jelber2

# goes along with http://seqanswers.com/forums/showthread.php?p=220925#post220925
#
# assumes you have PBJelly, blasr, tabix, bcftools, samtools installed
# below I am using a machine with 70 cores on a single node, adjust to the number of cores to your machine
# The scripts below are obviously not designed for use with a cluster, but can be modified
#
#########################
# STEP 1 Combine the FASTQ files and remove the originals to save space
#########################
## first combine files and delete the originals to save space

jelber2

#! /bin/bash

set -e

# installing fasta-splitter.pl
## wget http://kirill-kryukov.com/study/tools/fasta-splitter/files/fasta-splitter-0.2.6.zip
## unzip fasta-splitter-0.2.6.zip

# assumes initial genome to be error-corrected by pilon is called
## genome.pilon-0.fasta

jelber2

Adapter trimming with BBDuk 38.82

module load bbtools/38.82
module load bcftools/1.14
bbduk.sh threads=8 \
in1=raw/170283.mate1.fastq.gz \
in2=raw/170283.mate2.fastq.gz \
out1=fastq/170283-trimmed.mate1.fastq.gz \
out2=fastq/170283-trimmed.mate2.fastq.gz \

jelber2

This was with https://zymo-files.s3.amazonaws.com/BioPool/ZymoBIOMICS.STD.refseq.v2.zip

RAW_SUP_Duplex                                         pg_asm_1x_corrected_SUP_duplex                         pg_asm_2x_corrected_SUP_duplex                         pg_asm_3x_corrected_SUP_duplex
Bacillus_subtilis                                      Bacillus_subtilis                                      Bacillus_subtilis                                      Bacillus_subtilis
# target bases: 4041255                                # target bases: 4041255                                # target bases: 4041255                                # target bases: 4041255
# target bases overlapping regions: 4041255 (100.00%)  # target bases overlapping regions: 4041255 (100.00%)  # target bases overlapping regions: 4041255 (100.00%)  # target bases overlapping regions: 4041255 (100.00%)
1159311 reference bases covered by exactly one contig  3791080 reference bases covered by exactly one contig  3642732 reference bases covered by exa

jelber2

MethPhaser installation

Install micromamba or mamba or conda

# Install micromamba
"${SHELL}" <(curl -L micro.mamba.pm/install.sh)

You will then see something like this in a BASH shell (parts with "(type....)" are added for instructions

jelber2

# output from best commit #fcdfa97 (https://github.com/google/best), .summary_identity_stats.csv files using reads
# aligned to concatenated chr20_MATERNAL and chr20_PATERNAL from hg002v1.0.1.fasta.gz (https://github.com/marbl/HG002) (https://s3-us-west-2.amazonaws.com/human-pangenomics/T2T/HG002/assemblies/hg002v1.0.1.fasta.gz)
# using mm2-fast commit # 10bde16 using settings: --eqx --secondary=no -Y -c -ax map-ont -k 19 -w 13 -t 48 
# or using these settings for Illumina NextSeq2000 reads: -t 48 --eqx --secondary=no -acx sr
#
# brutal_rewrite (br) commit # ad87f92 (https://github.com/natir/br) using settings: -k 19 -m graph
# kmer read filter (kmrf) commit # 36cad24 (https://github.com/natir/kmrf) using setting: -k 17
# peregrine-2021 (pg_asm) commit # 6698eb1 (https://github.com/cschin/peregrine-2021): using default settings
#
# herro (herro) commit # c41dc30 (https://github.com/lbcb-sci/herro) using defaults and model at time of commit

jelber2

# previous versions allowed to generate directly from BAM, but there seemed to have been some troubles 
# between versions of XAM, so this version is working so far for its intended purpose on https://github.com/brendanofallon/jovian
# also, this version is rather fast
#
#
# note: ignores quality scores at the moment - fixed in revision#4
# note2: outputs to STDOUT a SAM file without a header
# tested with julialang v1.10.2 and XAM v0.4.0
# $ julia shredBAM.jl input.bam 300 > test.sam.noheader
#

jelber2

# tested on Julialang v.1.10.2 , DataStructures v0.18.16, and FASTX v2.1.4
# Usage
# $ julia stitch-fastq.jl chr20.herro.fasta.Q30.recal.shred.fastq > chr20.herro.fasta.Q30.recal.fastq
#
import Pkg; Pkg.add("FASTX")
import Pkg; Pkg.add("DataStructures")
using DataStructures
using FASTX

function process_fastq_file(filename::String)

jelber2

# tested on Julialang v.1.10.2, DataStructures v0.18.16, and FASTX v2.1.4
# Usage
# $ julia stitch-fasta.jl chr20.herro.fasta.Q30.recal.shred.fasta > chr20.herro.fasta.Q30.recal.fasta
#
import Pkg; Pkg.add("FASTX")
import Pkg; Pkg.add("DataStructures")
using DataStructures
using FASTX

function process_fasta_file(filename::String)

jelber2

using XAM
using ArgParse
using DataFrames
using Dates
using Plots
using StatsBase
using Plots.PlotMeasures


function parse_commandline()