class SplicingMaxEntDataset(Dataset):
"""
args:
MISO_AS:
doc: Whether the given annotation file is MISO alternative splicing annotation. default False.
fasta_file:
doc: Reference Genome sequence in fasta format
example:
md5: 936544855b253835442a0f253dd4b083
url: https://zenodo.org/record/1466099/files/3prime-example_files-hg19.chr22.fa?download=1
type: str
gtf_file:
doc: file path; Genome annotation GTF file
example:
md5: 174fd11303ae2c2369094bfcbe303c07
url: https://zenodo.org/record/1466099/files/3prime-example_files-hg19.chr22.gtf?download=1
label_col:
doc: response label column name
target_file:
doc: path to the targets (txt) file
optional: true
side:
doc: 5 or 3prime splice-site
dependencies:
conda:
- pysam=0.15.2
- python=3.5.6
info:
authors:
- github: s6juncheng
name: Jun Cheng
doc: MaxEnt Splicing Model
name: MaxEnt
version: 0.1
output_schema:
inputs:
associated_metadata: ranges
doc: a junction (donor or acceptor) sequence
name: seq
shape: ()
special_type: DNAStringSeq
metadata:
biotype:
doc: gene biotype, can be used to filter protein coding genes for instance
type: str
geneID:
doc: gene ID
type: str
order:
doc: order of the donor site in the transcript, counted from 5' to 3'.
type: int
ranges:
doc: ranges that the sequences were extracted
type: GenomicRanges
transcriptID:
doc: transcript id
type: str
targets:
doc: Predicted psi
name: psi
shape: (1,)
"""
def __init__(
self,
gtf_file,
fasta_file,
side='5prime', # 5prime/3prime
target_file=None,
MISO_AS=False,
label_col='event_name'):
from gtf_utils import loadgene
self.genes = loadgene(gtf_file)
self.fasta_file = fasta_file
self.fasta = None # open the file later
if side in ["5prime", "3prime"]:
self.side = side
else:
raise Exception("side should be 5prime or 3prime")
if self.side == "5prime":
self.overhang_l = 3
self.overhang_r = 6
else:
self.overhang_l = 3
self.overhang_r = 20
if target_file is not None:
self.Y = Target(target_file, label_col)
else:
self.Y = None
self.MISO_AS = MISO_AS
if not MISO_AS:
self.spliceSites = self.get_spliceSites()
self._name = None
self._species = None
def __len__(self):
if self.MISO_AS:
return len(self.genes)
else:
return len(self.spliceSites)
def __getitem__(self, idx):
if self.fasta is None:
from fasta_utils import FastaFile
self.fasta = FastaFile(self.fasta_file)
out = {}
if self.MISO_AS:
gene = self.genes[idx]
inputs, ranges = self.get_seq(gene)
out['inputs'] = inputs
if self.Y is not None:
out['targets'] = self.Y.get_target(gene.geneName)
else:
out['targets'] = np.nan
out['metadata'] = {}
out['metadata']['geneName'] = gene.geneName
out['metadata']['chrom'] = gene.chrom
out['metadata']['strand'] = gene.strand
out['metadata']['start'] = gene.start
out['metadata']['stop'] = gene.stop
out['metadata']['extracted_regions'] = ranges
else:
spliceSite = self.spliceSites[idx]
out['inputs'] = spliceSite.get_seq(self.fasta)
out['metadata'] = {}
out['metadata']['geneID'] = spliceSite.geneID
out['metadata']['transcriptID'] = spliceSite.transcriptID
out['metadata']['biotype'] = spliceSite.biotype
out['metadata']['order'] = spliceSite.order
out['metadata']['ranges'] = GenomicRanges(
spliceSite.chrom,
spliceSite.grange[0] - 1, # use 0-base indexing
spliceSite.grange[1],
spliceSite.geneID,
spliceSite.strand)
return out
def get_seq(self, gene):
""" Get exon and intron sequences """
exons = gene.get_all_exons()
# N_exon = exons.shape[0]
introns = gene.get_all_introns()
# Take intron coordinate
# Try both normal gtf and AS_gtf
if self.side == "5prime":
if gene.strand == "+":
seq_ranges = exons[:-1, 1].reshape(-1, 1) + np.array(
[-self.overhang_l + 1, self.overhang_r])
else:
seq_ranges = exons[:-1, 0].reshape(-1, 1) + np.array(
[-self.overhang_r, self.overhang_l - 1])
else:
if gene.strand == "+":
seq_ranges = exons[1:, 0].reshape(-1, 1) + np.array(
[-self.overhang_r, self.overhang_l - 1])
else:
seq_ranges = exons[1:, 1].reshape(-1, 1) + np.array(
[-self.overhang_l + 1, self.overhang_r])
seq = [
self.fasta.get_seq(gene.chrom, seq_range, gene.strand)
for seq_range in seq_ranges
]
return np.array(seq), seq_ranges
def _get_spliceSites(self, gene):
''' Get splice site sequence for all transcripts of a single gene.
