diff --git a/Start_RQC.sh b/Start_RQC.sh
index 32d3fa6aa29af0e42d9696c05de51b67d3e50ee7..0682d5d4c36c6644c34782f1adaba01028d25caa 100755
--- a/Start_RQC.sh
+++ b/Start_RQC.sh
@@ -1,14 +1,15 @@
#!/bin/bash
-rqc_version="v.2022.11"
+snakemake_base_version="v.2023.02"
+rqc_version="v.2023.03"
###I###R###D######U###2###3###3#######T###R###A###N###S###V###I###H###M###I####
# Name ___________________ Start_RQC.sh
-# Version ________________ v.2022.11
+# Version ________________ v.2023.03
# Author _________________ Nicolas Fernandez
# Affiliation ____________ IRD_U233_TransVIHMI
# Aim ____________________ Bash script running quality_control.smk snakefile
# Date ___________________ 2021.10.12
-# Latest modifications ___ 2022.11.18
+# Latest modifications ___ 2023.03.01
# Use ____________________ bash Start_RQC.sh
###############################################################################
@@ -32,7 +33,7 @@ ${blue}Author${nc} _________________ Nicolas Fernandez
${blue}Affiliation${nc} ____________ IRD_U233_TransVIHMI
${blue}Aim${nc} ____________________ Bash script for ${red}R${nc}eads ${red}Q${nc}quality ${red}C${nc}ontrol
${blue}Date${nc} ___________________ 2021.10.12
-${blue}Latest modifications${nc} ___ 2022.11.18
+${blue}Latest modifications${nc} ___ 2023.03.01
${blue}Run${nc} ____________________ bash Start_RQC.sh
"
@@ -106,22 +107,29 @@ ${green}#####${nc} ${red}SETTINGS${nc} ${green}#####${nc}
${green}--------------------${nc}
"
-workdir=$(cd "$(dirname "${BASH_SOURCE[0]}" )" && pwd) # Get working directory
-fastq=$(expr $(ls -l ${workdir}/resources/reads/*.fastq.gz | wc -l)) # Get fastq.gz files count
-samples=$(expr ${fastq} \/ 2) # {fastq.gz count} / 2 = samples count (paired-end)
-conda_version=$(conda --version | sed "s/conda //") # Get conda version
-snakemake_version=$(grep -o -E "snakemake_version: '.+'" ${workdir}/config/config.yaml | \
- sed "s/snakemake_version: //" | sed "s/'//g") # Get snakemake version
-conda_frontend=$(grep -o -E "conda_frontend: '.+'" ${workdir}/config/config.yaml | \
- sed "s/conda_frontend: //" | sed "s/'//g") # Get conda frontend
-max_threads=$(grep -o -E "cpus: [0-9]+" ${workdir}/config/config.yaml | sed "s/cpus: //") # Get user config for max threads
-max_memory=$(grep -o -E "ram: [0-9]+" ${workdir}/config/config.yaml | sed "s/ram: //") # Get user config for max memory
-memory_per_job=$(expr ${max_memory} \/ ${max_threads}) # Calcul maximum memory usage per job
-mapper=$(grep -o -E "mapper: '.+'" ${workdir}/config/config.yaml | \
- sed "s/mapper: //" | sed "s/'//g") # Get user config mapper
-subset=$(grep -o -E "subset: [0-9]+" ${workdir}/config/config.yaml | sed "s/subset: //") # Get user config subset
-time_stamp_start=$(date +"%Y-%m-%d %H:%M") # Get analyzes starting time
-SECONDS=0 # Initialize SECONDS counter
+workdir=$(cd "$(dirname "${BASH_SOURCE[0]}" )" && pwd) # Get working directory
+config_file="${workdir}/configuration/config.yaml" # Get configuration file
+fastq=$(expr $(ls -l ${workdir}/resources/reads/*.fastq.gz | wc -l)) # Get fastq.gz files count
+
+if [[ "${fastq}" == "0" ]] # Start GeVarLi with at least 1 sample
+then
+ echo -e "${red}¡${nc} No fastq file detected in ${ylo}resources/reads/${nc} ${red}!${nc}
+${red}SARS-CoV-2${nc} ${ylo}resources/data_test/${nc} fastq will be used as sample example
+"
+ cp ${workdir}/resources/data_test/*.fastq.gz ${workdir}/resources/reads/ # use data_test/*.fastq.gz
+fi
+
+samples=$(expr ${fastq} \/ 2) # {fastq.gz count} / 2 = samples count (paired-end)
+conda_version=$(conda --version | sed "s/conda //") # Get conda version
+snakemake_version=$(grep -o -E "snakemake_version: '.+'" ${config_file} | sed "s/snakemake_version: //" | sed "s/'//g") # Get snakemake version
+conda_frontend=$(grep -o -E "frontend: '.+'" ${config_file} | sed "s/frontend: //" | sed "s/'//g") # Get conda frontend
+max_threads=$(grep -o -E "cpus: [0-9]+" ${config_file} | sed "s/cpus: //") # Get user config for max threads
