import pytest
import numpy as np
from kipoi.data import Dataset
from kipoi.specs import DataLoaderArgument, DataLoaderSchema, DataLoaderDescription
from kipoi.specs import Author, Dependencies
from kipoi_utils.utils import inherits_from
from collections import OrderedDict
import related
from kipoi.data import kipoi_dataloader
deps = Dependencies(pip='kipoiseq')
package_authors = [Author(name='John')]
@kipoi_dataloader(override={
"dependencies": deps,
'info.authors': package_authors
})
class Dl(Dataset):
"""
info:
doc: short doc
args:
arg1:
doc: this is arg1
example: hey
n:
doc: length of the dataset
output_schema:
inputs:
name: seq
from kipoiseq.extractors import FastaStringExtractor
from kipoiseq.transforms import SwapAxes, DummyAxis, Compose, OneHot, ReorderedOneHot
from kipoiseq.transforms.functional import resize_interval
from kipoiseq.utils import to_scalar, parse_dtype
import pybedtools
from pybedtools import BedTool, Interval
# general dependencies
# bioconda::genomelake', TODO - add genomelake again once it gets released with pyfaidx to bioconda
deps = Dependencies(
conda=['bioconda::pybedtools', 'bioconda::pyfaidx', 'numpy', 'pandas'],
pip=['kipoiseq'])
package_authors = [
Author(name='Ziga Avsec', github='avsecz'),
Author(name='Roman Kreuzhuber', github='krrome')
]
# Object exported on import *
__all__ = ['SeqIntervalDl', 'StringSeqIntervalDl', 'BedDataset']
class BedDataset(object):
"""Reads a tsv file in the following format:
```
chr start stop task1 task2 ...
```
# Arguments
tsv_file: tsv file type
from kipoi.data import Dataset, kipoi_dataloader
from kipoi.metadata import GenomicRanges
from kipoi.specs import Author, Dependencies
from kipoi.data import SampleIterator
import gffutils
from pyfaidx import Fasta
import pickle
# general dependencies
# bioconda::genomelake', TODO - add genomelake again once it gets released with pyfaidx to bioconda
deps = Dependencies(conda=['bioconda::pyfaidx', 'numpy', 'pandas'],
pip=['kipoiseq', 'kipoi'])
package_authors = [Author(name='Jun Cheng', github='s6juncheng')]
__all__ = ['ExonInterval', 'generate_exons', 'MMSpliceDl']
# python 2.7 compatibility
try:
FileNotFoundError
except NameError:
FileNotFoundError = IOError
try:
ModuleNotFoundError
except NameError:
ModuleNotFoundError = ImportError
# ------------
from kipoi_conda.dependencies import Dependencies
from kipoiseq.transforms import ReorderedOneHot
from kipoi.specs import Author
from kipoi_utils.utils import default_kwargs
from kipoiseq.extractors import FastaStringExtractor
from kipoiseq.transforms.functional import resize_interval, one_hot_dna
from kipoiseq.utils import to_scalar, parse_dtype
from kipoiseq.dataclasses import Interval
deps = Dependencies(conda=[
'bioconda::pybedtools', 'bioconda::pyfaidx', 'bioconda::pyranges', 'numpy',
'pandas'
],
pip=['kipoiseq'])
package_authors = [
Author(name='Ziga Avsec', github='avsecz'),
Author(name='Roman Kreuzhuber', github='krrome')
]
# Add Alex here?
# Object exported on import *
__all__ = [
'SeqIntervalDl', 'StringSeqIntervalDl', 'BedDataset', 'AnchoredGTFDl'
]
class BedDataset(object):
"""Reads a tsv file in the following format:
```
chr start stop task1 task2 ...
```
__all__ = [
'SingleVariantProteinDataLoader',
'SingleVariantUTRDataLoader',
]
deps = Dependencies(conda=[
'bioconda::pybedtools',
'bioconda::pyfaidx',
'bioconda::pyranges',
'bioconda::biopython',
'numpy',
'pandas',
],
pip=['kipoiseq'])
package_authors = [
Author(name='Florian R. Hölzlwimmer', github='hoeze'),
Author(name='Kalin Nonchev', github='KalinNonchev')
]
class SingleVariantProteinDataLoader(SampleIterator):
"""
info:
doc: >
Dataloader for protein sequence models. With inputs as gtf annotation file and fasta file,
each output is a protein sequence with flanking intronic seuqences. Intronic sequnce
lengths specified by the users. Returned sequences are of the type np.array([str])
type: SampleIterator
args:
gtf_file:
doc: file path; Genome annotation GTF file