class Input:
"""Input fields for SlamdunkAllPaired."""
reads = DataField('reads:fastq:paired', label='Reads')
transcriptome = DataField(
'seq:nucleotide',
label='FASTA file containig sequences for alingnig.')
regions = DataField(
'bed', label='BED file with coordinates of regions of interest.')
filter_multimappers = BooleanField(
label='Filter multimappers',
description=
'If true filter and reasign multimappers based on provided BED file with regions of interest.',
default=True)
max_alignments = IntegerField(
label='Maximum number of multimapper alignments',
description=
'The maximum number of alignments that will be reported for a multi-mapping read (i.e. reads'
'with multiple alignments of equal best scores).',
default=1)
read_length = IntegerField(
label='Maximum read length',
description='Maximul length of reads in the input FASTQ file.',
default=150)
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,
)
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",
)
class Output:
"""Output fields."""
out_foo = IntegerField(label="Foo.", required=False)
out_bar = StringField(label="Bar.", required=False)
out_foo2 = IntegerField(label="Foo2.", required=False)
out_subgroup = IntegerField(label="SubGroupFoo", required=True)
class Input:
"""Input fields for SlamdunkAllPaired."""
reads = DataField("reads:fastq:paired", label="Reads")
ref_seq = DataField("seq:nucleotide", label="FASTA file")
regions = DataField(
"bed", label="BED file with coordinates of regions of interest"
)
filter_multimappers = BooleanField(
label="Filter multimappers",
description="If true filter and reasign multimappers based on provided BED file with regions of interest",
default=True,
)
max_alignments = IntegerField(
label="Maximum number of multimapper alignments",
description="The maximum number of alignments that will be reported for a multi-mapping read (i.e. reads"
"with multiple alignments of equal best scores)",
default=1,
)
read_length = IntegerField(
label="Maximum read length",
description="Maximum length of reads in the input FASTQ file",
default=150,
)
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="Minimum read length",
default=20,
)
min_overlap = IntegerField(
label="Mimimum overlap",
description=
"Minimum overlap between adapter and read for an adapter to be found.",
default=20,
)
class Output:
"""Output field of the process UploadOrangeMetadata."""
table = FileField(label="Uploaded table")
n_samples = IntegerField(label="Number of samples")
features = StringField(label="Number of features")
target = StringField(label="Target class description")
n_metas = IntegerField(label="Number of meta attributes")
class Input:
"""Input fields to process ROSE2."""
input_macs = DataField(
"chipseq:callpeak",
label="BED/narrowPeak file (MACS results)",
required=False,
hidden="input_upload",
)
input_upload = DataField(
"bed",
label="BED file (Upload)",
required=False,
hidden="input_macs || use_filtered_bam",
)
use_filtered_bam = BooleanField(
label="Use Filtered BAM File",
default=False,
hidden="input_upload",
description=("Use filtered BAM file from a MACS2 object to rank "
"enhancers by. Only applicable if input is MACS2."),
)
rankby = DataField(
"alignment:bam",
label="BAM file",
required=False,
hidden="use_filtered_bam",
description="BAM file to rank enhancers by.",
)
control = DataField(
"alignment:bam",
label="Control BAM File",
required=False,
hidden="use_filtered_bam",
description="BAM file to rank enhancers by.",
)
tss = IntegerField(
label="TSS exclusion",
default=0,
description=
"Enter a distance from TSS to exclude. 0 = no TSS exclusion.",
)
stitch = IntegerField(
label="Stitch",
required=False,
description=(
"Enter a max linking distance for stitching. If not "
"given, optimal stitching parameter will be determined"
" automatically."),
)
mask = DataField(
"bed",
label="Masking BED file",
required=False,
description=(
"Mask a set of regions from analysis. Provide a BED of"
" masking regions."),
)
class Input:
"""Input fields to process ImportScRNA10x."""
