diff --git a/README.md b/README.md index e37fac6bb56377c7deefce0c601846703effcc15..b893b21e159ac086bf475cf08bb1f887e33398e9 100644 --- a/README.md +++ b/README.md @@ -199,6 +199,10 @@ Hub-CDB and Institut Pasteur <br /><br /> ## WHAT'S NEW IN +### v17.0.0 + +1) scan() improved to be adapted to any header of fasta file + ### v16.0.0 1) New critical_pos.txt file format diff --git a/cnr_curation_voc_qc.R b/cnr_curation_voc_qc.R index 365fe961b17ad755d59b51e53ad8802585da13e1..e557296e7794b660e99aba0ef753dfad79a4e7a9 100644 --- a/cnr_curation_voc_qc.R +++ b/cnr_curation_voc_qc.R @@ -698,9 +698,9 @@ orf <- read.table(orf.path, header = TRUE, sep = "\t", stringsAsFactors = FALSE, fun_report(data = paste0("THE LIST OF ORF COORDINATES USED IS: "), output = log.file, path = out.path, sep = 1) fun_report(data = orf, output = log.file, path = out.path, sep = 1) # ref: sars-cov2 ref sequence -tempo <- scan(ref.seq.path, what = "character", quiet = TRUE) -ref.seq.ini <- tempo[5] # seq in the 5th position -fun_report(data = paste0("THE SARS-COV2 REFERENCE SEQUENCE USED IS: ", tempo[2]), output = log.file, path = out.path, sep = 1) +ref.seq.ini <- scan(ref.seq.path, what = "character", skip = 1, quiet = TRUE) # do not take the header +tempo <- scan(ref.seq.path, what = "character", nlines = 1, quiet = TRUE) # take the first line only +fun_report(data = paste0("THE SARS-COV2 REFERENCE SEQUENCE USED IS: ", paste(tempo, collapse = " ")), output = log.file, path = out.path, sep = 1) ################ End Data import diff --git a/cnr_curation_voc_qc.config b/cnr_curation_voc_qc.config index 880d1057cada460096d9162fae8b8252e31f8800..d54c58fa67be60392a3494be44ae8cfe1daac346 100644 --- a/cnr_curation_voc_qc.config +++ b/cnr_curation_voc_qc.config @@ -21,7 +21,7 @@ #### files in the main.nf result folder -in.path <- "C:/Users/gael/Documents/Git_projects/cnr_curation/dataset/results_210421_NB501703_0325_AH3NFCBGXJ/" # single character string indicating the path of the result file containing the coverage and vcf folders. Example: "/pasteur/zeus/projets/p01/CNRVIR_bioinfoSEQ/sarscov2mapping/results_210126_NB501755_0296_AHCH5JBGXH/" +in.path <- "C:/Users/gael/Documents/Git_projects/cnr_curation/dataset/results_210615_NB501703_0339_AHHJ5JBGXJ/" # single character string indicating the path of the result file containing the coverage and vcf folders. Example: "/pasteur/zeus/projets/p01/CNRVIR_bioinfoSEQ/sarscov2mapping/results_210126_NB501755_0296_AHCH5JBGXH/" cov.file <- ".cov" # single character string indicating the end of the name of the coverage file. Example: ".cov" mpileup.file <- ".mpileup.gz" # single character string indicating the end of the name of the gatk vcf haplotyper file. Example: ".haplotyper.vcf.gz" call.file <- ".call.gz" # single character string indicating the end of the name of the tmp gatk vcf haplotyper file. Example: "_haplotyper_tmp.vcf.gz" @@ -48,7 +48,7 @@ out.path <- "C:/Users/Gael/Desktop/" # absolute pathway of the destination folde ######## R packages and cute_little_R_functions file locations -function1.path <- "https://gitlab.pasteur.fr/gmillot/cute_little_R_functions/-/raw/v10.6.0/cute_little_R_functions.R" # tag version v10.0.0 # single character string indicating the file (and absolute pathway) of the required cute_little_R_functions toolbox. With ethernet connection available, this can also be used: "https://gitlab.pasteur.fr/gmillot/cute_little_R_functions/-/raw/10.3.0/cute_little_R_functions.R" or local "C:/Users/Gael/Documents/Git_projects/cute_little_R_functions/cute_little_R_functions.R" +function1.path <- "https://gitlab.pasteur.fr/gmillot/cute_little_R_functions/-/raw/v10.7.0/cute_little_R_functions.R" # tag version v10.0.0 # single character string indicating the file (and absolute pathway) of the required cute_little_R_functions toolbox. With ethernet connection available, this can also be used: "https://gitlab.pasteur.fr/gmillot/cute_little_R_functions/-/raw/10.3.0/cute_little_R_functions.R" or local "C:/Users/Gael/Documents/Git_projects/cute_little_R_functions/cute_little_R_functions.R" ######## QC