mon Sep 17 00:00:00 2001
From: svarona <sarai.var.fer@gmail.com>
Date: Fri, 30 Aug 2024 09:00:37 +0200
Subject: [PATCH 06/19] Updated changelog

---
 CHANGELOG.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index c899f7d9..72314508 100755
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -114,6 +114,7 @@ Code contributions to the new version:
 - Added permissions fixing after running scratch_copy, as well as a new fix-permissions module in the tools [#332](https://github.com/BU-ISCIII/buisciii-tools/pull/332).
 - Updated MAG lablogs and utils.py [#334](https://github.com/BU-ISCIII/buisciii-tools/pull/334).
 - Updated some files (setup.py, __main__.py, README, etc) for the 2.2.0 release [#335](https://github.com/BU-ISCIII/buisciii-tools/pull/335).
+- Fixed IRMAs config for amended consensus [#325](https://github.com/BU-ISCIII/buisciii-tools/pull/325).
 
 ### Modules
 

From b584e753c03fba47fcaa4e5a64fc4ebbf33139f8 Mon Sep 17 00:00:00 2001
From: svarona <sarai.var.fer@gmail.com>
Date: Thu, 19 Sep 2024 15:49:44 +0200
Subject: [PATCH 07/19] Fixd changelog

---
 CHANGELOG.md | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 72314508..8b7e3f90 100755
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,12 +9,16 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 ### Credits
 
 Code contributions to the new version:
-- [Daniel Valle](https://github.com/Daniel-VM)
 
+- [Daniel Valle](https://github.com/Daniel-VM)
+- [Sarai Varona](https://github.com/svarona)
 
 ### Template fixes and updates
+
 - Fixed path to blast database and update Emmtyper params [#339](https://github.com/BU-ISCIII/buisciii-tools/pull/339)
 - Updated sarek version (v3.4.4) in ExomeEB-ExomeTrio-WGSTrio templates [#341] (https://github.com/BU-ISCIII/buisciii-tools/pull/341)
+- Fixed IRMAs config for amended consensus [#325](https://github.com/BU-ISCIII/buisciii-tools/pull/325).
+
 ### Modules
 
 #### Added enhancements
@@ -114,7 +118,6 @@ Code contributions to the new version:
 - Added permissions fixing after running scratch_copy, as well as a new fix-permissions module in the tools [#332](https://github.com/BU-ISCIII/buisciii-tools/pull/332).
 - Updated MAG lablogs and utils.py [#334](https://github.com/BU-ISCIII/buisciii-tools/pull/334).
 - Updated some files (setup.py, __main__.py, README, etc) for the 2.2.0 release [#335](https://github.com/BU-ISCIII/buisciii-tools/pull/335).
-- Fixed IRMAs config for amended consensus [#325](https://github.com/BU-ISCIII/buisciii-tools/pull/325).
 
 ### Modules
 

From bc1a72f699e4fe87524487361ffe2fc7bfe5456d Mon Sep 17 00:00:00 2001
From: svarona <sarai.var.fer@gmail.com>
Date: Thu, 19 Sep 2024 15:50:58 +0200
Subject: [PATCH 08/19] Created postprocessing script for amended files

---
 .../04-irma/postprocessing.sh                 | 71 +++++++++++++++++++
 1 file changed, 71 insertions(+)
 create mode 100644 bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/04-irma/postprocessing.sh

diff --git a/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/04-irma/postprocessing.sh b/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/04-irma/postprocessing.sh
new file mode 100644
index 00000000..051b6117
--- /dev/null
+++ b/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/04-irma/postprocessing.sh
@@ -0,0 +1,71 @@
+#CLEAN
+if test -f all_samples_completo.txt; then rm all_samples_completo.txt; fi
+if test -d A_*; then rm -rf A_*; fi
+if test -d B; then rm -rf B; fi
+if test -d C; then rm -rf C; fi
+if test -d D; then rm -rf D; fi
+
+cat ../samples_id.txt | while read sample; do
+    FLUSUBTYPE=$(ls ${sample}/*H*.fasta | cut -d '/' -f2 | cut -d '.' -f1 | cut -d '_' -f1,3 | sort -u)
+    FLUTYPE=$(ls ${sample}/*H*.fasta | cut -d '/' -f2 | cut -d '.' -f1 | cut -d '_' -f1 | sort -u)
+    mkdir -p $FLUSUBTYPE
+    ls ${sample}/amended_consensus/*.fa | cut -d '_' -f3 | cut -d '.' -f1 | while read fragment; do
+        if [ $fragment == 1 ]; then
+            if [ $FLUTYPE == "B" ]; then
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_1/_PB1/' >> ${FLUSUBTYPE}/B_PB1.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_1/_PB1/' >> all_samples_completo.txt
+            else
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_1/_PB2/' >> ${FLUSUBTYPE}/${FLUTYPE}_PB2.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_1/_PB2/' >> all_samples_completo.txt
+            fi
+        elif [ $fragment == 2 ]; then
+            if [ $FLUTYPE == "B" ]; then
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_2/_PB2/' >> ${FLUSUBTYPE}/B_PB2.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_2/_PB2/' >> all_samples_completo.txt
+            else
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_2/_PB1/' >> ${FLUSUBTYPE}/${FLUTYPE}_PB1.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_2/_PB1/' >> all_samples_completo.txt
+            fi
+        elif [ $fragment == 3 ]; then
+            if [ $FLUTYPE == "B" ] || [ $FLUTYPE == "A" ]; then
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_3/_PA/' >> ${FLUSUBTYPE}/${FLUTYPE}_PA.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_3/_PA/' >> all_samples_completo.txt
+            else
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_3/_P3/' >> ${FLUSUBTYPE}/${FLUTYPE}_P3.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_3/_P3/' >> all_samples_completo.txt
+            fi
+        elif [ $fragment == 4 ]; then
+            if [ $FLUTYPE == "B" ] || [ $FLUTYPE == "A" ]; then
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_4/_HA/' >> ${FLUSUBTYPE}/${FLUTYPE}_HA.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_4/_HA/' >> all_samples_completo.txt
+            else
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_4/_HE/' >> ${FLUSUBTYPE}/${FLUTYPE}_HE.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_4/_HE/' >> all_samples_completo.txt
+            fi
+        elif [ $fragment == 5 ]; then
+            cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_5/_NP/' >> ${FLUSUBTYPE}/${FLUTYPE}_NP.txt
+            cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_5/_NP/' >> all_samples_completo.txt
+        elif [ $fragment == 6 ]; then
+            if [ $FLUTYPE == "B" ] || [ $FLUTYPE == "A" ]; then
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_6/_NA/' >> ${FLUSUBTYPE}/${FLUTYPE}_NA.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_6/_NA/' >> all_samples_completo.txt
+            else
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_6/_MP/' >> ${FLUSUBTYPE}/${FLUTYPE}_MP.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_6/_MP/' >> all_samples_completo.txt
+            fi
+        elif [ $fragment == 7 ]; then
+            if [ $FLUTYPE == "B" ] || [ $FLUTYPE == "A" ]; then
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_7/_MP/' >> ${FLUSUBTYPE}/${FLUTYPE}_MP.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_7/_MP/' >> all_samples_completo.txt
+            else
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_7/_NS/' >> ${FLUSUBTYPE}/${FLUTYPE}_NS.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_7/_NS/' >> all_samples_completo.txt
+            fi
+        elif [ $fragment == 8 ]; then
+            cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_8/_NS/' >> ${FLUSUBTYPE}/${FLUTYPE}_NS.txt
+            cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_8/_NS/' >> all_samples_completo.txt
+        else
+            echo "The sample $sample has a segment with number $fragment, but I don't know which segment it is."
+        fi
+    done
+done

