IMPROVE: remove 'Chr' strings in grep commands

.gitignore

@@ -5,4 +5,4 @@ resultsDEV
 .snakemake
 pipeline_v0.1.tar.gz
 run_*
-slurm-*.out
+slurm*

config.yaml

 ##### QUERY related files/parameters (refseqv2.1)
 # GFF annotatin to transfert
-annotationQuery: 'data/IWGSC_refseqv2.1/IWGSC_refseqv2.1_annotation.gff3'
+annotationQuery: 'data/IWGSC_refseqv2.1_annotation_200916_HC.gff3'
 # feature type used for anchoring on target genome
 featureType: 'gene'
 # FASTA of the query (used to check the sequences after the coordinates are calculated on the target genome)
-queryFasta: '/home/herimbert/gdec/shared/triticum_aestivum/chinese_spring/iwgsc/REFSEQV2/v2.1/CS_pseudo_v2.1.fa'
+queryFasta: 'data/CS_pesudo_v2.1.fa'
 # blastdb of all mrnas. used to rescue genes which have failed in the transfert using the targeted approache
-blastdb: 'data/IWGSC_refseqv2.1/IWGSC_refseqv2.1_mrna.fa'
+blastdb: 'data/IWGSC_refseqv2.1_annotation_200916_HC_mrna.fasta'
 # map of all chromosome ids --> NEED TO BE UPDATED in another version WITH ONE ARRAY FOR THE QUERY AND ONE ARRAY FOR THE TARGET GENOME ASSEMBLY
 chromosomes: ['1A', '2A', '3A', '4A', '5A', '6A', '7A', '1B', '2B', '3B', '4B', '5B', '6B', '7B', '1D', '2D', '3D', '4D', '5D', '6D', '7D']
-refChrom: ['chr1A', 'chr1B', 'chr1D', 'chr2A', 'chr2B', 'chr2D', 'chr3A', 'chr3B', 'chr3D', 'chr4A', 'chr4B', 'chr4D', 'chr5A', 'chr5B', 'chr5D', 'chr6A', 'chr6B', 'chr6D', 'chr7A', 'chr7B', 'chr7D', 'chrUn']
+refChrom: ['Chr1A', 'Chr1B', 'Chr1D', 'Chr2A', 'Chr2B', 'Chr2D', 'Chr3A', 'Chr3B', 'Chr3D', 'Chr4A', 'Chr4B', 'Chr4D', 'Chr5A', 'Chr5B', 'Chr5D', 'Chr6A', 'Chr6B', 'Chr6D', 'Chr7A', 'Chr7B', 'Chr7D', 'ChrUn']
 
 ##### Transfert mode
 # transfert all isoforms (all) or only the '.1' (first)
 transferType: 'first'
 
-##### TARGET related files/parameters (julius)
-targetFasta: 'data/Renan_pseudo.fasta'
+##### TARGET related files/parameters
+targetFasta: 'data/Triticum_aestivum_arinalrfor.PGSBv2.1.dna.toplevel.fa'
 
 ##### ISBP/markers related config and parameters
-# BAM file of markers/ISBPs mapped on the target genome (Julius)
-isbpBam: 'data/Renan_isbps.bam'
+# BAM file of markers/ISBPs mapped on the target genome
+isbpBam: '/home/masirvent/wheat10plus-pangenome/data/mappingISBP/session2/arina/arina_CS_ISBP.bam'
 # BED file of coordinates on the query genome (REFSEQ v2.1)
-isbpBed: 'data/IWGSC_refseqv2.1/IWGSC_refseqv2.1_isbp.bed'
+isbpBed: 'data/Tae.Chinese_Spring.refSeqv2.1.ISBPs.bed'
 # minimum mapping quality of markers on the target genome
 mapq: 30
 # max mismatches per ISBP/marker
@@ -30,13 +30,13 @@ mismatches: 2
 
 ##### OUTPUT directory
 results: 'results'
-finalPrefix: 'TaeRenan_magatt_2109'
+finalPrefix: 'arina_magatt'
 # this file contains two columns: the first is the chromosome name as it appears in the genome.fasta of the new reference,
 # and the second the chromosome name as it will appear in the new gene Names
-chromMapID: 'data/chromosomeMappingID.csv'
+chromMapID: '/home/masirvent/wheat10plus-pangenome/data/liftoff/arina/chromstab.txt'
 
 ##### Nomenclature for final gene IDs
 # used in rule renameGeneIds (rules/geneAnchoring.smk)
-gff_prefix: 'TraesRN'
+gff_prefix: 'TraesAR'
 gff_version: '01G'
 gff_source: 'MAGATT-IWGSCCSv2.1'

rules/envs

+../envs
\ No newline at end of file

rules/preprocessGenomes.smk

@@ -13,7 +13,7 @@ rule splitGffPerChrom:
     input: config['results']+"/1.features.bed"
     output: temp(config['results']+"/1.features/{chrom}.bed")
     log: config['results']+"/1.features/{chrom}.fgrep.log"
-    params: "chr{chrom}"
+    params: "{chrom}"
     shell:  "fgrep -i {params} {input} 1> {output} 2> {log}"
 
 rule indexQuery:

rules/preprocessISBP.smk

@@ -13,7 +13,7 @@ rule bam2bed:
 	input: config['results']+"/1.filteredISBPs.bam"
 	output: config['results']+"/1.filteredISBPs/{chrom}/sorted.bed"
 	log: config['results']+"/1.filteredISBPs/{chrom}/sorted.log"
-        params: 'Chr{chrom}'
+        params: '{chrom}'
 	shell: "bamToBed -i {input} |fgrep -i {params}|cut -d ':' -f 1|sort -k1,1 -k2,2n  1> {output} 2> {log}"