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 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 Input:
"""Input fields for InsertSizeMetrics."""
bam = DataField("alignment:bam", label="Alignment BAM file")
genome = DataField("seq:nucleotide", label="Genome")
minimum_fraction = FloatField(
label="Minimum fraction of reads in a category to be considered ",
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).",
default=0.05,
)
include_duplicates = BooleanField(
label=
"Include reads marked as duplicates in the insert size histogram",
default=False,
)
deviations = FloatField(
label="Deviations limit",
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.",
default=10.0,
)
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 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 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 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 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.",
)
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 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 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."""
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 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 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 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,
)
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 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 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 Input:
"""Input fields to process Bamclipper."""
alignment = DataField('alignment:bam', label='Alignment BAM file')
bedpe = DataField('bedpe', label='BEDPE file', required=False)
skip = BooleanField(
label='Skip Bamclipper step',
description='Use this option to skip Bamclipper step.',
default=False)
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 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 to process Bamclipper."""
alignment = DataField("alignment:bam", label="Alignment BAM file")
bedpe = DataField("bedpe", label="BEDPE file", required=False)
skip = BooleanField(
label="Skip Bamclipper step",
description="Use this option to skip Bamclipper step.",
default=False,
)
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",
)
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 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 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 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 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")
