class EMPSingleEndCasavaDirFmt(model.DirectoryFormat):
# TODO: generalize this with a regex when we have validation in place for
# model.FileCollections. The file names are currently designed more
# specificially for handling MiSeq data.
sequences = model.File(r'Undetermined_S0_L001_R1_001.fastq.gz',
format=FastqGzFormat)
barcodes = model.File(r'Undetermined_S0_L001_I1_001.fastq.gz',
format=FastqGzFormat)
class EMPPairedEndCasavaDirFmt(model.DirectoryFormat):
forward = model.File(r'Undetermined_S0_L001_R1_001.fastq.gz',
format=FastqGzFormat)
reverse = model.File(r'Undetermined_S0_L001_R2_001.fastq.gz',
format=FastqGzFormat)
barcodes = model.File(r'Undetermined_S0_L001_I1_001.fastq.gz',
format=FastqGzFormat)
class RedundantSingleIntDirectoryFormat(model.DirectoryFormat):
"""
Two files of SingleIntFormat which are exactly the same.
"""
int1 = model.File('file1.txt', format=SingleIntFormat)
int2 = model.File('file2.txt', format=SingleIntFormat)
def _validate_(self, level):
if self.int1.view(int) != self.int2.view(int):
raise ValidationError("file1.txt does not match file2.txt")
class WinnowedDirectoryFormat(model.DirectoryFormat):
# this is an example of a fixed layout since it will always include Feature ordering w/ Jaccard results
# as well as complementary metadata files AUC values and Permanova files
featureOrdering = model.File(
r"feature_ordered.tsv",
format=WinnowedFeatureOrderingFormat) # Feature ordering w/ Jaccard
auc = model.File(
r"auc_ordered.tsv",
format=WinnowedAucOrderingFormat) # AUC values with ordering
permanova = model.File(r"permanova_ordered.tsv",
format=WinnowedPermanovaOrderingFormat
) # PERMANOVA values with ordering
class SBMLDirectory(model.DirectoryFormat):
manifest = model.File("manifest.csv", format=ModelManifest)
sbml_files = model.FileCollection(r".+\.xml", format=SBMLFormat)
@sbml_files.set_path_maker
def sbml_path_maker(self, model_id):
return "%s.xml" % model_id
class JSONDirectory(model.DirectoryFormat):
manifest = model.File("manifest.csv", format=ModelManifest)
json_files = model.FileCollection(r".+\.json", format=JSONFormat)
@json_files.set_path_maker
def sbml_path_maker(self, model_id):
return "%s.json" % model_id
class CommunityModelDirectory(model.DirectoryFormat):
manifest = model.File("manifest.csv", format=CommunityModelManifest)
model_files = model.FileCollection(r".+\.pickle",
format=CommunityModelFormat)
@model_files.set_path_maker
def model_path_maker(self, model_id):
return "%s.pickle" % model_id
class SeppReferenceDirFmt(model.DirectoryFormat):
alignment = model.File(r'aligned-dna-sequences.fasta',
format=AlignedDNAFASTAFormat)
phylogeny = model.File(r'tree.nwk', format=NewickFormat)
raxml_info = model.File(r'raxml-info.txt', format=RAxMLinfoFormat)
def _validate_(self, level):
seqs = self.alignment.view(skbio.TabularMSA)
tree = self.phylogeny.view(skbio.TreeNode)
seqs.reassign_index(minter='id')
alignment_ids = set(seqs.index)
phylogeny_ids = {t.name for t in tree.tips()}
if alignment_ids != phylogeny_ids:
raise ValidationError('IDs found in the alignment file that are '
'missing in the phylogeny file: %s. IDs '
'found in the phylogeny file that are '
'missing in the alignment file: %s.' %
(sorted(alignment_ids - phylogeny_ids),
sorted(phylogeny_ids - alignment_ids)))
class Bowtie2IndexDirFmt(model.DirectoryFormat):
idx1 = model.File(r'.+(?<!\.rev)\.1\.bt2', format=Bowtie2IndexFileFormat)
idx2 = model.File(r'.+(?<!\.rev)\.2\.bt2', format=Bowtie2IndexFileFormat)
ref3 = model.File(r'.+\.3\.bt2', format=Bowtie2IndexFileFormat)
ref4 = model.File(r'.+\.4\.bt2', format=Bowtie2IndexFileFormat)
rev1 = model.File(r'.+\.rev\.1\.bt2', format=Bowtie2IndexFileFormat)
rev2 = model.File(r'.+\.rev\.2\.bt2', format=Bowtie2IndexFileFormat)
def get_name(self):
filename = str(self.idx1.path_maker().relative_to(self.path))
return filename.rsplit('.1.bt2')[0]
class Bowtie2IndexDirFmt(model.DirectoryFormat):
idx1 = model.File(r'.+(?<!\.rev)\.1\.bt2l?', format=Bowtie2IndexFileFormat)
idx2 = model.File(r'.+(?<!\.rev)\.2\.bt2l?', format=Bowtie2IndexFileFormat)
ref3 = model.File(r'.+\.3\.bt2l?', format=Bowtie2IndexFileFormat)
ref4 = model.File(r'.+\.4\.bt2l?', format=Bowtie2IndexFileFormat)
rev1 = model.File(r'.+\.rev\.1\.bt2l?', format=Bowtie2IndexFileFormat)
rev2 = model.File(r'.+\.rev\.2\.bt2l?', format=Bowtie2IndexFileFormat)
def get_basename(self):
paths = [str(x.relative_to(self.path)) for x in self.path.iterdir()]
prefix = _get_prefix(paths)
return prefix[:-1] # trim trailing '.'