Applied for normal gtf annotation.
'''
spliceSites = []
for transcript in gene.trans:
exons = transcript.exons
ind = np.lexsort((exons[:, 1], exons[:, 0]))
if len(exons) > 1:
if self.side == "5prime":
if gene.strand == "+":
seq_ranges = exons[:-1, 1].reshape(-1, 1) + np.array(
[-self.overhang_l + 1, self.overhang_r])
else:
ind = ind[::-1]
exons = exons[ind]
seq_ranges = exons[:-1, 0].reshape(-1, 1) + np.array(
[-self.overhang_r, self.overhang_l - 1])
else:
if gene.strand == "+":
seq_ranges = exons[1:, 0].reshape(-1, 1) + np.array(
[-self.overhang_r, self.overhang_l - 1])
else:
ind = ind[::-1]
exons = exons[ind]
seq_ranges = exons[1:, 1].reshape(-1, 1) + np.array(
[-self.overhang_l + 1, self.overhang_r])
for i in range(seq_ranges.shape[0]):
spliceSite = SpliceSite(gene.chrom, seq_ranges[i, 0],
seq_ranges[i, 1], gene.strand,
transcript.tranID, gene.geneID,
gene.biotype, i)
# can call get_seq later in iterator to save memory
# spliceSite.seq = spliceSite.get_seq(self.fasta)
spliceSites.append(spliceSite)
return spliceSites
def get_spliceSites(self):
''' Get splice sites for all donors
'''
spliceSites = list(map(self._get_spliceSites, self.genes))
spliceSites = list(itertools.chain.from_iterable(spliceSites))
return spliceSites
@property
def name(self):
return self._name
@name.setter
def name(self, value):
self._name = value
@property
def species(self):
return self._species
@species.setter
def species(self, value):
self._species = value
class SplicingMaxEntDataset(Dataset):
"""
Args:
gtf_file: gtf file. Can be dowloaded from MISO or ensembl.
fasta_file: file path; Genome sequence
side: 5prime or 3prime
target_file: file path; path to the targets in MISO summary format.
MISO_AS: whether the used annotation file is from MISO alternative splicing annotation.
label_col: column name in target file which has PSI.
"""
def __init__(
self,
gtf_file,
fasta_file,
side='5prime', # 5prime/3prime
target_file=None,
MISO_AS=False,
label_col='event_name'):
self.genes = loadgene(gtf_file)
self.fasta_file = fasta_file
self.fasta = None # open the file later
if side in ["5prime", "3prime"]:
self.side = side
else:
raise Exception("side should be 5prime or 3prime")
if self.side == "5prime":
self.overhang_l = 3
self.overhang_r = 6
else:
self.overhang_l = 3
self.overhang_r = 20
if target_file is not None:
self.Y = Target(target_file, label_col)
else:
self.Y = None
self.MISO_AS = MISO_AS
if not MISO_AS:
self.spliceSites = self.get_spliceSites()
self._name = None
self._species = None
def __len__(self):
if self.MISO_AS:
return len(self.genes)
else:
return len(self.spliceSites)
def __getitem__(self, idx):
if self.fasta is None:
self.fasta = FastaFile(self.fasta_file)
out = {}
if self.MISO_AS:
gene = self.genes[idx]
inputs, ranges = self.get_seq(gene)
out['inputs'] = inputs
if self.Y is not None:
out['targets'] = self.Y.get_target(gene.geneName)
else:
out['targets'] = np.nan
out['metadata'] = {}
out['metadata']['geneName'] = gene.geneName
out['metadata']['chrom'] = gene.chrom
out['metadata']['strand'] = gene.strand
out['metadata']['start'] = gene.start
out['metadata']['stop'] = gene.stop
out['metadata']['extracted_regions'] = ranges
else:
spliceSite = self.spliceSites[idx]
out['inputs'] = spliceSite.get_seq(self.fasta)
out['metadata'] = {}
out['metadata']['geneID'] = spliceSite.geneID
out['metadata']['transcriptID'] = spliceSite.transcriptID
out['metadata']['biotype'] = spliceSite.biotype
out['metadata']['order'] = spliceSite.order
out['metadata']['ranges'] = GenomicRanges(
spliceSite.chrom,
spliceSite.grange[0] - 1, # use 0-base indexing
spliceSite.grange[1],
spliceSite.geneID,
spliceSite.strand)
return out
def get_seq(self, gene):
""" Get exon and intron sequences """
exons = gene.get_all_exons()
# N_exon = exons.shape[0]
introns = gene.get_all_introns()
# Take intron coordinate
# Try both normal gtf and AS_gtf
if self.side == "5prime":
if gene.strand == "+":
seq_ranges = exons[:-1, 1].reshape(-1, 1) + np.array(
[-self.overhang_l + 1, self.overhang_r])
else:
seq_ranges = exons[:-1, 0].reshape(-1, 1) + np.array(
[-self.overhang_r, self.overhang_l - 1])
else:
if gene.strand == "+":
seq_ranges = exons[1:, 0].reshape(-1, 1) + np.array(
[-self.overhang_r, self.overhang_l - 1])
else:
seq_ranges = exons[1:, 1].reshape(-1, 1) + np.array(
[-self.overhang_l + 1, self.overhang_r])
seq = [
self.fasta.get_seq(gene.chrom, seq_range, gene.strand)
for seq_range in seq_ranges
]
return np.array(seq), seq_ranges
def _get_spliceSites(self, gene):
''' Get splice site sequence for all transcripts of a single gene.
Applied for normal gtf annotation.
'''
spliceSites = []
for transcript in gene.trans:
exons = transcript.exons
ind = np.lexsort((exons[:, 1], exons[:, 0]))
if len(exons) > 1:
if self.side == "5prime":
if gene.strand == "+":
seq_ranges = exons[:-1, 1].reshape(-1, 1) + np.array(
[-self.overhang_l + 1, self.overhang_r])
else:
ind = ind[::-1]
exons = exons[ind]
seq_ranges = exons[:-1, 0].reshape(-1, 1) + np.array(
[-self.overhang_r, self.overhang_l - 1])
else:
if gene.strand == "+":
seq_ranges = exons[1:, 0].reshape(-1, 1) + np.array(
[-self.overhang_r, self.overhang_l - 1])
else:
ind = ind[::-1]
exons = exons[ind]
seq_ranges = exons[1:, 1].reshape(-1, 1) + np.array(
[-self.overhang_l + 1, self.overhang_r])
for i in range(seq_ranges.shape[0]):
spliceSite = SpliceSite(gene.chrom, seq_ranges[i, 0],
seq_ranges[i, 1], gene.strand,
transcript.tranID, gene.geneID,
gene.biotype, i)
# can call get_seq later in iterator to save memory
# spliceSite.seq = spliceSite.get_seq(self.fasta)
spliceSites.append(spliceSite)
return spliceSites
def get_spliceSites(self):
''' Get splice sites for all donors
'''
spliceSites = list(map(self._get_spliceSites, self.genes))
spliceSites = list(itertools.chain.from_iterable(spliceSites))
return spliceSites
@property
def name(self):
return self._name
@name.setter
def name(self, value):
self._name = value
@property
def species(self):
return self._species
@species.setter
def species(self, value):
self._species = value
class SplicingKmerDataset(Dataset):
"""
Args:
gtf_file: gtf file. Can be dowloaded from MISO or ensembl.
fasta_file: file path; Genome sequence
target_file: file path; path to the targets in MISO summary format.
overhang: length of overhang.
