./run_clairs_to -T tumor.bam -R ref.fa -o output -t 8 -p ont_r10_guppy_sup_4khz

## Final SNV output VCF file: output/snv.vcf.gz
## Final Indel output VCF file: output/indel.vcf.gz

docker run -it \
  -v ${INPUT_DIR}:${INPUT_DIR} \
  -v ${OUTPUT_DIR}:${OUTPUT_DIR} \
  hkubal/clairs-to:latest \
  /opt/bin/run_clairs_to \
  --tumor_bam_fn ${INPUT_DIR}/tumor.bam \      ## use your tumor bam file name here
  --ref_fn ${INPUT_DIR}/ref.fa \               ## use your reference file name here
  --threads ${THREADS} \                       ## maximum threads to be used
  --platform ${PLATFORM} \                     ## options: {ont_r10_dorado_sup_4khz, ont_r10_dorado_hac_4khz, ont_r10_dorado_sup_5khz, ont_r10_guppy_sup_4khz, ont_r10_guppy_hac_5khz, ilmn, hifi_revio}
  --output_dir ${OUTPUT_DIR}                   ## output path prefix 

INPUT_DIR="[YOUR_INPUT_FOLDER]"        # e.g. /home/user1/input (absolute path needed)
OUTPUT_DIR="[YOUR_OUTPUT_FOLDER]"      # e.g. /home/user1/output (absolute path needed)
mkdir -p ${OUTPUT_DIR}

conda config --add channels defaults
conda create -n singularity-env -c conda-forge singularity -y
conda activate singularity-env

# singularity pull docker pre-built image
singularity pull docker://hkubal/clairs-to:latest

# run the sandbox like this afterward
singularity exec \
  -B ${INPUT_DIR},${OUTPUT_DIR} \
  clairs-to_latest.sif \
  /opt/bin/run_clairs_to \
  --tumor_bam_fn ${INPUT_DIR}/tumor.bam \      ## use your tumor bam file name here
  --ref_fn ${INPUT_DIR}/ref.fa \               ## use your reference file name here
  --threads ${THREADS} \                       ## maximum threads to be used
  --platform ${PLATFORM} \                     ## options: {ont_r10_dorado_sup_4khz, ont_r10_dorado_hac_4khz, ont_r10_dorado_sup_5khz, ont_r10_guppy_sup_4khz, ont_r10_guppy_hac_5khz, ilmn, hifi_revio}
  --output_dir ${OUTPUT_DIR} \                 ## output path prefix
  --conda_prefix /opt/micromamba/envs/clairs-to

wget -O linux-64_micromamba-1.5.1-2.tar.bz2 https://micro.mamba.pm/api/micromamba/linux-64/latest
mkdir micromamba
tar -xvjf linux-64_micromamba-1.5.1-2.tar.bz2 -C micromamba
cd micromamba
./bin/micromamba shell init -s bash -p .
source ~/.bashrc

wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
chmod +x ./Miniconda3-latest-Linux-x86_64.sh 
./Miniconda3-latest-Linux-x86_64.sh

# create and activate an environment named clairs-to
# install pypy and packages in the environment
# for micromamba
micromamba create -n clairs-to -c bioconda -c pytorch -c conda-forge pytorch tqdm clair3 bcftools einops scipy scikit-learn python=3.9.0 -y
micromamba activate clairs-to

## for anaconda 
#conda create -n clairs-to -c bioconda -c pytorch -c conda-forge pytorch tqdm clair3 bcftools einops python=3.9.0 -y
#source activate clairs-to

git clone https://github.com/HKU-BAL/ClairS-TO.git
cd ClairS-TO

# make sure in clairs-to environment
# download pre-trained models and other resources
echo ${CONDA_PREFIX}
mkdir -p ${CONDA_PREFIX}/bin/clairs-to_models
mkdir -p ${CONDA_PREFIX}/bin/clairs-to_databases
mkdir -p ${CONDA_PREFIX}/bin/clairs-to_cna_data
wget http://www.bio8.cs.hku.hk/clairs-to/models/clairs-to_models.tar.gz
wget http://www.bio8.cs.hku.hk/clairs-to/databases/clairs-to_databases.tar.gz
wget http://www.bio8.cs.hku.hk/clairs-to/cna_data/reference_files.tar.gz
tar -zxvf clairs-to_models.tar.gz -C ${CONDA_PREFIX}/bin/clairs-to_models/
tar -zxvf clairs-to_databases.tar.gz -C ${CONDA_PREFIX}/bin/clairs-to_databases/
tar -zxvf reference_files.tar.gz -C ${CONDA_PREFIX}/bin/clairs-to_cna_data/

