diff --git a/mhcflurry/__init__.py b/mhcflurry/__init__.py
index 3e0abd0483da2095b8249ebb5918829f6d170e41..8538c4d3a9afb4f3b3b07b4de7c38c85f765be0a 100644
--- a/mhcflurry/__init__.py
+++ b/mhcflurry/__init__.py
@@ -1,7 +1,6 @@
-from mhcflurry.class1_affinity_predictor import Class1AffinityPredictor
-from mhcflurry.class1_neural_network import Class1NeuralNetwork
-
-__version__ = "1.1.0"
+from .class1_affinity_predictor import Class1AffinityPredictor
+from .class1_neural_network import Class1NeuralNetwork
+from .version import __version__
__all__ = [
"__version__",
diff --git a/mhcflurry/class1_affinity_predictor.py b/mhcflurry/class1_affinity_predictor.py
index ffd9744b1ba3c6d5077d12c0cc652936c118a412..b463b7b463e58d106d06eaef1251b4aa8af84fae 100644
--- a/mhcflurry/class1_affinity_predictor.py
+++ b/mhcflurry/class1_affinity_predictor.py
@@ -7,6 +7,8 @@ import time
import warnings
from os.path import join, exists
from os import mkdir
+from socket import gethostname
+from getpass import getuser
import mhcnames
import numpy
@@ -20,6 +22,7 @@ from .downloads import get_path
from .encodable_sequences import EncodableSequences
from .percent_rank_transform import PercentRankTransform
from .regression_target import to_ic50
+from .version import __version__
class Class1AffinityPredictor(object):
@@ -193,7 +196,8 @@ class Class1AffinityPredictor(object):
the configurations of each Class1NeuralNetwork, along with per-network
files giving the model weights. If there are pan-allele predictors in
the ensemble, the allele pseudosequences are also stored in the
- directory.
+ directory. There is also a small file "index.txt" with basic metadata:
+ when the models were trained, by whom, on what host.
Parameters
----------
@@ -234,6 +238,18 @@ class Class1AffinityPredictor(object):
write_manifest_df.to_csv(manifest_path, index=False)
logging.info("Wrote: %s" % manifest_path)
+ # Write "info.txt"
+ info_path = join(models_dir, "info.txt")
+ rows = [
+ ("trained on", time.asctime()),
+ ("package ", "mhcflurry %s" % __version__),
+ ("hostname ", gethostname()),
+ ("user ", getuser()),
+ ]
+ pandas.DataFrame(rows).to_csv(
+ info_path, sep="\t", header=False, index=False)
+ print("Wrote: %s" % info_path)
+
if self.allele_to_percent_rank_transform:
percent_ranks_df = None
for (allele, transform) in self.allele_to_percent_rank_transform.items():
diff --git a/mhcflurry/version.py b/mhcflurry/version.py
new file mode 100644
index 0000000000000000000000000000000000000000..6849410aae0a8010e76d5f0a44ced13d750b0989
--- /dev/null
+++ b/mhcflurry/version.py
@@ -0,0 +1 @@
+__version__ = "1.1.0"
diff --git a/setup.py b/setup.py
index a66f0d8255cb82c5f978d1d019004797dd1f11b9..cfcb98f43d590a796776ab7ae5f1bbfef17ed770 100644
--- a/setup.py
+++ b/setup.py
@@ -40,7 +40,7 @@ except:
logging.warning("Conversion of long_description from MD to RST failed")
pass
-with open('mhcflurry/__init__.py', 'r') as f:
+with open('mhcflurry/version.py', 'r') as f:
version = re.search(
r'^__version__\s*=\s*[\'"]([^\'"]*)[\'"]',
f.read(),
diff --git a/test/test_class1_affinity_predictor.py b/test/test_class1_affinity_predictor.py
index 8532b76a3662581f4e439b136af5ddd42def4a03..40ac8c2f9ea22b1b6ad80495da061bd6b0acf5c5 100644
--- a/test/test_class1_affinity_predictor.py
+++ b/test/test_class1_affinity_predictor.py
@@ -51,7 +51,7 @@ def test_a1_known_epitopes_in_newly_trained_model():
allele = "HLA-A*01:01"
df = pandas.read_csv(
get_path(
- "data_curated", "curated_training_data.csv.bz2"))
+ "data_curated", "curated_training_data.no_mass_spec.csv.bz2"))
df = df.ix[
(df.allele == allele) &
(df.peptide.str.len() >= 8) &
@@ -137,7 +137,7 @@ def test_class1_affinity_predictor_a0205_memorize_training_data():
df = pandas.read_csv(
get_path(
- "data_curated", "curated_training_data.csv.bz2"))
+ "data_curated", "curated_training_data.no_mass_spec.csv.bz2"))
df = df.ix[
df.allele == allele
]
diff --git a/test/test_class1_neural_network.py b/test/test_class1_neural_network.py
index f3d4ca4980c82d22d8c078a281a55a8328d6947e..b082f28cf89276bf842cc427d98ad7defab0985a 100644
--- a/test/test_class1_neural_network.py
+++ b/test/test_class1_neural_network.py
@@ -37,7 +37,7 @@ def test_class1_neural_network_a0205_training_accuracy():
df = pandas.read_csv(
get_path(
- "data_curated", "curated_training_data.csv.bz2"))
+ "data_curated", "curated_training_data.no_mass_spec.csv.bz2"))
df = df.ix[
df.allele == allele
]
diff --git a/test/test_train_allele_specific_models_command.py b/test/test_train_allele_specific_models_command.py
index affcde7569b0ae5766ae554f50a73122f3e3894f..1489d1d1baf16d7b19fc5189560bd19f04ef4649 100644
--- a/test/test_train_allele_specific_models_command.py
+++ b/test/test_train_allele_specific_models_command.py
@@ -57,12 +57,13 @@ def run_and_check(n_jobs=0):
json.dump(HYPERPARAMETERS, fd)
args = [
- "--data", get_path("data_curated", "curated_training_data.csv.bz2"),
+ "--data", get_path("data_curated", "curated_training_data.no_mass_spec.csv.bz2"),
"--hyperparameters", hyperparameters_filename,
"--allele", "HLA-A*02:01", "HLA-A*01:01", "HLA-A*03:01",
"--out-models-dir", models_dir,
"--percent-rank-calibration-num-peptides-per-length", "10000",
"--parallelization-num-jobs", str(n_jobs),
+ "--ignore-inequalities",
]
print("Running with args: %s" % args)
train_allele_specific_models_command.run(args)