Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Lablog_viralrecon is now able to download references from ncbi that don't belong to any family #310

Merged
merged 7 commits into from
Aug 16, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,7 @@ Code contributions to the new version:
- Fixed IRMA's lablog so that the sequences of the samples are not displayed several times neither in the .txt files of each influenza type nor in all_samples_completo.txt [#305](https://github.com/BU-ISCIII/buisciii-tools/pull/305)
- Modified bioinfo_doc.py so that new lines in the delivery message are applied in the email [#307](https://github.com/BU-ISCIII/buisciii-tools/pull/307)
- Added several improvements in lablog_viralrecon (created log files, modified check_references function behaviour, enabled config files regeneration) [#306](https://github.com/BU-ISCIII/buisciii-tools/pull/306)
- Fixed bug when lablog_viralrecon tries to download references that don't belong to any family. [#310](https://github.com/BU-ISCIII/buisciii-tools/pull/310)

### Modules

Expand Down
46 changes: 35 additions & 11 deletions bu_isciii/templates/viralrecon/ANALYSIS/lablog_viralrecon
Original file line number Diff line number Diff line change
Expand Up @@ -182,6 +182,11 @@ check_references() {
family=$(curl -s "https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=${organism_id}" | grep -o 'TITLE="family">.*<' | awk -F 'TITLE="family">' '{print $2}' | cut -d '<' -f 1 | tr '[:upper:]' '[:lower:]')
if [ -z $family ]; then
family=$(curl -s "https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=${organism_id}" | grep -o 'ALT="family">.*<' | awk -F 'ALT="family">' '{print $2}' | cut -d '<' -f 1 | tr '[:upper:]' '[:lower:]')
if [ -z $family ]; then
family="miscellanous"
log_message "Reference $ref does not currently belong to any family. Assigned to $family."
return
fi
fi
log_message "Reference $ref belongs to $family family."
}
Expand All @@ -200,6 +205,15 @@ check_references() {
log_message "SAMtools module not loaded. Exiting..." blk_red
exit 1
fi
eval "$(micromamba shell hook --shell bash)"
micromamba activate refgenie_v0.12.1
environment=$(micromamba info | awk '/environment/ && /active/ {print $3}')
if [[ $environment == *"refgenie"* ]]; then
log_message "$environment environment succesfully activated." green
else
log_message "Refgenie environment is NOT ACTIVE. Exiting..." blk_red
exit 1
fi
if [ ! -e "/data/bi/references/refgenie/alias/${family}" ]; then # Check if directory doesn't exists
log_message "Creating new directory: /data/bi/references/refgenie/alias/${family}/ and saving file ${ref}.fasta in /data/bi/references/refgenie/alias/${family}/fasta/${ref}."
digest=$(openssl rand -hex 24)
Expand All @@ -209,8 +223,8 @@ check_references() {
log_message "File ${ref}.fasta downloaded in /data/bi/references/refgenie/data/${digest}/fasta/${ref}." green
gzip /data/bi/references/refgenie/data/${digest}/fasta/${ref}/${ref}.fasta
log_message "Building asset for ${ref}.fasta file..."
srun --partition short_idx --output ${ref}.fasta_build.log refgenie build ${family}/fasta:${ref} --files fasta=/data/bi/references/refgenie/data/${digest}/fasta/${ref}/${ref}.fasta.gz -c /data/bi/references/refgenie/genome_config.yaml -R
if [ $? -eq 0 ]; then
refgenie build ${family}/fasta:${ref} --files fasta=/data/bi/references/refgenie/data/${digest}/fasta/${ref}/${ref}.fasta.gz -c /data/bi/references/refgenie/genome_config.yaml -R > ${ref}.fasta_build.log 2>&1
if grep -q "Created" "${ref}.fasta_build.log"; then
log_message "$(grep Created ${ref}.fasta_build.log) $(grep "/data/bi/references/refgenie/alias/" ${ref}.fasta_build.log)" bold
bash /data/bi/references/refgenie/alias/ref.sh
REF_FASTA=$(awk -v ref="$ref" '$0 ~ ref && /fasta/ {print $4}' /data/bi/references/refgenie/alias/references.txt)
Expand All @@ -229,8 +243,8 @@ check_references() {
log_message "File ${ref}.fasta downloaded in /data/bi/references/refgenie/data/${digest}/fasta/${ref}." green
gzip /data/bi/references/refgenie/data/${digest}/fasta/${ref}/${ref}.fasta
log_message "Building asset for ${ref}.fasta file..."
srun --partition short_idx --output ${ref}.fasta_build.log refgenie build ${family}/fasta:${ref} --files fasta=/data/bi/references/refgenie/data/${digest}/fasta/${ref}/${ref}.fasta.gz -c /data/bi/references/refgenie/genome_config.yaml -R
if [ $? -eq 0 ]; then
refgenie build ${family}/fasta:${ref} --files fasta=/data/bi/references/refgenie/data/${digest}/fasta/${ref}/${ref}.fasta.gz -c /data/bi/references/refgenie/genome_config.yaml -R > ${ref}.fasta_build.log 2>&1
if grep -q "Created" "${ref}.fasta_build.log"; then
log_message "$(grep Created ${ref}.fasta_build.log) $(grep "/data/bi/references/refgenie/alias/" ${ref}.fasta_build.log)" bold
bash /data/bi/references/refgenie/alias/ref.sh
