Phlya

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Coverage analysis API for genomic pairs data.

This module provides functions to calculate coverage from pairs files,
supporting various filtering and binning options.
"""

import multiprocessing

Phlya

Phlya

#########################################
# THIS IS A TYPICAL project.yml TEMPLATE
# most of the settings present here
# are GO for mapping production data
# but nonetheless user must consider
# carefully every presented option
#########################################

#########################################
# When commmenting parameters out, make sure

Phlya

(test-snakemake-wrappers) ilya@f346m-7eff66 snakemake-wrappers % pytest test.py -v -k cooltools
======================================================================= test session starts ========================================================================
platform darwin -- Python 3.10.5, pytest-7.1.2, pluggy-1.0.0 -- /Users/ilya/opt/anaconda3/envs/test-snakemake-wrappers/bin/python
cachedir: .pytest_cache
rootdir: /Users/ilya/Projects/snakemake-wrappers
collected 380 items / 379 deselected / 1 selected

test.py::test_cooltools_insulation FAILED                                                                                                                    [100%]

============================================================================= FAILURES =============================================================================

Phlya

walkpolicies = ["all", "mask"]
backends = ["cython", "scipy", "sklearn"]
cores = [1, 2, 4, 8]
chunksizes = [1000, 10_000, 100_000, 1_000_000, 10_000_000]
mismatches = [0, 3]
carryovers = [10, 100, 1000]

extensions = ["nodups.pairs", "dups.pairs", "unmapped.pairs", "stats"]

cython = expand(

Phlya

Phlya

# Fastqs can be provided as:
# -- a pairs of relative/absolute paths
# -- sra:<SRA_NUMBER>, optionally followed by the indices of the first and
# the last entry in the SRA in the form of "?start=<first>&end=<last>
# [to implement] -- as a path to a folder with fastqs '<base_folder>', with the structure
# <base_folder>/<library_name>/<run_name>/, with each folder containing only
# two fastq.gz files
# python bin/geo2yaml.py PRJNA385337 --title_column library_name --title_sub '\.[^.]*$' '' --title_sub '\.' '_' --group_sub '_[^_]+$' ''
input:
    raw_reads_paths:

Phlya

import sys
import argparse
import re

import numpy as np
import pandas as pd
import pysradb


# def unescaped_str(arg_str):

Phlya

genome: hg38
path_genomes: /exports/igmm/eddie/wendy-lab/ilia/genomes/

project_folder: /exports/igmm/eddie/wendy-lab/ilia/MCM/

filter: mapq_30

resolutions:
    - 10000000
    - 5000000

Phlya