Newer
Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
import numpy
import pandas
numpy.random.seed(0)
from mhcflurry import Class1NeuralNetwork
from nose.tools import eq_
from numpy import testing
from mhcflurry.downloads import get_path
def test_class1_affinity_predictor_a0205_training_accuracy():
# Memorize the dataset.
hyperparameters = dict(
activation="tanh",
layer_sizes=[16],
max_epochs=500,
early_stopping=False,
validation_split=0.0,
locally_connected_layers=[],
dense_layer_l1_regularization=0.0,
dropout_probability=0.0)
# First test a Class1NeuralNetwork, then a Class1AffinityPredictor.
allele = "HLA-A*02:05"
df = pandas.read_csv(
get_path(
"data_curated", "curated_training_data.csv.bz2"))
df = df.ix[
df.allele == df
]
df = df.ix[
df.peptide.str.len() == 9
]
df = df.ix[
df.measurement_type == "quantitative"
]
df = df.ix[
df.measurement_source == "kim2014"
]
predictor = Class1NeuralNetwork(**hyperparameters)
predictor.fit(df.peptide.values, df.measurement_value.values)
ic50_pred = predictor.predict(df.peptide.values)
ic50_true = df.measurement_value.values
eq_(len(ic50_pred), len(ic50_true))
testing.assert_allclose(
numpy.log(ic50_pred),
numpy.log(ic50_true),
rtol=0.2,
atol=0.2)