diff --git a/bin/gmapRescue.sh b/bin/gmapRescue.sh index 8e9422e516db40bea934de22bc83d725b6fa67cb..b5b9b860491e81c781d945736073c78d1fbf6a20 100755 --- a/bin/gmapRescue.sh +++ b/bin/gmapRescue.sh @@ -53,16 +53,21 @@ do echo " Gene $geneid has status UNMAPPED: mapping on the whole genome" cat $rootdir'/query.mrna.fasta' >> $unmappedMrnaFasta && rm $rootdir'/query.mrna.fasta' - #targetindex=$gmapdb - #targetindexdir=$gmapdbdir - #targetgff=$rootdir'/gmap.wholeGenome.gff3' - #gmapexe='gmapl' - #eval $gmapexe --min-identity 0.80 --min-trimmed-coverage 0.50 --ordered -n 1 -d $targetindex -D $targetindexdir -f 2 $rootdir'/query.mrna.fasta' 1> $targetgff 2> $rootdir'/gmap.wg.log' && rm $rootdir'/query.mrna.fasta' - else - echo "running gmap on target" + + elif [ -f "$rootdir/GMAPRESCUE" ] + then + echo " Gene $geneid has status GMAPRESCUE: mapping on the target with gmap" eval gmap --ordered --min-identity 0.80 --min-trimmed-coverage 0.50 -n 1 -g $rootdir'/target.fasta' -f 2 $rootdir'/query.mrna.fasta' 1> $targetgff 2> $rootdir'/gmap.target.log' && rm $rootdir'/query.mrna.fasta' + + + elif [ -f "$rootdir/FULLPERFECTMATCH" ] || [ -f "$rootdir/FULLMATCHWITHMISSMATCHES" ] + then + echo " Gene $geneid has been mapped on the target with BLAT: next" + + else + echo " FAIL TO EVAL THE ANCHORING STATUS OF GENE $geneid: rescue on whole genome" + cat $rootdir'/query.mrna.fasta' >> $unmappedMrnaFasta && rm $rootdir'/query.mrna.fasta' fi - eval gmap --ordered --min-identity 0.80 --min-trimmed-coverage 0.50 -n 1 -g $rootdir'/query.fasta' -f 2 $rootdir'/query.mrna.fasta' 1> $rootdir'/gmap.query.gff3' && rm $rootdir'/query.mrna.fasta' echo "3. indexing the query and target genomic" samtools faidx $rootdir'/query.fasta' & diff --git a/config.yaml b/config.yaml index 3aa0624b3a00c91287033cb1b3eaa3c3c9a2a961..42900cb0079a4f783c9da635deeb74db7077fa42 100644 --- a/config.yaml +++ b/config.yaml @@ -19,9 +19,9 @@ transferType: 'first' # FASTA of the target genome targetFasta: 'data/Triticum_aestivum_arinalrfor.PGSBv2.1.dna.toplevel.fa' #GMAP index of the genome for -d option -targetGmapIndex: 'ensembl_Triticum_aestivum_julius_2022-9-16' +targetGmapIndex: 'ensembl_Triticum_aestivum_arinalrfor_2023-2-17' #GMAP index: path to the gmapindex directory, for -D option -targetGmapIndexPath: '/home/herimbert/gdec/shared/triticum_aestivum/julius/current/gmapdb/all/' +targetGmapIndexPath: '/home/herimbert/gdec/shared/triticum_aestivum/arinalrfor/current/gmapdb/all/' ##### ISBP/markers related config and parameters # BAM file of markers/ISBPs mapped on the target genome