From 2ec82801e802fbe9176b1ca4b9af43c7285ea84b Mon Sep 17 00:00:00 2001 From: Felipe Marques de Almeida Date: Fri, 16 Feb 2024 15:45:17 +0000 Subject: [PATCH] update docs/assets --- docs/assets/defaults.config | 40 +++++++++++++++++++++++++++++-------- 1 file changed, 32 insertions(+), 8 deletions(-) diff --git a/docs/assets/defaults.config b/docs/assets/defaults.config index a7541241..2a926041 100644 --- a/docs/assets/defaults.config +++ b/docs/assets/defaults.config @@ -56,14 +56,16 @@ params { // Select the appropriate shasta config to use for assembly // Since shasta v0.8 (Oct/2021) this parameter is now mandatory. +// You can check availability at: https://paoloshasta.github.io/shasta/Configurations.html shasta_config = "Nanopore-Oct2021" // Tells the pipeline to interpret the long reads as "corrected" long reads. -// This will activate (if available) the options for corrected reads in the -// assemblers: -corrected (in canu), --pacbio-corr|--nano-corr (in flye), etc. -// Be cautious when using this parameter. If your reads are not corrected, and +// This will activate (if available) the options for corrected or even high +// quality (hq) reads in the assemblers. +// Be cautious when using this parameter. If your reads are not corrected|hq, and // you use this parameter, you will probably do not generate any contig. - corrected_long_reads = false + corrected_longreads = false + high_quality_longreads = false // This parameter below (hybrid_strategy) is to select the hybrid strategies adopted by the pipeline. // Read the documentation https://mpgap.readthedocs.io/en/latest/manual.html to know more about the hybrid strategies. @@ -132,10 +134,32 @@ params { skip_shasta = false // Nanopore longreads only assemblies shasta_additional_parameters = null // Must be given as shown in shasta manual. E.g. " --Reads.minReadLength 5000 " -// Max resource options -// Defaults only, expecting to be overwritten - max_memory = '14.GB' - max_cpus = 6 + + /* + * Resources controlling parameters + * + * Here some parameters that allow the user to better tune the resources used by the pipeline. + * + * The start_asm_{mem,cpus} parameter tells the pipeline how much memory should the assembly + * modules and quast request in the first try. This is essential for bigger genomes in order + * to avoid having to fail the first try due lack of memory and then running again (automatically) + * using all the max values allowed with the max_{mem,cpus} parameters. + * + * The max_memory and max_cpus parameters, tell the pipeline how much is the maximum number of + * these items that is allowoed per job. The pipeline start by requesting less mem&cpus than + * what is defined by these params, and, in case the first try fails, it then maxes out the job + * to use the maximum number you allowed. + * + * The max_time parameter defines how long a single job is allowed to run. + */ + + // starting values for the assembly jobs (and quast) to ask for in the very first try + start_asm_mem = 20.GB + start_asm_cpus = 6 + + // maximum values to be used on automatic second try in case of lack of memory (all jobs) + max_memory = 40.GB + max_cpus = 10 max_time = '40.h' } \ No newline at end of file