Created
April 22, 2021 04:00
-
-
Save jaclynsaunders/5064316e98fb9e5cd7bcac8738431869 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import pandas as pd | |
| import re | |
| INPUT_FILE = "CAT-taxa-out.txt" | |
| OUTPUT_FILE = "formatted_CAT-taxa-out.txt" | |
| ORF_list = [] | |
| taxid_list = [] | |
| no_hits = [] | |
| with open(INPUT_FILE, "r") as f: | |
| next(f) | |
| for line in f: | |
| data = line.split("\t") | |
| if ("ORF has no hit to database") in line: | |
| no_hits.append(data[0]) | |
| else: | |
| ORF_list.append(data[0]) | |
| taxaStr = data[2] | |
| z = re.match("(.*);{1,1}(.+)", taxaStr) | |
| try: | |
| lastTax = z.group(2) | |
| except: | |
| lastTax = taxaStr | |
| taxid_list.append(str(lastTax).replace("*", "")) | |
| ORF_list = ORF_list + no_hits | |
| taxid_list = taxid_list + (len(no_hits) * ['-1']) #Give ORFs without hits taxid -1 | |
| df = pd.DataFrame(list(zip(ORF_list, taxid_list)), columns = ['Taxon_name', 'NCBI_taxon_id']) | |
| fake_name = [""]*len(df) | |
| df.insert(loc=0, column='Taxon_fasta_file_name', value=fake_name) | |
| df['NCBI_taxon_id'] = df['NCBI_taxon_id'].astype(str) | |
| df.to_csv(OUTPUT_FILE, index=False) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment