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
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
"""
Test train, calibrate percentile ranks, and model selection commands.
"""
import json
import os
import shutil
import tempfile
import subprocess
from copy import deepcopy
from numpy.testing import assert_array_less, assert_equal
from mhcflurry import Class1AffinityPredictor
from mhcflurry.downloads import get_path
HYPERPARAMETERS = [
{
"n_models": 2,
"max_epochs": 500,
"patience": 10,
"minibatch_size": 128,
"early_stopping": True,
"validation_split": 0.2,
"random_negative_rate": 0.0,
"random_negative_constant": 25,
"peptide_amino_acid_encoding": "BLOSUM62",
"use_embedding": False,
"kmer_size": 15,
"batch_normalization": False,
"locally_connected_layers": [
{
"filters": 8,
"activation": "tanh",
"kernel_size": 3
}
],
"activation": "tanh",
"output_activation": "sigmoid",
"layer_sizes": [
16
],
"random_negative_affinity_min": 20000.0,
"random_negative_affinity_max": 50000.0,
"dense_layer_l1_regularization": 0.001,
"dropout_probability": 0.0
}
]
def run_and_check(n_jobs=0):
models_dir = tempfile.mkdtemp(prefix="mhcflurry-test-models")
hyperparameters_filename = os.path.join(
models_dir, "hyperparameters.yaml")
with open(hyperparameters_filename, "w") as fd:
json.dump(HYPERPARAMETERS, fd)
args = [
"mhcflurry-class1-train-allele-specific-models",
"--data", get_path("data_curated", "curated_training_data.no_mass_spec.csv.bz2"),
"--hyperparameters", hyperparameters_filename,
"--allele", "HLA-A*02:01", "HLA-A*03:01",
"--out-models-dir", models_dir,
"--num-jobs", str(n_jobs),
]
print("Running with args: %s" % args)
subprocess.check_call(args)
# Calibrate percentile ranks
args = [
"mhcflurry-calibrate-percentile-ranks",
"--models-dir", models_dir,
"--num-peptides-per-length", "10000",
"--num-jobs", str(n_jobs),
]
print("Running with args: %s" % args)
subprocess.check_call(args)
result = Class1AffinityPredictor.load(models_dir)
predictions = result.predict(
peptides=["SLYNTVATL"],
alleles=["HLA-A*02:01"])
assert_equal(predictions.shape, (1,))
assert_array_less(predictions, 500)
df = result.predict_to_dataframe(
peptides=["SLYNTVATL"],
alleles=["HLA-A*02:01"])
print(df)
assert "prediction_percentile" in df.columns
print("Deleting: %s" % models_dir)
shutil.rmtree(models_dir)
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
models_dir1 = tempfile.mkdtemp(prefix="mhcflurry-test-models")
hyperparameters_filename = os.path.join(
models_dir1, "hyperparameters.yaml")
# Include one architecture that has max_epochs = 0. We check that it never
# gets selected in model selection.
hyperparameters = [
deepcopy(HYPERPARAMETERS[0]),
deepcopy(HYPERPARAMETERS[0]),
]
hyperparameters[-1]["max_epochs"] = 0
with open(hyperparameters_filename, "w") as fd:
json.dump(hyperparameters, fd)
args = [
"mhcflurry-class1-train-allele-specific-models",
"--data", get_path("data_curated", "curated_training_data.no_mass_spec.csv.bz2"),
"--hyperparameters", hyperparameters_filename,
"--allele", "HLA-A*02:01", "HLA-A*03:01",
"--out-models-dir", models_dir1,
"--num-jobs", str(n_jobs),
"--held-out-fraction-reciprocal", "10",
"--n-models", "1",
]
print("Running with args: %s" % args)
subprocess.check_call(args)
result = Class1AffinityPredictor.load(models_dir1)
assert_equal(len(result.neural_networks), 4)
models_dir2 = tempfile.mkdtemp(prefix="mhcflurry-test-models")
args = [
"mhcflurry-class1-select-allele-specific-models",
"--data",
get_path("data_curated", "curated_training_data.no_mass_spec.csv.bz2"),
"--exclude-data", models_dir1 + "/train_data.csv.bz2",
"--out-models-dir", models_dir2,
"--models-dir", models_dir1,
"--num-jobs", str(n_jobs),
"--max-models", "1"
]
print("Running with args: %s" % args)
subprocess.check_call(args)
result = Class1AffinityPredictor.load(models_dir2)
assert_equal(len(result.neural_networks), 2)
assert_equal(
len(result.allele_to_allele_specific_models["HLA-A*02:01"]), 1)
assert_equal(
len(result.allele_to_allele_specific_models["HLA-A*03:01"]), 1)
assert_equal(
result.allele_to_allele_specific_models["HLA-A*02:01"][0].hyperparameters["max_epochs"], 500)
assert_equal(
result.allele_to_allele_specific_models["HLA-A*03:01"][
0].hyperparameters["max_epochs"], 500)
print("Deleting: %s" % models_dir1)
print("Deleting: %s" % models_dir2)
shutil.rmtree(models_dir1)
if os.environ.get("KERAS_BACKEND") != "theano":
def test_run_parallel():
run_and_check(n_jobs=2)
run_and_check(n_jobs=1)
run_and_check_with_model_selection(n_jobs=1)