A. Murat Eren meren

## get_genes.py
from anvio.dbops import ContigsSuperclass

# if your args object contains a `contigs_db` entry in its
# namespace all you don't need the following two lines and
# you can directly pass it to the ContigsSuperclass.
import argparse
args = argparse.Namespace(contigs_db="INFANT-GUT-TUTORIAL/SPLITAH/E_facealis/CONTIGS.db")

# get an instance of the contigs super:
contigs_db = ContigsSuperclass(args)

## gff_parser.py
#!/usr/bin/env python

## Antti Karkman
## University of Gothenburg
## antti.karkman@gmail.com
## 2017

import gffutils
import argparse

## anvi-script-gen-alluvial
#!/usr/bin/env python

# lousy script that works with the outputs of `anvi-export-collection`
# to reconcstruct the fate of contigs for a given algorithm and bin and
# spit out some text to be visualized on https://app.rawgraphs.io/

import sys

from collections import OrderedDict

## fastalib.py
# -*- coding: utf-8 -*-
# pylint: disable=line-too-long
# v.140713
"""A very lightweight FASTA I/O library"""

import io
import sys
import gzip
import numpy
import hashlib

## summarize_blast_results.py
#!/usr/bin/env python

# Click 'Download > Multiple-file JSON' from NCBI search results page,
# unzip it, run this script in it without any parameters, get the
# markdown formatted table.

import json
import glob

# poor man's whatever:

## Oligotyping_Dockerfile_v2.1.sh
FROM ubuntu:xenial

ENV OLIGOTYPING_VERSION 2.1

ENV DEBIAN_FRONTEND noninteractive

RUN apt-key adv --keyserver keyserver.ubuntu.com --recv-keys E084DAB9
RUN apt-get update
RUN apt-get install locales
RUN locale-gen en_US.UTF-8

## for_steve.py
>>> n = 21
>>> (n * n - n) / 2
210
>>>
>>> l = ['Cys', 'Asp', 'Ser', 'Gln', 'Lys', 'Trp', 'Pro', 'Thr', 'Ile', 'Ala', 'Phe', 'Gly', 'His', 'STP', 'Leu', 'Arg', 'Met', 'Glu', 'Asn', 'Tyr', 'Val']
>>> len(l)
21
>>> len(set(sorted([''.join(sorted([t[0], t[1]])) for t in list(itertools.product(l, l)) if t[0] != t[1]])))
210
>>>

## gen_primer_match_report.py
# run this script like this:
#
#           python gen_primer_match_report.py primers.txt sequences.txt
#
# it will generate a report file called `primer_matches_report.txt`
#
# example primers file (TAB-delimited, no spaces):
#
#           name	pair	direction	sequence
#           PolF	P1	F	TGCGAYCCSAARGCBGACTC

## external-genomes.txt
name	contigs_db_path
Bacteroides_fragilis_2334	Bacteroides_fragilis_2334.db
Bacteroides_fragilis_2346	Bacteroides_fragilis_2346.db
Bacteroides_fragilis_2347	Bacteroides_fragilis_2347.db
Escherichia_albertii_6917	Escherichia_albertii_6917.db
Escherichia_coli_6920	Escherichia_coli_6920.db
Escherichia_coli_9038	Escherichia_coli_9038.db
Prevotella_dentalis_19591	Prevotella_dentalis_19591.db
Prevotella_denticola_19594	Prevotella_denticola_19594.db
Prevotella_intermedia_19600	Prevotella_intermedia_19600.db

## boxes.R
#!/usr/bin/env Rscript

library(reshape)
library(ggplot2)

# set the work directory
setwd('~/Downloads')

# matrix-boxplots.txt should be a three-column, TAB-delimited matrix with a header for 'region', 'haplotype', and 'ratio'.
m <- data.frame(read.table('matrix-boxplots.txt', header = TRUE, sep="\t"))
	from anvio.dbops import ContigsSuperclass

	# if your args object contains a `contigs_db` entry in its
	# namespace all you don't need the following two lines and
	# you can directly pass it to the ContigsSuperclass.
	import argparse
	args = argparse.Namespace(contigs_db="INFANT-GUT-TUTORIAL/SPLITAH/E_facealis/CONTIGS.db")

	# get an instance of the contigs super:
	contigs_db = ContigsSuperclass(args)
	#!/usr/bin/env python

	## Antti Karkman
	## University of Gothenburg
	## antti.karkman@gmail.com
	## 2017

	import gffutils
	import argparse
	#!/usr/bin/env python

	# lousy script that works with the outputs of `anvi-export-collection`
	# to reconcstruct the fate of contigs for a given algorithm and bin and
	# spit out some text to be visualized on https://app.rawgraphs.io/

	import sys

	from collections import OrderedDict
	# -- coding: utf-8 --
	# pylint: disable=line-too-long
	# v.140713
	"""A very lightweight FASTA I/O library"""

	import io
	import sys
	import gzip
	import numpy
	import hashlib
	#!/usr/bin/env python

	# Click 'Download > Multiple-file JSON' from NCBI search results page,
	# unzip it, run this script in it without any parameters, get the
	# markdown formatted table.

	import json
	import glob

	# poor man's whatever:
	FROM ubuntu:xenial

	ENV OLIGOTYPING_VERSION 2.1

	ENV DEBIAN_FRONTEND noninteractive

	RUN apt-key adv --keyserver keyserver.ubuntu.com --recv-keys E084DAB9
	RUN apt-get update
	RUN apt-get install locales
	RUN locale-gen en_US.UTF-8
	>>> n = 21
	>>> (n * n - n) / 2
	210
	>>>
	>>> l = ['Cys', 'Asp', 'Ser', 'Gln', 'Lys', 'Trp', 'Pro', 'Thr', 'Ile', 'Ala', 'Phe', 'Gly', 'His', 'STP', 'Leu', 'Arg', 'Met', 'Glu', 'Asn', 'Tyr', 'Val']
	>>> len(l)
	21
	>>> len(set(sorted([''.join(sorted([t[0], t[1]])) for t in list(itertools.product(l, l)) if t[0] != t[1]])))
	210
	>>>
	# run this script like this:
	#
	# python gen_primer_match_report.py primers.txt sequences.txt
	#
	# it will generate a report file called `primer_matches_report.txt`
	#
	# example primers file (TAB-delimited, no spaces):
	#
	# name pair direction sequence
	# PolF P1 F TGCGAYCCSAARGCBGACTC
	name contigs_db_path
	Bacteroides_fragilis_2334 Bacteroides_fragilis_2334.db
	Bacteroides_fragilis_2346 Bacteroides_fragilis_2346.db
	Bacteroides_fragilis_2347 Bacteroides_fragilis_2347.db
	Escherichia_albertii_6917 Escherichia_albertii_6917.db
	Escherichia_coli_6920 Escherichia_coli_6920.db
	Escherichia_coli_9038 Escherichia_coli_9038.db
	Prevotella_dentalis_19591 Prevotella_dentalis_19591.db
	Prevotella_denticola_19594 Prevotella_denticola_19594.db
	Prevotella_intermedia_19600 Prevotella_intermedia_19600.db
	#!/usr/bin/env Rscript

	library(reshape)
	library(ggplot2)

	# set the work directory
	setwd('~/Downloads')

	# matrix-boxplots.txt should be a three-column, TAB-delimited matrix with a header for 'region', 'haplotype', and 'ratio'.
	m <- data.frame(read.table('matrix-boxplots.txt', header = TRUE, sep="\t"))