conda create -n <your_env_name> -c conda-forge -c bioconda compleasm
conda activate <your_env_name>
compleasm -h

VERSION=0.2.6
docker run huangnengcsu/compleasm:v${VERSION} compleasm -h

VERSION=0.2.6
singularity exec docker:https://huangnengcsu/compleasm:v${VERSION} compleasm -h

wget https://github.com/huangnengCSU/compleasm/releases/download/v0.2.6/compleasm-0.2.6_x64-linux.tar.bz2
tar -jxvf compleasm-0.2.6_x64-linux.tar.bz2
compleasm_kit/compleasm.py -h

git clone https://github.com/huangnengCSU/compleasm.git

git clone https://github.com/lh3/miniprot
cd miniprot && make

wget https://eddylab.org/software/hmmer/hmmer.tar.gz 
tar zxf hmmer.tar.gz
cd hmmer-3.3.2
./configure --prefix /your/install/path
make
make check
make install

git clone https://github.com/smirarab/sepp.git
cd sepp
python setup.py config -c
python setup.py install

run             Run compleasm including miniprot alignment and completeness evaluation
analyze         Evaluate genome completeness from provided miniprot alignment
download        Download specified BUSCO lineage
list            List local or remote BUSCO lineages
miniprot        Run miniprot alignment

python compleasm.py run [-h] -a ASSEMBLY_PATH -o OUTPUT_DIR [-t THREADS] 
                        [-l LINEAGE] [-L LIBRARY_PATH] [-m {lite,busco}] [--specified_contigs SPECIFIED_CONTIGS [SPECIFIED_CONTIGS ...]] 
                        [--miniprot_execute_path MINIPROT_EXECUTE_PATH] [--hmmsearch_execute_path HMMSEARCH_EXECUTE_PATH] 
                        [--autolineage] [--sepp_execute_path SEPP_EXECUTE_PATH] 
                        [--min_diff MIN_DIFF] [--min_identity MIN_IDENTITY] [--min_length_percent MIN_LENGTH_PERCENT] 
                        [--min_complete MIN_COMPLETE] [--min_rise MIN_RISE]

  -a, --assembly_path        Input genome file in FASTA format
  -o, --output_dir           The output folder
  -t, --threads              Number of threads to use
  -l, --lineage              Specify the name of the BUSCO lineage to be used. (e.g. eukaryota, primates, saccharomycetes etc.)
  -L, --library_path         Folder path to download lineages or already downloaded lineages. 
                             If not specified, a folder named "mb_downloads" will be created on the current running path by default to store the downloaded lineage files.
  -m, --mode                 The mode of evaluation. Default mode is busco. 
                             lite:  Without using hmmsearch to filtering protein alignment.
                             busco: Using hmmsearch on all candidate predicted proteins to purify the miniprot alignment to improve accuracy.
  --specified_contigs        Specify the contigs to be evaluated, e.g. chr1 chr2 chr3. If not specified, all contigs will be evaluated.
  --outs                     output if score at least FLOAT*bestScore [0.95]
  --miniprot_execute_path    Path to miniprot executable file. 
                             If not specified, compleasm will search for miniprot in the directory where compleasm.py is located, the current execution directory, and system environment variables.
  --hmmsearch_execute_path   Path to hmmsearch executable file.
                             If not specified, compleasm will search for hmmsearch in the directory where compleasm.py is located, the current execution directory, and system environment variables.
  --autolineage              Automatically search for the best matching lineage without specifying lineage file.
  --sepp_execute_path        Path to sepp executable file. This is required if you want to use the autolineage mode.

  --min_diff               The thresholds for the best matching and second best matching. default=0.2
  --min_identity           The identity threshold for valid mapping results. default=0.4
  --min_length_percent     The fraction of protein for valid mapping results. default=0.6
  --min_complete           The length threshold for complete gene. default=0.9

# with lineage specified
python compleasm.py run -a genome.fasta -o output_dir -l eukaryota -t 8

# autolineage mode
python compleasm.py run -a genome.fasta -o output_dir -t 8 --autolineage

# with custom specified already downloaded lineage folder
python compleasm.py run -a genome.fasta -o output_dir -l eukaryota -t 8 -L /path/to/lineages_folder

# specify contigs
python compleasm.py run -a genome.fasta -o output_dir -l eukaryota -t 8 --specified_contigs chr1 chr2 chr3 chr4 chr5 chr6 chr7 chr8 chr9 chr10 chr11 chr12 chr13 chr14 chr15 chr16 chr17 chr18 chr19 chr20 chr21 chr22

python compleasm.py analyze [-h] -g GFF -l LINEAGE -o OUTPUT_DIR [-t THREADS] [-L LIBRARY_PATH] 
                            [-m {lite,busco}] [--hmmsearch_execute_path HMMSEARCH_EXECUTE_PATH]
                            [--specified_contigs SPECIFIED_CONTIGS [SPECIFIED_CONTIGS ...]] 
                            [--min_diff MIN_DIFF] [--min_identity MIN_IDENTITY] [--min_length_percent MIN_LENGTH_PERCENT] 
                            [--min_complete MIN_COMPLETE] [--min_rise MIN_RISE]

  -g, --gff                 Miniprot output gff file
  -l, --lineage             BUSCO lineage name
  -o, --output_dir          Output analysis folder
  -t, --threads             Number of threads to use
  -L, --library_path        Folder path to stored lineages.
  -m, --mode                The mode of evaluation. Default mode is fast. 
                            lite:  Without using hmmsearch to filtering protein alignment.
                            busco: Using hmmsearch on all candidate predicted proteins to purify the miniprot alignment to improve accuracy.
  --hmmsearch_execute_path  Path to hmmsearch executable
                            If not specified, compleasm will search for hmmsearch in the directory where compleasm.py is located, the current execution directory, and system environment variables.
  --specified_contigs       Specify the contigs to be evaluated, e.g. chr1 chr2 chr3. If not specified, all contigs will be evaluated.

# analysis with miniprot output gff file
python compleasm.py analyze -g miniprot.gff -o output_dir -l eukaryota -t 8

# specify contigs
compleasm analyze -g miniprot.gff -o output_dir -l eukaryota -t 8 --specified_contigs chr1 chr2 chr3 chr4 chr5 chr6 chr7 chr8 chr9 chr10 chr11 chr12 chr13 chr14 chr15 chr16 chr17 chr18 chr19 chr20 chr21 chr22

python compleasm.py download [-h] [-L LIBRARY_PATH] lineages [lineages ...]

positional arguments:  
  lineages                Specify the names of the BUSCO lineages to be downloaded. (e.g. eukaryota, primates, saccharomycetes etc.)

optional arguments:
  -L, --library_path      The destination folder to store the downloaded lineage files.
                          If not specified, a folder named "mb_downloads" will be created on the current running path by default.

python compleasm.py download saccharomycetes primates brassicales -L /path/to/lineages_folder

python compleasm.py download saccharomycetes,primates,brassicales -L /path/to/lineages_folder

python compleasm.py miniprot [-h] -a ASSEMBLY -p PROTEIN -o OUTDIR [-t THREADS] [--miniprot_execute_path MINIPROT_EXECUTE_PATH]

  -a, --assembly             Input genome file in FASTA format
  -p, --protein              Input protein file
  -o, --outdir               Miniprot alignment output directory
  -t, --threads              Number of threads to use
  --outs                     output if score at least FLOAT*bestScore [0.95]
  --miniprot_execute_path    Path to miniprot executable file. 
                             If not specified, compleasm will search for miniprot in the directory where compleasm.py is located, the current execution directory, and system environment variables.

python compleasm.py miniprot -a genome.fasta -p protein.faa -o output_dir -t 8

python compleasm.py list [-h] [--remote] [--local] [-L LIBRARY_PATH]

  --remote             List remote BUSCO lineages
  --local              List local BUSCO lineages
  -L, --library_path   Folder path to stored lineages.

# list local lineages
python compleasm.py list --local -L /path/to/lineages_folder

# list remote lineages
python compleasm.py list --remote

python compleasm.py protein [-h] -p PROTEINS -l LINEAGE -o OUTDIR [-t THREADS]
                            [-L LIBRARY_PATH]
                            [--hmmsearch_execute_path HMMSEARCH_EXECUTE_PATH]

-p, --proteins             Input protein file
-l, --lineage              BUSCO lineage name
-o, --outdir               Output analysis folder
-t, --threads              Number of threads to use
-L, --library_path         Folder path to stored lineages
--hmmsearch_execute_path   Path to hmmsearch executable.
                           If not specified, compleasm will search for miniprot in the directory where compleasm.py is located, the current execution directory, and system environment variables.

python compleasm.py protein -p input.faa -l eukaryota -t 8 -o output_dir