Removed trap dataset read limit

workflow/config/main.yaml

@@ -18,7 +18,6 @@ pod5_dataset_size : 293
 pod5_stride : 12 # Use 1 in x pod5 files from the ONT NO-MISS dataset to reduce dataset size / compute requirements
 trap_dataset_size: 1717
 trap_pod5_stride: 72
-trap_read_limit : '-n 500000'
 
 # custom ML
 torch_env : '../envs/torch_cpu.yaml'

workflow/rules/baseline_pipeline.smk

@@ -34,11 +34,6 @@ def get_batch_range(wildcards):
     if wildcards.dataset == 'trap':
         return [f'batch{x}' for x in range(1,config['trap_dataset_size']+1,config['trap_pod5_stride'])]
 
-def get_read_limit(wildcards):
-    if wildcards.dataset == 'trap':
-        return config["trap_read_limit"]
-    return ''
-
 wildcard_constraints:
     batch=r"(batch)?\d+",
     model=r'hac|fast'
@@ -91,10 +86,9 @@ rule basecall_pod5:
         benchmarking=get_benchmarking_file,
         min_qscore=get_qscore,
         dorado_model=get_model_name,
-        n_reads=get_read_limit
     shell:
         """
-        dorado basecaller --models-directory {config[dorado_model_dir]} {params.n_reads} --emit-fastq {params.benchmarking} {params.min_qscore} {params.dorado_model} {input.pod5} > {output}
+        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: