Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

docs: updates for Sprocket #219

Draft
wants to merge 3 commits into
base: main
Choose a base branch
from
Draft

docs: updates for Sprocket #219

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e68cf38
Update star.wdl
a-frantz Feb 14, 2025
1965882
revise: Capitalize group: Common
a-frantz Feb 14, 2025
1ff9620
WIP
a-frantz Feb 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 10 additions & 10 deletions tools/bwa.wdl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,15 +16,15 @@ task bwa_aln {
prefix: "Prefix for the BAM file. The extension `.bam` will be added."
read_group: {
description: "Read group information for BWA to insert into the header. BWA format: '@RG\tID:foo\tSM:bar'",
group: "common",
group: "Common",
}
use_all_cores: {
description: "Use all cores? Recommended for cloud environments.",
group: "common",
group: "Common",
}
ncpu: {
description: "Number of cores to allocate for task",
group: "common",
group: "Common",
}
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
}
Expand Down Expand Up @@ -112,15 +112,15 @@ task bwa_aln_pe {
prefix: "Prefix for the BAM file. The extension `.bam` will be added."
read_group: {
description: "Read group information for BWA to insert into the header. BWA format: '@RG\tID:foo\tSM:bar'",
group: "common",
group: "Common",
}
use_all_cores: {
description: "Use all cores? Recommended for cloud environments.",
group: "common",
group: "Common",
}
ncpu: {
description: "Number of cores to allocate for task",
group: "common",
group: "Common",
}
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
}
Expand Down Expand Up @@ -207,15 +207,15 @@ task bwa_mem {
prefix: "Prefix for the BAM file. The extension `.bam` will be added."
read_group: {
description: "Read group information for BWA to insert into the header. BWA format: '@RG\tID:foo\tSM:bar'",
group: "common",
group: "Common",
}
use_all_cores: {
description: "Use all cores? Recommended for cloud environments.",
group: "common",
group: "Common",
}
ncpu: {
description: "Number of cores to allocate for task",
group: "common",
group: "Common",
}
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
}
Expand Down Expand Up @@ -300,7 +300,7 @@ task build_bwa_db {
reference_fasta: "Input reference Fasta file to index with bwa. Should be compressed with gzip."
db_name: {
description: "Name of the output gzipped tar archive of the bwa reference files. The extension `.tar.gz` will be added.",
group: "common",
group: "Common",
}
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
}
Expand Down
4 changes: 2 additions & 2 deletions tools/deeptools.wdl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,11 +16,11 @@ task bam_coverage {
prefix: "Prefix for the BigWig file. The extension `.bw` will be added."
use_all_cores: {
description: "Use all cores? Recommended for cloud environments.",
group: "common",
group: "Common",
}
ncpu: {
description: "Number of cores to allocate for task",
group: "common",
group: "Common",
}
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
}
Expand Down
4 changes: 2 additions & 2 deletions tools/fastqc.wdl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,11 +16,11 @@ task fastqc {
prefix: "Prefix for the FastQC results directory. The extension `.tar.gz` will be added."
use_all_cores: {
description: "Use all cores? Recommended for cloud environments.",
group: "common",
group: "Common",
}
ncpu: {
description: "Number of cores to allocate for task",
group: "common",
group: "Common",
}
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
}
Expand Down
6 changes: 3 additions & 3 deletions tools/fq.wdl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,7 @@ task fqlint {
}
panic: {
description: "Panic on first error (true) or log all errors (false)?",
group: "common",
group: "Common",
}
modify_memory_gb: "Add to or subtract from dynamic memory allocation. Default memory is determined by the size of the inputs. Specified in GB."
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
Expand Down Expand Up @@ -113,11 +113,11 @@ task subsample {
prefix: "Prefix for the output FASTQ file(s). The extension `.R1.subsampled.fastq.gz` and `.R2.subsampled.fastq.gz` will be added."
probability: {
description: "The probability a record is kept, as a decimal (0.0, 1.0). Cannot be used with `record-count`. Any `probability<=0.0` or `probability>=1.0` to disable.",
group: "common",
group: "Common",
}
record_count: {
description: "The exact number of records to keep. Cannot be used with `probability`. Any `record_count<=0` to disable.",
group: "common",
group: "Common",
}
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
}
Expand Down
2 changes: 1 addition & 1 deletion tools/gatk4.wdl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -419,7 +419,7 @@ task mark_duplicates_spark {
}
create_bam: {
description: "Enable BAM creation (true)? Or only output MarkDuplicates metrics (false)?",
group: "common",
group: "Common",
}
optical_distance: "Maximum distance between read coordinates to consider them optical duplicates. If `0`, then optical duplicate marking is disabled. Suggested settings of 100 for unpatterned versions of the Illumina platform (e.g. HiSeq) or 2500 for patterned flowcell models (e.g. NovaSeq). Calculation of distance depends on coordinate data embedded in the read names, typically produced by the Illumina sequencing machines. Optical duplicate detection will not work on non-standard names without modifying `read_name_regex`."
modify_memory_gb: "Add to or subtract from the default memory allocation. Default memory allocation is determined by the size of the input BAM. Specified in GB."
Expand Down
16 changes: 8 additions & 8 deletions tools/htseq.wdl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,11 +25,11 @@ task count {
prefix: "Prefix for the feature counts file. The extension `.feature-counts.txt` will be added."
feature_type: {
description: "Feature type (3rd column in GTF file) to be used, all features of other type are ignored",
group: "common",
group: "Common",
}
idattr: {
description: "GFF attribute to be used as feature ID",
group: "common",
group: "Common",
}
mode: {
description: "Mode to handle reads overlapping more than one feature. `union` is recommended for most use-cases.",
Expand All @@ -42,27 +42,27 @@ task count {
}
include_custom_header: {
description: "Include a custom header for the output file? This is not an official feature of HTSeq. If true, the first line of the output file will be `~{idattr}\t~{prefix}`. This may break downstream tools that expect the typical headerless HTSeq output format.",
group: "common",
group: "Common",
}
pos_sorted: {
description: "Is the BAM position sorted (true) or name sorted (false)? It is **highly** recommended to use a name sorted BAM file. This is because HTSeq will re-sort position-sorted BAMs with an inefficient algorithm, causing very large memory and disk space allocations (especially for large BAMs).",
group: "common",
group: "Common",
}
nonunique: {
description: "Score reads that align to or are assigned to more than one feature?",
group: "common",
group: "Common",
}
secondary_alignments: {
description: "Score secondary alignments (SAM flag 0x100)?",
group: "common",
group: "Common",
}
supplementary_alignments: {
description: "Score supplementary/chimeric alignments (SAM flag 0x800)?",
group: "common",
group: "Common",
}
minaqual: {
description: "Skip all reads with alignment quality lower than the given minimum value",
group: "common",
group: "Common",
}
modify_memory_gb: "Add to or subtract from dynamic memory allocation. Default memory is determined by the size of the inputs. Specified in GB."
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
Expand Down
12 changes: 6 additions & 6 deletions tools/kraken2.wdl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -191,20 +191,20 @@ task build_db {
tarballs: "Tarballs containing the NCBI taxonomy (generated by the `download_taxonomy` task) and at least one library (generated by the `download_library` or `create_library_from_fastas` task). Tarballs must not have a root directory."
db_name: {
description: "Name for output in compressed, archived format. The suffix `.tar.gz` will be added.",
group: "common",
group: "Common",
}
protein: "Construct a protein database?"
use_all_cores: {
description: "Use all cores? Recommended for cloud environments.",
group: "common",
group: "Common",
}
kmer_len: "K-mer length in bp that will be used to build the database"
minimizer_len: "Minimizer length in bp that will be used to build the database"
minimizer_spaces: "Number of characters in minimizer that are ignored in comparisons"
max_db_size_gb: "Maximum number of GBs for Kraken 2 hash table; if the Kraken 2 estimator determines more would normally be needed, the reference library will be downsampled to fit."
ncpu: {
description: "Number of cores to allocate for task",
group: "common",
group: "Common",
}
modify_memory_gb: "Add to or subtract from dynamic memory allocation. Default memory is determined by the size of the inputs. Specified in GB."
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
Expand Down Expand Up @@ -311,17 +311,17 @@ task kraken {
prefix: "Prefix for the Kraken2 output files. The extensions `.kraken2.txt` and `.kraken2.sequences.txt.gz` will be added."
store_sequences: {
description: "Store and output main Kraken2 output in addition to the summary report?",
group: "common",
group: "Common",
}
use_names: "Print scientific names instead of just taxids?"
use_all_cores: {
description: "Use all cores? Recommended for cloud environments.",
group: "common",
group: "Common",
}
min_base_quality: "Minimum base quality used in classification"
ncpu: {
description: "Number of cores to allocate for task",
group: "common",
group: "Common",
}
modify_memory_gb: "Add to or subtract from dynamic memory allocation. Default memory is determined by the size of the inputs. Specified in GB."
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
Expand Down
2 changes: 1 addition & 1 deletion tools/mosdepth.wdl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ task coverage {
use_fast_mode: "Use Mosdepth's 'fast mode'? This enables the `-x` flag."
min_mapping_quality: {
description: "Minimum mapping quality to pass to the `-Q` flag of `mosdepth`",
group: "common",
group: "Common",
}
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
}
Expand Down
36 changes: 18 additions & 18 deletions tools/ngsderive.wdl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,19 +18,19 @@ task strandedness {
outfile_name: "Name for the strandedness TSV file"
split_by_rg: {
description: "Contain one entry in the output TSV per read group, in addition to an `overall` entry",
group: "common",
group: "Common",
}
min_reads_per_gene: {
description: "Filter any genes that don't have at least `min_reads_per_gene` reads mapping to them",
group: "common",
group: "Common",
}
num_genes: {
description: "How many genes to sample",
group: "common",
group: "Common",
}
min_mapq: {
description: "Minimum MAPQ to consider for supporting reads",
group: "common",
group: "Common",
}
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
}
Expand Down Expand Up @@ -103,7 +103,7 @@ task instrument {
outfile_name: "Name for the instrument TSV file"
num_reads: {
description: "How many reads to analyze from the start of the file. Any n < 1 to parse whole file.",
group: "common",
group: "Common",
}
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
}
Expand Down Expand Up @@ -156,11 +156,11 @@ task read_length {
outfile_name: "Name for the readlen TSV file"
majority_vote_cutoff: {
description: "To call a majority readlen, the maximum read length must have at least `majority-vote-cutoff`% reads in support",
group: "common",
group: "Common",
}
num_reads: {
description: "How many reads to analyze from the start of the file. Any n < 1 to parse whole file.",
group: "common",
group: "Common",
}
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
}
Expand Down Expand Up @@ -219,7 +219,7 @@ task encoding {
outfile_name: "Name for the encoding TSV file"
num_reads: {
description: "How many reads to analyze from the start of the file(s). Any n < 1 to parse whole file(s).",
group: "common",
group: "Common",
}
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
}
Expand Down Expand Up @@ -271,19 +271,19 @@ task junction_annotation {
prefix: "Prefix for the summary TSV and junction files. The extensions `.junction_summary.tsv` and `.junctions.tsv` will be added."
min_intron: {
description: "Minimum size of intron to be considered a splice",
group: "common",
group: "Common",
}
min_mapq: {
description: "Minimum MAPQ to consider for supporting reads",
group: "common",
group: "Common",
}
min_reads: {
description: "Filter any junctions that don't have at least `min_reads` reads supporting them",
group: "common",
group: "Common",
}
fuzzy_junction_match_range: {
description: "Consider found splices within `+-k` bases of a known splice event annotated",
group: "common",
group: "Common",
}
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
}
Expand Down Expand Up @@ -355,27 +355,27 @@ task endedness {
outfile_name: "Name for the endedness TSV file"
lenient: {
description: "Return a zero exit code on unknown results",
group: "common",
group: "Common",
}
calc_rpt: {
description: "Calculate and output Reads-Per-Template. This will produce a more sophisticated estimate for endedness, but uses substantially more memory (can reach up to 200% of BAM size in memory consumption for some inputs).",
group: "common",
group: "Common",
}
round_rpt: {
description: "Round RPT to the nearest INT before comparing to expected values. Appropriate if using `--num-reads` > 0.",
group: "common",
group: "Common",
}
split_by_rg: {
description: "Contain one entry per read group",
group: "common",
group: "Common",
}
paired_deviance: {
description: "Distance from 0.5 split between number of f+l- reads and f-l+ reads allowed to be called 'Paired-End'. Default of `0.0` only appropriate if the whole file is being processed.",
group: "common",
group: "Common",
}
num_reads: {
description: "How many reads to analyze from the start of the file. Any n < 1 to parse whole file.",
group: "common",
group: "Common",
}
modify_memory_gb: "Add to or subtract from dynamic memory allocation. Default memory is determined by value of `calc_rpt` and the size of the input. Specified in GB."
modify_disk_size_gb: "Add to or subtract from dynamic disk space allocation. Default disk size is determined by the size of the inputs. Specified in GB."
Expand Down
Loading
Loading