Skip to content
Snippets Groups Projects
Commit fc911927 authored by Simeon's avatar Simeon
Browse files

working minimal nextflow script

parent 379a671f
No related branches found
No related tags found
No related merge requests found
params.genome = "MP1831"
/* Concept for the genome annotation pipeline /* Concept for the genome annotation pipeline
1. Parse genome to protein using gff2prot util from funannotate 1. Parse genome to protein using gff2prot util from funannotate
2. Remove everything after stop codon in protein fasta with: 2. Remove everything after stop codon in protein fasta with:
seqkit -> sed seqkit -> sed
3. 3. */
*/
// Script parameters // Script parameters
params.project = "/home/nibio/Documents/Erik_NCBI_tbl_test/Simeon_annotering/table2asn/"
params.genome = "genome_basename" params.genome = "genome_basename"
params.genomeGFF = "${params.project}${params.genome}.gff"
params.genomeFasta = "${params.project}${params.genome}.fsa"
process extractProteins { process extractProteins {
input: input:
...@@ -17,11 +16,15 @@ process extractProteins { ...@@ -17,11 +16,15 @@ process extractProteins {
path genomeGFF path genomeGFF
output: output:
path "${genome}_protein.fa" path "${params.genome}_protein.fa"
""" """
funannotate util gff2prot -g $genomeGFF -f $genomeFasta --no_stop |\ funannotate util gff2prot -g $genomeGFF -f $genomeFasta --no_stop | seqkit seq -w 0 | sed 's/\\*.*//' > "${params.genome}_protein.fa"
seqkit seq -w 0 |\
sed 's/\*.*//' >\
${genome}_protein.fa
""" """
} }
workflow {
def genome_ch = Channel.fromPath(params.genomeFasta)
extractProteins(genome_ch, params.genomeGFF)
}
\ No newline at end of file
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment