ShaiberAlon

#!/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:

ShaiberAlon

import pandas as pd
import os

project_name = "GATA4"
SAMPLES = pd.read_csv('samples.txt', sep='\t', header=0, index_col=False)
SAMPLES = SAMPLES['samples'].values
os.makedirs("00_LOGS", exist_ok=True)
print(SAMPLES)
localrules: all,QC_report, merge, get_sample_info, prepare_things_for_GAST

ShaiberAlon

#!/bin/bash

# CALL THIS SCRIPT WITH A PROJECT NAME PARAMETER

set -e

if [ "$#" -ne 1 ]; then
    echo "You need to give a project name as an argument to this script (and it better be a single, short and descriptive word without funny characters)."
    exit -1
fi

ShaiberAlon

# Short bash to create an artificial gene call for a sequence for a collection of genes
# the artificial gene call would start at the first nucleotide of the first gene (denoted n_i) and end at the
# last nucleotide of the second gene (denoted n_f). The assumption is that n_i < n_f.
# Another assumption: both genes are from the same contig.
# The output is a file in the external gene calls format of anvi'o

# Example
# $ bash create_my_gene_calls_file.shx MY_GENE_CALL_FILE.txt CONTIGS.db 45 105
# this will give a gene call starting from the first nucleotide of gene 45 and ending at the last nucleotide of gene 105

ShaiberAlon

Homebrew build logs for vim on macOS 10.11.6
Build date: 2017-04-13 11:53:13

ShaiberAlon

import anvio.utils as utils
fasta_suffix = '.fna'
output_file = 'merged_fasta.fna'
samples_list = 'samples.txt'
output_fasta_dictionary = {}
with open(samples_list,'r') as s:
        for sample in s:
                sample=sample.strip()
                sample_fasta = "".join([sample,fasta_suffix])
                print(sample)

ShaiberAlon

#!/bin/bash

### DEFAULTS (FEEL FREE TO EDIT THESE) ##################
NUM_THREADS_FOR_MAPPING=10
NUM_THREADS_FOR_HMMSCAN=4
NUM_THREADS_FOR_ANVI_GEN_CONTIG=4
NUM_THREADS_FOR_ANVI_PROFILE=4
NUM_THREADS_FOR_ANVI_MERGE=4

# configure whether SNV analysis will be included or not (if you want it included then leave this empty

ShaiberAlon

#!/usr/bin/env python

import anvio.utils as u
import argparse
import sys
parser =  argparse.ArgumentParser(description='Get nucleotides from fasta file beyween user defined nucleotide positions inside a specified contig')
parser.add_argument('-1','--N1',metavar='INT',dest='n1',type=int,help='Nucleotide sequence start position')
parser.add_argument('-2','--N2',metavar='INT',dest='n2',type=int,help='Nucleotide sequence start position')
parser.add_argument('-c','--contig',metavar='STRING',dest='c',help='Contig name')
parser.add_argument('-o','--out',metavar='FILE',dest='output',help='Output file')

ShaiberAlon

#!/usr/bin/env python
# -*- coding: utf-8


__author__ = "Alon Shaiber"
__copyright__ = ""
__credits__ = []
__license__ = ""
__version__ = 1
__maintainer__ = "Alon Shaiber"

ShaiberAlon

import csv
import numpy as np
import argparse

parser = argparse.ArgumentParser(description='Adding the 2MA column to anvio AA table')
parser.add_argument('-i','--input',metavar='FILE',dest='input_file',help='Input file')
parser.add_argument('-o','--out',metavar='FILE',dest='output_file',help='Name of file for output')
parser.add_argument('-r','--ratio',metavar='NUMBER',dest='ratio',type=float,help='Minimal ratio between consensus and the second most covered amino-acid. If the ratio is lower than the provided threshold, then the 2MA value would be in the form concensus_concensus')
args = parser.parse_args()