https://edge-dl.lanl.gov/PanGIA/database/

git clone https://github.com/poeli/pangia.git && cd pangia

curl -O https://edge-dl.lanl.gov/PanGIA/database/PanGIA_20180915_taxonomy.tar.gz
curl -O https://edge-dl.lanl.gov/PanGIA/database/PanGIA_20180915_NCBI_genomes_refseq89_BAV.fa.tar
curl -O https://edge-dl.lanl.gov/PanGIA/database/PanGIA_20180915_NCBI_genomes_refseq89_adds.fa.tar
curl -O https://edge-dl.lanl.gov/PanGIA/database/PanGIA_20180915_NCBI_genomes_refseq89_Human_GRCh38.p12.fa.tar

tar -xzf PanGIA_20180915_taxonomy.tar.gz
tar -xzf PanGIA_20180915_NCBI_genomes_refseq89_BAV.fa.tar
tar -xzf PanGIA_20180915_NCBI_genomes_refseq89_adds.fa.tar
tar -xzf PanGIA_20180915_NCBI_genomes_refseq89_Human_GRCh38.p12.fa.tar

./pangia.py \
  -i test.1.fastq test.2.fastq\
  -db database/NCBI_genomes_refseq89_*.fa  \
  -t 24

./pangia.py \
  -i SRR172902.fastq \
  -db database/NCBI_genomes_refseq89_BAV.fa database/NCBI_genomes_refseq89_adds.fa \
  -sb \
  -t 24

./pangia.py \
  -i HPV_test.fq \
  -db database/NCBI_genomes_*.fa \
  -lb background/QCB_background_REP1_allQC.pHostDB_NoHost.pangia.json.gz \
  -st combined \
  -t 24

conda install -c bokeh bokeh

pangia-vis.pl pangia_vis/data/test.tsv

usage: pangia.py [-h] (-i [FASTQ] [[FASTQ] ...] | -s [SAMFILE])
                 [-d [[BWA_INDEX] [[BWA_INDEX] ...]]] [-dp [PATH]]
                 [-asl <INT>] [-ams <INT>] [-ao <STR>] [-se]
                 [-st {bg,standalone,combined}]
                 [-m {report,class,extract,lineage}]
                 [-rf {basic,r,rnb,rnr,ri,patho,score,ref,full,all} [{basic,r,rnb,rnr,ri,patho,score,ref,full,all} ...]]
                 [-da] [-par <INT>] [-xnm <INT>] [-x [TAXID]] [-r [FIELD]]
                 [-t <INT>] [-o [DIR]] [-td [DIR]] [-kt] [-p <STR>] [-ps]
                 [-sb] [-lb [<FILE> [<FILE> ...]]] [-ms <FLOAT>] [-mr <INT>]
                 [-mb <INT>] [-ml <INT>] [-mc <FLOAT>] [-md <FLOAT>]
                 [-mrd <FLOAT>] [-np] [-pd] [-if <STR>] [-nc] [-c] [--silent]
                 [--verbose] [--version]

PanGIA Bioinformatics 1.0.0

optional arguments:
  -h, --help            show this help message and exit
  -i [FASTQ] [[FASTQ] ...], --input [FASTQ] [[FASTQ] ...]
                        Input one or multiple FASTQ file(s). Use space to
                        separate multiple input files.
  -s [SAMFILE], --sam [SAMFILE]
                        Specify the input SAM file. Use '-' for standard
                        input.
  -d [[BWA_INDEX] [[BWA_INDEX] ...]], --database [[BWA_INDEX] [[BWA_INDEX] ...]]
                        Name/path of BWA-MEM index(es). [default: None]
  -dp [PATH], --dbPath [PATH]
                        Path of databases. If this option isn't specified but
                        a path is provided in "--database" option, this path
                        of database will also be used in dbPath. Otherwise,
                        the program will search "database/" in program
                        directory. [default: database/]
  -asl <INT>, --alignSeedLength <INT>
                        Minimum seed length uses in BWA-MEM [default: 40]
  -ams <INT>, --alignMinScore <INT>
                        Minimum alignment score (AS:i tag) for BWA-MEM
                        [default: 60]
  -ao <STR>, --addOptions <STR>
                        Additional options for BWA-MEM (no need to add -t)
                        [default: '-h150 -B2']
  -se, --singleEnd      Input single-end reads or treat paired-end reads as
                        single-end [default: False]
  -st {bg,standalone,combined}, --scoreMethod {bg,standalone,combined}
                        You can specify one of the following scoring method:
                        "bg"         : compare mapping results with the background;
                        "standalone" : score based on uniqueness;
                        "combined"       : bg * standalone;
                        [default: 'standalone']
  -m {report,class,extract,lineage}, --mode {report,class,extract,lineage}
                        You can specify one of the following output modes:
                        "report"  : report a summary of profiling result;
                        "class"   : output results of classified reads;
                        "extract" : extract mapped reads;
                        "lineage" : output abundance and lineage in a line;
                        Note that only results/reads belongs to descendants of TAXID will be reported/extracted if option [--taxonomy TAXID] is specified. [default: 'report']
  -rf {basic,r,rnb,rnr,ri,patho,score,ref,full,all} [{basic,r,rnb,rnr,ri,patho,score,ref,full,all} ...], --reportFields {basic,r,rnb,rnr,ri,patho,score,ref,full,all} [{basic,r,rnb,rnr,ri,patho,score,ref,full,all} ...]
                        You can specify following set of fields to display in the report:
                        "basic" : essential fields that will display in the reports;
                        "r"     : rank specific read count;
                        "rnb"   : rank specific read count normalized by 
                                  both identity and # of ref (1*identity/num_refs);
                        "rnr"   : rank specific read count normalized by 
                                  the number of references (1/num_refs);
                        "ri"    : rank specific read identity
                                  (mapped_length-nm)/read_length;
                        "patho" : metadata of pathogen;
                        "score" : detail score information;
                        "ref"   : mapped reference(s) and their locations
                        "full"  : display additional information
                        "all"   : display all of above;
                        [default: 'all']
  -da, --displayAll     Display all taxonomies including being filtered out
                        [default: None]
  -par <INT>, --procAltRefs <INT>
                        Process the number of different references in
                        alternative alignments [default: 30]
  -xnm <INT>, --extraNM <INT>
                        Process alternative alignments with extra number of
                        mismatches than primary alignment [default: 1]
  -x [TAXID], --taxonomy [TAXID]
                        Specify a NCBI taxonomy ID. The program will only
                        report/extract the taxonomy you specified.
  -r [FIELD], --relAbu [FIELD]
                        The field will be used to calculate relative
                        abundance. [default: DEPTH_COV]
  -t <INT>, --threads <INT>
                        Number of threads [default: 1]
  -o [DIR], --outdir [DIR]
                        Output directory [default: .]
  -td [DIR], --tempdir [DIR]
                        Default temporary directory [default:
                        <OUTDIR>/<PREFIX>_tmp]
  -kt, --keepTemp       Keep temporary directory after finishing the pipeline.
  -p <STR>, --prefix <STR>
                        Prefix of the output file [default:
                        <INPUT_FILE_PREFIX>]
  -ps, --pathoScoreOnly
                        Only calculate score for pathogen under '--scoreMethod
                        bg'
  -sb, --saveBg         Save current readmapping result in JSON to
                        <PREFIX>.json
  -lb [<FILE> [<FILE> ...]], --loadBg [<FILE> [<FILE> ...]]
                        Load one or more background JSON gzip file(s)
                        [default: None
  -ms <FLOAT>, --minScore <FLOAT>
                        Minimum score to be considered valid [default: 0]
  -mr <INT>, --minReads <INT>
                        Minimum number of reads to be considered valid
                        [default: 10]
  -mb <INT>, --minRsnb <INT>
                        Minimum number of reads to be considered valid
                        [default: 2.5]
  -ml <INT>, --minLen <INT>
                        Minimum linear length to be considered valid [default:
                        200]
  -mc <FLOAT>, --minCov <FLOAT>
                        Minimum linear coverage to be considered a valid
                        strain [default: 0.004]
  -md <FLOAT>, --minDc <FLOAT>
                        Minimum depth of coverage to be considered a valid
                        strain [default: 0.01]
  -mrd <FLOAT>, --minRsdcnr <FLOAT>
                        Minimum rank specific depth of coverage normalized by
                        the number of mapped references to be considered a
                        valid strain [default: 0.0009]
  -np, --nanopore       Input reads is nanopore data. This option is
                        equivalent to use [-oa='-h 150 -x ont2d' -ms 0 -mr 1
                        -mb 3 -ml 50 -asl 24 -ams 70]. [default: FALSE]
  -pd, --pathogenDiscovery
                        Adjust options for pathogen discovery. This option is
                        equivalent to use [-ms 0 -mr 3 -mb 1 -ml 50 -asl 24
                        -ams 50 -mc 0 -md 0 -mrd 0]. [default: FALSE]
  -if <STR>, --ignoreFlag <STR>
                        Ignore reads that mapped to the references that have
                        the flag(s) [default: None]
  -nc, --noCutoff       Remove all cutoffs. This option is equivalent to use
                        [-ms 0 -mr 0 -mb 0 -ml 0 -mc 0 -md 0 -mrd 0].
  -c, --stdout          Write on standard output.
  --silent              Disable all messages.
  --verbose             Provide verbose running messages and keep all
                        temporary files.
  --version             Print version number.