TEST: updated test data archive and test_config.yaml

test_data/config.yaml

+##### QUERY related files/parameters (refseqv2.1)
+# GFF annotatin to transfert
+annotationQuery: 'test_data/reference.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: 'test_data/reference.fa'
+# blastdb of all mrnas. used to rescue genes which have failed in the transfert using the targeted approache
+blastdb: 'test_data/reference_mrna.fa'
+# 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']
+
+##### Transfert mode
+# transfert all isoforms (all) or only the '.1' (first)
+transferType: 'first'
+
+##### TARGET related files/parameters
+# FASTA of the target genome
+targetFasta: 'test_data/target.fa'
+#GMAP index of the genome for -d option
+targetGmapIndex: 'target.fa.gmapidx'
+#GMAP index: path to the gmapindex directory, for -D option
+targetGmapIndexPath: './test_data/'
+#BWA index prefix
+targetBwaIdx: 'test_data/target.fa'
+
+##### ISBP/markers related config and parameters
+# BED file of coordinates on the query genome (REFSEQ v2.1)
+isbpBed: 'test_data/isbps.bed'
+# BWA threads for mapping
+bwaThreads: 16
+# FLAG : F flag for samtools
+flag_F: 3844
+# minimum mapping quality of markers on the target genome
+mapq: 30
+# max mismatches per ISBP/marker
+mismatches: 2
+
+##### OUTPUT directory
+results: 'test_data/results'
+finalPrefix: 'MAGATT_TEST'
+# 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: 'test_data/chrMapping.txt'
+
+##### Nomenclature for final gene IDs
+# used in rule renameGeneIds (rules/geneAnchoring.smk)
+gff_prefix: 'TraesCSTest'
+gff_version: '01G'
+gff_source: 'MAGATT-TEST'