afrendeiro

"""
Run the experiments for the quantization speedup and plot results.
"""

import subprocess

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

afrendeiro

Introduction to linux command line/ipython/git/R for bioinformatics:

• https://github.com/biom262/biom262-2016
• https://github.com/ricket-sjtu/bi028
• https://github.com/YeoLab/single-cell-bioinformatics/
• https://github.com/YeoLab/single-cell-bioinformatics/tree/master/notebooks
• https://github.com/ltminty/Bioinformatics-and-R/blob/master/Rbioinformatics.ipynb

RNA-seq:

• https://github.com/Caroldm/RNA-Seq-Tutorial---Jupyter-notebook/blob/master/RNAseq%20tutorial.ipynb

afrendeiro

import numpy as np
import matplotlib.pyplot as plt


# class from here: http://nbviewer.ipython.org/gist/tillahoffmann/f844bce2ec264c1c8cb5
class gaussian_kde(object):
    """Representation of a kernel-density estimate using Gaussian kernels.

    Kernel density estimation is a way to estimate the probability density
    function (PDF) of a random variable in a non-parametric way.

afrendeiro

Introduction to next-generation sequencing (NGS)

General workflow

The current used technology for next generation sequencing is Illumina sequencing - all others cannot compete with its speed, price and output power - they have therefore specialized in niche applications (not discussed here).

Nevertheless, no sequencing technology cannot simply start sequencing one end of a chromosome until the other end.

The approach therefore is:

afrendeiro

"""
Convert a TIFF file generated by IndicaLabs (HALO) to a usable TIFF file.
"""

import typing as tp
from pathlib import Path
from xml.etree import ElementTree

import tifffile
from tifffile.tiffcomment import tiffcomment

afrendeiro

from pathlib import Path
import tifffile
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.backends.backend_pdf import PdfPages
from stardist.models import StarDist2D
from csbdeep.utils import normalize

_dir = Path("HumanLiverH35")
files = list(

afrendeiro

# This annotation of cell type markers is tailored for surface proteins
# normally profilid with multiplexed imaging (IMC, CODEX).
# It is a simple reference for myself and may be more detailed in some parts than others.
# This reference is hierarchical.
# This annotation is generally pan-tissue.
# Author: Andre Rendeiro
# License: CC BY-SA 2.0

cell_types:
    structural:

afrendeiro

import pathlib

import numpy as np

def mask_to_labelme(
    labeled_image: np.ndarray,
    filename: pathlib.Path,
    overwrite: bool = False,
    simplify: bool = True,
    simplification_threshold: float = 5.0,

afrendeiro

import string

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

# generate some data
n_groups = 4
n_per_group = 5

afrendeiro

def plot_fragment_sizes_fit(bam, plot, outputCSV, maxInsert=1500, smallestInsert=30):
    """
    Heavy inspiration from here:
    https://github.com/dbrg77/ATAC/blob/master/ATAC_seq_read_length_curve_fitting.ipynb
    """
    try:
        import pysam
        import numpy as np
        import matplotlib.mlab as mlab