+max_memory=$(grep -o -E "ram: [0-9]+" ${config_file} | sed "s/ram: //") # Get user config for max memory
+memory_per_job=$(expr ${max_memory} \/ ${max_threads}) # Calcul maximum memory usage per job
+aligner=$(grep -o -E "aligner: '.+'" ${config_file} | sed "s/aligner: //" | sed "s/'//g") # Get user config aligner
+time_stamp_start=$(date +"%Y-%m-%d %H:%M") # Get analyzes starting time
+time_stamp_archive=$(date +"%Y-%m-%d_%Hh%M") # Get analyzes time to archive (wo space)
+SECONDS=0 # Initialize SECONDS counter
# Print some analyzes settings
echo -e "
@@ -136,38 +144,41 @@ ${blue}max Threads${nc} ____________ ${red}${max_threads}${nc} of ${ylo}${logica
${blue}max Memory${nc} _____________ ${red}${max_memory}${nc} of ${ylo}${ram_gb}${nc} Gb available
${blue}job Memory${nc} _____________ ${red}${memory_per_job}${nc} Gb per job
-${blue}Mapper${nc} _________________ ${ylo}${mapper}${nc}
-${blue}Subet${nc} __________________ ${ylo}${subset}${nc} reads
+${blue}Aligner${nc} ________________ ${ylo}${aligner}${nc}
${blue}Start time${nc} _____________ ${time_stamp_start}
"
###############################################################################
-###### RQC Base Conda Environment Installation ######
+###### Snakemake Installation ######
echo -e "
${green}------------------------------------------------------------------------${nc}
-${green}#####${nc} ${red}RQC-BASE CONDA ENVIRONMENT INSTALLATION${nc} ${green}#####${nc}
-${green}---------------------------------------------------${nc}
+${green}#####${nc} ${red}SNAKEMAKE-BASE INSTALLATION${nc} ${green}#####${nc}
+${green}---------------------------------------${nc}
"
-# Test if 'rqc-base' environment exist
-if [[ $(conda info --envs | grep -o -E "^rqc-base_${rqc_version}") ]]
+# Test if latest 'snakemake-base' environment exist
+if [[ $(conda info --envs | grep -o -E "^snakemake-base_${snakemake_base_version}") ]]
then
- echo -e "
-Conda environment ${ylo}rqc-base_${rqc_version}${nc} it's already created
+ echo -e "
+Conda environment ${ylo}snakemake-base_${snakemake_base_version}${nc} it's already created!
"
else
- echo -e "
-Conda environment ${ylo}rqc-base_${rqc_version}${nc} will be now created
+ echo -e "
+Conda environment ${red}snakemake-base${nc} ${ylo}${snakemake_base_version}${nc} will be now created, with:
+
+# ${red}Mamba${nc} ver. ${ylo}1.0.0${nc} (to create snakemake-conda's environments faster)
+# ${red}Snakemake${nc} ver. ${ylo}7.18.1${nc} (to run GeVarLi)
+# ${red}Rename${nc} ver. ${ylo}1.601${nc} (to rename fastq files)
+# ${red}Graphviz${nc} ver. ${ylo}6.0.1${nc} (to dot snakemake DAG)
"
- # Create a 'rqc-base' environment, with :
- # Mamba ver. 1.0.0 (to create snakemake-conda's environments faster)
- # Snakemake ver. 7.18.1 (to run RQC)
- # Rename ver. 1.601 (to rename fastq files)
- # Graphviz ver. 6.0.1 (to dot snakemake DAG)
- conda env create -f ${workdir}/workflow/envs/${os}/rqc-base_${rqc_version}.yaml
+ conda env create -f ${workdir}/workflow/environments/${os}/snakemake-base_${snakemake_base_version}.yaml
fi
+# Remove old 'gevarli-base' environment
+conda env remove --name rqc-base_v.2022.11
+
+
###############################################################################
###### Conda Env. Activation ######
echo -e "
@@ -176,10 +187,12 @@ ${green}#####${nc} ${red}CONDA ACTIVATION${nc} ${green}#####${nc}
${green}----------------------------${nc}
"
+echo -e "conda activate ${red}snakemake-base${nc} ${ylo}${snakemake_base_version}${nc}"
+
# intern shell source conda
source ~/miniconda3/etc/profile.d/conda.sh 2> /dev/null # local user
source /usr/local/miniconda3/etc/profile.d/conda.sh 2> /dev/null # HPC server
-conda activate rqc-base_${rqc_version}
+conda activate snakemake-base_${snakemake_base_version}
###############################################################################
###### Rename samples ######
@@ -189,12 +202,18 @@ ${green}#####${nc} ${red}RENAME FASTQ FILES${nc} ${green}#####${nc}
${green}------------------------------${nc}
"
-# Rename fastq files to remove "_001" Illumina pattern.
-## De/comment (#) if you want keep Illumina barcode-ID and/or Illumina line-ID
-#rename "s/_S\d+_/_/" ${workdir}/resources/reads/*.fastq.gz 2> /dev/null # Remove barcode-ID like {_S001_}
-#rename "s/_L\d+_/_/" ${workdir}/resources/reads/*.fastq.gz 2> /dev/null # Remove line-ID ID like {_L001_}
+# Rename fastq files to remove "_001" Illumina pattern (mandatory)
+## De/comment line (#) if you want keep Illumina barcode-ID and/or Illumina line-ID
+echo -e "Removing ${red}'_S'${nc} index tag ID"
+rename "s/_S\d+_/_/" ${workdir}/resources/reads/*.fastq.gz 2> /dev/null # Remove barcode-ID like {_S001_}
+echo -e "Removing ${red}'_L'${nc} line tag ID"
+rename "s/_L\d+_/_/" ${workdir}/resources/reads/*.fastq.gz 2> /dev/null # Remove line-ID ID like {_L001_}
+echo -e "Removing ${red}'_001'${nc} illumina tag ID"
rename "s/_001.fastq.gz/.fastq.gz/" ${workdir}/resources/reads/*.fastq.gz 2> /dev/null # Remove end-name ID like {_001}.fastq.gz
+echo -e "
+If you want to keep Illumina ${blue}barcode-ID${nc} and/or Illumina ${blue}line-ID${nc}, please edit ${ylo}Start_GeVarLi.sh${nc} script (l.199).
+"
###############################################################################
###### Call snakemake pipelines ######
@@ -220,7 +239,7 @@ for snakefile in ${snakefile_list} ; do
echo -e "${blue}-- ${snakefile} --${nc}" ;
snakemake \
--directory ${workdir}/ \
- --snakefile ${workdir}/workflow/rules/${snakefile}.smk \
+ --snakefile ${workdir}/workflow/snakefiles/${snakefile}.smk \
--config os=${os} \
--rerun-incomplete \
--unlock ;
@@ -241,7 +260,7 @@ for snakefile in ${snakefile_list} ; do
echo -e "${blue}-- ${snakefile} --${nc}" ;
snakemake \
--directory ${workdir}/ \
- --snakefile ${workdir}/workflow/rules/${snakefile}.smk \
+ --snakefile ${workdir}/workflow/snakefiles/${snakefile}.smk \
--cores ${max_threads} \
--config os=${os} \
--rerun-incomplete \
@@ -266,7 +285,7 @@ for snakefile in ${snakefile_list} ; do
echo -e "${blue}-- ${snakefile} --${nc}" ;
snakemake \
--directory ${workdir}/ \
- --snakefile ${workdir}/workflow/rules/${snakefile}.smk \
+ --snakefile ${workdir}/workflow/snakefiles/${snakefile}.smk \
--cores ${max_threads} \
--config os=${os} \
--rerun-incomplete \
@@ -295,7 +314,7 @@ for snakefile in ${snakefile_list} ; do
echo -e "${blue}-- ${snakefile} --${nc}" ;
snakemake \
--directory ${workdir}/ \
- --snakefile ${workdir}/workflow/rules/${snakefile}.smk \
+ --snakefile ${workdir}/workflow/snakefiles/${snakefile}.smk \
--cores ${max_threads}\
--config os=${os} \
--rerun-incomplete \
@@ -326,7 +345,7 @@ for snakefile in ${snakefile_list} ; do
echo -e "${blue}-- ${snakefile} --${nc}" ;
snakemake \
--directory ${workdir}/ \
- --snakefile ${workdir}/workflow/rules/${snakefile}.smk \
+ --snakefile ${workdir}/workflow/snakefiles/${snakefile}.smk \
--cores ${max_threads} \
--max-threads ${max_threads} \
--config os=${os} \
@@ -362,7 +381,7 @@ for snakefile in ${snakefile_list} ; do
for extention in ${extention_list} ; do
snakemake \
--directory ${workdir}/ \
- --snakefile ${workdir}/workflow/rules/${snakefile}.smk \
+ --snakefile ${workdir}/workflow/snakefiles/${snakefile}.smk \
--${graph} \
| dot -T${extention} \
2> /dev/null \
@@ -374,7 +393,7 @@ done
for snakefile in ${snakefile_list} ; do
snakemake \
--directory ${workdir} \
- --snakefile ${workdir}/workflow/rules/${snakefile}.smk \
+ --snakefile ${workdir}/workflow/snakefiles/${snakefile}.smk \
--summary > ${workdir}/results/10_Reports/files-summaries/${snakefile}_files-summary.txt \
2> /dev/null ;
done
@@ -420,7 +439,7 @@ Author _________________ Nicolas Fernandez
Affiliation ____________ IRD_U233_TransVIHMI
Aim ____________________ Bash script for RQC
Date ___________________ 2021.10.12
-Latest modifications ___ 2022.11.18
+Latest modifications ___ 2023.03.01
Run ____________________ bash Start_RQC.sh
Operating System _______ ${os}
@@ -456,8 +475,9 @@ cd ${workdir}/results/
tar -zcf 10_Reports_archive.tar.gz 10_Reports
# Gzip results directory
+mkdir -p ${workdir}/archives/ 2> /dev/null
cd ${workdir}/
-tar -zcf Results_${time_stamp_archive}_${reference}_${aligner}-${min_cov}X_${samples}sp_archive.tar.gz results
+tar -zcf archives/Results_${time_stamp_archive}_${samples}sp_archive.tar.gz results/
echo -e "
${green}------------------------------------------------------------------------${nc}
diff --git a/config/config.yaml b/configuration/config.yaml
similarity index 59%
rename from config/config.yaml
rename to configuration/config.yaml
index 3b57aeb3e5d9648c0221ec08c721d791f4e0305f..706fa49849760dab4281bf92dccca83641fca03d 100644
--- a/config/config.yaml
+++ b/configuration/config.yaml
@@ -1,12 +1,12 @@
---
###I###R###D######U###2###3###3#######T###R###A###N###S###V###I###H###M###I####
# Name ___________________ config.yaml
-# Version ________________ v.2022.11
+# Version ________________ v.2023.03
# Author _________________ Nicolas Fernandez
# Affiliation ____________ IRD_U233_TransVIHMI
# Aim ____________________ Configuration yaml file for quality_control.smk snakefile
# Date ___________________ 2021.10.12
-# Latest modifications ___ 2022.11.18
+# Latest modifications ___ 2023.03.01
# Use ____________________ Edit default settings
###############################################################################
@@ -21,41 +21,15 @@ resources:
## '.' # Local (i.e. GeVarLi root directory)
## '/scratch' # HPC (set it to match your HPC usage)
-conda_frontend: 'mamba' # Conda frontend (conda or mamba)
-
-# conda_version: '22.9.0' # Conda version (upgrade from "4.12.0")
-# mamba_version: '1.0.0' # Mamba version (faster than conda)
-# snakemake_version: '7.18.1' # Snakemake version (upgrade from "6.12.3")
-# rename_version: '1.601' # Rename version (to rename fastq files)
-# graphviz_version: '6.0.1' # GraphViz version (to do dot snakemake DAG)
-
-
-### ENVIRONNEMENTS -----------------------------------------------------------------------------------
-conda:
- osx: # Conda OSX environement yaml files:
- bowtie2: '../envs/osx/bowtie2_v.2.4.5.yaml' # Bowtie2 ver. 2.4.5
- bwa: '../envs/osx/bwa_v.0.7.17.yaml' # BWA ver. 0.7.17
- fastq-screen: '../envs/osx/fastq-screen_v.0.15.2.yaml' # Fastq-Screen ver. 0.15.2
- fastqc: '../envs/osx/fastqc_v.0.11.9.yaml' # FastQC ver. 0.11.9
- rqc-base: '../envs/osx/rqc-base_v.2022.11' # RQC-Base ver. 2022.11
- multiqc: '../envs/osx/multiqc_v.1.12.yaml' # MultiQC ver. 1.12
- linux: # Conda Linux environement yaml files:
- bowtie2: '../envs/linux/bowtie2_v.2.4.5.yaml' # Bowtie2 ver. 2.4.5
- bwa: '../envs/linux/bwa_v.0.7.17.yaml' # BWA ver. 0.7.17
- fastq-screen: '../envs/linux/fastq-screen_v.0.15.2.yaml' # Fastq-Screen ver. 0.15.2
- fastqc: '../envs/linux/fastqc_v.0.11.9.yaml' # FastQC ver. 0.11.9
- rqc-base: '../envs/linux/rqc-base_v.2022.11' # RQC-Base ver. 2022.11