From 1b59d9a23b50cfa9d6c698e758e98c472318e9d0 Mon Sep 17 00:00:00 2001
From: svarona <sarai.var.fer@gmail.com>
Date: Thu, 19 Sep 2024 15:51:08 +0200
Subject: [PATCH 09/19] included postprocessing script in lablog

---
 .../ANALYSIS01_FLU_IRMA/04-irma/lablog        | 29 ++-----------------
 1 file changed, 2 insertions(+), 27 deletions(-)

diff --git a/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/04-irma/lablog b/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/04-irma/lablog
index 5e9d933b..be910a9e 100644
--- a/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/04-irma/lablog
+++ b/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/04-irma/lablog
@@ -9,31 +9,6 @@ cat ../samples_id.txt | while read in; do echo "srun --partition short_idx --cpu
 
 echo 'bash create_irma_stats.sh' > _02_create_stats.sh
 
-echo "ls */*HA*.fasta | cut -d '/' -f2 | cut -d '.' -f1 | sort -u | cut -d '_' -f3  | sed '/^\$/d' | sed 's/^/A_/g' > HA_types.txt" > _03_post_processing.sh
+echo 'bash postprocessing.sh' > _03_post_processing.sh
 
-echo 'cat HA_types.txt | while read type; do if test -d ${type}; then rm -rf ${type}; fi; done; if test -d B ; then rm -rf B; fi; if test -d C; then rm -rf C; fi' >> _03_post_processing.sh
-
-echo 'if test -f all_samples_completo.txt; then rm all_samples_completo.txt; fi' >> _03_post_processing.sh
-
-echo "cat HA_types.txt | while read in; do mkdir \${in}; done" >> _03_post_processing.sh
-
-echo "if grep -qw 'B__' irma_stats.txt; then mkdir B; fi" >> _03_post_processing.sh
-
-echo "if grep -qw 'C__' irma_stats.txt; then mkdir C; fi" >> _03_post_processing.sh
-
-echo "ls */*.fasta | cut -d '/' -f2 | cut -d '.' -f1 | cut -d '_' -f1,2 | sort -u | grep 'A_' > A_fragment_list.txt" >> _03_post_processing.sh
-
-echo "ls */*.fasta | cut -d '/' -f2 | cut -d '.' -f1 | cut -d '_' -f1,2 | sort -u | grep 'B_' > B_fragment_list.txt" >> _03_post_processing.sh
-
-echo "ls */*.fasta | cut -d '/' -f2 | cut -d '.' -f1 | cut -d '_' -f1,2 | sort -u | grep 'C_' > C_fragment_list.txt" >> _03_post_processing.sh
-
-echo 'cat HA_types.txt | while read type; do grep ${type} irma_stats.txt | cut -f1 | while read sample; do cat A_fragment_list.txt | while read fragment; do if test -f ${sample}/${fragment}*.fasta; then cat ${sample}/${fragment}*.fasta | sed "s/^>/\>${sample}_/g" | sed 's/_H1//g' | sed 's/_H3//g' | sed 's/_N1//g' | sed 's/_N2//g' | sed s@-@/@g | sed s/_A_/_/g ; fi >> ${type}/${fragment}.txt; done; done; done' >> _03_post_processing.sh
-
-echo 'grep -w 'B__' irma_stats.txt | cut -f1 | while read sample; do cat B_fragment_list.txt | while read fragment; do if test -f ${sample}/${fragment}*.fasta; then cat ${sample}/${fragment}*.fasta | sed "s/^>/\>${sample}_/g" | sed s/_H1//g | sed s/_H3//g | sed s/_N1//g | sed s/_N2//g | sed s@-@/@g | sed s/_B_/_/g ; fi >> B/${fragment}.txt; done; done' >> _03_post_processing.sh
-
-echo 'grep -w 'C__' irma_stats.txt | cut -f1 | while read sample; do cat C_fragment_list.txt | while read fragment; do if test -f ${sample}/${fragment}*.fasta; then cat ${sample}/${fragment}*.fasta | sed "s/^>/\>${sample}_/g" | sed s/_H1//g | sed s/_H3//g | sed s/_N1//g | sed s/_N2//g | sed s@-@/@g | sed s/_C_/_/g ; fi >> C/${fragment}.txt; done; done' >> _03_post_processing.sh
-
-echo 'cat ../samples_id.txt | while read in; do cat ${in}/*.fasta | sed "s/^>/\>${in}_/g" | sed 's/_H1//g' | sed 's/_H3//g' | sed 's/_N1//g' | sed 's/_N2//g' | sed 's@-@/@g' | sed 's/_A_/_/g' | sed 's/_B_/_/g' | sed 's/_C_/_/g' >> all_samples_completo.txt; done' >> _03_post_processing.sh
-
-echo 'sed "s/__//g" irma_stats.txt > clean_irma_stats.txt' >> _03_post_processing.sh
-echo 'sed "s/_\t/\t/g" irma_stats.txt > clean_irma_stats.txt' >> _03_post_processing.sh
+echo 'sed "s/__//g" irma_stats.txt | sed "s/_\t/\t/g" > clean_irma_stats.txt' >> _03_post_processing.sh

From ac6f23eb7b70c67ae0e0fff08ac6d954c9eac2c3 Mon Sep 17 00:00:00 2001
From: svarona <sarai.var.fer@gmail.com>
Date: Thu, 19 Sep 2024 16:37:14 +0200
Subject: [PATCH 10/19] Shortened code to look better

