Mercurial > repos > artbio > repenrich
diff RepEnrich_setup.py @ 15:2e3d976e7d5d draft default tip
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/repenrich commit 03183e29f807ec33548016a7c4144f52720b7b9e
author | artbio |
---|---|
date | Sun, 21 Apr 2024 09:44:51 +0000 |
parents | bf866bedd4b4 |
children |
line wrap: on
line diff
--- a/RepEnrich_setup.py Sat Apr 20 12:13:52 2024 +0000 +++ b/RepEnrich_setup.py Sun Apr 21 09:44:51 2024 +0000 @@ -71,7 +71,7 @@ genome = defaultdict(dict) for chr in g.keys(): - genome[chr]['sequence'] = g[chr].seq + genome[chr]['sequence'] = str(g[chr].seq) genome[chr]['length'] = len(g[chr].seq) # Build a bedfile of repeatcoordinates to use by RepEnrich region_sorter @@ -100,7 +100,7 @@ # generate metagenomes and save them to FASTA files for bowtie build for repname in rep_coords: - metagenome = '' + genomes_list = [] # iterating coordinate list by block of 3 (chr, start, end) block = 3 for i in range(0, len(rep_coords[repname]) - block + 1, block): @@ -109,11 +109,8 @@ start = max(int(batch[1]) - flankingl, 0) end = min(int(batch[2]) + flankingl, int(genome[chromosome]['length'])-1) + 1 - metagenome = ( - f"{metagenome}{spacer}" - f"{genome[chromosome]['sequence'][start:end]}" - ) - + genomes_list.append(genome[chromosome]['sequence'][start:end]) + metagenome = spacer.join(genomes_list) # Create Fasta of repeat pseudogenome fastafilename = f"{repname}.fa" record = SeqRecord(Seq(metagenome), id=repname, name='', description='')