class Input:
"""Input fields."""
class MyGroup:
foo = IntegerField(label="Foo", required=False, default=42)
bar = StringField(label="Bar", required=False)
class MyGroup2:
foo = IntegerField(label="Foo", required=False)
my_group = GroupField(MyGroup, label="My group")
my_group2 = GroupField(
MyGroup2,
label="My group2 that has all elements without defaults.")
class Input:
"""Input fields to process ImportSra."""
sra_accession = ListField(StringField(), label="SRA accession(s)")
show_advanced = BooleanField(label="Show advanced options", default=False)
class Advanced:
"""Advanced options."""
prefetch = BooleanField(label="Prefetch SRA file", default=True)
max_size_prefetch = StringField(
label="Maximum file size to download in KB",
default="20G",
description="A unit prefix can be used instead of a value in KB (e.g. 1024M or 1G).",
)
min_spot_id = IntegerField(label="Minimum spot ID", required=False)
max_spot_id = IntegerField(label="Maximum spot ID", required=False)
min_read_len = IntegerField(label="Minimum read length", required=False)
clip = BooleanField(label="Clip adapter sequences", default=False)
aligned = BooleanField(label="Dump only aligned sequences", default=False)
unaligned = BooleanField(
label="Dump only unaligned sequences", default=False
)
advanced = GroupField(
Advanced, label="Advanced options", hidden="!show_advanced"
)
class Input:
"""Input fields."""
gse_accession = StringField(
label="GEO accession",
description="Enter a GEO series accession number.")
show_advanced = BooleanField(label="Show advanced options",
default=False)
class Advanced:
"""Advanced options."""
prefetch = BooleanField(label="Prefetch SRA file", default=True)
max_size_prefetch = StringField(
label="Maximum file size to download in KB",
default="20G",
description=
"A unit prefix can be used instead of a value in KB (e.g. 1024M or 1G).",
)
min_spot_id = IntegerField(label="Minimum spot ID", required=False)
max_spot_id = IntegerField(label="Maximum spot ID", required=False)
min_read_len = IntegerField(label="Minimum read length",
required=False)
clip = BooleanField(label="Clip adapter sequences", default=False)
aligned = BooleanField(label="Dump only aligned sequences",
default=False)
unaligned = BooleanField(label="Dump only unaligned sequences",
default=False)
mapping_file = FileField(
label="File with probe ID mappings",
description=
"The file should be tab-separated and contain two columns with their column names. The "
"first column should contain Gene IDs and the second one should contain probe names. Supported file "
"extensions are .tab.*, .tsv.*, .txt.*",
required=False,
)
source = StringField(
label="Gene ID source",
description=
"Gene ID source used for probe mapping is required when using a custom file.",
allow_custom_choice=True,
required=False,
choices=[
("AFFY", "AFFY"),
("DICTYBASE", "DICTYBASE"),
("ENSEMBL", "ENSEMBL"),
("NCBI", "NCBI"),
("UCSC", "UCSC"),
],
)
build = StringField(
label="Genome build",
description=
"Genome build of mapping file is required when using a custom file.",
required=False,
)
advanced = GroupField(Advanced,
label="Advanced options",
hidden="!show_advanced")
class Input:
"""Input fields for GatkHaplotypeCallerGvcf."""
bam = DataField("alignment:bam", label="Analysis ready BAM file")
ref_seq = DataField("seq:nucleotide", label="Reference sequence")
advanced = BooleanField(
label="Show advanced options",
description="Inspect and modify parameters.",
default=False,
)
class Options:
"""Options."""
intervals = DataField(
"bed",
label=
"Use intervals BED file to limit the analysis to the specified parts of the genome.",
required=False,
)
contamination = FloatField(
label="Contamination fraction",
default=0,
description=
"Fraction of contamination in sequencing data (for all samples) to aggressively remove.",
)
options = GroupField(Options, label="Options", hidden="!advanced")
class Input:
"""Input fields to process WgsPreprocess."""
reads = DataField("reads:fastq:paired", label="Input sample")
ref_seq = DataField("seq:nucleotide", label="Reference sequence")
bwa_index = DataField("index:bwa", label="BWA genome index")
known_sites = ListField(DataField("variants:vcf"),
label="Known sites of variation (VCF)")
advanced = BooleanField(
label="Show advanced options",
description="Inspect and modify parameters.",
default=False,
)
class AdvancedOptions:
"""Advanced options."""
pixel_distance = IntegerField(
label="--OPTICAL_DUPLICATE_PIXEL_DISTANCE",
default=2500,
description="Set the optical pixel distance, e.g. "
"distance between clusters. Modify this parameter to "
"ensure compatibility with older Illumina platforms.",
)
advanced_options = GroupField(AdvancedOptions,
label="Advanced options",
hidden="!advanced")
class Input:
"""Input fields."""
my_field = StringField(label="My field")
my_list = ListField(StringField(), label="My list")
input_data = DataField("test:save", label="My input data")
input_entity_data = DataField("entity", label="My entity data")
bar = DataField(data_type="test:save", label="My bar")
url = UrlField(UrlField.DOWNLOAD, label="My URL")
integer = IntegerField(label="My integer")
my_float = FloatField(label="My float")
my_json = JsonField(label="Blah blah")
my_optional = StringField(label="Optional",
required=False,
default="default value")
my_optional_no_default = StringField(label="Optional no default",
required=False)
class MyGroup:
foo = IntegerField(label="Foo")
bar = StringField(label="Bar")
group_optional_no_default = StringField(
label="Group optional no default", required=False)
my_group = GroupField(MyGroup, label="My group")
class Input:
"""Input fields to process ChipQC."""
alignment = DataField(
data_type="alignment:bam",
label="Aligned reads",
)
peaks = DataField(
data_type="chipseq:callpeak",
label="Called peaks",
)
blacklist = DataField(
data_type="bed",
label="Blacklist regions",
description="BED file containing genomic regions that should be "
"excluded from the analysis.",
required=False,
)
calculate_enrichment = BooleanField(
label="Calculate enrichment",
description="Calculate enrichment of signal in known genomic "
"annotation. By default annotation is provided from "
"the TranscriptDB package specified by genome bulid "
"which should match one of the supported annotations "
"(hg19, hg38, hg18, mm10, mm9, rn4, ce6, dm3). If "
"annotation is not supported the analysis is skipped.",
default=False,
)
class Advanced:
"""Add advanced list of options."""
quality_threshold = IntegerField(
label="Mapping quality threshold",
description="Only reads with mapping quality scores above "
"this threshold will be used for some statistics.",
default=15,
)
profile_window = IntegerField(
label="Window size",
description="An integer indicating the width of the window "
"used for peak profiles. Peaks will be centered "
"on their summits and include half of the window "
"size upstream and half downstream of this point.",
default=400,
)
shift_size = StringField(
label="Shift size",
description="Vector of values to try when computing optimal "
"shift sizes. It should be specifeird as "
"consecutive numbers vector with start:end",
default="1:300",
)
advanced = GroupField(
Advanced,
label="Advanced parameters",
)
class Input:
"""Input fields for GatkGenotypeGVCFs."""
gvcfs = ListField(
DataField("variants:gvcf"),
label="Input data (GVCF)",
)
ref_seq = DataField("seq:nucleotide", label="Reference sequence")
intervals = DataField(
"bed",
label="Intervals file (.bed)",
)
dbsnp = DataField("variants:vcf", label="dbSNP file")
advanced = BooleanField(
label="Show advanced options",
description="Inspect and modify parameters.",
default=False,
)
class AdvancedOptions:
"""Advanced options."""
batch_size = IntegerField(
label="Batch size",
default=0,
description="Batch size controls the number of samples "
"for which readers are open at once and therefore provides "
"a way to minimize memory consumption. However, it can "
"take longer to complete. Use the consolidate flag if more "
"than a hundred batches were used. This will improve feature "
"read time. batchSize=0 means no batching "
"(i.e. readers for all samples will be opened at once).",
)
consolidate = BooleanField(
label="Consolidate",
default=False,
description="Boolean flag to enable consolidation. If "
"importing data in batches, a new fragment is created for "
"each batch. In case thousands of fragments are created, "
"GenomicsDB feature readers will try to open ~20x as many "
"files. Also, internally GenomicsDB would consume more "
"memory to maintain bookkeeping data from all fragments. "
"Use this flag to merge all fragments into one. Merging "
"can potentially improve read performance, however overall "
"benefit might not be noticeable as the top Java layers "
"have significantly higher overheads. This flag has no "
"effect if only one batch is used.",
)
advanced_options = GroupField(AdvancedOptions,
label="Advanced options",
hidden="!advanced")
class MyGroup:
foo = IntegerField(label="Foo")
bar = StringField(label="Bar")
group_optional_no_default = StringField(
label="Group optional no default", required=False)
class SubGroup:
foo = IntegerField(label="Foo", default=2)
subgroup = GroupField(SubGroup, label="Subgroup")
class Input:
"""Input fields to process MultiQC."""
data = ListField(
DataField(
data_type="",
description=
"Select multiple data objects for which the MultiQC report is to be "
"generated.",
),
label="Input data",
)
class Advanced:
"""Options."""
dirs = BooleanField(
label="--dirs",
default=True,
description="Prepend directory to sample names.",
)
dirs_depth = IntegerField(
label="--dirs-depth",
default=-1,
description=
"Prepend a specified number of directories to sample names. Enter a "
"negative number (default) to take from start of path.",
)
fullnames = BooleanField(
label="--fullnames",
default=False,
description=
"Disable the sample name cleaning (leave as full file name).",
)
config = BooleanField(
label="Use configuration file",
default=True,
description=
"Use Genialis configuration file for MultiQC report.",
)
cl_config = StringField(
label="--cl-config",
required=False,
description=
"Enter text with command-line configuration options to override the "
"defaults (e.g. custom_logo_url: https://www.genialis.com).",
)
advanced = GroupField(Advanced, label="Advanced options")
class Input:
"""Input fields."""
reads = DataField("reads:fastq:single", label="Select sample(s)")
class Options:
"""Options."""