- multiqc: '../envs/linux/multiqc_v.1.12.yaml' # MultiQC ver. 1.12
-
### FASTQSCREEN --------------------------------------------------------------------------------------
fastq-screen:
- config: 'config/fastq-screen_bwa.conf' # Path to the fastq-screen configuration file
+ config: 'configuration/fastq-screen_bwa.conf' # Path to the fastq-screen configuration file
# Available options:
- #- 'config/fastq-screen_bwa.conf' # Default fastq-screen configuration file for bwa users
- #- 'config/fastq-screen_bowtie2.conf' # Default fastq-screen configuration file for bowtie2 users
- #- 'config/fastq-screen_custom.conf' # Your cutom fastq-screen configuration file
+ #- 'configuration/fastq-screen_bwa.conf' # Default fastq-screen configuration file for bwa users
+ #- 'configuration/fastq-screen_bowtie2.conf' # Default fastq-screen configuration file for bowtie2 users
+ #- 'configuration/fastq-screen_custom.conf' # Your cutom fastq-screen configuration file
subset: 10000 # Don't use whole sequences, but a subset reads (default: "1000") [INT] (0=all)
- mapper: 'bwa' # Mapper used by fastq-screen for alignments (default "bwa")
+ aligner: 'bwa' # Mapper used by fastq-screen for alignments (default "bwa")
# Available options:
#- 'bwa' # Burrows-Wheeler Aligner (default, somme small genomes indexes provided, see "fastq-screen_bwa.conf")
#- 'bowtie2' # Bowtie2 (somme small genomes indexes provided, see "fastq-screen_bowtie2.conf")
@@ -84,6 +58,36 @@ bowtie2:
#- '' # (default)
#- '--large-index' # Force generated index to be "large", even if reference has fewer than 4 billion nucleotides
+### ENVIRONNEMENTS -----------------------------------------------------------------------------------
+
+# conda_version: '22.9.0' # Conda version (upgrade from "4.12.0")
+# mamba_version: '1.0.0' # Mamba version (faster than conda)
+# snakemake_version: '7.18.1' # Snakemake version (upgrade from "6.12.3")
+# rename_version: '1.601' # Rename version (to rename fastq files)
+# graphviz_version: '6.0.1' # GraphViz version (to do dot snakemake DAG)
+
+conda:
+ frontend: 'mamba' # Conda frontend (conda or mamba)
+ # Available options:
+ #- 'mamba' # mamba (default)
+ #- 'conda' # conda
+ osx: # Conda OSX environement yaml files:
+ snakemake-base: '../environments/osx/snakemake-base_v.2023.02.yaml' # Snakemake-Base ver. 2023.02
+ #rqc-tools: '../environments/osx/rqc-tools_v.2023.03' # RQC-Tools ver. 2023.03
+ bowtie2: '../environments/osx/bowtie2_v.2.4.5.yaml' # Bowtie2 ver. 2.4.5
+ bwa: '../environments/osx/bwa_v.0.7.17.yaml' # BWA ver. 0.7.17
+ fastq-screen: '../environments/osx/fastq-screen_v.0.15.2.yaml' # Fastq-Screen ver. 0.15.2
+ fastqc: '../environments/osx/fastqc_v.0.11.9.yaml' # FastQC ver. 0.11.9
+ multiqc: '../environments/osx/multiqc_v.1.12.yaml' # MultiQC ver. 1.12
+ linux: # Conda Linux environement yaml files:
+ snakemake-base: '../environments/linux/snakemake-base_v.2023.02.yaml' # Snakemake-Base ver. 2023.02
+ #rqc-tools: '../environments/linux/rqc-tools_v.2023.03' # RQC-Tools ver. 2023.03
+ bowtie2: '../environments/linux/bowtie2_v.2.4.5.yaml' # Bowtie2 ver. 2.4.5
+ bwa: '../environments/linux/bwa_v.0.7.17.yaml' # BWA ver. 0.7.17
+ fastq-screen: '../environments/linux/fastq-screen_v.0.15.2.yaml' # Fastq-Screen ver. 0.15.2
+ fastqc: '../environments/linux/fastqc_v.0.11.9.yaml' # FastQC ver. 0.11.9
+ multiqc: '../environments/linux/multiqc_v.1.12.yaml' # MultiQC ver. 1.12
+
### OPERATING-SYSTEM ---------------------------------------------------------------------------------
os: 'osx' # Operating System (default: "osx")
# Available options:
diff --git a/config/fastq-screen_bowtie2.conf b/configuration/fastq-screen_bowtie2.conf
similarity index 100%
rename from config/fastq-screen_bowtie2.conf
rename to configuration/fastq-screen_bowtie2.conf
diff --git a/config/fastq-screen_bwa.conf b/configuration/fastq-screen_bwa.conf
similarity index 78%
rename from config/fastq-screen_bwa.conf
rename to configuration/fastq-screen_bwa.conf
index ecdbcac5b97dc4738a3e954023ef5da275b1eaa1..05134f52c6a478d31176331b8f7038ecc3b84009 100644
--- a/config/fastq-screen_bwa.conf
+++ b/configuration/fastq-screen_bwa.conf
@@ -26,13 +26,13 @@ DATABASE Vectors resources/indexes/bwa/UniVec_wo_phiX_and_kanamycin
#### Putative Hosts (Large genomes) -----
### Gorilla g4
-#DATABASE Gorilla resources/indexes/bwa/Gorilla-gorilla_g4
+DATABASE Gorilla resources/indexes/bwa/Gorilla-gorilla_g4
### Chimpanzee t3
-#DATABASE Chimpanzee resources/indexes/bwa/Pan_troglodytes_t3
+DATABASE Chimpanzee resources/indexes/bwa/Pan_troglodytes_t3
### Human - Homo-sapiens_h38_NC-000001.11
-#DATABASE Human resources/indexes/bwa/Homo-sapiens_h38_NC000001-11
+DATABASE Human resources/indexes/bwa/Homo-sapiens_h38_NC000001-11
### Bat v1
-#DATABASE Bat resources/indexes/bwa/Pteropus-vampyrus_v1
+DATABASE Bat resources/indexes/bwa/Pteropus-vampyrus_v1
#### Main Viruses (Small genomes) -----
@@ -52,18 +52,18 @@ DATABASE HIV resources/indexes/bwa/HIV-1_HXB2_K03455-1
### E. coli (Bacteria) - QC_Echerichia-coli_CP060121.1
DATABASE Ecoli resources/indexes/bwa/Echerichia-coli_CP060121-1
### S. cerevisiae (Yeast) - sequence
-#DATABASE Scerevisiae resources/indexes/bwa/Saccharomyces-cerevisiae
+DATABASE Scerevisiae resources/indexes/bwa/Saccharomyces-cerevisiae
### C. elegans (Nematode) - sequence
-#DATABASE Celegans resources/indexes/bwa/Caenorhabditis-elegans
+DATABASE Celegans resources/indexes/bwa/Caenorhabditis-elegans
### D. melanogaster (Fruit fly) - sequence
-#DATABASE Dmelanogaster resources/indexes/bwa/Drosophila-melanogaster
+DATABASE Dmelanogaster resources/indexes/bwa/Drosophila-melanogaster
### D. rerio (Zebrafish) - sequence
-#DATABASE Drerio resources/indexes/bwa/Danio-rerio
+DATABASE Drerio resources/indexes/bwa/Danio-rerio
### X. laevis (Xenope) - sequence
-#DATABASE Xlaevis resources/indexes/bwa/Xenopus-laevis
+DATABASE Xlaevis resources/indexes/bwa/Xenopus-laevis
### G. gallus - sequence
-#DATABASE Ggallus ressources/indexes/bwa/Gallus-gallus
+DATABASE Ggallus ressources/indexes/bwa/Gallus-gallus
### Mouse m39
-#DATABASE Mouse resources/indexes/bwa/Mus-musculus_m39
+DATABASE Mouse resources/indexes/bwa/Mus-musculus_m39
### Arabidopsis t10 (Plant) - sequence from NCBI (ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/001/735/GCF_000001735.3_TAIR10/GCF_000001735.3_TAIR10_genomic.fna.gz)
-#DATABASE Arabidopsis resources/indexes/bwa/Arabidopsis-thaliana_t10_NC003070-9
+DATABASE Arabidopsis resources/indexes/bwa/Arabidopsis-thaliana_t10_NC003070-9
diff --git a/resources/data_test/.gitkeep b/resources/data_test/.gitkeep
new file mode 100644
index 0000000000000000000000000000000000000000..f13c79cb973f7529714edbaff5ce25450f3cf7ff
--- /dev/null
+++ b/resources/data_test/.gitkeep
@@ -0,0 +1 @@
+Git: keep this non empty file!
