meren

#!/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"))

meren

FROM ubuntu:xenial

ENV ANVIO_VERSION 5.5

ENV DEBIAN_FRONTEND noninteractive

RUN apt-get update
RUN apt-get install locales
RUN locale-gen en_US.UTF-8
ENV LANG='en_US.UTF-8' LANGUAGE='en_US:en' LC_ALL='en_US.UTF-8'

meren

#!/usr/bin/env python

# you run this first:
#
#    python 01-gen-nucmer-jobs.py affiliations.txt MAGs_input_dir
#

import os
import sys
import anvio.fastalib as u

meren

#!/bin/bash

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). For instance, CMX_PAN_v5 would be a good one."
    exit -1
fi

PROJECT=$1

meren

diff --git a/anvio/bottleroutes.py b/anvio/bottleroutes.py
index 6953f0a..400901d 100644
--- a/anvio/bottleroutes.py
+++ b/anvio/bottleroutes.py
@@ -224,7 +224,9 @@ def charts(d, split_name, show_outlier_SNVs=False):

     layers = sorted(d.p_meta['samples'])

+    print('AM I OK? :(')
     coverage_values_dict = d.split_coverage_values.get(split_name)

meren

#!/bin/bash

# RUN THIS SCRIPT LIKE THIS:
#
#   /groups/merenlab/merens-master-script-for-pangenomics.shx PROJECT_NAME E_MAIL
#
#
# This is how the samples.txt must look like (don't use anything but underscore character for sample names):
# sample    fasta
# S_01	fasta-01.fa

meren

# let's assume we have two FASTA files for two samples:
#
# sample_01: fasta_01.fa
# sample_02: fasta_02.fa
#

# genrating trna profile dtabases for each sample:
trna-profile fasta_01.fa --name sample_01 -o sample_01.db
trna-profile fasta_01.fa --name sample_01 -o sample_01.db

meren

#!/bin/bash

# CALL THIS SCRIPT WITH A PROJECT NAME PARAMETER

set -e

PROJECT_NAME=$1

if [ ! -f "samples.txt"  ]
then

meren

#!/bin/bash

# A simple loop to serially map all samples.
# referenced from within http://merenlab.org/tutorials/assembly_and_mapping/

# how many threads should each mapping task use?
NUM_THREADS=4

for sample in `awk '{print $1}' samples.txt`
do

meren

diff --git a/anvio/merger.py b/anvio/merger.py
index 1986e88..614f0b4 100644
--- a/anvio/merger.py
+++ b/anvio/merger.py
@@ -247,6 +247,8 @@ class MultipleRuns:
             sample_profile_db = dbops.ProfileDatabase(runinfo['profile_db'], quiet = True)
             sample_gene_profiles = sample_profile_db.db.get_table_as_dict(tables.gene_coverages_table_name, tables.gene_coverages_table_structure)
             for g in sample_gene_profiles.values():
+                if not g['mean_coverage']:
+                    g['mean_coverage'] = 0