---
 .../04-irma/postprocessing.sh                 | 42 +++++++------------
 1 file changed, 14 insertions(+), 28 deletions(-)

diff --git a/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/04-irma/postprocessing.sh b/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/04-irma/postprocessing.sh
index 051b6117..2ef0e02c 100644
--- a/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/04-irma/postprocessing.sh
+++ b/bu_isciii/templates/IRMA/ANALYSIS/ANALYSIS01_FLU_IRMA/04-irma/postprocessing.sh
@@ -12,58 +12,44 @@ cat ../samples_id.txt | while read sample; do
     ls ${sample}/amended_consensus/*.fa | cut -d '_' -f3 | cut -d '.' -f1 | while read fragment; do
         if [ $fragment == 1 ]; then
             if [ $FLUTYPE == "B" ]; then
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_1/_PB1/' >> ${FLUSUBTYPE}/B_PB1.txt
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_1/_PB1/' >> all_samples_completo.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_1/_PB1/' | tee -a ${FLUSUBTYPE}/B_PB1.txt all_samples_completo.txt > /dev/null
             else
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_1/_PB2/' >> ${FLUSUBTYPE}/${FLUTYPE}_PB2.txt
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_1/_PB2/' >> all_samples_completo.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_1/_PB2/' | tee -a ${FLUSUBTYPE}/${FLUTYPE}_PB2.txt all_samples_completo.txt > /dev/null
             fi
         elif [ $fragment == 2 ]; then
             if [ $FLUTYPE == "B" ]; then
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_2/_PB2/' >> ${FLUSUBTYPE}/B_PB2.txt
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_2/_PB2/' >> all_samples_completo.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_2/_PB2/' | tee -a ${FLUSUBTYPE}/B_PB2.txt all_samples_completo.txt > /dev/null
             else
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_2/_PB1/' >> ${FLUSUBTYPE}/${FLUTYPE}_PB1.txt
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_2/_PB1/' >> all_samples_completo.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_2/_PB1/' | tee -a ${FLUSUBTYPE}/${FLUTYPE}_PB1.txt all_samples_completo.txt > /dev/null
             fi
         elif [ $fragment == 3 ]; then
             if [ $FLUTYPE == "B" ] || [ $FLUTYPE == "A" ]; then
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_3/_PA/' >> ${FLUSUBTYPE}/${FLUTYPE}_PA.txt
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_3/_PA/' >> all_samples_completo.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_3/_PA/' | tee -a ${FLUSUBTYPE}/${FLUTYPE}_PA.txt all_samples_completo.txt > /dev/null
             else
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_3/_P3/' >> ${FLUSUBTYPE}/${FLUTYPE}_P3.txt
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_3/_P3/' >> all_samples_completo.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_3/_P3/' | tee -a ${FLUSUBTYPE}/${FLUTYPE}_P3.txt all_samples_completo.txt > /dev/null
             fi
         elif [ $fragment == 4 ]; then
             if [ $FLUTYPE == "B" ] || [ $FLUTYPE == "A" ]; then
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_4/_HA/' >> ${FLUSUBTYPE}/${FLUTYPE}_HA.txt
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_4/_HA/' >> all_samples_completo.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_4/_HA/' | tee -a ${FLUSUBTYPE}/${FLUTYPE}_HA.txt all_samples_completo.txt > /dev/null
             else
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_4/_HE/' >> ${FLUSUBTYPE}/${FLUTYPE}_HE.txt
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_4/_HE/' >> all_samples_completo.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_4/_HE/' | tee -a ${FLUSUBTYPE}/${FLUTYPE}_HE.txt all_samples_completo.txt > /dev/null
             fi
         elif [ $fragment == 5 ]; then
-            cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_5/_NP/' >> ${FLUSUBTYPE}/${FLUTYPE}_NP.txt
-            cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_5/_NP/' >> all_samples_completo.txt
+            cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_5/_NP/' | tee -a ${FLUSUBTYPE}/${FLUTYPE}_NP.txt all_samples_completo.txt > /dev/null
         elif [ $fragment == 6 ]; then
             if [ $FLUTYPE == "B" ] || [ $FLUTYPE == "A" ]; then
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_6/_NA/' >> ${FLUSUBTYPE}/${FLUTYPE}_NA.txt
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_6/_NA/' >> all_samples_completo.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_6/_NA/' | tee -a ${FLUSUBTYPE}/${FLUTYPE}_NA.txt all_samples_completo.txt > /dev/null
             else
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_6/_MP/' >> ${FLUSUBTYPE}/${FLUTYPE}_MP.txt
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_6/_MP/' >> all_samples_completo.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_6/_MP/' | tee -a ${FLUSUBTYPE}/${FLUTYPE}_MP.txt all_samples_completo.txt > /dev/null
             fi
         elif [ $fragment == 7 ]; then
             if [ $FLUTYPE == "B" ] || [ $FLUTYPE == "A" ]; then
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_7/_MP/' >> ${FLUSUBTYPE}/${FLUTYPE}_MP.txt
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_7/_MP/' >> all_samples_completo.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_7/_MP/' | tee -a ${FLUSUBTYPE}/${FLUTYPE}_MP.txt all_samples_completo.txt > /dev/null
             else
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_7/_NS/' >> ${FLUSUBTYPE}/${FLUTYPE}_NS.txt
-                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_7/_NS/' >> all_samples_completo.txt
+                cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_7/_NS/' | tee -a ${FLUSUBTYPE}/${FLUTYPE}_NS.txt all_samples_completo.txt > /dev/null
             fi
         elif [ $fragment == 8 ]; then
-            cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_8/_NS/' >> ${FLUSUBTYPE}/${FLUTYPE}_NS.txt
-            cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_8/_NS/' >> all_samples_completo.txt
+            cat ${sample}/amended_consensus/*_${fragment}.fa | sed 's/-/\//g' | sed 's/_8/_NS/' | tee -a ${FLUSUBTYPE}/${FLUTYPE}_NS.txt all_samples_completo.txt > /dev/null
         else
             echo "The sample $sample has a segment with number $fragment, but I don't know which segment it is."
         fi

From 89469fd9bd891b56f6305db711a08385c6908b87 Mon Sep 17 00:00:00 2001
From: victor5lm <victor_lopez_5@hotmail.com>
Date: Mon, 30 Sep 2024 16:42:43 +0200
Subject: [PATCH 11/19] Updated the 03-annotation/lablogs in exomeeb, exometrio
 and wgstrio services to have all the necessary -bind routes

---
 .../exomeeb/ANALYSIS/ANALYSIS01_EXOME/03-annotation/lablog      | 2 +-
 .../exometrio/ANALYSIS/ANALYSIS01_EXOME/03-annotation/lablog    | 2 +-
 .../wgstrio/ANALYSIS/ANALYSIS01_GENOME/03-annotation/lablog     | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/bu_isciii/templates/exomeeb/ANALYSIS/ANALYSIS01_EXOME/03-annotation/lablog b/bu_isciii/templates/exomeeb/ANALYSIS/ANALYSIS01_EXOME/03-annotation/lablog
index 61892d9b..ef8d93ad 100644
--- a/bu_isciii/templates/exomeeb/ANALYSIS/ANALYSIS01_EXOME/03-annotation/lablog
+++ b/bu_isciii/templates/exomeeb/ANALYSIS/ANALYSIS01_EXOME/03-annotation/lablog
@@ -22,7 +22,7 @@ echo "srun --partition short_idx --time 2:00:00 --chdir ${scratch_dir} --output
 
 ## 4-5. Lablog for annotating whole genome samples using Variant Effect Predictor (VEP).
 
-echo "srun --partition short_idx --mem 100G --time 4:00:00 --chdir ${scratch_dir} --output logs/VEP.log --job-name VEP singularity exec -B ${scratch_dir}/../../../ /data/bi/pipelines/singularity-images/ensembl-vep:103.1--pl5262h4a94de4_2 vep --fasta /data/bi/references/eukaria/homo_sapiens/hg19/1000genomes_b37/genome/human_g1k_v37.fasta -i ${scratch_dir}/vep/variants_fil_mod.vcf -o ${scratch_dir}/vep/vep_annot.vcf --cache --offline --dir_cache /data/bi/references/eukaria/homo_sapiens/cache_vep/ --everything --dir_plugins /data/bi/references/eukaria/homo_sapiens/cache_vep/Plugins/ --assembly GRCh37 --tab --plugin dbNSFP,/data/bi/references/eukaria/homo_sapiens/cache_vep/custom_databases/dbNSFP/GRCh37/dbNSFP4.1a_grch37.gz,clinvar_id,clinvar_trait,clinvar_OMIM_id,clinvar_Orphanet_id,HGVSc_snpEff,HGVSp_snpEff,SIFT_score,SIFT_pred,Polyphen2_HDIV_score,Polyphen2_HDIV_pred,Polyphen2_HVAR_score,Polyphen2_HVAR_pred,MutationTaster_score,MutationTaster_pred,MutationAssessor_score,MutationAssessor_pred,FATHMM_score,FATHMM_pred,PROVEAN_score,PROVEAN_pred,VEST4_score,MetaSVM_score,MetaSVM_pred,MetaLR_score,MetaLR_pred,CADD_raw,CADD_phred,CADD_raw_hg19,CADD_phred_hg19,GERP++_NR,GERP++_RS,phyloP100way_vertebrate,phastCons100way_vertebrate &" > _02_vep_annotation.sh
+echo "srun --partition short_idx --mem 100G --time 4:00:00 --chdir ${scratch_dir} --output logs/VEP.log --job-name VEP singularity exec -B /data/bi/references/eukaria/homo_sapiens/hg19/1000genomes_b37/genome/ -B /data/bi/references/eukaria/homo_sapiens/cache_vep/homo_sapiens -B /data/bi/references/eukaria/homo_sapiens/cache_vep/custom_databases/dbNSFP/GRCh37/ -B ${scratch_dir}/../../../ /data/bi/pipelines/singularity-images/ensembl-vep:103.1--pl5262h4a94de4_2 vep --fasta /data/bi/references/eukaria/homo_sapiens/hg19/1000genomes_b37/genome/human_g1k_v37.fasta -i ${scratch_dir}/vep/variants_fil_mod.vcf -o ${scratch_dir}/vep/vep_annot.vcf --cache --offline --dir_cache /data/bi/references/eukaria/homo_sapiens/cache_vep/ --everything --dir_plugins /data/bi/references/eukaria/homo_sapiens/cache_vep/Plugins/ --assembly GRCh37 --tab --plugin dbNSFP,/data/bi/references/eukaria/homo_sapiens/cache_vep/custom_databases/dbNSFP/GRCh37/dbNSFP4.1a_grch37.gz,clinvar_id,clinvar_trait,clinvar_OMIM_id,clinvar_Orphanet_id,HGVSc_snpEff,HGVSp_snpEff,SIFT_score,SIFT_pred,Polyphen2_HDIV_score,Polyphen2_HDIV_pred,Polyphen2_HVAR_score,Polyphen2_HVAR_pred,MutationTaster_score,MutationTaster_pred,MutationAssessor_score,MutationAssessor_pred,FATHMM_score,FATHMM_pred,PROVEAN_score,PROVEAN_pred,VEST4_score,MetaSVM_score,MetaSVM_pred,MetaLR_score,MetaLR_pred,CADD_raw,CADD_phred,CADD_raw_hg19,CADD_phred_hg19,GERP++_NR,GERP++_RS,phyloP100way_vertebrate,phastCons100way_vertebrate &" > _02_vep_annotation.sh
 
 echo "grep -v '^##' ./vep/vep_annot.vcf > ./vep/vep_annot_head.txt" > _03_merge_data1.sh
 echo "sed -i 's/#Uploaded_variation/ID/' ./vep/vep_annot_head.txt" >> _03_merge_data1.sh
diff --git a/bu_isciii/templates/exometrio/ANALYSIS/ANALYSIS01_EXOME/03-annotation/lablog b/bu_isciii/templates/exometrio/ANALYSIS/ANALYSIS01_EXOME/03-annotation/lablog
index 063393c2..e771e6dc 100644
--- a/bu_isciii/templates/exometrio/ANALYSIS/ANALYSIS01_EXOME/03-annotation/lablog
+++ b/bu_isciii/templates/exometrio/ANALYSIS/ANALYSIS01_EXOME/03-annotation/lablog
@@ -28,7 +28,7 @@ echo "srun --partition short_idx --time 2:00:00 --chdir ${scratch_dir} --output
 # 3. Lablog for annotating whole genome samples using Variant Effect Predictor (VEP).
 # Run Vep without the plugin columns
 
-echo "srun --partition short_idx --mem 100G --time 12:00:00 --chdir ${scratch_dir} --output logs/VEP.log --job-name VEP singularity exec -B ${scratch_dir}/../../../ /data/bi/pipelines/singularity-images/ensembl-vep:103.1--pl5262h4a94de4_2 vep --fasta /data/bi/references/eukaria/homo_sapiens/hg19/1000genomes_b37/genome/human_g1k_v37.fasta -i ${scratch_dir}/vep/variants_fil_mod.vcf -o ${scratch_dir}/vep/vep_annot.vcf --cache --offline --dir_cache /data/bi/references/eukaria/homo_sapiens/cache_vep/ --everything --assembly GRCh37 --tab &" > _02_vep_annotation.sh
+echo "srun --partition short_idx --mem 100G --time 12:00:00 --chdir ${scratch_dir} --output logs/VEP.log --job-name VEP singularity exec -B /data/bi/references/eukaria/homo_sapiens/hg19/1000genomes_b37/genome -B /data/bi/references/eukaria/homo_sapiens/cache_vep -B ${scratch_dir}/../../../ /data/bi/pipelines/singularity-images/ensembl-vep:103.1--pl5262h4a94de4_2 vep --fasta /data/bi/references/eukaria/homo_sapiens/hg19/1000genomes_b37/genome/human_g1k_v37.fasta -i ${scratch_dir}/vep/variants_fil_mod.vcf -o ${scratch_dir}/vep/vep_annot.vcf --cache --offline --dir_cache /data/bi/references/eukaria/homo_sapiens/cache_vep/ --everything --assembly GRCh37 --tab &" > _02_vep_annotation.sh
 
 #--------------------------------------------------------------------------------------------------------------------
 
diff --git a/bu_isciii/templates/wgstrio/ANALYSIS/ANALYSIS01_GENOME/03-annotation/lablog b/bu_isciii/templates/wgstrio/ANALYSIS/ANALYSIS01_GENOME/03-annotation/lablog
index 50d87f79..c6a964bd 100644
--- a/bu_isciii/templates/wgstrio/ANALYSIS/ANALYSIS01_GENOME/03-annotation/lablog
+++ b/bu_isciii/templates/wgstrio/ANALYSIS/ANALYSIS01_GENOME/03-annotation/lablog
@@ -31,7 +31,7 @@ echo "srun --partition short_idx --time 2:00:00 --chdir ${scratch_dir} --output
 
 # Run Vep without the plugin columns
 
-echo "srun --partition short_idx --mem 100G --time 12:00:00 --chdir ${scratch_dir} --output logs/VEP.log --job-name VEP singularity exec -B ${scratch_dir}/../../../ /data/bi/pipelines/singularity-images/ensembl-vep:103.1--pl5262h4a94de4_2 vep --fasta /data/bi/references/eukaria/homo_sapiens/hg19/1000genomes_b37/genome/human_g1k_v37.fasta -i ${scratch_dir}/vep/variants_fil_mod.vcf -o ${scratch_dir}/vep/vep_annot.vcf --cache --offline --dir_cache /data/bi/references/eukaria/homo_sapiens/cache_vep/ --everything --assembly GRCh37 --tab &" > _02_vep_annotation.sh
+echo "srun --partition short_idx --mem 100G --time 12:00:00 --chdir ${scratch_dir} --output logs/VEP.log --job-name VEP singularity exec -B /data/bi/references/eukaria/homo_sapiens/hg19/1000genomes_b37/genome/ -B /data/bi/references/eukaria/homo_sapiens/cache_vep/ -B ${scratch_dir}/../../../ /data/bi/pipelines/singularity-images/ensembl-vep:103.1--pl5262h4a94de4_2 vep --fasta /data/bi/references/eukaria/homo_sapiens/hg19/1000genomes_b37/genome/human_g1k_v37.fasta -i ${scratch_dir}/vep/variants_fil_mod.vcf -o ${scratch_dir}/vep/vep_annot.vcf --cache --offline --dir_cache /data/bi/references/eukaria/homo_sapiens/cache_vep/ --everything --assembly GRCh37 --tab &" > _02_vep_annotation.sh
 
 #--------------------------------------------------------------------------------------------------------------------
 

From 14bd968dfe5b52b349cac3a2a9d8ba2e192de20f Mon Sep 17 00:00:00 2001
From: victor5lm <victor_lopez_5@hotmail.com>
Date: Mon, 30 Sep 2024 16:50:49 +0200
Subject: [PATCH 12/19] Updated bioinfo_doc.py to allow more options when
 creating the delivery email

---
 bu_isciii/bioinfo_doc.py | 30 +++++++++++++++++++++++++++---
 1 file changed, 27 insertions(+), 3 deletions(-)
 mode change 100755 => 100644 bu_isciii/bioinfo_doc.py

diff --git a/bu_isciii/bioinfo_doc.py b/bu_isciii/bioinfo_doc.py
old mode 100755
new mode 100644
index 4da84672..458dd899
--- a/bu_isciii/bioinfo_doc.py
+++ b/bu_isciii/bioinfo_doc.py
@@ -646,10 +646,34 @@ def email_creation(self):
                     email_data["email_notes"] = self.delivery_notes.replace(
                         "\n", "<br />"
                     )
+                else:
+                    email_data["email_notes"] = bu_isciii.utils.ask_for_some_text(
+                        msg="Write email notes"
+                    ).replace("\n", "<br />")
             else:
-                email_data["email_notes"] = bu_isciii.utils.ask_for_some_text(
-                    msg="Write email notes"
-                ).replace("\n", "<br />")
+                if bu_isciii.utils.prompt_yn_question(
+                    msg="Do you wish to provide a text file for email notes?", dflt=False
+                ):
+                    for i in range(3, -1, -1):
+                        email_data["email_notes"] = bu_isciii.utils.prompt_path(
+                            msg="Write the path to the file with RAW text as email notes"
+                        )
+                        if not os.path.isfile(os.path.expanduser(email_data["email_notes"])):
+                            stderr.print(f"Provided file doesn't exist. Attempts left: {i}")
+                        else:
+                            stderr.print(f"File selected: {email_data["email_notes"]}")
+                            break
+                    else:
+                        stderr.print("No more attempts. Email notes will be given by prompt")
+                        email_data["email_notes"] = None
+                else:
+                    email_data["email_notes"] = None
+
+                if email_data["email_notes"]:
+                    with open(os.path.expanduser(email_data["email_notes"])) as f:
+                        email_data["email_notes"] = f.read().replace("\n", "<br />")
+                else:
+                    email_data["email_notes"] = bu_isciii.utils.ask_for_some_text(msg="Write email notes").replace("\n", "<br />")
 
         email_data["user_data"] = self.resolution_info["service_user_id"]
         email_data["service_id"] = self.service_name.split("_", 5)[0]

From db6aa1996b01336167f7300e704bf86fdc93cac8 Mon Sep 17 00:00:00 2001
From: victor5lm <victor_lopez_5@hotmail.com>
Date: Mon, 30 Sep 2024 16:54:57 +0200
Subject: [PATCH 13/19] Updated excel_generator.py to be more informative

---
 .../viralrecon/RESULTS/excel_generator.py     | 32 ++++++++++++-------
 1 file changed, 20 insertions(+), 12 deletions(-)

diff --git a/bu_isciii/templates/viralrecon/RESULTS/excel_generator.py b/bu_isciii/templates/viralrecon/RESULTS/excel_generator.py
index 8467c414..ffeece39 100755
--- a/bu_isciii/templates/viralrecon/RESULTS/excel_generator.py
+++ b/bu_isciii/templates/viralrecon/RESULTS/excel_generator.py
@@ -68,7 +68,7 @@ def merge_lineage_tables(
                 csvs_in_folder=csvs_in_folder, merged_csv_name=merged_csv_name
             )
         else:
-            print(f"No pangolin folder could be found for {ref}, omitting")
+            print(f"\033[93mNo pangolin folder could be found for {ref}, omitting\033[0m")
 
         if os.path.isdir(os.path.abspath(folder + "/nextclade")):
             nextcl_dir = os.path.join(folder, "nextclade")
@@ -82,17 +82,18 @@ def merge_lineage_tables(
                 csvs_in_folder=csvs_in_folder, merged_csv_name=merged_csv_name
             )
         else:
-            print(f"No nextclade folder could be found for {ref}, omitting")
+            print(f"\033[93mNo nextclade folder could be found for {ref}, omitting\033[0m\n")
 
     return
 
 
 def excel_generator(csv_files: List[str]):
+    #print("Proceeding")
     for file in csv_files:
         if not os.path.exists(file):
-            print(f"File {file} does not exist, omitting...")
+            print(f"\033[91mFile {file} does not exist, omitting...\033[0m")
             continue
-        print(f"Generating excel file for {file}")
+        print(f"\033[92mGenerating excel file for {file}\033[0m")
         output_name = os.path.splitext(os.path.basename(file))[0] + ".xlsx"
         # workbook = openpyxl.Workbook(output_name)
         if "nextclade" in str(file):
@@ -108,7 +109,7 @@ def excel_generator(csv_files: List[str]):
             try:
                 table = pd.read_csv(file)
             except pd.errors.EmptyDataError:
-                print("Could not parse table from ", str(file))
+                print("\033[91mCould not parse table from ", str(file), "\033[0m")
                 continue
         table = table.drop(["index"], axis=1, errors="ignore")
         table.to_excel(output_name, index=False)
@@ -119,22 +120,22 @@ def single_csv_to_excel(csv_file: str):
     try:
         excel_generator([csv_file])
     except FileNotFoundError as e:
-        print(f"Could not find file {e}")
+        print(f"\033[91mCould not find file {e}\033[0m")
 
 
 def main(args):
     if args.single_csv:
         # If single_csv is called, just convert target csv to excel and skip the rest
-        print("Single file convertion selected. Skipping main process...")
+        print("\033[92mSingle file convertion selected. Skipping main process...\033[0m")
         single_csv_to_excel(args.single_csv)
         exit(0)
 
     print(
-        "Extracting references used for analysis and the samples associated with each reference\n"
+        "\033[92mExtracting references used for analysis and the samples associated with each reference\033[0m"
     )
     with open(args.reference_file, "r") as file:
         references = [line.rstrip() for line in file]
-        print(f"\nFound {len(references)} references: {str(references).strip('[]')}")
+        print(f"\n\033[92mFound {len(references)} references: {str(references).strip('[]')}\033[0m")
 
     reference_folders = {ref: str("excel_files_" + ref) for ref in references}
     samples_ref_files = {
@@ -145,7 +146,7 @@ def main(args):
         # Merge pangolin and nextclade csv files separatedly and create excel files for them
         merge_lineage_tables(reference_folders, samples_ref_files)
         for reference, folder in reference_folders.items():
-            print(f"Creating excel files for reference {reference}")
+            print(f"\033[92mCreating excel files for reference {reference}\033[0m")
             csv_files = [
                 file.path for file in os.scandir(folder) if file.path.endswith(".csv")
             ]
@@ -160,8 +161,9 @@ def main(args):
             csvs_in_folder=variants_tables, merged_csv_name="variants_long_table.csv"
         )
     except FileNotFoundError as e:
-        print(str(e))
-        print("Merged variants_long_table.csv might be empty")
+        print("\033[93mWARNING!\033[0m")
+        print("\033[93mAt least one variants_long_table.csv file could not be found. Therefore, merged variants_long_table.csv will be incomplete.\033[0m")
+        print("\033[93mPlease, check the following report in order to know which links are broken and, therefore, which tables could not be found:\033[0m\n")
 
     # Create excel files for individual tables
     valid_extensions = [".csv", ".tsv", ".tab"]
@@ -173,6 +175,12 @@ def main(args):
     link_csvs = [file for file in rest_of_csvs if os.path.islink(file)]
     broken_links = [file for file in link_csvs if not os.path.exists(os.readlink(file))]
     valid_csvs = [file for file in rest_of_csvs if file not in broken_links]
+
+    if broken_links:
+     print(f"\033[93mWARNING! {len(broken_links)} broken links found (for .csv, .tsv or .tab files). Please fix them.\033[0m")
+     for broken_link in broken_links:
+         print(f"\033[93mBroken link: {broken_link} (target: {os.readlink(broken_link)})\033[0m")
+
     excel_generator(valid_csvs)
 
 

From 7038b86232082607471fcea237fbd3d417c6048b Mon Sep 17 00:00:00 2001
From: victor5lm <victor_lopez_5@hotmail.com>
Date: Mon, 30 Sep 2024 16:55:21 +0200
Subject: [PATCH 14/19] Updated sftp_user.json

---
 bu_isciii/templates/sftp_user.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/bu_isciii/templates/sftp_user.json b/bu_isciii/templates/sftp_user.json
index bc7f4528..344c8b49 100755
--- a/bu_isciii/templates/sftp_user.json
+++ b/bu_isciii/templates/sftp_user.json
@@ -44,7 +44,7 @@
     "sara.perez": ["GeneticDiagnosis"],
     "sbarturen": ["Labvirushep"],
     "sergio.sanchez": ["LabFWDB_ssanchez"],
-    "sherrera": ["LabFWBD", "LabFWBD_ext"],
+    "sherrera": ["LabFWBD", "LabFWBD_ext", "Labtuberculosis"],
     "sresino": ["Labvirushep"],
     "svaldezate": ["Labtaxonomia"],
     "svazquez": ["Labvirusres"],

From 99edee6ad07ea0e4553886cfd8c92f59ad0f8b21 Mon Sep 17 00:00:00 2001
From: victor5lm <victor_lopez_5@hotmail.com>
Date: Mon, 30 Sep 2024 16:56:29 +0200
Subject: [PATCH 15/19] Updated 03-MTBSeq/lablog to handle the first sample
 name appropriately

---
 .../mtbseq/ANALYSIS/ANALYSIS01_MTBSEQ/03-MTBSeq/lablog        | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/bu_isciii/templates/mtbseq/ANALYSIS/ANALYSIS01_MTBSEQ/03-MTBSeq/lablog b/bu_isciii/templates/mtbseq/ANALYSIS/ANALYSIS01_MTBSEQ/03-MTBSeq/lablog
index e5bdac16..0eff7900 100644
--- a/bu_isciii/templates/mtbseq/ANALYSIS/ANALYSIS01_MTBSEQ/03-MTBSeq/lablog
+++ b/bu_isciii/templates/mtbseq/ANALYSIS/ANALYSIS01_MTBSEQ/03-MTBSeq/lablog
@@ -13,9 +13,9 @@ cat ../samples_id.txt | xargs -I @@ echo -e "srun --job-name MTBSEQ.@@  --output
 