\ No newline at end of file
diff --git a/resources/data_test/SARS-CoV-2_Omicron-BA-1-1_Covid-Seq-Lib-on-MiSeq_250000-reads_R1.fastq.gz b/resources/data_test/SARS-CoV-2_Omicron-BA-1-1_Covid-Seq-Lib-on-MiSeq_250000-reads_R1.fastq.gz
new file mode 100644
index 0000000000000000000000000000000000000000..efda6523124e705811d70e9ee78e11f542bdd582
Binary files /dev/null and b/resources/data_test/SARS-CoV-2_Omicron-BA-1-1_Covid-Seq-Lib-on-MiSeq_250000-reads_R1.fastq.gz differ
diff --git a/resources/data_test/SARS-CoV-2_Omicron-BA-1-1_Covid-Seq-Lib-on-MiSeq_250000-reads_R2.fastq.gz b/resources/data_test/SARS-CoV-2_Omicron-BA-1-1_Covid-Seq-Lib-on-MiSeq_250000-reads_R2.fastq.gz
new file mode 100644
index 0000000000000000000000000000000000000000..852cc3f5735a9b9c2628b78f12b8e1f2719d7d6f
Binary files /dev/null and b/resources/data_test/SARS-CoV-2_Omicron-BA-1-1_Covid-Seq-Lib-on-MiSeq_250000-reads_R2.fastq.gz differ
diff --git a/workflow/envs/linux/bowtie2_v.2.4.5.yaml b/workflow/environments/linux/bowtie2_v.2.4.5.yaml
similarity index 100%
rename from workflow/envs/linux/bowtie2_v.2.4.5.yaml
rename to workflow/environments/linux/bowtie2_v.2.4.5.yaml
diff --git a/workflow/envs/linux/bwa_v.0.7.17.yaml b/workflow/environments/linux/bwa_v.0.7.17.yaml
similarity index 100%
rename from workflow/envs/linux/bwa_v.0.7.17.yaml
rename to workflow/environments/linux/bwa_v.0.7.17.yaml
diff --git a/workflow/envs/linux/fastq-screen_v.0.15.2.yaml b/workflow/environments/linux/fastq-screen_v.0.15.2.yaml
similarity index 100%
rename from workflow/envs/linux/fastq-screen_v.0.15.2.yaml
rename to workflow/environments/linux/fastq-screen_v.0.15.2.yaml
diff --git a/workflow/envs/linux/fastqc_v.0.11.9.yaml b/workflow/environments/linux/fastqc_v.0.11.9.yaml
similarity index 100%
rename from workflow/envs/linux/fastqc_v.0.11.9.yaml
rename to workflow/environments/linux/fastqc_v.0.11.9.yaml
diff --git a/workflow/envs/linux/multiqc_v.1.12.yaml b/workflow/environments/linux/multiqc_v.1.12.yaml
similarity index 100%
rename from workflow/envs/linux/multiqc_v.1.12.yaml
rename to workflow/environments/linux/multiqc_v.1.12.yaml
diff --git a/workflow/envs/linux/rqc-base_v.2022.11.yaml b/workflow/environments/linux/snakemake-base_v.2023.02.yaml
similarity index 99%
rename from workflow/envs/linux/rqc-base_v.2022.11.yaml
rename to workflow/environments/linux/snakemake-base_v.2023.02.yaml
index 4fa951d8536984a62a3dfc887099b1b0de18d22b..1fdbaa7f5f6bef1bc50ec3873c97ff980f8bcc96 100644
--- a/workflow/envs/linux/rqc-base_v.2022.11.yaml
+++ b/workflow/environments/linux/snakemake-base_v.2023.02.yaml
@@ -1,4 +1,4 @@
-name: rqc-base_v.2022.11
+name: snakemake-base_v.2023.02
channels:
- bioconda
- conda-forge
diff --git a/workflow/envs/osx/bowtie2_v.2.4.5.yaml b/workflow/environments/osx/bowtie2_v.2.4.5.yaml
similarity index 100%
rename from workflow/envs/osx/bowtie2_v.2.4.5.yaml
rename to workflow/environments/osx/bowtie2_v.2.4.5.yaml
diff --git a/workflow/envs/osx/bwa_v.0.7.17.yaml b/workflow/environments/osx/bwa_v.0.7.17.yaml
similarity index 100%
rename from workflow/envs/osx/bwa_v.0.7.17.yaml
rename to workflow/environments/osx/bwa_v.0.7.17.yaml
diff --git a/workflow/envs/osx/fastq-screen_v.0.15.2.yaml b/workflow/environments/osx/fastq-screen_v.0.15.2.yaml
similarity index 100%
rename from workflow/envs/osx/fastq-screen_v.0.15.2.yaml
rename to workflow/environments/osx/fastq-screen_v.0.15.2.yaml
diff --git a/workflow/envs/osx/fastqc_v.0.11.9.yaml b/workflow/environments/osx/fastqc_v.0.11.9.yaml
similarity index 100%
rename from workflow/envs/osx/fastqc_v.0.11.9.yaml
rename to workflow/environments/osx/fastqc_v.0.11.9.yaml
diff --git a/workflow/envs/osx/multiqc_v.1.12.yaml b/workflow/environments/osx/multiqc_v.1.12.yaml
similarity index 100%
rename from workflow/envs/osx/multiqc_v.1.12.yaml
rename to workflow/environments/osx/multiqc_v.1.12.yaml
diff --git a/workflow/envs/osx/rqc-base_v.2022.11.yaml b/workflow/environments/osx/snakemake-base_v.2023.02.yaml