REF_FASTA=$(awk -v ref="$ref" '$0 ~ ref && /fasta/ {print $4}' /data/bi/references/refgenie/alias/references.txt)
Expand All @@ -250,17 +264,27 @@ check_references() {
if [ -z "$REF_GFF" ]; then
log_message "File ${ref}.gff is not yet downloaded."
if [ ! -v family ]; then obtain_family; if [ -z ${family} ]; then return; fi; fi
if [[ $environment != *"refgenie"* ]]; then
eval "$(micromamba shell hook --shell bash)"
micromamba activate refgenie_v0.12.1
environment=$(micromamba info | awk '/environment/ && /active/ {print $3}')
if [[ $environment == *"refgenie"* ]]; then
log_message "$environment environment succesfully activated." green
else
log_message "Refgenie environment is NOT ACTIVE. Exiting..." blk_red
fi
fi
if [ ! -e "/data/bi/references/refgenie/alias/${family}" ]; then # Check if directory doesn't exist
log_message "Creating new directory: /data/bi/references/refgenie/alias/${family}/ and saving file ${ref}.gff in /data/bi/references/refgenie/alias/${family}/gff/${ref}."
digest=$(openssl rand -hex 24)
refgenie alias set --aliases ${family} --digest ${digest} -f -c /data/bi/references/refgenie/genome_config.yaml
mkdir -p /data/bi/references/refgenie/data/${digest}/ensembl_rb/${ref}/
wget -q -O "/data/bi/references/refgenie/data/${digest}/ensembl_rb/${ref}/${ref}.gff" "https://www.ncbi.nlm.nih.gov/sviewer/viewer.cgi?db=nuccore&report=gff3&id=${ref}"
wget -q -O "/data/bi/references/refgenie/data/${digest}/ensembl_rb/${ref}/${family}.gff" "https://www.ncbi.nlm.nih.gov/sviewer/viewer.cgi?db=nuccore&report=gff3&id=${ref}"
if [ $? -eq 0 ]; then
log_message "File ${ref}.gff downloaded in /data/bi/references/refgenie/data/${digest}/ensembl_rb/${ref}." green
log_message "Adding asset for ${ref}.gff file..."
srun --partition short_idx --output ${ref}.gff_add.log refgenie add ${family}/gff:${ref} --path data/${digest}/ensembl_rb/${ref}/ --seek-keys '{"gff" : "'"${family}.gff"'"}' -c /data/bi/references/refgenie/genome_config.yaml
if [ $? -eq 0 ]; then
refgenie add ${family}/gff:${ref} --path data/${digest}/ensembl_rb/${ref}/ --seek-keys '{"gff" : "'"${family}.gff"'"}' -c /data/bi/references/refgenie/genome_config.yaml > ${ref}.gff_add.log 2>&1
jaimeozaez marked this conversation as resolved.
Show resolved Hide resolved
if grep -q "Created" "${ref}.gff_add.log"; then
log_message "$(grep Created ${ref}.gff_add.log) $(grep "/data/bi/references/refgenie/alias/" ${ref}.gff_add.log)" bold
bash /data/bi/references/refgenie/alias/ref.sh
REF_GFF=$(awk -v ref="$ref" '$0 ~ ref && /gff/ {print $4}' /data/bi/references/refgenie/alias/references.txt)
Expand All @@ -274,12 +298,12 @@ check_references() {
log_message "Directory /data/bi/references/refgenie/alias/${family}/ ALREADY EXISTS. Downloading ${ref}.gff."
digest=$(refgenie alias get -a ${family} -c /data/bi/references/refgenie/genome_config.yaml)
mkdir -p /data/bi/references/refgenie/data/${digest}/ensembl_rb/${ref}/
wget -q -O "/data/bi/references/refgenie/data/${digest}/ensembl_rb/${ref}/${ref}.gff" "https://www.ncbi.nlm.nih.gov/sviewer/viewer.cgi?db=nuccore&report=gff3&id=${ref}"
wget -q -O "/data/bi/references/refgenie/data/${digest}/ensembl_rb/${ref}/${family}.gff" "https://www.ncbi.nlm.nih.gov/sviewer/viewer.cgi?db=nuccore&report=gff3&id=${ref}"
if [ $? -eq 0 ]; then
log_message "File ${ref}.gff downloaded in /data/bi/references/refgenie/data/${digest}/ensembl_rb/${ref}." green
log_message "Adding asset for ${ref}.gff file..."
srun --partition short_idx --output ${ref}.gff_add.log refgenie add ${family}/gff:${ref} --path data/${digest}/ensembl_rb/${ref}/ --seek-keys '{"gff" : "'"${family}.gff"'"}' -c /data/bi/references/refgenie/genome_config.yaml
if [ $? -eq 0 ]; then
refgenie add ${family}/gff:${ref} --path data/${digest}/ensembl_rb/${ref}/ --seek-keys '{"gff" : "'"${family}.gff"'"}' -c /data/bi/references/refgenie/genome_config.yaml > ${ref}.gff_add.log 2>&1
if grep -q "Created" "${ref}.gff_add.log"; then
log_message "$(grep Created ${ref}.gff_add.log) $(grep "/data/bi/references/refgenie/alias/" ${ref}.gff_add.log)" bold
bash /data/bi/references/refgenie/alias/ref.sh
REF_GFF=$(awk -v ref="$ref" '$0 ~ ref && /gff/ {print $4}' /data/bi/references/refgenie/alias/references.txt)
Expand Down Expand Up @@ -523,4 +547,4 @@ rm percentajeNs.py
rm _02_create_run_percentage_Ns.sh
cd 00-reads; cat ../samples_id.txt | xargs -I % echo "ln -s ../../RAW/%_*R1*.fastq.gz %_R1.fastq.gz" | bash; cat ../samples_id.txt | xargs -I % echo "ln -s ../../RAW/%_*R2*.fastq.gz %_R2.fastq.gz" | bash; cd ..

log_message "Lablog_viralrecon execution has been completed. Please verify all the configurations are set up correctly." green
log_message "Lablog_viralrecon execution has been completed. Please verify all the configurations are set up correctly." bold
Loading