 # classification
 echo "mkdir classification_all" > _03_gather_results.sh 
-echo "FIRST_SAMPLE=$(head -n1 ../samples_id.txt); head -n 1 ${FIRST_SAMPLE}/Classification/Strain_Classification.tab > classification_all/strain_classification_all.tab; grep \"^'$analysis_year\" */Classification/Strain_Classification.tab | cut -d \":\" -f 2 >> classification_all/strain_classification_all.tab" >> _03_gather_results.sh
+echo 'FIRST_SAMPLE=$(head -n1 samples_id.txt); head -n 1 ${FIRST_SAMPLE}/Classification/Strain_Classification.tab > classification_all/strain_classification_all.tab; grep "^'\'''"$analysis_year"'" */Classification/Strain_Classification.tab | cut -d ":" -f 2 >> classification_all/strain_classification_all.tab' >> _03_gather_results.sh
 # resistances
 echo "mkdir resistances_all" >> _03_gather_results.sh
 cat ../samples_id.txt | xargs -I % echo "cp %/Amend/NONE_joint_cf4_cr4_fr75_ph4_samples1_amended.tab resistances_all/%_var_res.tab" >> _03_gather_results.sh
 # stats
-echo "mkdir stats_all; FIRST_SAMPLE=$(head -n1 ../samples_id.txt); head -n 1 ${FIRST_SAMPLE}/Statistics/Mapping_and_Variant_Statistics.tab > stats_all/statistics_all.tab; grep \"^'$analysis_year\" */Statistics/Mapping_and_Variant_Statistics.tab | cut -d \":\" -f 2 >> stats_all/statistics_all.tab" >> _03_gather_results.sh
+echo 'mkdir stats_all; FIRST_SAMPLE=$(head -n1 ../samples_id.txt); head -n 1 ${FIRST_SAMPLE}/Statistics/Mapping_and_Variant_Statistics.tab > stats_all/statistics_all.tab; grep "^'\'''"$analysis_year"'" */Statistics/Mapping_and_Variant_Statistics.tab | cut -d ":" -f 2 >> stats_all/statistics_all.tab' >> _03_gather_results.sh

From baa1925d6045f833e24813f7af5e76a3d1a3affb Mon Sep 17 00:00:00 2001
From: victor5lm <victor_lopez_5@hotmail.com>
Date: Mon, 30 Sep 2024 17:16:18 +0200
Subject: [PATCH 16/19] Fixed linting mistakes

---
 bu_isciii/bioinfo_doc.py                      | 21 +++++++---
 .../viralrecon/RESULTS/excel_generator.py     | 38 +++++++++++++------
 2 files changed, 42 insertions(+), 17 deletions(-)

diff --git a/bu_isciii/bioinfo_doc.py b/bu_isciii/bioinfo_doc.py
index 458dd899..519cb382 100644
--- a/bu_isciii/bioinfo_doc.py
+++ b/bu_isciii/bioinfo_doc.py
@@ -652,19 +652,26 @@ def email_creation(self):
                     ).replace("\n", "<br />")
             else:
                 if bu_isciii.utils.prompt_yn_question(
-                    msg="Do you wish to provide a text file for email notes?", dflt=False
+                    msg="Do you wish to provide a text file for email notes?",
+                    dflt=False,
                 ):
                     for i in range(3, -1, -1):
                         email_data["email_notes"] = bu_isciii.utils.prompt_path(
                             msg="Write the path to the file with RAW text as email notes"
                         )
-                        if not os.path.isfile(os.path.expanduser(email_data["email_notes"])):
-                            stderr.print(f"Provided file doesn't exist. Attempts left: {i}")
+                        if not os.path.isfile(
+                            os.path.expanduser(email_data["email_notes"])
+                        ):
+                            stderr.print(
+                                f"Provided file doesn't exist. Attempts left: {i}"
+                            )
                         else:
-                            stderr.print(f"File selected: {email_data["email_notes"]}")
+                            stderr.print(f"File selected: {email_data['email_notes']}")
                             break
                     else:
-                        stderr.print("No more attempts. Email notes will be given by prompt")
+                        stderr.print(
+                            "No more attempts. Email notes will be given by prompt"
+                        )
                         email_data["email_notes"] = None
                 else:
                     email_data["email_notes"] = None
@@ -673,7 +680,9 @@ def email_creation(self):
                     with open(os.path.expanduser(email_data["email_notes"])) as f:
                         email_data["email_notes"] = f.read().replace("\n", "<br />")
                 else:
-                    email_data["email_notes"] = bu_isciii.utils.ask_for_some_text(msg="Write email notes").replace("\n", "<br />")
+                    email_data["email_notes"] = bu_isciii.utils.ask_for_some_text(
+                        msg="Write email notes"
+                    ).replace("\n", "<br />")
 
         email_data["user_data"] = self.resolution_info["service_user_id"]
         email_data["service_id"] = self.service_name.split("_", 5)[0]
diff --git a/bu_isciii/templates/viralrecon/RESULTS/excel_generator.py b/bu_isciii/templates/viralrecon/RESULTS/excel_generator.py
index ffeece39..2cdb83b4 100755
--- a/bu_isciii/templates/viralrecon/RESULTS/excel_generator.py
+++ b/bu_isciii/templates/viralrecon/RESULTS/excel_generator.py
@@ -68,7 +68,9 @@ def merge_lineage_tables(
                 csvs_in_folder=csvs_in_folder, merged_csv_name=merged_csv_name
             )
         else:
-            print(f"\033[93mNo pangolin folder could be found for {ref}, omitting\033[0m")
+            print(
+                f"\033[93mNo pangolin folder could be found for {ref}, omitting\033[0m"
+            )
 
         if os.path.isdir(os.path.abspath(folder + "/nextclade")):
             nextcl_dir = os.path.join(folder, "nextclade")
@@ -82,13 +84,15 @@ def merge_lineage_tables(
                 csvs_in_folder=csvs_in_folder, merged_csv_name=merged_csv_name
             )
         else:
-            print(f"\033[93mNo nextclade folder could be found for {ref}, omitting\033[0m\n")
+            print(
+                f"\033[93mNo nextclade folder could be found for {ref}, omitting\033[0m\n"
+            )
 
     return
 
 
 def excel_generator(csv_files: List[str]):
-    #print("Proceeding")
+    # print("Proceeding")
     for file in csv_files:
         if not os.path.exists(file):
             print(f"\033[91mFile {file} does not exist, omitting...\033[0m")
@@ -126,7 +130,9 @@ def single_csv_to_excel(csv_file: str):
 def main(args):
     if args.single_csv:
         # If single_csv is called, just convert target csv to excel and skip the rest
-        print("\033[92mSingle file convertion selected. Skipping main process...\033[0m")
+        print(
+            "\033[92mSingle file convertion selected. Skipping main process...\033[0m"
+        )
         single_csv_to_excel(args.single_csv)
         exit(0)
 