reads = DataField(
data_type="screads:10x:",
label="10x reads data object",
)
genome_index = DataField(
data_type="genomeindex:10x:",
label="10x genome index data object",
)
chemistry = StringField(
label="Chemistry",
required=False,
default="auto",
description=
("Assay configuration. By default the assay configuration is detected "
"automatically, which is the recommended mode. You should only specify "
"chemistry if there is an error in automatic detection."),
choices=[
("auto", "auto"),
("Single Cell 3'", "threeprime"),
("Single Cell 5'", "fiveprime"),
("Single Cell 3' v1", "SC3Pv1"),
("Single Cell 3' v2", "SC3Pv2"),
("Single Cell 3' v3", "SC3Pv3"),
("Single Cell 5' paired-end", "C5P-PE"),
("Single Cell 5' R2-only", "SC5P-R2"),
],
)
trim_r1 = IntegerField(
label="Trim R1",
required=False,
description=
("Hard-trim the input R1 sequence to this length. Note that the length "
"includes the Barcode and UMI sequences so do not set this below 26 for "
"Single Cell 3' v2 or Single Cell 5'. This and \"Trim R2\" are useful for "
"determining the optimal read length for sequencing."),
)
trim_r2 = IntegerField(
label="Trim R2",
required=False,
description="Hard-trim the input R2 sequence to this length.",
)
expected_cells = IntegerField(
label="Expected number of recovered cells",
default=3000,
)
force_cells = IntegerField(
label="Force cell number",
required=False,
description=
("Force pipeline to use this number of cells, bypassing the cell "
"detection algorithm. Use this if the number of cells estimated by Cell "
"Ranger is not consistent with the barcode rank plot."),
)
class Output:
"""Output fields."""
relation_id = IntegerField(label="Relation id")
relation_type = StringField(label="Relation type")
relation_ordered = StringField(label="Relation ordering")
relation_category = StringField(label="Relation category")
relation_unit = StringField(label="Relation unit")
relation_partition_label = StringField(label="Relation partition label")
relation_partition_position = IntegerField(label="Relation partition label")
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,
)
class Input:
"""Input fields for BsConversionRate."""
mr = DataField(
"alignment:bam:walt",
label="Aligned reads from bisulfite sequencing",
description="Bisulfite specifc alignment such as WALT is required as .mr file type is used. Duplicates"
"should be removed to reduce any bias introduced by incomplete conversion on PCR duplicate"
"reads.",
)
skip = BooleanField(
label="Skip Bisulfite conversion rate step",
description="Bisulfite conversion rate step can be skipped.",
default=False,
)
sequence = DataField(
"seq:nucleotide",
label="Unmethylated control sequence",
description="Separate unmethylated control sequence FASTA file is required to estimate bisulfite"
"conversion rate.",
required=False,
)
count_all = BooleanField(
label="Count all cytosines including CpGs", default=True
)
read_length = IntegerField(label="Average read length", default=150)
max_mismatch = FloatField(
label="Maximum fraction of mismatches", required=False
)
a_rich = BooleanField(label="Reads are A-rich", default=False)
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).",
)
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.",
)
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 for CollectRrbsMetrics."""
bam = DataField("alignment:bam", label="Alignment BAM file")
genome = DataField("seq:nucleotide", label="Genome")
min_quality = IntegerField(
label=
"Threshold for base quality of a C base before it is considered",
default=20,
)
next_base_quality = IntegerField(
label=
"Threshold for quality of a base next to a C before the C base is considered",
default=10,
)
min_lenght = IntegerField(label="Minimum read length", default=5)
mismatch_rate = FloatField(
label=
"Maximum fraction of mismatches in a read to be considered (Range: 0 and 1)",
default=0.1,
)
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_sorted = BooleanField(
label="Sorted BAM file",
description=
"If true the sort order in the header file will be ignored.",
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,
)
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
)
class Output:
"""Output field of the process ImportFastaNucleotide."""
fastagz = FileField(label="FASTA file (compressed)")
fasta = FileField(label="FASTA file")
fai = FileField(label="FASTA file index")
fasta_dict = FileField(label="FASTA dictionary")
num_seqs = IntegerField(label="Number of sequences")
species = StringField(label="Species")
build = StringField(label="Build")
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,
)
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.",
)
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 AlignmentSieve."""
alignment = DataField("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 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 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",
)
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,
)
class Input:
"""Input fields for AlleyoopSnpEval."""
ref_seq = DataField(
"seq:nucleotide",
label="FASTA file containig sequences for aligning")
regions = DataField(
"bed", label="BED file with coordinates of regions of interest")
slamdunk = DataField("alignment:bam:slamdunk",
label="Slamdunk results")
read_length = IntegerField(
label="Maximum read length",
description="Maximum length of reads in the input FASTQ file",
default=150,
)
class Input:
"""Input fields for AlignmentSummary."""
bam = DataField("alignment:bam", label="Alignment BAM file")
genome = DataField("seq:nucleotide", label="Genome")
adapters = DataField("seq:nucleotide",
label="Adapter sequences",
required=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",
)
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"),
],
)
bisulfite = BooleanField(
label="BAM file consists of bisulfite sequenced reads",
default=False)
assume_sorted = BooleanField(
label="Sorted BAM file",
description=
"If true the sort order in the header file will be ignored.",
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 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",
)
