intial version

workflow/rules/baseline_pipeline.smk

@@ -0,0 +1,68 @@
+def get_model_name(wildcards):
+    config_param=f'{wildcards.model}_model_name'
+    return config[config_param]
+
+def get_model_requirement(wildcards):
+    return f"{config['dorado_model_dir']}/{config[f'{wildcards.model}_model_name']}
+
+def get_benchmarking_file(wildcards):
+    config_param = f'{wildcards.model}_benchmarks_file'
+    if config[config_param]:
+        return f'--batchsize-benchmarks-file {config[config_param]}'
+    return ''
+
+def get_qscore(wildcards):
+    config_param = f'{wildcards.model}_min_q'
+    if config[config_param]:
+        return f'--min-qscore {config[config_param]}'
+    return ''
+
+def get_batch_names(input_file):
+    with open(input_file,'rt') as ih:
+        return [line.strip().split('/')[-1].split('.')[0] for line in ih]
+
+rule download_pod5:
+    output:
+        '../data/raw_pod5/PBK98658_853a956f_57f83f46_{batch}.pod5'
+    threads: 1
+    wildcard_constraints:
+        batch="\d+"
+    shell:
+        """
+        aws s3 cp --no-sign-request s3://ont-open-data/nomiss_96BC_P2I_SUP_2026/raw/pod5/PBK98658_853a956f_57f83f46_{wildcards.batch}.pod5 {output}
+        """
+
+rule basecall_pod5:
+    input:
+        pod5='../data/raw_pod5/PBK98658_853a956f_57f83f46_{batch}.pod5',
+        model=get_model_requirement
+    output:
+        '../data/basecalled_reads/{model}/PBK98658_853a956f_57f83f46_{batch}.fastq.gz'
+    threads:
+        32
+    resources:
+        gpu=1
+    params:
+        benchmarking=get_benchmarking_file,
+        min_qscore=get_qscore,
+        dorado_model=get_model_name
+    wildcard_constraints:
+        batch="\d+",
+        model="hac|fast"
+    shell:
+        """
+        dorado basecaller --models-directory {config[dorado_model_dir]} --emit-fastq {params.benchmarking} {params.min_qscore} {params.dorado_model} {input.pod5} > {output}
+        """
+
+rule concatenate_basecalled_fastq:
+    input:
+        expand('../data/basecalled_reads/{{model}}/PBK98658_853a956f_57f83f46_{batch}.fastq.gz',batch=range(1,config["pod5_dataset_size"]+1,config["pod5_stride"]))
+    output:
+        '../data/basecalled_reads/{model}.fastq.gz'
+    threads: 1
+    wildcard_constraints:
+        model="hac|fast"
+    shell:
+        """
+        zcat {input} > {output}
+        """

workflow/rules/preparation.smk

@@ -0,0 +1,84 @@
+import os
+import hashlib
+
+# Prepwork
+
+def get_genome_file_name(wildcards):
+    return '../data/reference_genomes/'+'_'.join(x.lower() for x in wildcards.species.split())+'.fasta'
+
+def get_unique_download_dir(wildcards):
+    unique_id = hashlib.md5(wildcards.species.encode()).hexdigest()[:8]
+    return config["tmp_dir"]+'/'+unique_id
+
+def format_cli_arg(wildcards):
+    # Replaces underscores with spaces for the CLI command
+    return wildcards.species.replace("_", " ")
+
+rule pull_ncbi_datasets_cli:
+    output:
+        config["datasets_binary"]
+    params:
+        arch=config["arch"]
+    threads: 1
+    shell:
+        """
+        curl https://ftp.ncbi.nlm.nih.gov/pub/datasets/command-line/v2/linux-{params.arch}/datasets -o {output}
+        chmod a+x {output}
+        """
+
+rule pull_dorado_models:
+    output:
+        directory(f"{config['dorado_model_dir']}/{config['fast_model_name']}"),
+        directory(f"{config['dorado_model_dir']}/{config['hac_model_name']}")
+    threads: 1
+    shell:
+        """
+        dorado download --models-directory {config[dorado_model_dir]} --model {config[fast_model_name]}
+        dorado download --models-directory {config[dorado_model_dir]} --model {config[hac_model_name]}
+        """
+
+rule download_reference_genome:
+    input:
+        config["datasets_binary"]
+    output:
+        temp('../data/reference_genomes/{species}.fasta')
+    params:
+        api_key=os.environ['NCBI_API_KEY'],
+        wd=get_unique_download_dir,
+        ncbi_tax_name=lambda w: format_cli_arg(w)
+    threads: 1
+    shell:
+        """
+        echo {wildcards.species}
+        rm -rf {params.wd}
+        mkdir {params.wd}
+        {config[datasets_binary]} download genome taxon "{params.ncbi_tax_name}" --reference --no-progressbar --filename {params.wd}/{wildcards.species}.zip
+        unzip -d {params.wd} -o {params.wd}/{wildcards.species}.zip 
+        mv {params.wd}/ncbi_dataset/data/*/*fna {output}
+        rm -rf {params.wd}
+        """
+
+rule concatenate_reference_genomes:
+    input:
+        expand("../data/reference_genomes/{species}.fasta",species=config["species_list"])
+    output:
+        "../data/reference_genomes/full_reference.fasta"
+    threads: 1
+    shell:
+        """
+        cat {input} > {output}
+        """
+
+rule create_minimap_index:
+    input: 
+        "../data/reference_genomes/full_reference.fasta"
+    output:
+        "../data/reference_genomes/full_reference.mmi"
+    threads:
+        32
+    conda:
+        "../envs/minimap.yaml"
+    shell:
+        """
+        minimap2 -x map-ont -t {threads} -d {output} {input}
+        """