bede

22,23c22,23
< \documentclass[unnumsec,webpdf,contemporary,large]{oup-authoring-template}%
< %\documentclass[unnumsec,webpdf,contemporary,large,namedate]{oup-authoring-template}% uncomment this line for author year citations and comment the above
---
> % \documentclass[unnumsec,webpdf,contemporary,large]{oup-authoring-template}%
> \documentclass[unnumsec,webpdf,contemporary,large,namedate]{oup-authoring-template}% uncomment this line for author year citations and comment the above
957,958c957,958
< %\bibliographystyle{abbrvnat}
< %\bibliography{reference}
---

bede

"""
Purpose: Concatenate demultiplexed FASTQs by barcode for one or more ONT runs
Usage: python concat_by_barcode.py run1/fastq_pass run2/fastq_pass
Author: Bede Constantinides
"""

import subprocess
import sys

from collections import defaultdict

bede

from io import StringIO

import pandas as pd
import pandera as pa
import pandera.extensions as extensions
from pandera.typing import Index, Series

csv_string = """
sample_name,country,region
cDNA-VOC-1-v4-1,USA,Bretagne

bede

def split_summary_by_barcode(summary_path, out_dir, run_name):
    '''Given a sequencing summary file path, write per barcode summaries to an output directory'''
    
    dtypes = {
        'filename_fastq': 'object',
        'filename_fast5': 'object',
        'read_id': 'object',
        'run_id': 'category',
        'channel': 'int64',
        'mux': 'int64',

bede

import pandas as pd
from bokeh.models.widgets import Select
from bokeh.layouts import widgetbox
from bokeh.models import ColumnDataSource, DataTable, TableColumn, CustomJS
from bokeh.io import show, output_file, output_notebook, reset_output
from bokeh.layouts import row, column, layout


raw_data = {'ORG': ['APPLE', 'ORANGE', 'MELON'],
        'APPROVED': [5, 10, 15],

bede

import pandas as pd
from scipy.spatial.distance import squareform
from scipy.cluster.hierarchy import fcluster, linkage

def cluster_df(df, method='single', threshold=100):
    '''
    Accepts a square distance matrix as an indexed DataFrame and returns a dict of index keyed flat clusters 
    Performs single linkage clustering by default, see scipy.cluster.hierarchy.linkage docs for others
    '''
   

bede

# Resilio, Dropbox, JupyterLab, Firefox, Sublime, Atom, Zotero, VPNs,
# Slack, Bitwarden, Office, Sketch, Typora
# Brew, Miniconda, Jupyterlab, RStudio, Docker
# Install custom jupyterlab envs https://ipython.readthedocs.io/en/latest/install/kernel_install.html#kernels-for-different-environments
# Create /opt/ and /opt/bin, place nextflow inside latter.
# Put toggle-able symlinks to brewed GCC inside here, prepend to path in .bashrc (`gcc_links_on`, `gcc_links_off`)
# Nextflow
# .ssh
# Generate keys
# Create /opt and opt/bin, add to path

bede

FROM ubuntu:16.04

RUN apt-get update && \
	apt-get --yes install \
	kmc smalt python3-pip zlib1g-dev libncurses5-dev libncursesw5-dev mummer samtools 

RUN pip3 install iva

ENTRYPOINT ["iva"]

bede

# SAM to consensus FASTA code golf, inspired by http://lab.loman.net/2015/07/28/calling-haploid-consensus-sequence/

# Starting with a SAM:
samtools view -bS seqs.sam | samtools sort - seqs # Generate and sort BAM
samtools index seqs.bam # Index BAM

# Starting with an indexed BAM:
samtools mpileup -ud 1000 -f seqs_ref.fasta seqs.bam | bcftools call -c | vcfutils.pl vcf2fq | seqtk seq -a - > seqs.consensus.fa # Generate pileup, call variants, convert to fq, convert to fa

# Who can do better? The bar is set low...

bede