# <codecell> from itertools import product list(product('abcdefg', range(5))) # <codecell> fields = ['Name','RegionName', 'QueryNucStart','QueryNucStop','QueryNuc', 'RegionNucStart','RegionNucStop','RegionAAStart', 'RegionAAStop', 'QueryAA'] with open('TestData/LocatorRes.tsv', 'w') as handle: writer = csv.DictWriter(handle, fields, delimiter='\t') writer.writeheader() for row in process_seqs(input_seqs, extract_regions = True): writer.writerow(row) #print row #raise KeyError # <codecell> import csv headers = ['Name', 'RegionName', 'QueryNucStart', 'QueryNucStop', 'QueryNuc', 'RegionNucStart', 'RegionNucStop', 'RegionAAStart','RegionAAStop','QueryAA'] with open('test_output.tsv', 'w') as handle: writer = csv.DictWriter(handle, headers, delimiter='\t') found_pats = set()
# <codecell> !/home/will/staden-2.0.0b9.x86_64/bin/convert_trace --help # <codecell> res = call_muscle(seqs) with open('align_data.fasta', 'w') as handle: fasta_writer(handle, res) # <codecell> from HIVTransTool import process_seqs results = list(process_seqs(seqs[:50], extract_regions = True, known_names = 50)) # <codecell> for row in results: if row['RegionName'] == 'LTR5': print row['Name'], row['QueryNuc'] # <codecell> results[:5] # <codecell>