apcamargo

from pathlib import Path
from typing import Iterator, Optional, Union

import polars as pl
from needletail import parse_fastx_file
from polars.io.plugins import register_io_source


def scan_fastx(fastx_file: Union[str, Path]) -> pl.LazyFrame:
    schema = pl.Schema(

apcamargo

#!/usr/bin/env python

"""
This script processes SAM (Sequence Alignment/Map format) inputs from standard
input and extracts alignment information that is then provided in a tab-separated
table. The following fields are produced: query, target, query_length, query_start,
query_end, target_start, target_end, alignment_length, alignment_identity.

This script was designed for use with SAM files produced by minimap2. However,
it will work with any SAM data that:

apcamargo

#!/usr/bin/env python

import math
import re

import click
from scipy.cluster.hierarchy import fcluster, linkage
from skbio import DistanceMatrix, Protein, TabularMSA, io
from skbio.sequence.distance import hamming

apcamargo

apcamargo

from coloraide import Color


def lighten(
    color: Color,
    amount: float,
) -> Color:
    """
    Lighten a color by a given amount.
    """

apcamargo

import subprocess

def get_assembly_accession(genbank_accession):
    p1 = subprocess.Popen(
        ["elink", "-db", "nuccore", "-target", "assembly", "-id", genbank_accession],
        stdout=subprocess.PIPE,
        stderr=subprocess.PIPE,
    )
    p2 = subprocess.Popen(
        ["efetch", "-format", "docsum"],

apcamargo

#!/usr/bin/env python

# hhblits -v 0 -cpu 1 -n 1 -p 90 -z 0 -Z 5000 -b 0 -B 5000 -M 50 -d busco_db/busco -i msa.faa -o msa.hhr

from collections import namedtuple
from pathlib import Path
import argparse

parser = argparse.ArgumentParser(description='Parse hhsearch hhr output file.')
parser.add_argument('-i', help='input hrr path', dest='input_file',type=str, required=True)

apcamargo

import bz2
import gzip
import lzma
import textwrap
from contextlib import contextmanager
from enum import Enum, auto
from pathlib import Path


class Compression(Enum):

apcamargo

import bz2
import gzip
import lzma
from contextlib import contextmanager
from enum import Enum, auto
from pathlib import Path
from typing import TextIO


class Compression(Enum):

apcamargo

# Requires jupytext (https://github.com/mwouts/jupytext) and Glow (https://github.com/charmbracelet/glow)

ipynb-view () {
    if [ -z "$1" ]; then
        echo "Usage: ipynb-view <notebook.ipynb>";
        return 1;
    fi;
    jupytext --from ipynb --to markdown --output - "$1" | glow --preserve-new-lines --pager
}