class Output:
"""Output fields."""
fastq = ListField(FileField(), label='Reads file.')
report = FileField(label='Cutadapt report')
fastqc_url = ListField(FileHtmlField(), label='Quality control with FastQC.')
fastqc_archive = ListField(FileField(), label='Download FastQC archive.')
class Input:
"""Input fields to process ClusterTimeCourse."""
expressions = ListField(
DataField("expression"),
relation_type="series",
label="Time series relation",
description=
"Select time course to which the expressions belong to.",
)
genes = ListField(
StringField(),
label="Gene subset",
required=False,
description="Select at least two genes or leave this field empty.",
)
gene_species = StringField(
label="Species",
description="Species to which the selected genes belong to. "
"This field is required if gene subset is set.",
required=False,
hidden="!genes",
allow_custom_choice=True,
choices=[
("Dictyostelium discoideum", "Dictyostelium discoideum"),
("H**o sapiens", "H**o sapiens"),
("Macaca mulatta", "Macaca mulatta"),
("Mus musculus", "Mus musculus"),
("Rattus norvegicus", "Rattus norvegicus"),
],
)
gene_source = StringField(
label="Gene ID database of selected genes",
description="This field is required if gene subset is set.",
required=False,
hidden="!genes",
)
distance = StringField(
label="Distance metric",
choices=[
("spearman", "Spearman"),
("pearson", "Pearson"),
],
default="spearman",
)
linkage = StringField(
label="Linkage method",
choices=[
("single", "single"),
("average", "average"),
("complete", "complete"),
],
default="average",
)
ordering = BooleanField(
label="Use optimal ordering",
description="Results in a more intuitive tree structure, "
"but may slow down the clustering on large datasets",
default=False,
)
class Output:
"""Output fields."""
fastq = ListField(FileField(), label="Reverse complemented FASTQ file")
fastqc_url = ListField(FileHtmlField(),
label="Quality control with FastQC")
fastqc_archive = ListField(FileField(),
label="Download FastQC archive")
class Output:
string_output = StringField(label="My string output")
list_string_output = ListField(StringField(), label="My list string output")
file_output = FileField(label="My output")
list_file_output = ListField(FileField(), label="My list output")
dir_output = DirField(label="My output")
input_data_name = StringField(label="Input data name")
input_entity_name = StringField(label="Input entity name")
docker_image = StringField(label="Docker image")
class Output:
"""Output fields to process ImportSraSingle."""
fastq = ListField(FileField(), label="Reads file")
fastqc_url = ListField(
FileHtmlField(),
label="Quality control with FastQC",
)
fastqc_archive = ListField(FileField(), label="Download FastQC archive")
class Output:
"""Output fields."""
fastq = ListField(FileField(), label="Reads file")
report = FileField(label="Cutadapt report")
fastqc_url = ListField(FileHtmlField(),
label="Quality control with FastQC")
fastqc_archive = ListField(FileField(),
label="Download FastQC archive")
class Output:
"""Output fields to process ImportScRNA10x."""
barcodes = ListField(FileField(), label='Barcodes')
reads = ListField(FileField(), label='Reads')
fastqc_url_barcodes = ListField(
FileHtmlField(),
label='Quality control with FastQC (Barcodes)',
)
fastqc_url_reads = ListField(
FileHtmlField(),
label='Quality control with FastQC (Reads)',
)
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 to process MergeFastqSingle."""
reads = ListField(
DataField(data_type="reads:fastq:single:"),
label="Reads data objects",
)
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."""
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 MapMicroarrayProbes."""
expressions = ListField(
DataField("microarray:normalized"),
label="Normalized expressions",
)
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,
)
class Input:
"""Input fields to process MergeFastqPaired."""
reads = ListField(
DataField(data_type="reads:fastq:paired:"),
label="Reads data objects",
)
class Input:
"""Input fields to process ImportScRNA10x."""
barcodes = ListField(
FileField(
description=
'Barcodes file(s) in FASTQ format. Usually the forward FASTQ files (R1).',
),
label='Barcodes (.fastq.gz)',
)
reads = ListField(
FileField(
description=
'Reads file(s) in FASTQ format. Usually the reverse FASTQ files (R2).',
),
label='Reads (.fastq.gz)',
)
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 Input:
"""Input fields for AlleyoopSummary."""
slamdunk = ListField(
DataField(
data_type="alignment:bam:slamdunk",
description="Select one or multiple data objects from slamdunk process.",
),
label="Slamdunk results",
)
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 to process EdgeR."""
case = ListField(
DataField("expression"),
label="Case",
description="Case samples (replicates)",
)
control = ListField(
DataField("expression"),
label="Control",
description="Control samples (replicates)",
)
count_filter = IntegerField(
label="Raw counts filtering threshold",
default=10,
description="Filter genes in the expression matrix input. "
"Remove genes where the number of counts in all samples is "
"below the threshold.",
)
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 Output:
"""Output fields to process MergeData"""
file_out = FileField(
label="Labels are short and do not end in a period")
dir_optional = DirField(
label="Labels are short and do not end in a period",
required=False)
list_out = ListField(
FileField(),
label="Labels are short and do not end in a period",
description="Description ends in a period.",
)
class Output:
"""Output fields."""
fastq = ListField(FileField(), label='Reverse complemented FASTQ file')
fastq2 = ListField(FileField(), label='Remaining mate')
fastqc_url = ListField(FileHtmlField(), label='Quality control with FastQC (Mate 1)')
fastqc_archive = ListField(FileField(), label='Download FastQC archive (Mate 1)')
fastqc_url2 = ListField(FileHtmlField(), label='Quality control with FastQC (Mate 2)')
fastqc_archive2 = ListField(FileField(), label='Download FastQC archive (Mate 2)')
class Input:
"""Input fields to perform Base quality score recalibration."""
bam = DataField("alignment:bam", label="BAM file containing reads")
reference = DataField("seq:nucleotide", label="Reference genome file")
known_sites = ListField(
DataField(
data_type="variants:vcf",
description=
"One or more databases of known polymorphic sites used to exclude regions around known "
"polymorphisms from analysis.",
),
label="List of known sites of variation",
)
intervals = DataField(
data_type="bed",
required=False,
label="One or more genomic intervals over which to operate.",
description=
"This field is optional, but it can speed up the process by restricting calculations to "
"specific genome regions.",
)
read_group = StringField(
label="Replace read groups in BAM",
description=
"Replace read groups in a BAM file.This argument enables the user to replace all read groups "
"in the INPUT file with a single new read group and assign all reads to this read group in "
"the OUTPUT BAM file. Addition or replacement is performed using Picard's "
"AddOrReplaceReadGroups tool. Input should take the form of -name=value delimited by a "
'";", e.g. "-ID=1;-LB=GENIALIS;-PL=ILLUMINA;-PU=BARCODE;-SM=SAMPLENAME1". See tool\'s '
"documentation for more information on tag names. Note that PL, LB, PU and SM are require "
"fields. See caveats of rewriting read groups in the documentation.",
default="",
)
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. This setting is "
"used in BaseRecalibrator and ApplyBQSR processes.",
choices=[
("STRICT", "STRICT"),
("LENIENT", "LENIENT"),
("SILENT", "SILENT"),
],
default="STRICT",
)
class Input:
"""Input fields to perform Base quality score recalibration."""
bam = DataField('alignment:bam', label='BAM file containing reads')
reference = DataField('genome:fasta', label='Reference genome file')
known_sites = ListField(
DataField(
data_type='variants:vcf',
description=
'One or more databases of known polymorphic sites used to exclude regions around known '
'polymorphisms from analysis.'),
label='List of known sites of variation',
)
intervals = DataField(
data_type='bed',
label='One or more genomic intervals over which to operate.',
description=
'This field is optional, but it can speed up the process by restricting calculations to '
'specific genome regions.')