similarity index 99%
rename from workflow/envs/osx/rqc-base_v.2022.11.yaml
rename to workflow/environments/osx/snakemake-base_v.2023.02.yaml
index 876cff05f607863c51bf12cf4eef6f9695f84cae..fdb030f2764c252707b1b8a35c2dec6e2af21926 100644
--- a/workflow/envs/osx/rqc-base_v.2022.11.yaml
+++ b/workflow/environments/osx/snakemake-base_v.2023.02.yaml
@@ -1,4 +1,4 @@
-name: rqc-base_v.2022.11
+name: snakemake-base_v.2023.02
channels:
- bioconda
- conda-forge
diff --git a/workflow/rules/indexing_genomes.smk b/workflow/snakefiles/indexing_genomes.smk
similarity index 98%
rename from workflow/rules/indexing_genomes.smk
rename to workflow/snakefiles/indexing_genomes.smk
index d496a05d5725846a2918c78e905a08337f34a263..33e428bdeb4dabd7fa733d1bb7fb60680b88a2e3 100755
--- a/workflow/rules/indexing_genomes.smk
+++ b/workflow/snakefiles/indexing_genomes.smk
@@ -4,13 +4,13 @@
# Affiliation ____________ IRD_U233_TransVIHMI
# Aim ____________________ Snakefile with indexing genomes rules
# Date ___________________ 2022.09.28
-# Latest modifications ___ 2022.11.18
+# Latest modifications ___ 2023.03.01
# Use ____________________ snakemake -s indexing_genomes.smk --use-conda
###############################################################################
###### CONFIGURATION ######
-configfile: "config/config.yaml"
+configfile: "configuration/config.yaml"
###############################################################################
###### FUNCTIONS ######
diff --git a/workflow/rules/quality_control.smk b/workflow/snakefiles/quality_control.smk
similarity index 93%
rename from workflow/rules/quality_control.smk
rename to workflow/snakefiles/quality_control.smk
index f65e0cc26d9ee81d16868b880d2b586b95fdd294..91d283e2905037938b667d3b5d0091436c5eea11 100755
--- a/workflow/rules/quality_control.smk
+++ b/workflow/snakefiles/quality_control.smk
@@ -4,13 +4,13 @@
# Affiliation ____________ IRD_U233_TransVIHMI
# Aim ____________________ Snakefile with quality control rules
# Date ___________________ 2021.09.28
-# Latest modifications ___ 2022.11.18
+# Latest modifications ___ 2023.03.01
# Run ____________________ snakemake -s quality_control.smk --use-conda
###############################################################################
###### CONFIGURATION ######
-configfile: "config/config.yaml"
+configfile: "configuration/config.yaml"
###############################################################################
###### FUNCTIONS ######
@@ -38,9 +38,9 @@ MULTIQC = config["conda"][OS]["multiqc"] # MultiQC
###############################################################################
###### PARAMETERS ######
-CONFIG = config["fastq-screen"]["config"] # Fastq-screen --conf
-MAPPER = config["fastq-screen"]["mapper"] # Fastq-screen --aligner
-SUBSET = config["fastq-screen"]["subset"] # Fastq-screen --subset
+CONFIG = config["fastq-screen"]["config"] # Fastq-screen --conf
+ALIGNER = config["fastq-screen"]["aligner"] # Fastq-screen --aligner
+SUBSET = config["fastq-screen"]["subset"] # Fastq-screen --subset
###############################################################################
@@ -86,7 +86,7 @@ rule fastqscreen_contamination_checking:
cpus = CPUS
params:
config = CONFIG,
- mapper = MAPPER,
+ aligner = ALIGNER,
subset = SUBSET
input:
fastq = "resources/reads/"
@@ -99,7 +99,7 @@ rule fastqscreen_contamination_checking:
"-q " # --quiet: Only show log warning
"--threads {resources.cpus} " # --threads: Specifies across how many threads bowtie will be allowed to run
"--conf {params.config} " # path to configuration file
- "--aligner {params.mapper} " # -a: choose aligner 'bowtie', 'bowtie2', 'bwa'
+ "--aligner {params.aligner} " # -a: choose aligner 'bowtie', 'bowtie2', 'bwa'
"--subset {params.subset} " # Don't use the whole sequence file, but create a subset of specified size
"--outdir {output.fastqscreen} " # Output directory
"{input.fastq}/*.fastq.gz " # Input file.fastq