MISO_AS: whether the used annotation file is from MISO alternative splicing annotation.
"""
def __init__(self,
gtf_file,
fasta_file,
overhang=80,
MISO_AS=False): # intron + ~ bp exon from both side
self.genes = loadgene(gtf_file)
self.fasta_file = fasta_file
self.fasta = None
self.overhang = overhang
self.MISO_AS = MISO_AS
if not MISO_AS:
self.spliceSites = self.get_spliceSites()
self._name = None
self._species = None
def __len__(self):
if self.MISO_AS:
return len(self.genes)
else:
return len(self.spliceSites)
def __getitem__(self, idx):
if self.fasta is None:
self.fasta = FastaFile(self.fasta_file)
out = {}
if self.MISO_AS:
gene = self.genes[idx]
out['inputs'] = self.get_seq(gene)
out['metadata'] = {}
out['metadata']['geneName'] = gene.geneName
out['metadata']['chrom'] = gene.chrom
out['metadata']['strand'] = gene.strand
out['metadata']['start'] = gene.start
out['metadata']['stop'] = gene.stop
else:
spliceSite = self.spliceSites[idx]
out['inputs'] = spliceSite.get_seq(self.fasta)
out['metadata'] = {}
out['metadata']['geneID'] = spliceSite.geneID
out['metadata']['transcriptID'] = spliceSite.transcriptID
out['metadata']['biotype'] = spliceSite.biotype
out['metadata']['order'] = spliceSite.order
out['metadata']['ranges'] = GenomicRanges(
spliceSite.chrom,
spliceSite.grange[0] - 1, # use 0-base indexing
spliceSite.grange[1],
spliceSite.geneID,
spliceSite.strand)
return out
def get_seq(self, gene):
""" Get splice site sequence with flanking exon and intron sequences.
This function is applied for MISO annotation with 3 exon alternative splicing model.
"""
exons = gene.get_all_exons()
# N_exon = exons.shape[0]
if gene.strand == "+":
seq_ranges = exons[:-1, 1].reshape(-1, 1) + np.array(
[-self.overhang + 1, self.overhang])
else:
seq_ranges = exons[:-1, 0].reshape(-1, 1) + np.array(
[-self.overhang, self.overhang - 1])
seq = [
self.fasta.get_seq(gene.chrom, seq_range, gene.strand)
for seq_range in seq_ranges
]
return np.array(seq)
def _get_spliceSites(self, gene):
''' Get splice site sequence for all transcripts of a single gene.
Applied for normal gtf annotation.
'''
spliceSites = []
for transcript in gene.trans:
exons = transcript.exons
ind = np.lexsort((exons[:, 1], exons[:, 0]))
if len(exons) > 1:
if gene.strand == "+":
seq_ranges = exons[:-1, 1].reshape(-1, 1) + np.array(
[-self.overhang + 1, self.overhang])
else:
ind = ind[::-1]
exons = exons[ind]
seq_ranges = exons[:-1, 0].reshape(-1, 1) + np.array(
[-self.overhang, self.overhang - 1])
for i in range(seq_ranges.shape[0]):
spliceSite = SpliceSite(gene.chrom, seq_ranges[i, 0],
seq_ranges[i, 1], gene.strand,
transcript.tranID, gene.geneID,
gene.biotype, i)
# can call get_seq later in iterator to save memory
# spliceSite.seq = spliceSite.get_seq(self.fasta)
spliceSites.append(spliceSite)
return spliceSites
def get_spliceSites(self):
''' Get splice sites for all donors
'''
spliceSites = list(map(self._get_spliceSites, self.genes))
spliceSites = list(itertools.chain.from_iterable(spliceSites))
return spliceSites
@property
def name(self):
return self._namem
@name.setter
def name(self, value):
self._name = value
@property
def species(self):
return self._species
@species.setter
def species(self, value):
self._species = value