噬菌体基因组快速注释工具——pharokka教程

# 使用conda创建虚拟环境，并安装pharokka
conda create -n Pharokka -c conda-forge -c bioconda pharokka
# 下载pharokka数据库并解压，如下图所示
wget -c -nv "https://zenodo.org/record/8276347/files/pharokka_v1.8.0_databases.tar.gz"
tar -xzf pharokka_v1.8.0_databases.tar.gz

# 查看或运行 pharokka.py 时因 NumPy 版本不兼容会触发警告并导致报错
export PYTHONWARNINGS="ignore"
# 查看pharokka帮助文档
pharokka.py --help 
usage: pharokka.py [-h] [-i INFILE] [-o OUTDIR] [-d DATABASE] [-t THREADS] [-f] [-p PREFIX] [-l LOCUSTAG] [-g GENE_PREDICTOR] [-m] [-s] [-c CODING_TABLE] [-e EVALUE] [--fast] [--mmseqs2_only] [--meta_hmm] [--dnaapler] [--custom_hmm CUSTOM_HMM] [--genbank] [--terminase]
                   [--terminase_strand TERMINASE_STRAND] [--terminase_start TERMINASE_START] [--skip_extra_annotations] [--skip_mash] [--minced_args MINCED_ARGS] [--mash_distance MASH_DISTANCE] [--trna_scan_model {general,bacterial}] [-V] [--citation]
pharokka: fast phage annotation program
options:
  -h, --help            show this help message and exit
  -i INFILE, --infile INFILE
                        Input genome file in fasta format.
  -o OUTDIR, --outdir OUTDIR
                        Directory to write the output to.
  -d DATABASE, --database DATABASE
                        Database directory. If the databases have been installed in the default directory, this is not required. Otherwise specify the path.
  -t THREADS, --threads THREADS
                        Number of threads. Defaults to 1.
  -f, --force           Overwrites the output directory.
  -p PREFIX, --prefix PREFIX
                        Prefix for output files. This is not required.
  -l LOCUSTAG, --locustag LOCUSTAG
                        User specified locus tag for the gff/gbk files. This is not required. A random locus tag will be generated instead.
  -g GENE_PREDICTOR, --gene_predictor GENE_PREDICTOR
                        User specified gene predictor. Use "-g phanotate" or "-g prodigal" or "-g prodigal-gv" or "-g genbank". 
                        Defaults to phanotate usually and prodigal-gv in meta mode.
  -m, --meta            meta mode for metavirome input samples
  -s, --split           split mode for metavirome samples. -m must also be specified. 
                        Will output separate split FASTA, gff and genbank files for each input contig.
  -c CODING_TABLE, --coding_table CODING_TABLE
                        translation table for prodigal. Defaults to 11.
  -e EVALUE, --evalue EVALUE
                        E-value threshold for MMseqs2 database PHROGs, VFDB and CARD and PyHMMER PHROGs database search. Defaults to 1E-05.
  --fast, --hmm_only    Runs PyHMMER (HMMs) with PHROGs only, not MMseqs2 with PHROGs, CARD or VFDB. 
                        Designed for phage isolates, will not likely be faster for large metagenomes.
  --mmseqs2_only        Runs MMseqs2 with PHROGs, CARD and VFDB only (same as Pharokka v1.3.2 and prior). Default in meta mode.
  --meta_hmm            Overrides --mmseqs2_only in meta mode. Will run both MMseqs2 and PyHMMER.
  --dnaapler            Runs dnaapler to automatically re-orient all contigs to begin with terminase large subunit if found. 
                        Recommended over using '--terminase'.
  --custom_hmm CUSTOM_HMM
                        Run pharokka with a custom HMM profile database suffixed .h3m. 
                        Please use create this with the create_custom_hmm.py script.
  --genbank             Flag denoting that -i/--input is a genbank file instead of the usual FASTA file. 
                         The CDS calls in this file will be preserved and re-annotated.
  --terminase           Runs terminase large subunit re-orientation mode. 
                        Single genome input only and requires --terminase_strand and --terminase_start to be specified.
  --terminase_strand TERMINASE_STRAND
                        Strand of terminase large subunit. Must be "pos" or "neg".
  --terminase_start TERMINASE_START
                        Start coordinate of the terminase large subunit.
  --skip_extra_annotations
                        Skips tRNAscan-SE 2, MinCED and Aragorn.
  --skip_mash           Skips running mash to find the closest match for each contig in INPHARED.
  --minced_args MINCED_ARGS
                        extra commands to pass to MINced (please omit the leading hyphen for the first argument). You will need to use quotation marks e.g. --minced_args "minNR 2 -minRL 21"
  --mash_distance MASH_DISTANCE
                        mash distance for the search against INPHARED. Defaults to 0.2.
  --trna_scan_model {general,bacterial}
                        tRNAscan-SE model
  -V, --version         Print pharokka Version
  --citation            Print pharokka Citation

# 使用phanotate预测基因组CDS 
pharokka.py -d Pharokka/Version-V4 -g phanotate -i MW460250.1.fasta -o MW460250.1 --threads 16 --force --prefix MW460250.1 --locustag MW460250.1 --dnaapler
# 使用prodigal-gv预测基因组CDS 指定 tRNAscan 模型
pharokka.py -d Pharokka/Version-V4 -g prodigal-gv -i MW460250.1.fasta -o MW460250.1 --threads 16 --force --prefix MW460250.1 --locustag MW460250.1  --trna_scan_model general