#CLAIRSTO_PATH=`pwd`

## to enable realignment module
#sudo apt install g++ libboost-all-dev -y
#cd ${CLAIRSTO_PATH}/src/realign && g++ -std=c++14 -O1 -shared -fPIC -o realigner ssw_cpp.cpp ssw.c realigner.cpp && g++ -std=c++11 -shared -fPIC -o debruijn_graph -O3 debruijn_graph.cpp

## to install allele counter for verdict module
#sudo apt install curl zlib1g-dev libbz2-dev liblzma-dev libcurl4-openssl-dev gcc -y
#cd ${CLAIRSTO_PATH}/src/verdict/allele_counter && chmod +x ./setup.sh && /bin/bash ./setup.sh ${CLAIRSTO_PATH}/src/verdict/allele_counter

#cd ${CLAIRSTO_PATH}

./run_clairs_to --help

git clone https://github.com/HKU-BAL/ClairS-TO.git
cd ClairS-TO

# build a docker image named hkubal/clairs-to:latest
# might require docker authentication to build docker image
docker build -f ./Dockerfile -t hkubal/clairs-to:latest .

# run the docker image like Option 1
docker run -it hkubal/clairs-to:latest /opt/bin/run_clairs_to --help

./run_clairs_to \
  --tumor_bam_fn ${INPUT_DIR}/tumor.bam \    ## use your tumor bam file name here
  --ref_fn ${INPUT_DIR}/ref.fa \             ## use your reference file name here
  --threads ${THREADS} \                     ## maximum threads to be used
  --platform ${PLATFORM} \                   ## options: {ont_r10_dorado_sup_4khz, ont_r10_dorado_hac_4khz, ont_r10_dorado_sup_5khz, ont_r10_guppy_sup_4khz, ont_r10_guppy_hac_5khz, ilmn, hifi_revio}
  --output_dir ${OUTPUT_DIR}                 ## output path prefix
 
## Final SNV output VCF file: output/snv.vcf.gz
## Final Indel output VCF file: output/indel.vcf.gz

  -T, --tumor_bam_fn TUMOR_BAM_FN   Tumor BAM file input. The input file must be samtools indexed.
  -R, --ref_fn FASTA                Reference file input. The input file must be samtools indexed.
  -o, --output_dir OUTPUT_DIR       VCF output directory.
  -t, --threads THREADS             Max threads to be used.
  -p, --platform PLATFORM           Select the sequencing platform of the input. Possible options {ont_r10_dorado_sup_4khz, ont_r10_dorado_hac_4khz, ont_r10_dorado_sup_5khz, ont_r10_guppy_sup_4khz, ont_r10_guppy_hac_5khz, ilmn, hifi_revio}.

  -s SAMPLE_NAME, --sample_name SAMPLE_NAME
                        Define the sample name to be shown in the VCF file. Default: SAMPLE.
  -c CTG_NAME, --ctg_name CTG_NAME                                                                                                                                                                         
                        The name of the contigs to be processed. Split by ',' for multiple contigs. Default: all contigs will be processed.
  --include_all_ctgs    Call variants on all contigs, otherwise call in chr{1..22,X,Y} and {1..22,X,Y}.                                                                
  -r REGION, --region REGION                                                                                                                                                                               
                        A region to be processed. Format: `ctg_name:start-end` (start is 1-based, including both end positions).                                                                                                         
  -b BED_FN, --bed_fn BED_FN                                                                                                                                                                               
                        Path to a BED file. Call variants only in the provided BED regions.                                                                                                                
  -G VCF_FN, --genotyping_mode_vcf_fn VCF_FN                                                                                                                               
                        VCF file input containing candidate sites to be genotyped. Variants will only be called at the sites in the VCF file if provided.                                                  
  -H VCF_FN, --hybrid_mode_vcf_fn VCF_FN                                                                                                                                           
                        Enable hybrid calling mode that combines the de novo calling results and genotyping results at the positions in the VCF file given.
  --print_ref_calls     Show reference calls (0/0) in VCF file in genotyping or hybrid mode.
  --disable_indel_calling
                        Disable Indel calling. Default: Enabled.
  --snv_min_af FLOAT
                        Minimal SNV AF required for a variant to be called. Decrease SNV_MIN_AF might increase a bit of sensitivity, but in trade of precision, speed and accuracy. Default: 0.05.
  --indel_min_af FLOAT
                        Minimal Indel AF required for a variant to be called. Default: 0.05.
  --min_coverage INT
                        Minimal coverage required for a variant to be called. Default: 4.
  -q INT, --qual INT    If set, variants with >INT will be tagged as PASS, or LowQual otherwise. Default: ONT - 12 , PacBio HiFi - 8, Illumina - 4.
  --qual_cutoff_phaseable_region INT
                        If set, variants called in phaseable regions with >INT will be tagged as PASS, or LowQual otherwise. Supersede by `--qual`.
  --qual_cutoff_unphaseable_region INT
                        If set, variants called in unphaseable regions with >INT will be tagged as PASS, or LowQual otherwise. Supersede by `--qual`.
  --panel_of_normals FILENAMES
                        The path of the panel of normals (PoNs) used for tagging non-somatic variants. Split by ',' if using multiple PoNs. Default: 'gnomad.r2.1.af-ge-0.001.sites.vcf.gz,dbsnp.b138.non-somatic.sites.vcf.gz,1000g-pon.sites.vcf.gz'.
  --panel_of_normals_require_allele_matching BOOLEANS
                        Use together with `--panel_of_normals`. Whether to require allele matching for each PoN. Split by ',' if using multiple PoNs. Default: 'True,True,False'.
  --snv_output_prefix PATH_PREFIX
                        Prefix for SNV output VCF filename. Default: snv.
  --indel_output_prefix PATH_PREFIX
                        Prefix for Indel output VCF filename. Default: indel.
  --call_indels_only_in_these_regions BED_FN
                        Call Indel only in the provided regions. Supersede by `--bed_fn`. To call Indel in the whole genome, input a BED covering the whole genome. Default: 'GRCh38Chr1-22XY_excludedGIABStratifV3.3AllDifficultRegions_includedCMRGv1.0.bed'                     
  --do_not_print_nonsomatic_calls
                        Do not print those non-somatic variants tagged by `--panel_of_normals`.