class NinjaOpsDBDirFmt(model.DirectoryFormat):
# NOTE: `db` is used as a placeholder prefix -- NINJA-OPS doesn't care
# what the prefix is, just that it's constant. The prefix must be used as
# the enclosing directory name, as well as the prefix of each filename
# within the directory.
index1 = model.File('db/db.1.bt2', format=Bowtie2IndexFormat)
index2 = model.File('db/db.2.bt2', format=Bowtie2IndexFormat)
index3 = model.File('db/db.3.bt2', format=Bowtie2IndexFormat)
index4 = model.File('db/db.4.bt2', format=Bowtie2IndexFormat)
rev_index1 = model.File('db/db.rev.1.bt2', format=Bowtie2IndexFormat)
rev_index2 = model.File('db/db.rev.2.bt2', format=Bowtie2IndexFormat)
replicate_map = model.File('db/db.db', format=NinjaReplicateMapFormat)
# TODO does the name `sequences` make sense or is there something more
# descriptive?
sequences = model.File('db/db.tcf', format=TerrificCompressedFormat)
# TODO is there any additional validation that needs to happen on the
# directory format that isn't taken care of by the individual FileFormat
# classes above?
def _validate_(self, level):
pass
class MultiplexedPairedEndBarcodeInSequenceDirFmt(model.DirectoryFormat):
forward_sequences = model.File('forward.fastq.gz', format=FastqGzFormat)
reverse_sequences = model.File('reverse.fastq.gz', format=FastqGzFormat)
class MicomResultsDirectory(model.DirectoryFormat):
growth_rates = model.File("growth_rates.csv", format=GrowthRates)
exchange_fluxes = model.File("exchange_fluxes.parquet", format=Fluxes)
class EMPMultiplexedDirFmt(model.DirectoryFormat):
sequences = model.File(r'sequences.fastq.gz', format=FastqGzFormat)
barcodes = model.File(r'barcodes.fastq.gz', format=FastqGzFormat)
class EMPPairedEndDirFmt(model.DirectoryFormat):
forward = model.File(r'forward.fastq.gz', format=FastqGzFormat)
reverse = model.File(r'reverse.fastq.gz', format=FastqGzFormat)
barcodes = model.File(r'barcodes.fastq.gz', format=FastqGzFormat)
class TaxonomicClassifierDirFmt(model.DirectoryFormat):
preprocess_params = model.File('preprocess_params.json', format=JSONFormat)
sklearn_pipeline = model.File('sklearn_pipeline.tar', format=PickleFormat)
class TaxonomicClassiferTemporaryPickleDirFmt(model.DirectoryFormat):
version_info = model.File('sklearn_version.json', format=JSONFormat)
sklearn_pipeline = model.File('sklearn_pipeline.tar', format=PickleFormat)
class _SingleLanePerSampleFastqDirFmt(CasavaOneEightSingleLanePerSampleDirFmt):
manifest = model.File('MANIFEST', format=FastqManifestFormat)
metadata = model.File('metadata.yml', format=YamlFormat)
class IDSelectionDirFmt(model.DirectoryFormat):
included = model.File('included.txt', format=UNIXListFormat)
excluded = model.File('excluded.txt', format=UNIXListFormat)
metadata = model.File('metadata.tsv', format=IDMetadataFormat)
label = model.File('label.txt', format=UNIXListFormat)
class MicomResultsDirectory(model.DirectoryFormat):
growth_rates = model.File("growth_rates.csv", format=GrowthRates)
exchange_fluxes = model.File("exchange_fluxes.csv", format=Fluxes)
annotations = model.File("annotations.csv", format=Annotations)
class MappingDirectoryFormat(model.DirectoryFormat):
mapping = model.File('mapping.tsv', format=MappingFormat)
class BEASTPosteriorDirFmt(model.DirectoryFormat):
log = model.File('posterior.log', format=PosteriorLogFormat)
trees = model.File('posterior.trees', format=NexusFormat)
ops = model.File('posterior.ops', format=BEASTOpsFileFormat)
control = model.File('control_file.xml', format=BEASTControlFileFormat)
class PairedDNASequencesDirectoryFormat(model.DirectoryFormat):
left_dna_sequences = model.File('left-dna-sequences.fasta',
format=DNAFASTAFormat)
right_dna_sequences = model.File('right-dna-sequences.fasta',
format=DNAFASTAFormat)
class SampleEstimatorDirFmt(model.DirectoryFormat):
version_info = model.File('sklearn_version.json', format=JSONFormat)
sklearn_pipeline = model.File('sklearn_pipeline.tar', format=PickleFormat)