nextseq_trim = IntegerField(
label="NextSeq/NovaSeq trim",
description=
"NextSeq/NovaSeq-specific quality trimming. Trims also dark "
"cycles appearing as high-quality G bases. This option is mutually "
"exclusive with the use of standard quality-cutoff trimming and is "
"suitable for the use with data generated by the recent Illumina "
"machines that utilize two-color chemistry to encode the four bases.",
default=10,
)
quality_cutoff = IntegerField(
label="Quality cutoff",
description=
"Trim low-quality bases from 3' end of each read before adapter "
"removal. The use of this option will override the use of "
"NextSeq/NovaSeq trim option.",
required=False,
)
min_len = IntegerField(
label="Discard reads shorter than specified minimum length.",
default=20,
)
min_overlap = IntegerField(
label="Mimimum overlap",
description=
"Minimum overlap between adapter and read for an adapter to be found.",
default=20,
)
times = IntegerField(
label=
"Remove up to a specified number of adapters from each read.",
default=2,
)
options = GroupField(Options, label="Options")
class Input:
"""Input fields."""
alignment = DataField('alignment:bam', label="Alignment")
annotation = DataField('annotation:gtf', label="GTF annotation")
class Options:
"""Options."""
stranded = StringField(
label="Assay type",
default='non_specific',
choices=[
('non_specific', 'Strand non-specific'),
('forward', 'Strand-specific forward'),
('reverse', 'Strand-specific reverse'),
('auto', 'Detect automatically'),
],
)
cdna_index = DataField(
'index:salmon',
label="cDNA index file",
required=False,
hidden="options.stranded != 'auto'"
)
n_reads = IntegerField(
label="Number of reads in subsampled alignment file",
default=5000000,
hidden="options.stranded != 'auto'"
)
maxPhredScore = IntegerField(
label="Max Phred Score",
required=False,
)
adjustPhredScore = IntegerField(
label="Adjust Phred Score",
required=False,
)
options = GroupField(Options, label="Options")
class Input:
"""Input fields."""
alignment = DataField("alignment:bam", label="Alignment")
annotation = DataField("annotation:gtf", label="GTF annotation")
class Options:
"""Options."""
stranded = StringField(
label="Assay type",
default="non_specific",
choices=[
("non_specific", "Strand non-specific"),
("forward", "Strand-specific forward"),
("reverse", "Strand-specific reverse"),
("auto", "Detect automatically"),
],
)
cdna_index = DataField(
"index:salmon",
label="cDNA index file",
required=False,
hidden="options.stranded != 'auto'",
)
n_reads = IntegerField(
label="Number of reads in subsampled alignment file",
default=5000000,
hidden="options.stranded != 'auto'",
)
maxPhredScore = IntegerField(
label="Max Phred Score",
required=False,
)
adjustPhredScore = IntegerField(
label="Adjust Phred Score",
required=False,
)
options = GroupField(Options, label="Options")
class Input:
"""Input fields."""
alignment = DataField('alignment:bam', label="Alignment")
annotation = DataField('annotation:gtf', label="GTF annotation")
class Options:
"""Options."""
stranded = StringField(
label="Assay type",
default='non_specific',
choices=[
('non_specific', 'Strand non-specific'),
('forward', 'Strand-specific forward'),
('reverse', 'Strand-specific reverse'),
],
)
options = GroupField(Options, label="Options")
class Input:
"""Input fields to process AlignmentSieve."""
alignment = DataField(data_type="alignment:bam",
label="Alignment BAM file")
min_fragment_length = IntegerField(
label="--minFragmentLength",
description="The minimum fragment length needed for "
"read/pair inclusion. This option is primarily useful in "
"ATACseq experiments, for filtering mono- or di-nucleosome "
"fragments. (Default: 0)",
default=0,
)
max_fragment_length = IntegerField(
label="--maxFragmentLength",
description="The maximum fragment length needed for "
"read/pair inclusion. A value of 0 indicates "
"no limit. (Default: 0)",
default=0,
)
class BigWigOptions:
"""Options for calculating BigWig."""
bigwig_binsize = IntegerField(
label="BigWig bin size",
description="Size of the bins, in bases, for the output of the "
"bigwig/bedgraph file. Default is 50.",
default=50,
)
bigwig_timeout = IntegerField(
label="BigWig timeout",
description=
"Number of seconds before creation of BigWig timeouts. "
"Default is after 480 seconds (8 minutes).",
default=480,
)
bigwig_opts = GroupField(BigWigOptions, label="BigWig options")
class MySubGroup:
class SubGroup:
foo = IntegerField(label="Foo", default=2)
subgroup = GroupField(SubGroup, label="Subgroup foo")
class Input:
"""Input fields to process MergeData."""
string_field = StringField(
label="Labels are short and do not end in a period",
description="Description ends in a period.",
choices=[
("computer_readable1", "Human readable 1"),
("computer_readable2", "Human readable 2"),
],
default="computer_readable1",
required=False,
hidden=False,
allow_custom_choice=True,
)
text_field = TextField(
label="Labels are short and do not end in a period",
description="Description ends in a period.",
default="default text",
required=False,
hidden=True,
)
boolean_field1 = BooleanField(
label="Labels are short and do not end in a period",
description="Note that description fields always end in a period.",
default=False,
required=True,
hidden=False,
)
integer_field = IntegerField(
label="Labels are short and do not end in a period",
description="Description ends in a period.",
default=1,
)
float_field = FloatField(
label="Labels are short and do not end in a period",
description="Description ends in a period.",
default=3.14,
)
date_field = DateField(
label="Labels are short and do not end in a period",
description="Description ends in a period.",
default="2020-04-20",
)
datetime_field = DateTimeField(
label="Labels are short and do not end in a period",
description="Description ends in a period.",
default="2020-04-20 12:16:00",
)
url_field = UrlField(
label="Labels are short and do not end in a period",
description="Description ends in a period.",
)
secret_field = SecretField(
label="Labels are short and do not end in a period",
description="Description ends in a period.",
)
file_field = FileField(
label="Labels are short and do not end in a period",
description="Description ends in a period.",
)
filehtml_field = FileHtmlField(
label="Labels are short and do not end in a period",
description="Description ends in a period.",
)
dir_field = DirField(
label="Labels are short and do not end in a period",
description="Description ends in a period.",
)
json_field = JsonField(
label="Labels are short and do not end in a period",
description="Description ends in a period.",
)
list_field = ListField(
DataField(data_type="your:data:type"),
label="Labels are short and do not end in a period",
description="Description ends in a period.",
)
data_field = DataField(
# data_type should not start with data:
data_type="your:data:type",
label="Labels are short and do not end in a period",
description="Description ends in a period.",
)
class Advanced:
"""Add advanced list of options."""
boolean_field2 = BooleanField(
label="Labels are short and do not end in a period",
description="Description ends in a period.",
default=False,
)
group_field = GroupField(
Advanced,
label="Labels are short and do not end in a period",
disabled=False,
# Will show when boolean_field1 is flipped.
hidden="!boolean_field1",
collapsed=True,
)
class Input:
"""Input fields for CollectWgsMetrics."""
bam = DataField("alignment:bam", label="Alignment BAM file")
genome = DataField("seq:nucleotide", label="Genome")
read_length = IntegerField(label="Average read length", default=150)
create_histogram = BooleanField(
label="Include data for base quality histogram in the metrics file",
default=False,
)
advanced = BooleanField(
label="Show advanced options",
description="Inspect and modify parameters.",
default=False,
)
class Options:
"""Options."""
min_map_quality = IntegerField(
label=
"Minimum mapping quality for a read to contribute coverage",
default=20,
)
min_quality = IntegerField(
label="Minimum base quality for a base to contribute coverage",
description=
"N bases will be treated as having a base quality of "
"negative infinity and will therefore be excluded from coverage "
"regardless of the value of this parameter.",
default=20,
)
coverage_cap = IntegerField(
label="Maximum coverage cap",
description=
"Treat positions with coverage exceeding this value as "
"if they had coverage at this set value.",
default=250,
)
accumulation_cap = IntegerField(
label="Ignore positions with coverage above this value",
description="At positions with coverage exceeding this value, "
"completely ignore reads that accumulate beyond this value",
default=100000,
)
count_unpaired = BooleanField(
label=
"Count unpaired reads and paired reads with one end unmapped",
default=False,
)
sample_size = IntegerField(
label=
"Sample Size used for Theoretical Het Sensitivity sampling",
default=10000,
)
validation_stringency = StringField(
label="Validation stringency",
description=
"Validation stringency for all SAM files read by this "
"program. Setting stringency to SILENT can improve "
"performance when processing a BAM file in which "
"variable-length data (read, qualities, tags) do not "
"otherwise need to be decoded. Default is STRICT.",
choices=[
("STRICT", "STRICT"),
("LENIENT", "LENIENT"),
("SILENT", "SILENT"),
],
default="STRICT",
)
options = GroupField(Options, label="Options", hidden="!advanced")
class Input:
"""Input fields of trimGalorePaired."""
reads = DataField("reads:fastq:paired",
label="Select paired-end reads")
class QualityTrimming:
"""Quality trimming options."""
quality = IntegerField(
label="Quality cutoff",
description=
"Trim low-quality ends from reads based on phred score.",
default=20,
)
nextseq = IntegerField(
label="NextSeq/NovaSeq trim cutoff",
description="NextSeq/NovaSeq-specific quality "
"trimming. Trims also dark cycles appearing as "
"high-quality G bases. This will set a specific "
"quality cutoff, but qualities of G bases are ignored. "
"This can not be used with Quality cutoff and will "
"override it.",
required=False,
)
phred = StringField(
label="Phred score encoding",
description="Use either ASCII+33 quality scores as "
"Phred scores (Sanger/Illumina 1.9+ encoding) or "
"ASCII+64 quality scores (Illumina 1.5 encoding) for "
"quality trimming",
choices=[
("--phred33", "ASCII+33"),
("--phred64", "ASCII+64"),
],
default="--phred33",
)
min_length = IntegerField(
label="Minimum length after trimming",
description="Discard reads that became shorter than "
"selected length because of either quality or adapter "
"trimming. Both reads of a read-pair need to be longer "
"than specified length to be printed out to validated "
"paired-end files. If only one read became too short "
"there is the possibility of keeping such unpaired "
"single-end reads with Retain unpaired. A value of 0 "
"disables filtering based on length.",
default=20,
)
max_n = IntegerField(
label="Maximum number of Ns",
description="Read exceeding this limit will result in "
"the entire pair being removed from the trimmed output "
"files.",
required=False,
)
retain_unpaired = BooleanField(
label="Retain unpaired reads after trimming",
description="If only one of the two paired-end reads "
"became too short, the longer read will be written.",
default=False,
)
unpaired_len_1 = IntegerField(
label="Unpaired read length cutoff for mate 1",
default=35,
hidden="!quality_trim.retain_unpaired",
)
unpaired_len_2 = IntegerField(
label="Unpaired read length cutoff for mate 2",
default=35,
hidden="!quality_trim.retain_unpaired",
)
clip_r1 = IntegerField(
label="Trim bases from 5' end of read 1",
description="This may be useful if the qualities were "
"very poor, or if there is some sort of unwanted bias "
"at the 5' end.",
required=False,
)
clip_r2 = IntegerField(
label="Trim bases from 5' end of read 2",
description="This may be useful if the qualities were "
"very poor, or if there is some sort of unwanted bias "
"at the 5' end. For paired-end bisulfite sequencing, "
"it is recommended to remove the first few bp because "
"the end-repair reaction may introduce a bias towards "
"low methylation.",
required=False,
)
three_prime_r1 = IntegerField(
label="Trim bases from 3' end of read 1",
description="Remove bases from the 3' end of read 1 "
"after adapter/quality trimming has been performed. "
"This may remove some unwanted bias from the 3' end "
"that is not directly related to adapter sequence or "
"basecall quality.",
required=False,
)
three_prime_r2 = IntegerField(
label="Trim bases from 3' end of read 2",
description="Remove bases from the 3' end of read 2 "
"after adapter/quality trimming has been performed. "
"This may remove some unwanted bias from the 3' end "
"that is not directly related to adapter sequence or "
"basecall quality.",
required=False,
)
class AdapterTrimming:
"""Adapter trimming options."""
adapter = ListField(
StringField(),
label="Read 1 adapter sequence",
description="Adapter sequences to be trimmed. "
"Also see universal adapters field for predefined "
"adapters. This is mutually exclusive with read 1 "
"adapters file and universal adapters.",
required=False,
default=[],
)
adapter_2 = ListField(
StringField(),
label="Read 2 adapter sequence",
description="Optional adapter sequence to be trimmed "
"off read 2 of paired-end files. This is mutually "
"exclusive with read 2 adapters file and universal "
"adapters.",
required=False,
default=[],
)
adapter_file_1 = DataField(
"seq:nucleotide",
label="Read 1 adapters file",
description="This is mutually exclusive with read 1 "
"adapters and universal adapters.",
required=False,
)
adapter_file_2 = DataField(
"seq:nucleotide",
label="Read 2 adapters file",
description="This is mutually exclusive with read 2 "
"adapters and universal adapters.",
required=False,
)
universal_adapter = StringField(
label="Universal adapters",
description="Instead of default detection use specific "
"adapters. Use 13bp of the Illumina universal adapter, "
"12bp of the Nextera adapter or 12bp of the Illumina "
"Small RNA 3' Adapter. Selecting to trim smallRNA "
"adapters will also lower the length value to 18bp. "
"If the smallRNA libraries are paired-end then read 2 "
"adapter will be set to the Illumina small RNA 5' "
"adapter automatically (GATCGTCGGACT) unless defined "
"explicitly. This is mutually exclusive with manually "
"defined adapters and adapter files.",
choices=[
("--illumina", "Illumina"),
("--nextera", "Nextera"),
("--small_rna", "Illumina small RNA"),
],
required=False,
)
stringency = IntegerField(
label="Overlap with adapter sequence required to trim",
description="Defaults to a very stringent setting of "
"1, i.e. even a single base pair of overlapping "
"sequence will be trimmed of the 3' end of any read.",
default=1,
)
error_rate = FloatField(
label="Maximum allowed error rate",
description="Number of errors divided by the length of "
"the matching region",
default=0.1,
)
class HardTrimming:
"""Hard trim options."""
trim_5 = IntegerField(
label="Hard trim sequences from 3' end",
description="Instead of performing adapter-/quality "
"trimming, this option will simply hard-trim sequences "
"to bp from the 3' end. This is incompatible with "
"other hard trimming options.",
required=False,
)
trim_3 = IntegerField(
label="Hard trim sequences from 5' end",
description="Instead of performing adapter-/quality "
"trimming, this option will simply hard-trim sequences "
"to bp from the 5' end. This is incompatible with "
"other hard trimming options.",
required=False,
)
adapter_trim = GroupField(AdapterTrimming, label="Adapter trimming")
quality_trim = GroupField(QualityTrimming, label="Quality trimming")
hard_trim = GroupField(HardTrimming, label="Hard trimming")
class Input:
"""Input fields."""
reads = DataField("reads:fastq", label="Input sample(s)")
salmon_index = DataField("index:salmon", label="Salmon index")
annotation = DataField("annotation:gtf", label="GTF annotation")
advanced = BooleanField(
label="Show advanced options",
description="Inspect and modify parameters.",
default=False,
)
class Options:
"""Options."""
stranded = StringField(
label="Assay type",
default="A",
choices=[
("A", "Detect automatically"),
("U", "Strand non-specific (U)"),
("SF", "Strand-specific forward (SF)"),
("SR", "Strand-specific reverse (SR)"),
("IU", "Strand non-specific (paired-end IU)"),
("ISF", "Strand-specific forward (paired-end ISF)"),
("ISR", "Strand-specific reverse (paired-end (ISR)"),
],
)
seq_bias = BooleanField(
label="--seqBias",
default=False,
description="Perform sequence-specific bias correction.",
)
gc_bias = BooleanField(
label="--gcBias",
default=False,
description=
"[beta for single-end reads] Perform fragment GC bias correction.",
)
discard_orphans_quasi = BooleanField(
label="--discardOrphansQuasi",
default=False,
description="Discard orphan mappings in quasi-mapping mode. "
"If this flag is passed then only paired "
"mappings will be considered toward "
"quantification estimates. The default "
"behavior is to consider orphan mappings "
"if no valid paired mappings exist.",
)
no_length_correction = BooleanField(
label="--noLengthCorrection",
default=False,
description="[Experimental] Entirely disables "
"length correction when estimating the "
"abundance of transcripts. The abundance "
"estimates are reported in CPM (counts per "
"million) unit. This option can be used "
"with protocols where one expects that "
"fragments derive from their underlying "
"targets without regard to that target's "
"length (e.g. QuantSeq).",
)
consensus_slack = FloatField(
label="--consensusSlack",
required=False,
description="The amount of slack allowed in the quasi-mapping "
"consensus mechanism. Normally, a transcript must "
"cover all hits to be considered for mapping. "
"If this is set to a fraction, X, greater than 0 "
"(and in [0,1)), then a transcript can fail "
"to cover up to (100 * X)% of the hits before it "
"is discounted as a mapping candidate. The default "
"value of this option is 0.2 in selective alignment mode "
"and 0 otherwise.",
)
min_score_fraction = FloatField(
label="--minScoreFraction",
default=0.65,
description="The fraction of the optimal possible alignment "
"score that a mapping must achieve in order to be "
"considered valid - should be in (0,1]",
)
incompat_prior = FloatField(
label="---incompatPrior",
default=0,
description="This option sets the prior probability "
"that an alignment that disagrees with "
"the specified library type (--libType) "
"results from the true fragment origin. "
"Setting this to 0 specifies that "
"alignments that disagree with the "
"library type should be impossible, "
"while setting it to 1 says that "
"alignments that disagree with the "
"library type are no less likely than "
"those that do.",
)
range_factorization_bins = IntegerField(
label="--rangeFactorizationBins",
default=4,
description="Factorizes the likelihood used in "
"quantification by adopting a new notion "
"of equivalence classes based on the "
"conditional probabilities with which "
"fragments are generated from different "
"transcripts. This is a more "
"fine-grained factorization than the "
"normal rich equivalence classes. The "
"default value (4) corresponds to the "
"default used in Zakeri et al. 2017 "
"and larger values imply a more "
"fine-grained factorization. If range "
"factorization is enabled, a common "
"value to select for this parameter is "
"4. A value of 0 signifies the use of "
"basic rich equivalence classes.",
)
min_assigned_frag = IntegerField(
label="--minAssignedFrags",
default=10,
description="The minimum number of fragments that "
"must be assigned to the transcriptome "
"for quantification to proceed.",
)
options = GroupField(Options, label="Options", hidden="!advanced")
class Input:
"""Input fields for VariantFiltrationVqsr."""
vcf = DataField("variants:vcf", label="Input data (VCF)")
class ResourceFiles:
"""Resource files options."""
dbsnp = DataField("variants:vcf", label="dbSNP file")
mills = DataField(
"variants:vcf",
label="Mills and 1000G gold standard indels",
required=False,
)
axiom_poly = DataField(
"variants:vcf",
label="1000G Axiom genotype data",
required=False,
)
hapmap = DataField(
"variants:vcf",
label="HapMap variants",
required=False,
)
omni = DataField(
"variants:vcf",
label="1000G Omni variants",
required=False,
)
thousand_genomes = DataField(
"variants:vcf",
label="1000G high confidence SNPs",
required=False,
)
advanced = BooleanField(
label="Show advanced options",
description="Inspect and modify parameters.",
default=False,
)
class AdvancedOptions:
"""Advanced options."""
use_as_anno = BooleanField(
label="--use-allele-specific-annotations", default=False
)
indel_anno_fields = ListField(
StringField(),
label="Annotation fields (INDEL filtering)",
default=[
"FS",
"ReadPosRankSum",
"MQRankSum",
"QD",
"SOR",
"DP",
],
)
snp_anno_fields = ListField(
StringField(),
label="Annotation fields (SNP filtering)",
default=[
"QD",
"MQRankSum",
"ReadPosRankSum",
"FS",
"MQ",
"SOR",
"DP",
],
)
indel_filter_level = FloatField(
label="--truth-sensitivity-filter-level (INDELs)", default=99.0
)
snp_filter_level = FloatField(
label="--truth-sensitivity-filter-level (SNPs)", default=99.7
)
max_gaussians_indels = IntegerField(
label="--max-gaussians (INDELs)",
default=4,
description="This parameter determines the maximum number "
"of Gaussians that should be used when building a positive "
"model using the variational Bayes algorithm. This parameter "
"sets the expected number of clusters in modeling. If a "
"dataset gives fewer distinct clusters, e.g. as can happen "
"for smaller data, then the tool will tell you there is "
"insufficient data with a No data found error message. "
"In this case, try decrementing the --max-gaussians value.",
)
max_gaussians_snps = IntegerField(
label="--max-gaussians (SNPs)",
default=6,
description="This parameter determines the maximum number "
"of Gaussians that should be used when building a positive "
"model using the variational Bayes algorithm. This parameter "
"sets the expected number of clusters in modeling. If a "
"dataset gives fewer distinct clusters, e.g. as can happen "
"for smaller data, then the tool will tell you there is "
"insufficient data with a No data found error message. "
"In this case, try decrementing the --max-gaussians value.",
)
resource_files = GroupField(
ResourceFiles,
label="Resource files",
)
advanced_options = GroupField(
AdvancedOptions, label="Advanced options", hidden="!advanced"
)
class Input:
"""Input fields to process MarkDuplicates."""
bam = DataField("alignment:bam", label="Alignment BAM file")
skip = BooleanField(
label="Skip MarkDuplicates step",
description="MarkDuplicates step can be skipped.",
default=False,
)
remove_duplicates = BooleanField(
label="Remove duplicates",
description="If true do not write duplicates to the output file "
"instead of writing them with appropriate flags set.",
default=False,
)
validation_stringency = StringField(
label="Validation stringency",
description="Validation stringency for all SAM files read by this "
"program. Setting stringency to SILENT can improve "
"performance when processing a BAM file in which "
"variable-length data (read, qualities, tags) do not "
"otherwise need to be decoded. Default is STRICT.",
choices=[
("STRICT", "STRICT"),
("LENIENT", "LENIENT"),
("SILENT", "SILENT"),
],
default="STRICT",
)
assume_sort_order = StringField(
label="Assume sort order",
description="If not null (default), assume that the input file "
"has this order even if the header says otherwise."
"Possible values are unsorted, queryname, coordinate "
"and unknown.",
choices=[
("", "as in BAM header (default)"),
("unsorted", "unsorted"),
("queryname", "queryname"),
("coordinate", "coordinate"),
("duplicate", "duplicate"),
("unknown", "unknown"),
],
default="",
)
class BigWigOptions:
"""Options for calculating BigWig."""
bigwig_binsize = IntegerField(
label="BigWig bin size",
description="Size of the bins, in bases, for the output of the "
"bigwig/bedgraph file. Default is 50.",
default=50,
)
bigwig_timeout = IntegerField(
label="BigWig timeout",
description=
"Number of seconds before creation of BigWig timeouts. "
"Default is after 480 seconds (8 minutes).",
default=480,
)
bigwig_opts = GroupField(BigWigOptions, label="BigWig options")
class Input:
"""Input fields to process Deseq."""
case = ListField(
DataField("expression"),
label="Case",
description="Case samples (replicates)",
)
control = ListField(
DataField("expression"),
label="Control",
description="Control samples (replicates)",
)
create_sets = BooleanField(
label="Create gene sets",
description="After calculating differential gene "
"expressions create gene sets for up-regulated genes, "
"down-regulated genes and all genes.",
default=False,
)
logfc = FloatField(
label="Log2 fold change threshold for gene sets",
description="Genes above Log2FC are considered as "
"up-regulated and genes below -Log2FC as down-regulated.",
default=1.0,
hidden="!create_sets",
)
fdr = FloatField(
label="FDR threshold for gene sets",
default=0.05,
hidden="!create_sets",
)
class Options:
"""Options."""
beta_prior = BooleanField(
label="Beta prior",
default=False,
description="Whether or not to put a zero-mean normal prior "
"on the non-intercept coefficients.",
)
class FilterOptions:
"""Filtering options."""
count = BooleanField(
label="Filter genes based on expression count",
default=True,
)
min_count_sum = IntegerField(
label="Minimum gene expression count summed over all samples",
default=10,
description="Filter genes in the expression matrix input. "
"Remove genes where the expression count sum over all samples "
"is below the threshold.",
hidden="!filter_options.count",
)
cook = BooleanField(
label="Filter genes based on Cook's distance",
default=False,
)
cooks_cutoff = FloatField(
label="Threshold on Cook's distance",
required=False,
description="If one or more samples have Cook's distance "
"larger than the threshold set here, the p-value for the row "
"is set to NA. If left empty, the default threshold of 0.99 "
"quantile of the F(p, m-p) distribution is used, where p is "
"the number of coefficients being fitted and m is the number "
"of samples. This test excludes Cook's distance of samples "
"belonging to experimental groups with only two samples.",
hidden="!filter_options.cook",
)
independent = BooleanField(
label="Apply independent gene filtering",
default=False,
)
alpha = FloatField(
label="Significance cut-off used for optimizing independent "
"gene filtering",
default=0.1,
description="The value should be set to adjusted p-value "
"cut-off (FDR).",
hidden="!filter_options.independent",
)
options = GroupField(Options, label="Gene filtering options")
filter_options = GroupField(
FilterOptions, label="Differential expression analysis options")
class Input:
"""Input fields."""
reads = DataField("reads:fastq:paired", label="Input sample")
ref_seq = DataField("seq:nucleotide", label="Reference sequence")
bwa_index = DataField("index:bwa", label="BWA genome index")
known_sites = ListField(
DataField("variants:vcf"), label="Known sites of variation (VCF)"
)
advanced = BooleanField(
label="Show advanced options",
description="Inspect and modify parameters.",
default=False,
)
class GatkOptions:
"""Options."""
