301 lines
14 KiB
JSON
301 lines
14 KiB
JSON
{
|
|
"$schema": "http://json-schema.org/draft-07/schema",
|
|
"$id": "https://raw.githubusercontent.com/./master/nextflow_schema.json",
|
|
"title": "epi2me-labs/wf-isoforms",
|
|
"description": "Isoform detection and characterisation.",
|
|
"url": "https://github.com/epi2me-labs/wf-isoforms",
|
|
"type": "object",
|
|
"definitions": {
|
|
"basic_input_output_options": {
|
|
"title": "Basic Input/Output Options",
|
|
"type": "object",
|
|
"fa_icon": "fas fa-terminal",
|
|
"description": "Define where the pipeline should find input data and save output data.",
|
|
"properties": {
|
|
"out_dir": {
|
|
"type": "string",
|
|
"default": "output",
|
|
"description": "Directory for output of all user-facing files."
|
|
},
|
|
"fastq": {
|
|
"type": "string",
|
|
"format": "path",
|
|
"description": "A fastq file or directory containing fastq input files or directories of input files.",
|
|
"help_text": "If directories named \\\"barcode*\\\" are found under the `--fastq` directory the data is assumed to be multiplex and each barcode directory will be processed independently. If `.fastq(.gz)` files are found under the `--fastq` directory the sample is assumed to not be multiplexed. In this second case `--samples` should be a simple name rather than a CSV file."
|
|
},
|
|
"sample": {
|
|
"type": "string",
|
|
"description": "A sample name for non-multiplexed data. Permissible if passing a file or directory of .fastq(.gz)."
|
|
},
|
|
"sample_sheet": {
|
|
"type": "string",
|
|
"format": "file-path",
|
|
"description": "CSV file with columns named `barcode`, `sample_name` and `type`. Permissible if passing a directory containing barcodeXX sub-directories."
|
|
},
|
|
"sanitize_fastq": {
|
|
"type": "boolean",
|
|
"description": "Use additional heuristics to identify barcodes from file paths.",
|
|
"help_text": "Enabling this option will group together files into samples by the presence of strings of the form `barcodeXXX` present in filenames, rather than simply files grouped into directories (as output by MinKNOW and the Guppy basecaller)."
|
|
},
|
|
"ref_genome": {
|
|
"type": "string",
|
|
"format": "file-path",
|
|
"description": "Path to reference genome sequence [.fa/.fq/.fa.gz/fq.gz]. Required for reference-based workflow"
|
|
},
|
|
"ref_annotation": {
|
|
"type": "string",
|
|
"format": "file-path",
|
|
"description": "A reference annotation of gff format"
|
|
}
|
|
},
|
|
"required": [
|
|
"fastq"
|
|
]
|
|
},
|
|
"global_options": {
|
|
"title": "Global options",
|
|
"type": "object",
|
|
"description": "Options for both sub-workflows",
|
|
"properties": {
|
|
"threads": {
|
|
"type": "integer",
|
|
"default": 4
|
|
},
|
|
"pychopper_opts": {
|
|
"type": "string",
|
|
"description": "Extra pychopper opts",
|
|
"default": "-m edlib"
|
|
},
|
|
"direct_rna": {
|
|
"type": "boolean",
|
|
"description": "Set to true for direct RNA sequencing. Omits the pychopper step.",
|
|
"default": false
|
|
},
|
|
"bundle_min_reads": {
|
|
"type": "integer",
|
|
"description": "Minimum size of bam bundle for parallel processing."
|
|
},
|
|
"stringtie_opts": {
|
|
"type": "string",
|
|
"description": "Extra options for stringtie transcript assembly.",
|
|
"default": " --conservative "
|
|
},
|
|
"transcript_table_cov_thresh": {
|
|
"type": "integer",
|
|
"description": "Minimum coverage for a transcript to appear in the report table",
|
|
"default": 50
|
|
},
|
|
"denovo": {
|
|
"type": "boolean",
|
|
"description": "Use denovo transcript assembly rather than reference guided",
|
|
"default": false
|
|
}
|
|
}
|
|
},
|
|
"reference_wf_options": {
|
|
"title": "Options for reference-based workflow",
|
|
"type": "object",
|
|
"description": "Parameters that are used solely for the referenc-guided workflow",
|
|
"properties": {
|
|
"plot_gffcmp_stats": {
|
|
"type": "boolean",
|
|
"description": "Create a pdf of plots from showing gffcompare results"
|
|
},
|
|
"gffcompare_opts": {
|
|
"type": "string",
|
|
"description": "Extra options for gffcompare -r",
|
|
"default": " -R "
|
|
},
|
|
"minimap_index_opts": {
|
|
"type": "string",
|
|
"description": "minimap2 extra indexing options.",
|
|
"default": "-k14"
|
|
},
|
|
"minimap2_opts": {
|
|
"type": "string",
|
|
"description": "minimap2 extra mapping options.",
|
|
"default": "-uf"
|
|
},
|
|
"minimum_mapping_quality": {
|
|
"type": "integer",
|
|
"description": "filter aligned reads by MAPQ quality.",
|
|
"default": 40
|
|
},
|
|
"poly_context": {
|
|
"type": "integer",
|
|
"description": "Region size at end of reads to apply poly(A) filter.",
|
|
"default": 24
|
|
},
|
|
"max_poly_run": {
|
|
"type": "integer",
|
|
"description": "Max poly(A) region allowed with poly_context-sized end regions.",
|
|
"default": 8
|
|
}
|
|
}
|
|
},
|
|
"denovo_wf_options": {
|
|
"title": "Options for de novo-based workflow",
|
|
"type": "object",
|
|
"description": "Parameters that are used solely for the de novo workflow",
|
|
"properties": {
|
|
"batch_size": {
|
|
"type": "integer",
|
|
"description": "Maximum sequences per input batch (-1 means no limit)",
|
|
"default": -1
|
|
},
|
|
"batch_max_seq": {
|
|
"type": "integer",
|
|
"description": "Maximum sequences per input batch (-1 means no limit)",
|
|
"default": -1
|
|
},
|
|
"cls_mode": {
|
|
"type": "string",
|
|
"description": "Clustering mode",
|
|
"default": "sahlin"
|
|
},
|
|
"kmer_size": {
|
|
"type": "integer",
|
|
"description": "Kmer size",
|
|
"default": 11
|
|
},
|
|
"window_size": {
|
|
"type": "integer",
|
|
"description": "Window size",
|
|
"default": 15
|
|
},
|
|
"min_left_cls": {
|
|
"type": "integer",
|
|
"description": "Minimum cluser size in the left batch",
|
|
"default": 2
|
|
},
|
|
"consensus_period": {
|
|
"type": "integer",
|
|
"description": "Consensus period (-1 means no consensus)",
|
|
"default": 500
|
|
},
|
|
"consensus_minimum": {
|
|
"type": "integer",
|
|
"description": "Minimum consensus sample size:",
|
|
"default": 50
|
|
},
|
|
"consensus_maximum": {
|
|
"type": "integer",
|
|
"description": "Maximum consensus sample size",
|
|
"default": -150
|
|
},
|
|
"min_shared": {
|
|
"type": "integer",
|
|
"description": "Minimum number of minimizers shared between read and cluster",
|
|
"default": 5
|
|
},
|
|
"min_qual": {
|
|
"description": "Minimum average quality value",
|
|
"type": "number",
|
|
"default": 7.0
|
|
},
|
|
"mapped_threshold": {
|
|
"description": "Minimum mapped fraction of read to be included in cluster",
|
|
"type": "number",
|
|
"default": 0.65
|
|
},
|
|
"aligned_threshold": {
|
|
"tpye": "number",
|
|
"description": "Minimum aligned fraction of read to be included in cluster",
|
|
"default": 0.2
|
|
},
|
|
"min_fraction": {
|
|
"type": "number",
|
|
"description": "Minimum fraction of minimizers shared compared to best hit, in order to continue mapping",
|
|
"default": 0.8
|
|
},
|
|
"min_prob_no_hits": {
|
|
"type": "number",
|
|
"description": "Minimum probability for i consecutive minimizers to be different between read and representative",
|
|
"default": 0.2
|
|
}
|
|
}
|
|
},
|
|
"meta_data": {
|
|
"title": "Meta Data",
|
|
"type": "object",
|
|
"description": "",
|
|
"default": "",
|
|
"properties": {
|
|
"report_name": {
|
|
"type": "string",
|
|
"default": "report",
|
|
"description": "Output report filename suffix."
|
|
},
|
|
"disable_ping": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "Enable to prevent sending a workflow ping."