read_group = StringField(
label='Replace read groups in BAM',
description=
'Replace read groups in a BAM file.This argument enables the user to replace all read groups '
'in the INPUT file with a single new read group and assign all reads to this read group in '
'the OUTPUT BAM file. Addition or replacement is performed using Picard\'s '
'AddOrReplaceReadGroups tool. Input should take the form of -name=value delimited by a '
'";", e.g. "-ID=1;-LB=GENIALIS;-PL=ILLUMINA;-PU=BARCODE;-SM=SAMPLENAME1". See tool\'s '
'documentation for more information on tag names. Note that PL, LB, PU and SM are require '
'fields. See caveats of rewriting read groups in the documentation.',
default='')
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. This setting is '
'used in BaseRecalibrator and ApplyBQSR processes.',
choices=[
('STRICT', 'STRICT'),
('LENIENT', 'LENIENT'),
('SILENT', 'SILENT'),
],
default='STRICT',
)
class Output:
"""Output fields for BamToFastqPaired."""
fastq = ListField(FileField(), label="Remaining mate1 reads")
fastq2 = ListField(FileField(), label="Remaining mate2 reads")
fastqc_url = ListField(FileHtmlField(),
label="Mate1 quality control with FastQC")
fastqc_url2 = ListField(FileHtmlField(),
label="Mate2 quality control with FastQC")
fastqc_archive = ListField(FileField(),
label="Download mate1 FastQC archive")
fastqc_archive2 = ListField(FileField(),
label="Download mate2 FastQC archive")
class Input:
"""Input fields to process ShortHairpinRNADifferentialExpression."""
parameter_file = DataField(
data_type="file",
label="Excel parameter file (.xlsx)",
description="Select .xlsx file which holds parameters for analysis. "
"See [here](https://github.com/genialis/shRNAde/blob/master/inst/extdata/template_doDE_inputs"
".xlsx) for a template.",
)
expression_data = ListField(
DataField(
data_type="expression:shrna2quant:",
description=
"Data objects of expressions from process shrna-quant. These inputs should match sample "
"names specified in parameter file.",
),
label="List of expression files from shrna2quant",
)
class Output:
"""Output fields."""
fastq = ListField(FileField(), label='Remaining mate1 reads')
fastq2 = ListField(FileField(), label='Remaining mate2 reads')
report = FileField(label='Cutadapt report')
fastqc_url = ListField(FileHtmlField(),
label='Mate1 quality control with FastQC')
fastqc_url2 = ListField(FileHtmlField(),
label='Mate2 quality control with FastQC')
fastqc_archive = ListField(FileField(),
label='Download mate1 FastQC archive')
fastqc_archive2 = ListField(FileField(),
label='Download mate2 FastQC archive')
class Output:
"""Output fields."""
fastq = ListField(FileField(), label="Remaining mate 1 reads")
fastq2 = ListField(FileField(), label="Remaining mate 2 reads")
report = FileField(label="Trim galore report", required=False)
fastqc_url = ListField(FileHtmlField(),
label="Mate 1 quality control with FastQC")
fastqc_url2 = ListField(FileHtmlField(),
label="Mate 2 quality control with FastQC")
fastqc_archive = ListField(FileField(),
label="Download mate 1 FastQC archive")
fastqc_archive2 = ListField(FileField(),
label="Download mate 2 FastQC archive")
class Input:
"""Input fields to process FindSimilar."""
expressions = ListField(
DataField("expression"),
relation_type="series",
label="Time series relation",
description="Select time course to which the expressions belong to.",
)
gene = StringField(
label="Query gene",
description="Select a gene to which others are compared.",
)
distance = StringField(
label="Distance metric",
choices=[
("spearman", "Spearman"),
("pearson", "Pearson"),
],
default="spearman",
)
class Output:
"""Output fields to process MergeFastqPaired."""
fastq = ListField(FileField(), label="Reads file (mate 1)")
fastq2 = ListField(FileField(), label="Reads file (mate 2)")
fastqc_url = ListField(
FileHtmlField(),
label="Quality control with FastQC (mate 1)",
)
fastqc_url2 = ListField(
FileHtmlField(),
label="Quality control with FastQC (mate 2)",
)
fastqc_archive = ListField(FileField(),
label="Download FastQC archive (mate 1)")
fastqc_archive2 = ListField(FileField(),
label="Download FastQC archive (mate 2)")
class Input:
data_name = StringField(label="Data name")
sample_name = StringField(label="Collection name")
tags = ListField(StringField(), label="My tags")
class Input:
"""Input fields."""
data = ListField(DataField(data_type=""), label="Data.")