  --snv_pileup_affirmative_model_path PATH                                                                                                                                            
                        Specify the path to your own SNV pileup affirmative model.                                                                                                  
  --snv_pileup_negational_model_path PATH                                                                                                                                              
                        Specify the path to your own SNV pileup negational model. 
  --indel_pileup_affirmative_model_path PATH
                        Specify the path to your own Indel pileup affirmative model.
  --indel_pileup_negational_model_path PATH
                        Specify the path to your own Indel pileup negational model.
  -d, --dry_run         Print the commands that will be ran, but do not run them.
  --chunk_size INT
                        The size of each chuck for parallel processing. Default: 5000000.
  --remove_intermediate_dir
                        Remove the intermediate directory before finishing to save disk space.
  --python PATH         Absolute path of python, python3 >= 3.9 is required.
  --pypy PATH           Absolute path of pypy3, pypy3 >= 3.6 is required.
  --samtools PATH       Absolute path of samtools, samtools version >= 1.10 is required.
  --parallel PATH       Absolute path of parallel, parallel >= 20191122 is required.
  --longphase PATH
                        Absolute path of longphase, longphase >= 1.3 is required.
  --whatshap PATH       Absolute path of whatshap, whatshap >= 1.0 is required.
  --use_longphase_for_intermediate_phasing
                        Use longphase for intermediate phasing.
  --use_whatshap_for_intermediate_phasing
                        Use whatshap for phasing.
  --use_longphase_for_intermediate_haplotagging USE_LONGPHASE_FOR_INTERMEDIATE_HAPLOTAGGING
                        Use longphase instead of whatshap for intermediate haplotagging.
  --disable_intermediate_phasing
                        Disable intermediate phasing, runs faster but reduces precision.
  --disable_nonsomatic_tagging
                        Disable non-somatic variants tagging and ignore `--panel_of_normals`.
  --disable_verdict
                        Disable using verdict to tag the variants in CNA regions. We suggest using the parameter only for sample with tumor purity estimation lower than 0.8. Default: Enabled.                                    

./run_clairs_to -T tumor.bam -R ref.fa -o output -t 8 -p ont_r10_guppy_sup_4khz -C chr21,chr22

./run_clairs_to -T tumor.bam -R ref.fa -o output -t 8 -p ont_r10_guppy_sup_4khz -r chr20:1000000-2000000

./run_clairs_to -T tumor.bam -R ref.fa -o output -t 8 -p ont_r10_guppy_sup_4khz -G input.vcf

echo -e "${CTG1}\t${START_POS_1}\t${END_POS_1}" > input.bed
echo -e "${CTG2}\t${START_POS_2}\t${END_POS_2}" >> input.bed
...

./run_clairs_to -T tumor.bam -R ref.fa -o output -t 8 -p ont_r10_guppy_sup_4khz -B input.bed