[META] SPECIES.PRODUCTION_NAME = Lerema_accius_v1x1 SPECIES.SCIENTIFIC_NAME = Lerema accius SPECIES.COMMON_NAME = Clouded skipper SPECIES.DISPLAY_NAME = Lerema accius v1.1 SPECIES.DIVISION = EnsemblMetazoa SPECIES.URL = Lerema_accius_v1x1 SPECIES.TAXONOMY_ID = 691651 SPECIES.ALIAS = [ Lerema_accius_v1x1 Lerema%20accius%20v1.1 Lerema_accius_v1.1 lerema_accius_v1x1 lerema_accius lerema%20accius Lerema_accius Lerema%20accius clouded%20skipper ] ASSEMBLY.NAME = v1.1 ASSEMBLY.DATE = 2015-09-02 ASSEMBLY.ACCESSION = GCA_001278395.1 ASSEMBLY.DEFAULT = v1.1 PROVIDER.NAME = Grishin Lab UT Southwestern Medical Center PROVIDER.URL = http://prodata.swmed.edu/ GENEBUILD.ID = 2 GENEBUILD.START_DATE = 2015-07 GENEBUILD.VERSION = 2016-08 GENEBUILD.METHOD = import [GFF] SORT = 1 CHUNK = [ change region ] CONDITION1 = [ MULTILINE CDS ] CONDITION1a = [ MULTILINE five_prime_utr ] CONDITION1b = [ MULTILINE three_prime_utr ] CONDITION2 = [ EXPECTATION cds hasSister exon force ] CONDITION3 = [ EXPECTATION mrna hasParent gene find ]; CONDITION6 = [ EXPECTATION exon hasParent mrna find ]; CONDITION7 = [ EXPECTATION cds hasParent mrna find ]; CONDITION8 = [ EXPECTATION cds|exon|mrna|gene <=[_start,_end] SELF skip ]; [FILES] ; SCAFFOLD = [ fa http://prodata.swmed.edu/LepDB/lac/accius_assembly_V1.1.fa.gz ] ; A = [ txt http://prodata.swmed.edu/LepDB/lac/annotation_V1.1.tar.gz ] ; cat annotation_V1.1/accius_proteins_V1.1.gff \ ; | perl -lne ' ; if (/^(.*?)\t(gene|CDS|mRNA|exon)\t(.*?)\t(lac.*)$/) { ; if ($2 eq "gene") {print "$1\t$2\t$3\tID=$4"; $gene = $4} ; if ($2 eq "mRNA") {print "$1\t$2\t$3\tID=$4.mRNA;Parent=$gene"; $mRNA = "$4.mRNA"} ; if ($2 eq "exon") {print "$1\t$2\t$3\tID=$4.mRNA.exon" . ++$exoncount{$4} . ";Parent=$mRNA"} ; if ($2 eq "CDS") {print "$1\t$2\t$3\tID=$4.mRNA.CDS;Parent=$mRNA"} ; } ;' > accius_proteins_V1.1.added_ID_Parent.gff ; GFF = [ gff3 accius_proteins_V1.1.added_ID_Parent.gff ] ; PROTEIN = [ fa annotation_V1.1/accius_proteins_V1.1.fa ] ; Now with rephased GFF: SCAFFOLD = [ fa http://download.lepbase.org/v3/sequence/Lerema_accius_v1.1_-_scaffolds.fa.gz ] ; GFF = [ gff3 http://download.lepbase.org/v3/provider/accius_assembly_V1.1.rephased.gff.gz ] GFF = [ gff3 http://download.lepbase.org/v3/annotation/Lerema_accius_v1.1_-_genes.gff.gz ] PROTEIN = [ fa http://download.lepbase.org/v3/provider/accius_assembly_V1.1.rephased.nomrna.faa.gz ] [GENE_DESCRIPTIONS] [GENE_STABLE_IDS] GFF = [ gene->ID /(.+)/ ] [GENE_NAMES] [TRANSCRIPT_DESCRIPTIONS] [TRANSCRIPT_STABLE_IDS] GFF = [ SELF->ID /(.+).mRNA/ ] [TRANSCRIPT_NAMES] [TRANSLATION_STABLE_IDS] GFF = [ mRNA->ID /(.+).mRNA/ ] [DBXREFS] [EXTERNAL_DBS] [MODIFY] OVERWRITE_DB = 1 TRUNCATE_SEQUENCE_TABLES = 1 TRUNCATE_GENE_TABLES = 1 INVERT_PHASE = 0 [SCAFFOLD_NAMES] SCAFFOLD = [ /(.+)/ /_cov.*// ]