rpetit3

# The Base AMI should be an ECS-optimized Amazon Linux 2 AMI
# Create the AMI with ~30-50GB of storage to allow for programs and temporary storage.

sudo yum install -y bzip2 wget git emacs

# Install AWS CLI to ${HOME}
wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh
bash Miniconda3-latest-Linux-x86_64.sh -b -f 
~/miniconda3/bin/conda init bash
source ~/.bashrc

rpetit3

#!/usr/bin/env nextflow

// Input parameters
params.genbank = "./NRS384.gbk"
params.fastq = "fastq_files"
params.pattern = "N*P{1,2}_trim.fq.gz"
params.outdir = "breseq_analysis_results"

// Reference and paired read channels
fastq_file_path = "$params.fastq/${params.pattern}"

rpetit3

sudo apt-get update && sudo apt-get install -y \
    build-essential \
    libssl-dev \
    uuid-dev \
    libgpgme11-dev \
    squashfs-tools \
    libseccomp-dev \
    pkg-config \
    git \
    cryptsetup-bin \

rpetit3

library("ggplot2")
files <-dir("/home/rpetit/projects/narsa/remaps/coverages_agr", pattern =".txt")
for(iin1:length(files)) {
    name <-gsub("-cov.txt$", "", files[i])
    # Read Coverage File
    file_path =paste0("/home/rpetit/projects/narsa/remaps/coverages_agr/", files[i])
    coverage <-read.table(file_path, sep="\t", header=FALSE)
    colnames(coverage) <-c("reference", "position", "coverage")
    max_x =nrow(coverage)
    max_y =max(coverage$coverage) + 10

rpetit3

# ===========================================================================
#
#                            PUBLIC DOMAIN NOTICE
#               National Center for Biotechnology Information
#
#  This software/database is a "United States Government Work" under the
#  terms of the United States Copyright Act.  It was written as part of
#  the author's official duties as a United States Government employee and
#  thus cannot be copyrighted.  This software/database is freely available
#  to the public for use. The National Library of Medicine and the U.S.

rpetit3

#!/usr/bin/env nextflow

params.output = null
params.sample = null
params.fq1 = null
params.fq2 = null
params.cpu = 1
params.coverage = 100
params.is_paired = false
params.no_length_filter = false

rpetit3

#! /usr/bin/env python
"""Clean up an input FASTQ file."""
import sys

from ruffus import *

from staphopia.helpers.time_job import time_job
from staphopia.tasks import fastq, shared

parser = cmdline.get_argparse(description='Cleanup FASTQ files')

rpetit3

PATH = '/home/rpetit/staphopia/apps/analysis-pipeline'
sample = 'N315_R1'

rule all:
    input:
        'analyses/fastq-stats/{sample}.cleanup.fastq.json'.format(
            sample=sample
        )

rule bbduk_phix:

rpetit3

################################
# Elasticsearch
################################

# Elasticsearch home directory
ES_HOME=/usr/share/elasticsearch

# Elasticsearch Java path
#JAVA_HOME=

rpetit3

# ======================== Elasticsearch Configuration =========================
#
# NOTE: Elasticsearch comes with reasonable defaults for most settings.
#       Before you set out to tweak and tune the configuration, make sure you
#       understand what are you trying to accomplish and the consequences.
#
# The primary way of configuring a node is via this file. This template lists
# the most important settings you may want to configure for a production cluster.
#
# Please see the documentation for further information on configuration options: