comparison find_str.py @ 29:efc775ab30fe draft

planemo upload for repository https://github.com/fubar2/microsatbed commit d952bc313f408735456747c3d33e09a3170c8f59-dirty

28:4cb6cc083620

import argparse
import shutil
import subprocess

import pybigtools
import pytrf  # 1.3.0
from pyfastx import Fastx  # 0.5.2

"""
Allows all STR or those for a subset of motifs to be written to a bed file
Designed to build some of the microsatellite tracks from https://github.com/arangrhie/T2T-Polish/tree/master/pattern for the VGP.
"""


def getDensity(name, bed, chrlen, winwidth):
    nwin = int(chrlen / winwidth)
    d = [0.0 for x in range(nwin + 1)]
    for b in bed:
        nt = b[5]
        bin = int(b[1] / winwidth)
        d[bin] += nt
    dw = [
        (name, (x * winwidth), ((x + 1) * winwidth) - 1, float(d[x]))
        for x in range(nwin + 1)
        if (x + 1) * winwidth <= chrlen
    ]
    return dw


def write_ssrs(args):
    """
    The integers in the call change the minimum repeats for mono-, di-, tri-, tetra-, penta-, hexa-nucleotide repeats

            wig += w
        bed += cbed
    if args.bigwig:
        wig.sort()
        bedg = ['%s %d %d %.3f' % x for x in wig]
        # bedg.insert(0,'track type=bedGraph') https://genomebrowser.wustl.edu/goldenPath/help/bigWig.html
        with open("temp.bedg", "w") as bw:
            bw.write('\n'.join(bedg))
        chroms = ["%s\t%s" % (x, chrlens[x]) for x in chrlens.keys()]
        with open("temp.chromlen", "w") as cl:
            cl.write('\n'.join(chroms))
        cmd = ["bedGraphToBigWig", "temp.bedg", "temp.chromlen", "temp.bw" ]
        subprocess.run(cmd)
        #bw = pybigtools.open("temp.bw", "w")
        #bw.write(chrlens, wig)
        shutil.move("temp.bw", args.bed)
    else:
        bed.sort()
        obed = ["%s\t%d\t%d\t%s_%d\t%d" % x for x in bed]
        with open(args.bed, "w") as outbed:

29:efc775ab30fe

import argparse
import shutil
import subprocess

import pytrf  # 1.3.0
from pyfastx import Fastx  # 0.5.2

"""
Allows all STR or those for a subset of motifs to be written to a bed file
Designed to build some of the microsatellite tracks from https://github.com/arangrhie/T2T-Polish/tree/master/pattern for the VGP.
"""


def getDensity(name, bed, chrlen, winwidth):
    """
    pybigtools can write bigwigs and they are processed by other ucsc tools - but jb2 will not read them.
    Swapped the conversion to use a bedgraph file processed by bedGraphToBigWig
    """
    nwin = int(chrlen / winwidth)
    d = [0.0 for x in range(nwin + 1)]
    for b in bed:
        nt = b[5]
        bin = int(b[1] / winwidth)
        d[bin] += nt
    bedg = [
        (name, (x * winwidth), ((x + 1) * winwidth) - 1, float(d[x]))
        for x in range(nwin + 1)
        if (x + 1) * winwidth <= chrlen
    ]
    return bedg


def write_ssrs(args):
    """
    The integers in the call change the minimum repeats for mono-, di-, tri-, tetra-, penta-, hexa-nucleotide repeats

            wig += w
        bed += cbed
    if args.bigwig:
        wig.sort()
        bedg = ['%s %d %d %.3f' % x for x in wig]
        with open("temp.bedg", "w") as bw:
            bw.write('\n'.join(bedg))
        chroms = ["%s\t%s" % (x, chrlens[x]) for x in chrlens.keys()]
        with open("temp.chromlen", "w") as cl:
            cl.write('\n'.join(chroms))
        cmd = ["bedGraphToBigWig", "temp.bedg", "temp.chromlen", "temp.bw" ]
        subprocess.run(cmd)
        shutil.move("temp.bw", args.bed)
    else:
        bed.sort()
        obed = ["%s\t%d\t%d\t%s_%d\t%d" % x for x in bed]
        with open(args.bed, "w") as outbed: