def get_CDSs(self, force_all=False):
all_CDSs = gff.get_CDSs(
self.file_names['genes'],
self.file_names['genome'],
)
if self.transcripts_file_name == None:
CDSs = all_CDSs
else:
transcripts = {
line.strip()
for line in open(self.transcripts_file_name)
}
CDSs = [t for t in all_CDSs if t.name in transcripts]
max_gene_length = 0
for CDS in CDSs:
CDS.build_coordinate_maps()
max_gene_length = max(max_gene_length, CDS.transcript_length)
CDS.delete_coordinate_maps()
if force_all:
piece_CDSs = CDSs
else:
piece_CDSs = piece_of_list(CDSs, self.num_pieces, self.which_piece)
return piece_CDSs, max_gene_length
def produce_transcript_base_compositions():
gff_fn = '/home/jah/projects/ribosomes/data/organisms/saccharomyces_cerevisiae/EF4/transcriptome/genes.gff'
genome_dir = '/home/jah/projects/ribosomes/data/organisms/saccharomyces_cerevisiae/EF4/genome/'
composition_fn = '/home/jah/projects/ribosomes/data/organisms/saccharomyces_cerevisiae/EF4/transcript_recent_As.hdf5'
CDSs = gff.get_CDSs(gff_fn, genome_dir)
left_buffer = 500
right_buffer = 500
genes = {}
windows = [5, 10, 20]
for transcript in utilities.progress_bar(len(CDSs), CDSs):
genes[transcript.name] = {}
transcript.build_coordinate_maps()
landmarks = {
'start': 0,
'start_codon': transcript.transcript_start_codon,
'stop_codon': transcript.transcript_stop_codon,
'end': transcript.transcript_length,
}
sequence = transcript.get_transcript_sequence(left_buffer,
right_buffer)
A_locations = positions.PositionCounts(
landmarks,
left_buffer,
right_buffer,
data=(sequence.data == 'A'),
)
for window in windows:
recent_As = positions.PositionCounts(
landmarks,
left_buffer,
right_buffer,
)
for left_edge in range(
-left_buffer,
transcript.CDS_length + right_buffer - window):
num_As = sum(A_locations['start',
left_edge:left_edge + window])
recent_As['start', left_edge] = num_As
genes[transcript.name][window] = recent_As
transcript.delete_coordinate_maps()
Serialize.read_positions.write_file(genes, composition_fn)
def get_CDSs(self, force_all=False):
all_CDSs = gff.get_CDSs(self.file_names["genes"], self.file_names["genome"])
if self.transcripts_file_name == None:
CDSs = all_CDSs
else:
transcripts = {line.strip() for line in open(self.transcripts_file_name)}
CDSs = [t for t in all_CDSs if t.name in transcripts]
max_gene_length = 0
for CDS in CDSs:
CDS.build_coordinate_maps()
max_gene_length = max(max_gene_length, CDS.transcript_length)
CDS.delete_coordinate_maps()
if force_all:
piece_CDSs = CDSs
else:
piece_CDSs = piece_of_list(CDSs, self.num_pieces, self.which_piece)
return piece_CDSs, max_gene_length
def produce_transcript_base_compositions():
gff_fn = "/home/jah/projects/ribosomes/data/organisms/saccharomyces_cerevisiae/EF4/transcriptome/genes.gff"
genome_dir = "/home/jah/projects/ribosomes/data/organisms/saccharomyces_cerevisiae/EF4/genome/"
composition_fn = (
"/home/jah/projects/ribosomes/data/organisms/saccharomyces_cerevisiae/EF4/transcript_recent_As.hdf5"
)
CDSs = gff.get_CDSs(gff_fn, genome_dir)
left_buffer = 500
right_buffer = 500
genes = {}
windows = [5, 10, 20]
for transcript in utilities.progress_bar(len(CDSs), CDSs):
genes[transcript.name] = {}
transcript.build_coordinate_maps()
landmarks = {
"start": 0,
"start_codon": transcript.transcript_start_codon,
"stop_codon": transcript.transcript_stop_codon,
"end": transcript.transcript_length,
}
sequence = transcript.get_transcript_sequence(left_buffer, right_buffer)
A_locations = positions.PositionCounts(landmarks, left_buffer, right_buffer, data=(sequence.data == "A"))
for window in windows:
recent_As = positions.PositionCounts(landmarks, left_buffer, right_buffer)
for left_edge in range(-left_buffer, transcript.CDS_length + right_buffer - window):
num_As = sum(A_locations["start", left_edge : left_edge + window])
recent_As["start", left_edge] = num_As
genes[transcript.name][window] = recent_As
transcript.delete_coordinate_maps()
Serialize.read_positions.write_file(genes, composition_fn)
total = gene["all"]["start_codon", xs].sum()
if total == 0:
print transcript
if total > 9:
fraction = np.true_divide(most, total)
fractions[name].append(fraction)
joints[name].append((argmax, fraction))
if __name__ == "__main__":
gff_fn = "/home/jah/projects/ribosomes/data/organisms/saccharomyces_cerevisiae/EF4/transcriptome/genes.gff"
genome_dir = "/home/jah/projects/ribosomes/data/organisms/saccharomyces_cerevisiae/EF4/genome/"
composition_fn = (
"/home/jah/projects/ribosomes/data/organisms/saccharomyces_cerevisiae/EF4/transcript_recent_As.hdf5"
)
CDSs = gff.get_CDSs(gff_fn, genome_dir)
import select_work
exps = select_work.build_all_experiments(verbose=False)
reads_fn = exps["belgium_2014_12_10"]["WT_1_mRNA"].file_names["three_prime_read_positions"]
reads_fh = h5py.File(reads_fn, "r")
meta_counts = positions.PositionCounts({"A": 0}, left_buffer=100000, right_buffer=100000)
f = h5py.File(composition_fn, "r")
for t in utilities.progress_bar(len(CDSs), CDSs):
if t.name not in reads_fh:
continue
gene = Serialize.read_positions.build_gene(f[t.name])
argmaxes[name][argmax] += 1
most = gene['all']['start_codon', argmax]
total = gene['all']['start_codon', xs].sum()
if total == 0:
print transcript
if total > 9:
fraction = np.true_divide(most, total)
fractions[name].append(fraction)
joints[name].append((argmax, fraction))
if __name__ == '__main__':
gff_fn = '/home/jah/projects/ribosomes/data/organisms/saccharomyces_cerevisiae/EF4/transcriptome/genes.gff'
genome_dir = '/home/jah/projects/ribosomes/data/organisms/saccharomyces_cerevisiae/EF4/genome/'
composition_fn = '/home/jah/projects/ribosomes/data/organisms/saccharomyces_cerevisiae/EF4/transcript_recent_As.hdf5'
CDSs = gff.get_CDSs(gff_fn, genome_dir)
import select_work
exps = select_work.build_all_experiments(verbose=False)
reads_fn = exps['belgium_2014_12_10']['WT_1_mRNA'].file_names[
'three_prime_read_positions']
reads_fh = h5py.File(reads_fn, 'r')
meta_counts = positions.PositionCounts({'A': 0},
left_buffer=100000,
right_buffer=100000)
f = h5py.File(composition_fn, 'r')
for t in utilities.progress_bar(len(CDSs), CDSs):
if t.name not in reads_fh: