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 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 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."""
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 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 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 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.",
)
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."""
alignment = DataField("alignment:bam", label="Alignment BAM file")
bedpe = DataField(
"bedpe",
label="BEDPE Normalization factor",
description="The BEDPE file describes disjoint genome features, "
"such as structural variations or paired-end sequence alignments. "
"It is used to estimate the scale factor.",
)
scale = FloatField(
label="Scale for the normalization factor",
description="Magnitude of the scale factor. "
"The scaling factor is calculated by dividing the scale "
"with the number of features in BEDPE "
"(scale/(number of features)).",
default=10000,
)
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 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 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.",
)
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.",
)
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 to process Cuffdiff."""
case = ListField(
DataField("cufflinks:cuffquant"),
label="Case samples",
)
control = ListField(
DataField("cufflinks:cuffquant"),
label="Control samples",
)
labels = ListField(
StringField(),
label="Group labels",
description="Define labels for each sample group.",
default=["control", "case"],
)
annotation = DataField(
"annotation",
label="Annotation (GTF/GFF3)",
description="A transcript annotation file produced by "
"cufflinks, cuffcompare, or other tool.",
)
genome = DataField(
"seq:nucleotide",
label="Run bias detection and correction algorithm",
required=False,
description="Provide Cufflinks with a multifasta file "
"(genome file) via this option to instruct it to run a "
"bias detection and correction algorithm which can "
"significantly improve accuracy of transcript abundance "
"estimates.",
)
multi_read_correct = BooleanField(
label="Do initial estimation procedure to more accurately "
"weight reads with multiple genome mappings",
default=False,
)
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,
)
gene_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",
)
gene_fdr = FloatField(
label="FDR threshold for gene sets",
default=0.05,
hidden="!create_sets",
)
fdr = FloatField(
label="Allowed FDR",
description=
"The allowed false discovery rate. The default is 0.05.",
default=0.05,
)
library_type = StringField(
label="Library type",
description="In cases where Cufflinks cannot determine the "
"platform and protocol used to generate input reads, you "
"can supply this information manually, which will allow "
"Cufflinks to infer source strand information with certain "
"protocols. The available options are listed below. For "
"paired-end data, we currently only support protocols "
"where reads point towards each other: fr-unstranded - "
"Reads from the left-most end of the fragment (in "
"transcript coordinates) map to the transcript strand and "
"the right-most end maps to the opposite strand; "
"fr-firststrand - Same as above except we enforce the rule "
"that the right-most end of the fragment (in transcript "
"coordinates) is the first sequenced (or only sequenced "
"for single-end reads). Equivalently, it is assumed that "
"only the strand generated during first strand synthesis "
"is sequenced; fr-secondstrand - Same as above except we "
"enforce the rule that the left-most end of the fragment "
"(in transcript coordinates) is the first sequenced (or "
"only sequenced for single-end reads). Equivalently, it is "
"assumed that only the strand generated during second "
"strand synthesis is sequenced.",
default="fr-unstranded",
choices=[
("fr-unstranded", "fr-unstranded"),
("fr-firststrand", "fr-firststrand"),
("fr-secondstrand", "fr-secondstrand"),
],
)
library_normalization = StringField(
label="Library normalization method",
description="You can control how library sizes (i.e. "
"sequencing depths) are normalized in Cufflinks and "
"Cuffdiff. Cuffdiff has several methods that require "
"multiple libraries in order to work. Library "
"normalization methods supported by Cufflinks work on one "
"library at a time.",
default="geometric",
choices=[
("geometric", "geometric"),
("classic-fpkm", "classic-fpkm"),
("quartile", "quartile"),
],
)
dispersion_method = StringField(
label="Dispersion method",
description=" Cuffdiff works by modeling the variance in "
"fragment counts across replicates as a function of the "
"mean fragment count across replicates. Strictly speaking, "
"models a quantitity called dispersion - the variance "
"present in a group of samples beyond what is expected "
"from a simple Poisson model of RNA_Seq. You can control "
"how Cuffdiff constructs its model of dispersion in locus "
"fragment counts. Each condition that has replicates can "
"receive its own model, or Cuffdiff can use a global model "
"for all conditions. All of these policies are identical "
"to those used by DESeq (Anders and Huber, Genome Biology, "
"2010).",
default="pooled",
choices=[
("pooled", "pooled"),
("per-condition", "per-condition"),
("blind", "blind"),
("poisson", "poisson"),
],
)