comparison cdhit_analysis.py @ 2:706b7acdb230 draft

planemo upload for repository https://github.com/Onnodg/Naturalis_NLOOR/tree/main/NLOOR_scripts/process_clusters_tool commit c2020ecc91cea0c8cf7439180cf796743c838b4d-dirty

1:ff68835adb2b

import argparse
import os
import re
from collections import Counter, defaultdict
from math import sqrt
import pandas as pd
import matplotlib

matplotlib.use('Agg')  # Non-interactive backend for Galaxy
import matplotlib.pyplot as plt

"""
This script processes cluster output files from cd-hit-est for use in Galaxy.
It extracts cluster information, associates taxa and e-values from annotation files,
performs statistical calculations, and generates text and plot outputs
summarizing similarity and taxonomic distributions.

4. Generate requested outputs: text summaries, plots, and Excel reports.


Note: Uses a non-interactive matplotlib backend (Agg) for compatibility with Galaxy.
"""


def parse_arguments(args_list=None):
    """Parse command-line arguments for the script."""
    parser = argparse.ArgumentParser(

2:706b7acdb230

"""
This script processes cluster output files from cd-hit-est for use in Galaxy.
It extracts cluster information, associates taxa and e-values from annotation files,
performs statistical calculations, and generates text and plot outputs
summarizing similarity and taxonomic distributions.

4. Generate requested outputs: text summaries, plots, and Excel reports.


Note: Uses a non-interactive matplotlib backend (Agg) for compatibility with Galaxy.
"""

import argparse
from collections import Counter, defaultdict
import os
import re
import matplotlib.pyplot as plt
import pandas as pd
from math import sqrt
import openpyxl



def parse_arguments(args_list=None):
    """Parse command-line arguments for the script."""
    parser = argparse.ArgumentParser(