intervals = DataField(
"bed",
label="Intervals BED file",
description="Use intervals BED file to limit the analysis to "
"the specified parts of the genome.",
required=False,
)
contamination = IntegerField(
label="Contamination fraction",
default=0,
description="Fraction of contamination in sequencing "
"data (for all samples) to aggressively remove.",
)
class Trimming:
"""Trimming parameters."""
adapters = DataField(
"seq:nucleotide",
label="Adapter sequences",
required=False,
description="Adapter sequences in FASTA format that will "
"be removed from the reads.",
)
seed_mismatches = IntegerField(
label="Seed mismatches",
required=False,
disabled="!trimming_options.adapters",
description="Specifies the maximum mismatch count which "
"will still allow a full match to be performed. This field "
"is required to perform adapter trimming.",
)
simple_clip_threshold = IntegerField(
label="Simple clip threshold",
required=False,
disabled="!trimming_options.adapters",
description="Specifies how accurate the match between any "
"adapter sequence must be against a read. This field is "
"required to perform adapter trimming.",
)
min_adapter_length = IntegerField(
label="Minimum adapter length",
default=8,
disabled="!trimming_options.seed_mismatches && "
"!trimming_options.simple_clip_threshold && "
"!trimming_options.palindrome_clip_threshold",
description="In addition to the alignment score, palindrome "
"mode can verify that a minimum length of adapter has been "
"detected. If unspecified, this defaults to 8 bases, for "
"historical reasons. However, since palindrome mode has a "
"very low false positive rate, this can be safely reduced, "
"even down to 1, to allow shorter adapter fragments to be "
"removed.",
)
palindrome_clip_threshold = IntegerField(
label="Palindrome clip threshold",
required=False,
disabled="!trimming_options.adapters",
description="Specifies how accurate the match between the "
"two adapter ligated reads must be for PE palindrome read "
"alignment. This field is required to perform adapter "
"trimming.",
)
leading = IntegerField(
label="Leading quality",
required=False,
description="Remove low quality bases from the beginning, "
"if below a threshold quality.",
)
trailing = IntegerField(
label="Trailing quality",
required=False,
description="Remove low quality bases from the end, if "
"below a threshold quality.",
)
minlen = IntegerField(
label="Minimum length",
required=False,
description="Drop the read if it is below a specified length.",
)
class AlignmentSummary:
"""AlignmentSummary parameters."""
adapters = DataField(
"seq:nucleotide",
label="Adapter sequences",
required=False,
)
max_insert_size = IntegerField(
label="Maximum insert size",
default=100000,
)
pair_orientation = StringField(
label="Pair orientation",
default="null",
choices=[
("null", "Unspecified"),
("FR", "FR"),
("RF", "RF"),
("TANDEM", "TANDEM"),
],
)
class PicardWGSMetrics:
"""PicardWGSMetrics parameters."""
read_length = IntegerField(
label="Average read length",
default=150,
)
min_map_quality = IntegerField(
label="Minimum mapping quality for a read to contribute coverage",
default=20,
)
min_quality = IntegerField(
label="Minimum base quality for a base to contribute coverage",
default=20,
description="N bases will be treated as having a base quality of "
"negative infinity and will therefore be excluded from "
"coverage regardless of the value of this parameter.",
)
coverage_cap = IntegerField(
label="Maximum coverage cap",
default=250,
description="Treat positions with coverage exceeding this "
"value as if they had coverage at this set value.",
)
accumulation_cap = IntegerField(
label="Ignore positions with coverage above this value",
default=100000,
description="At positions with coverage exceeding this value, "
"completely ignore reads that accumulate beyond this value.",
)
sample_size = IntegerField(
label="Sample size used for Theoretical Het Sensitivity sampling",
default=10000,
)
class InsertSizeMetrics:
"""InsertSizeMetrics parameters."""
minimum_fraction = FloatField(
label="Minimum fraction of reads in a category to be considered",
default=0.05,
description="When generating the histogram, discard any data "
"categories (out of FR, TANDEM, RF) that have fewer than "
"this fraction of overall reads (Range: 0 and 0.5).",
)
include_duplicates = BooleanField(
label="Include reads marked as duplicates in the insert size histogram",
default=False,
)
deviations = FloatField(
label="Deviations limit",
default=10.0,
description="Generate mean, standard deviation and plots "
"by trimming the data down to MEDIAN + DEVIATIONS * "
"MEDIAN_ABSOLUTE_DEVIATION. This is done because insert "
"size data typically includes enough anomalous values "
"from chimeras and other artifacts to make the mean and "
"standard deviation grossly misleading regarding the real "
"distribution.",
)
trimming_options = GroupField(
Trimming,
label="Trimming options",
)
gatk_options = GroupField(GatkOptions, label="GATK options", hidden="!advanced")
alignment_summary = GroupField(
AlignmentSummary, label="Alignment summary options", hidden="!advanced"
)
wgs_metrics = GroupField(
PicardWGSMetrics, label="Picard WGS metrics options", hidden="!advanced"
)
insert_size = GroupField(
InsertSizeMetrics,
label="Picard InsertSizeMetrics options",
hidden="!advanced",
)
