coolneng
/
locimend
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Rename ref_sequence to label

This commit is contained in:
coolneng 2021-06-06 00:03:15 +02:00
parent 035162bd8d
commit 38903c5737
Signed by: coolneng
GPG Key ID: 9893DA236405AF57
1 changed files with 5 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
src/preprocessing.py
View File

@ -11,7 +11,7 @@ from tensorflow.train import Example, Feature, Features, FloatList, Int64List
from constants import * from constants import *
def generate_example(sequence, reference_sequence, weight_matrix) -> bytes: def generate_example(sequence, label, weight_matrix) -> bytes:
""" """
Create a binary-string for each sequence containing the sequence and the bases' frequency Create a binary-string for each sequence containing the sequence and the bases' frequency
""" """
@ -19,9 +19,7 @@ def generate_example(sequence, reference_sequence, weight_matrix) -> bytes:
"sequence": Feature( "sequence": Feature(
int64_list=Int64List(value=list(encode_sequence(sequence))) int64_list=Int64List(value=list(encode_sequence(sequence)))
), ),
"reference_sequence": Feature( "label": Feature(int64_list=Int64List(value=list(encode_sequence(label)))),
int64_list=Int64List(value=list(encode_sequence(reference_sequence)))
),
"A_counts": Feature(float_list=FloatList(value=weight_matrix["A"])), "A_counts": Feature(float_list=FloatList(value=weight_matrix["A"])),
"C_counts": Feature(float_list=FloatList(value=weight_matrix["C"])), "C_counts": Feature(float_list=FloatList(value=weight_matrix["C"])),
"G_counts": Feature(float_list=FloatList(value=weight_matrix["G"])), "G_counts": Feature(float_list=FloatList(value=weight_matrix["G"])),
@ -49,14 +47,14 @@ def read_fastq(data_file, label_file) -> List[bytes]:
motifs = create([element.seq]) motifs = create([element.seq])
example = generate_example( example = generate_example(
sequence=str(element.seq), sequence=str(element.seq),
reference_sequence=str(label.seq), label=str(label.seq),
weight_matrix=motifs.pwm, weight_matrix=motifs.pwm,
) )
examples.append(example) examples.append(example)
return examples return examples
def create_dataset(filepath) -> None: def create_dataset(data_file, label_file) -> None:
""" """
Create a training and test dataset with a 70/30 split respectively Create a training and test dataset with a 70/30 split respectively
""" """
@ -76,7 +74,7 @@ def process_input(byte_string) -> Example:
""" """
schema = { schema = {
"sequence": FixedLenFeature(shape=[], dtype=int64), "sequence": FixedLenFeature(shape=[], dtype=int64),
"reference_sequence": FixedLenFeature(shape=[], dtype=int64), "label": FixedLenFeature(shape=[], dtype=int64),
"A_counts": FixedLenFeature(shape=[], dtype=float32), "A_counts": FixedLenFeature(shape=[], dtype=float32),
"C_counts": FixedLenFeature(shape=[], dtype=float32), "C_counts": FixedLenFeature(shape=[], dtype=float32),
"G_counts": FixedLenFeature(shape=[], dtype=float32), "G_counts": FixedLenFeature(shape=[], dtype=float32),