| Next changeset 1:987ac30b5bb0 (2018-12-09) |
|
Commit message:
Uploaded-dev |
|
added:
Project_RM/codon_usage2.py Project_RM/codon_usage_complete.xml |
| b |
| diff -r 000000000000 -r 92d2b0a37086 Project_RM/codon_usage2.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/Project_RM/codon_usage2.py Sun Dec 09 06:00:26 2018 -0500 |
| [ |
| @@ -0,0 +1,149 @@ +#!/usr/bin/env python + +import Bio as Bio +from Bio import SeqIO +from Bio.Data import CodonTable +import re +from pprint import pprint +import argparse as ap +import sys +import os +import pandas as pd +#from BCBio import GFF + + +def read_input(data = "example.fna", type_ = "fasta"): + + """ + Accepted formats: + - fasta (multifasta) + - gff + - gbk + + """ + + + seqs = "" + + if type_ == "fasta": + with open(data, "rU") as handle: + for record in SeqIO.parse(handle, type_): + seqs = seqs + str(record.seq) + + + #elif type_ == "gff": + # with open(data, "rU") as handle: + # for record in GFF.parse(handle): + # seqs = seqs + str(record.seq) + + elif type_ == "gbk": + with open(data, "rU") as input_handle: + for record in SeqIO.parse(input_handle, "genbank"): + seqs = seqs + str(record.seq) + + + return seqs + +def codon_usage(seqs, codonTable): + + codon_usage = {} + tmp = [x for x in re.split(r'(\w{3})', seqs) if x != ""] + + b_cod_table = CodonTable.unambiguous_dna_by_name[codonTable].forward_table + + + for cod in CodonTable.unambiguous_dna_by_name[codonTable].stop_codons: + b_cod_table[cod] = "_Stop" + + for cod in CodonTable.unambiguous_dna_by_name[codonTable].start_codons: + b_cod_table[cod + " Start"] = b_cod_table[cod] + b_cod_table.pop(cod) + + aas = set(b_cod_table.values()) + + + for aa in aas: + codon_usage[aa] = {} + for codon in b_cod_table.keys(): + if b_cod_table[codon] == aa: + codon_usage[aa][codon] = tmp.count(codon.split(" ")[0]) + + + tups = {(outerKey, innerKey): values for outerKey, innerDict in codon_usage.iteritems() for innerKey, values in innerDict.iteritems()} + + codon_usage_ = pd.DataFrame(pd.Series(tups), columns = ["Count"]) + codon_usage_.index = codon_usage_.index.set_names(["AA", "Codon"]) + codon_usage_['Proportion'] = codon_usage_.groupby(level=0).transform(lambda x: (x / x.sum()).round(2)) + + return {"Dictionary": codon_usage, "Tuples": tups, "Table": codon_usage_} + +if __name__ == '__main__': + + parser = ap.ArgumentParser(description= + 'This script takes as input gff, gbk and single or multifasta files and \n' + 'compute the codon usage for a specified codon table.\n' + 'Usage:\n' + 'python codon_usage.py -i example.gbk -t genebank -o gbk_example -c Bacterial\n' + 'python codon_usage.py -i example.ffn -t fasta -o fasta_example -c Bacterial\n' + 'python codon_usage.py -i example.gff -t gff -o gff_example -c Bacterial\n', + formatter_class=ap.RawTextHelpFormatter) + + parser.add_argument('-i','--input', help='The path to the input file',required=True) + parser.add_argument('-t','--type', help= + 'The format of the file [genebank, fasta, gff ...]', required=True) + parser.add_argument('-c','--codonTable', help= + 'The codon table to be used [Standard, Bacterial, Archaeal ...]\n' + 'Alternative Flatworm Mitochondrial,\\n' + 'Alternative Yeast Nuclear,\n' + 'Archaeal,\n' + 'Ascidian Mitochondrial,\n' + 'Bacterial,\n' + 'Blastocrithidia Nuclear,\n' + 'Blepharisma Macronuclear,\n' + 'Candidate Division SR1,\n' + 'Chlorophycean Mitochondrial,\n' + 'Ciliate Nuclear,\n' + 'Coelenterate Mitochondrial,\n' + 'Condylostoma Nuclear,\n' + 'Dasycladacean Nuclear,\n' + 'Echinoderm Mitochondrial,\n' + 'Euplotid Nuclear,\n' + 'Flatworm Mitochondrial,\n' + 'Gracilibacteria,\n' + 'Hexamita Nuclear,\n' + 'Invertebrate Mitochondrial,\n' + 'Karyorelict Nuclear,\n' + 'Mesodinium Nuclear,\n' + 'Mold Mitochondrial,\n' + 'Mycoplasma,\n' + 'Pachysolen tannophilus Nuclear,\n' + 'Peritrich Nuclear,\n' + 'Plant Plastid,\n' + 'Protozoan Mitochondrial,\n' + 'Pterobranchia Mitochondrial,\n' + 'SGC0,\n' + 'SGC1,\n' + 'SGC2,\n' + 'SGC3,\n' + 'SGC4,\n' + 'SGC5,\n' + 'SGC8,\n' + 'SGC9,\n' + 'Scenedesmus obliquus Mitochondrial,\n' + 'Spiroplasma,\n' + 'Standard,\n' + 'Thraustochytrium Mitochondrial,\n' + 'Trematode Mitochondrial,\n' + 'Vertebrate Mitochondrial,\n' + 'Yeast Mitochondrial\n', required=True) + + parser.add_argument('-o','--output', help='Description for bar argument', required=True) + args = vars(parser.parse_args()) + + seqs = read_input(data=args['input'], type_=args['type']) + out = codon_usage(seqs, args['codonTable']) + + with open(args['output'], "w") as outf: + out["Table"].to_csv(outf, sep="\t", index_label=["AA", "Codon"]) + + \ No newline at end of file |
| b |
| diff -r 000000000000 -r 92d2b0a37086 Project_RM/codon_usage_complete.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/Project_RM/codon_usage_complete.xml Sun Dec 09 06:00:26 2018 -0500 |
| [ |
| @@ -0,0 +1,39 @@ +<tool id="codon_usage" name="Codon Usage" version="0.1.0"> + <description>for each sequence in a file</description> + <requirements> + <requirement type="python module">biopython</requirement> + <requirement type="python module">pandas</requirement> + </requirements> + + <command interpreter="python">codon_usage2.py python -i $input -t $input_type -o $output -c $codon_table</command> + <inputs> + <param name="input" format="fasta" type="data" label="Source file"/> + + <param name="input_type" type="select" format="text"> + <label>Indicate the input file format</label> + <option value="fasta">Fasta</option> + <option value="gbk">gbk</option> + <option value="gff">gff</option> + </param> + + + + </inputs> + + + + <outputs> + <data format="tabular" name="output" /> + </outputs> + + <tests> + <test> + <param name="input" value="fa_gc_content_input.fa"/> + <output name="out_file1" file="fa_gc_content_output.txt"/> + </test> + </tests> + + <help> +This tool compute codon usage of an annotated genome [preferably Prokaryotes]. + </help> +</tool> |