|
|
}
|
|
}
|
|
},
|
|
"generic_options": {
|
|
"title": "Generic options",
|
|
"type": "object",
|
|
"fa_icon": "far fa-question-circle",
|
|
"description": "Less common options for the pipeline, typically set in a config file.",
|
|
"help_text": "These options are common to all nf-core pipelines and allow you to customise some of the core preferences for how the pipeline runs.\n\nTypically these options would be set in a Nextflow config file loaded for all pipeline runs, such as `~/.nextflow/config`.",
|
|
"properties": {
|
|
"help": {
|
|
"type": "boolean",
|
|
"description": "Display help text.",
|
|
"fa_icon": "fas fa-question-circle",
|
|
"hidden": true
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"allOf": [
|
|
{
|
|
"$ref": "#/definitions/basic_input_output_options"
|
|
},
|
|
{
|
|
"$ref": "#/definitions/global_options"
|
|
},
|
|
{
|
|
"$ref": "#/definitions/reference_wf_options"
|
|
},
|
|
{
|
|
"$ref": "#/definitions/denovo_wf_options"
|
|
},
|
|
{
|
|
"$ref": "#/definitions/meta_data"
|
|
},
|
|
{
|
|
"$ref": "#/definitions/generic_options"
|
|
}
|
|
],
|
|
"properties": {
|
|
"aws_image_prefix": {
|
|
"type": "string",
|
|
"hidden": true
|
|
},
|
|
"aws_queue": {
|
|
"type": "string",
|
|
"hidden": true
|
|
},
|
|
"wfversion": {
|
|
"type": "string",
|
|
"default": "v0.1.2",
|
|
"hidden": true
|
|
},
|
|
"monochrome_logs": {
|
|
"type": "boolean"
|
|
},
|
|
"validate_params": {
|
|
"type": "boolean",
|
|
"default": true
|
|
},
|
|
"show_hidden_params": {
|
|
"type": "boolean"
|
|
}
|
|
},
|
|
"docs": {
|
|
"intro": "## Introduction\n\nThis workflow identifies RNA isoforms using either cDNA or direct RNA (dRNA) \nOxford Nanopore reads.\n\n### Preprocesing\ncDNA reads are initially preprocessed by [pychopper](https://github.com/nanoporetech/pychopper) \nfor the identification of full-length reads, as well as trimming and orientation correction (This step is omitted for \n direct RNA reads).\n\n### Reference-aided approach\n* Full length reads are mapped to a supplied reference genome using [minimap2](https://github.com/lh3/minimap2)\n* Transcripts are assembled by [stringtie](http://ccb.jhu.edu/software/stringtie) \nin long read mode (with or without a guide reference annotation) to generate the GFF annotation.\n* The annotation generated by the pipeline is compared to the reference annotation. \nusing [gffcompare](http://ccb.jhu.edu/software/stringtie/gffcompare.shtml)\n\n### de novo-based approach (experimental!)\n* Sequence clusters are generated using [isONclust2](https://github.com/nanoporetech/isONclust2)\n * If a reference genome is supplied, cluster quality metrics are determined by comparing \n with clusters generated from a minimap2 alignment.\n* A consensus sequence for each cluster is generated using [spoa](https://github.com/rvaser/spoa)\n* Three rounds of polishing using racon and minimap2 to give a final polished CDS for each gene.\n* Full-length reads are then mapped to these polished CDS.\n* Transcripts are assembled by stringtie as for the reference-based approach.\n* __Note__: This approach is currently not supported with direct RNA reads.\n\n### Workflow inputs\n- Directory containing cDNA/direct RNA reads. Or a directory containing subdirectories each with reads from different samples\n (in fastq/fastq.gz format)\n- Reference genome in fasta format (required for reference-based assembly).\n- Optional reference annotation in GFF2/3 format.",
|
|
"links": "## Useful links\n\n* [nextflow](https://www.nextflow.io/)\n* [docker](https://www.docker.com/products/docker-desktop)\n* [Singularity](https://sylabs.io/singularity/)\n* [conda](https://docs.conda.io/en/latest/miniconda.html)\n* [racon](https://github.com/isovic/racon)\n* [spoa](https://github.com/rvaser/spoa)\n* [inONclust](https://github.com/ksahlin/isONclust)\n* [isONclust2](https://github.com/nanoporetech/isONclust2)"
|
|
}
|
|
} |