diff --git a/config/config.yaml b/config/config.yaml index 49b0c31d8d5b3cbe83fb9f89a31bacab69ee560c..3b57aeb3e5d9648c0221ec08c721d791f4e0305f 100644 --- a/config/config.yaml +++ b/config/config.yaml @@ -49,13 +49,17 @@ conda: ### FASTQSCREEN -------------------------------------------------------------------------------------- fastq-screen: - config: 'config/fastq-screen.conf' # Path to the fastq-screen configuration file + config: 'config/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 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") # Available options: - #- 'bwa' # Burrows-Wheeler Aligner (default, somme small genomes indexes provided, see "fastq-screen.conf") - #- 'bowtie' # Bowtie (indexes not provided for fastq-screen) - #- 'bowtie2' # Bowtie2 (indexes not provided for fastq-screen) + #- '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") + #- 'bowtie' # Bowtie (indexes not provided for fastq-screen) ### BWA ---------------------------------------------------------------------------------------------- bwa: diff --git a/config/fastq-screen_bowtie2.conf b/config/fastq-screen_bowtie2.conf new file mode 100644 index 0000000000000000000000000000000000000000..4cf6ccc0281d32ec1d3a08ac8f0fca5917d8cfd7 --- /dev/null +++ b/config/fastq-screen_bowtie2.conf @@ -0,0 +1,69 @@ +###I###R###D######U###2###3###3#######T###R###A###N###S###V###I###H###M###I#### +# Name ___________________ fastq-screen.conf +# Version ________________ v.2022.11 +# Author _________________ Nicolas Fernandez +# Affiliation ____________ IRD_TransVIHMI +# Aim ____________________ Configuration file for Fastq-Screen (with bowtie2) +# Date ___________________ 2021.04.30 +# Latest modifications ___ 2022.11.18 +# Use ____________________ Edit default settings (and add fasta reference) + +############################################################################### + +#### MOLECULAR BIOLOGY SEQUENCES ---------------------------------------------------------------------------- + +### PhiX - QC_phi-X174_Coliphage_NC-001422.1 +DATABASE PhiX resources/indexes/bowtie2/QC_phi-X174_Coliphage_NC-001422-1 +### Kanamycin - Kanamycin-Resistance-Gene +DATABASE Kanamycin resources/indexes/bowtie2/QC_Kanamycin-Resistance-Gene +### Adapters - QC_NGS-Adapters (FastQC contaminants: www.bioinformatics.babraham.ac.uk/projects/fastqc) +DATABASE Adapters resources/indexes/bowtie2/QC_NGS-adapters +### Vectors - QC_UniVec_wo_PhiX_and_Kanamycin (UniVec database: http://www.ncbi.nlm.nih.gov/VecScreen/UniVec.html) without PhiX and Kanamycin +DATABASE Vectors resources/indexes/bowtie2/QC_UniVec_wo_phiX_and_kanamycin + +#### TRANSVIHMI ORGANISMS ----------------------------------------------------------------------------------- + +#### Putative Hosts (Large genomes) ----- + +### Gorilla g4 +#DATABASE Gorilla resources/indexes/bowtie2/Gorilla_gorilla_g4 +### Chimpanzee t3 +#DATABASE Chimpanzee resources/indexes/bowtie2/Pan_troglodytes_t3 +### Human - HOST_Homo-sapiens_h38_NC-000001.11 +#DATABASE Human resources/indexes/bowtie2/HOST_Homo-sapiens_h38_NC-000001-11 +### Bat v1 +#DATABASE Bat resources/indexes/bowtie2/Pteropus_vampyrus_v1 + +#### Main Viruses (Small genomes) ----- + +### SARS-CoV-2 - SARS-CoV-2_Wuhan_MN908947.3 +DATABASE SARS-CoV-2 resources/indexes/bowtie2/SARS-CoV-2_Wuhan_MN908947-3 +### MPXV - Monkeypox-virus_Zaire_AF380138.1 +DATABASE Monkeypox resources/indexes/bowtie2/Monkeypox-virus_Zaire_AF380138-1 +### SPXV - Swinepox-virus_India_MW036632.1 +DATABASE Swinepox resources/indexes/bowtie2/Swinepox-virus_India_MW036632-1 +### EBOV - Ebola-virus_Zaire_AF272001.1 +DATABASE Ebola resources/indexes/bowtie2/Ebola-virus_Zaire_AF272001-1 +### HIV - HIV-1_HXB2_K03455.1 +DATABASE HIV resources/indexes/bowtie2/HIV-1_HXB2_K03455-1 + +#### LAB MODEL ORGANISMS ------------------------------------------------------------------------------------ + +### E. coli (Bacteria) - QC_Echerichia-coli_CP060121.1 +DATABASE Ecoli resources/indexes/bowtie2/QC_Echerichia-coli_CP060121-1 +### S. cerevisiae (Yeast) - sequence +#DATABASE Scerevisiae resources/indexes/bowtie2/Saccharomyces_cerevisiae +### C. elegans (Nematode) - sequence +#DATABASE Celegans resources/indexes/bowtie2/Caenorhabditis_elegans +### D. melanogaster (Fruit fly) - sequence +#DATABASE Dmelanogaster resources/indexes/bowtie2/Drosophila_melanogaster +### D. rerio (Zebrafish) - sequence +#DATABASE Drerio resources/indexes/bowtie2/Danio_rerio +### X. laevis (Xenope) - sequence +#DATABASE Xlaevis resources/indexes/bowtie2/Xenopus_laevis +### G. gallus - sequence +#DATABASE Ggallus ressources/indexes/bowtie2/Gallus_gallus +### Mouse m39 +#DATABASE Mouse resources/indexes/bowtie2/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/bowtie2/Arabidopsis_thaliana_t10 diff --git a/config/fastq-screen.conf b/config/fastq-screen_bwa.conf similarity index 98% rename from config/fastq-screen.conf rename to config/fastq-screen_bwa.conf index 9b3037f57e25647b7d5a911dacc3727d8be12f7e..8d7780a85a9f28d31a3a9b89e8665ba5dd16ad5a 100644 --- a/config/fastq-screen.conf +++ b/config/fastq-screen_bwa.conf @@ -5,7 +5,7 @@ # Affiliation ____________ IRD_TransVIHMI # Aim ____________________ Configuration file for Fastq-Screen (with bwa) # Date ___________________ 2021.04.30 -# Latest modifications ___ 2022.11.10 +# Latest modifications ___ 2022.11.18 # Use ____________________ Edit default settings (and add fasta reference) ############################################################################### diff --git a/workflow/rules/indexing_genomes.smk b/workflow/rules/indexing_genomes.smk index fda213efd89e6e7b8e355eccb06270b1401c867e..d496a05d5725846a2918c78e905a08337f34a263 100755 --- a/workflow/rules/indexing_genomes.smk +++ b/workflow/rules/indexing_genomes.smk @@ -4,7 +4,7 @@ # Affiliation ____________ IRD_U233_TransVIHMI # Aim ____________________ Snakefile with indexing genomes rules # Date ___________________ 2022.09.28 -# Latest modifications ___ 2022.11.10 +# Latest modifications ___ 2022.11.18 # Use ____________________ snakemake -s indexing_genomes.smk --use-conda ############################################################################### diff --git a/workflow/rules/quality_control.smk b/workflow/rules/quality_control.smk index 568b802b041ce1d6363ef83c5fc8403bc6382c21..f65e0cc26d9ee81d16868b880d2b586b95fdd294 100755 --- a/workflow/rules/quality_control.smk +++ b/workflow/rules/quality_control.smk @@ -4,7 +4,7 @@ # Affiliation ____________ IRD_U233_TransVIHMI # Aim ____________________ Snakefile with quality control rules # Date ___________________ 2021.09.28 -# Latest modifications ___ 2022.11.10 +# Latest modifications ___ 2022.11.18 # Run ____________________ snakemake -s quality_control.smk --use-conda ###############################################################################