@@ -135,7 +141,9 @@ def main(args):
     )
     with open(args.reference_file, "r") as file:
         references = [line.rstrip() for line in file]
-        print(f"\n\033[92mFound {len(references)} references: {str(references).strip('[]')}\033[0m")
+        print(
+            f"\n\033[92mFound {len(references)} references: {str(references).strip('[]')}\033[0m"
+        )
 
     reference_folders = {ref: str("excel_files_" + ref) for ref in references}
     samples_ref_files = {
@@ -160,10 +168,14 @@ def main(args):
         concat_tables_and_write(
             csvs_in_folder=variants_tables, merged_csv_name="variants_long_table.csv"
         )
-    except FileNotFoundError as e:
+    except FileNotFoundError:
         print("\033[93mWARNING!\033[0m")
-        print("\033[93mAt least one variants_long_table.csv file could not be found. Therefore, merged variants_long_table.csv will be incomplete.\033[0m")
-        print("\033[93mPlease, check the following report in order to know which links are broken and, therefore, which tables could not be found:\033[0m\n")
+        print(
+            "\033[93mAt least one variants_long_table.csv file could not be found. Therefore, merged variants_long_table.csv will be incomplete.\033[0m"
+        )
+        print(
+            "\033[93mPlease, check the following report in order to know which links are broken and, therefore, which tables could not be found:\033[0m\n"
+        )
 
     # Create excel files for individual tables
     valid_extensions = [".csv", ".tsv", ".tab"]
@@ -177,9 +189,13 @@ def main(args):
     valid_csvs = [file for file in rest_of_csvs if file not in broken_links]
 
     if broken_links:
-     print(f"\033[93mWARNING! {len(broken_links)} broken links found (for .csv, .tsv or .tab files). Please fix them.\033[0m")
-     for broken_link in broken_links:
-         print(f"\033[93mBroken link: {broken_link} (target: {os.readlink(broken_link)})\033[0m")
+        print(
+            f"\033[93mWARNING! {len(broken_links)} broken links found (for .csv, .tsv or .tab files). Please fix them.\033[0m"
+        )
+        for broken_link in broken_links:
+            print(
+                f"\033[93mBroken link: {broken_link} (target: {os.readlink(broken_link)})\033[0m"
+            )
 
     excel_generator(valid_csvs)
 

From 1ce79569398d539e8dfaf69c8e456ff2bccfe10d Mon Sep 17 00:00:00 2001
From: victor5lm <victor_lopez_5@hotmail.com>
Date: Tue, 1 Oct 2024 12:05:50 +0200
Subject: [PATCH 17/19] Updated CHANGELOG.md

---
 CHANGELOG.md | 37 ++++++++++++++++++++++++++++++-------
 1 file changed, 30 insertions(+), 7 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 8b7e3f90..b76da9b9 100755
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -10,15 +10,8 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 
 Code contributions to the new version:
 
-- [Daniel Valle](https://github.com/Daniel-VM)
-- [Sarai Varona](https://github.com/svarona)
-
 ### Template fixes and updates
 
-- Fixed path to blast database and update Emmtyper params [#339](https://github.com/BU-ISCIII/buisciii-tools/pull/339)
-- Updated sarek version (v3.4.4) in ExomeEB-ExomeTrio-WGSTrio templates [#341] (https://github.com/BU-ISCIII/buisciii-tools/pull/341)
-- Fixed IRMAs config for amended consensus [#325](https://github.com/BU-ISCIII/buisciii-tools/pull/325).
-
 ### Modules
 
 #### Added enhancements
@@ -51,6 +44,36 @@ Code contributions to the hotfix:
 
 ### Requirements
 
+## [2.2.1] - 2024-10-01 : https://github.com/BU-ISCIII/buisciii-tools/releases/tag/2.2.1
+
+### Credits
+
+Code contributions to the new version:
+
+- [Daniel Valle](https://github.com/Daniel-VM)
+- [Sarai Varona](https://github.com/svarona)
+- [Victor Lopez](https://github.com/victor5lm)
+- [Sergio Olmos](https://github.com/OPSergio)
+
+### Template fixes and updates
+
+- Fixed path to blast database and update Emmtyper params [#339](https://github.com/BU-ISCIII/buisciii-tools/pull/339)
+- Updated sarek version (v3.4.4) in ExomeEB-ExomeTrio-WGSTrio templates [#341] (https://github.com/BU-ISCIII/buisciii-tools/pull/341)
+- Fixed IRMAs config for amended consensus [#325](https://github.com/BU-ISCIII/buisciii-tools/pull/325).
+- Improved excel_generator.py and bioinfo_doc.py email creation function, and updated sftp_user.json, setup.py, main.py and some lablogs [#344](https://github.com/BU-ISCIII/buisciii-tools/pull/344).
+
+### Modules
+
+#### Added enhancements
+
+#### Fixes
+
+#### Changed
+
+#### Removed
+
+### Requirements
+
 ## [2.2.0] - 2024-09-12 : https://github.com/BU-ISCIII/buisciii-tools/releases/tag/2.2.0
 
 ### Credits

From a104991be056528ecfad4d9828b75a2e22d15335 Mon Sep 17 00:00:00 2001
From: victor5lm <victor_lopez_5@hotmail.com>
Date: Tue, 1 Oct 2024 12:06:07 +0200
Subject: [PATCH 18/19] Updated setup.py

---
 setup.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/setup.py b/setup.py
index efa93a59..50fdff3d 100755
--- a/setup.py
+++ b/setup.py
@@ -2,7 +2,7 @@
 
 from setuptools import setup, find_packages
 
-version = "2.2.0"
+version = "2.2.1"
 
 with open("README.md") as f:
     readme = f.read()

From 96a7db8132b75f68e0f311fbe9a9f3139058cf26 Mon Sep 17 00:00:00 2001
From: victor5lm <victor_lopez_5@hotmail.com>
Date: Tue, 1 Oct 2024 12:06:22 +0200
Subject: [PATCH 19/19] Updated __main__.py

---
 bu_isciii/__main__.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/bu_isciii/__main__.py b/bu_isciii/__main__.py
index 3933a027..1aebd780 100755
--- a/bu_isciii/__main__.py
+++ b/bu_isciii/__main__.py
@@ -57,7 +57,7 @@ def run_bu_isciii():
     )
 
     # stderr.print("[green]                                          `._,._,'\n", highlight=False)
-    __version__ = "2.2.0"
+    __version__ = "2.2.1"
     stderr.print(
         "[grey39]    BU-ISCIII-tools version {}".format(__version__), highlight=False
     )