From d293a5ee7d5545602731265e3a4c3895ca644e4d Mon Sep 17 00:00:00 2001
From: Tim O'Donnell <timodonnell@gmail.com>
Date: Thu, 18 May 2017 22:20:01 -0400
Subject: [PATCH] add class1 mdoels download
---
.../class1_binding_predictor.py | 21 ++++++----
mhcflurry/downloads.yml | 12 ++++--
test/test_class1_binding_predictor_A0205.py | 41 +++++++++++--------
3 files changed, 44 insertions(+), 30 deletions(-)
diff --git a/mhcflurry/class1_affinity_prediction/class1_binding_predictor.py b/mhcflurry/class1_affinity_prediction/class1_binding_predictor.py
index 1b569929..04b87d06 100644
--- a/mhcflurry/class1_affinity_prediction/class1_binding_predictor.py
+++ b/mhcflurry/class1_affinity_prediction/class1_binding_predictor.py
@@ -150,7 +150,7 @@ class Class1BindingPredictor(object):
self.hyperparameters['random_negative_rate'] +
self.hyperparameters['random_negative_constant'])
num_random_negative = pandas.Series(num_random_negative)
- logging.info("Random negative counts per length: %s" % (
+ logging.info("Random negative counts per length:\n%s" % (
str(num_random_negative)))
aa_distribution = None
@@ -160,7 +160,7 @@ class Class1BindingPredictor(object):
smoothing=self.hyperparameters[
'random_negative_distribution_smoothing'])
logging.info(
- "Using amino acid distribution for random negative: %s" % (
+ "Using amino acid distribution for random negative:\n%s" % (
str(aa_distribution)))
y_values = from_ic50(affinities)
@@ -224,17 +224,14 @@ class Class1BindingPredictor(object):
"peptide": numpy.concatenate([
random_negative_peptides_encoding,
peptide_encoding,
- ])
+ ]) if len(random_negative_peptides_encoding) > 0
+ else peptide_encoding
}
if pseudosequence_length:
# TODO: add random pseudosequences for random negative peptides
raise NotImplemented(
"Allele pseudosequences unsupported with random negatives")
- logging.info("Epoch %3d / %3d. Min val loss at epoch %s" % (
- i,
- self.hyperparameters['max_epochs'],
- min_val_loss_iteration))
fit_history = self.network.fit(
x_dict_with_random_negatives,
y_dict_with_random_negatives,
@@ -248,6 +245,13 @@ class Class1BindingPredictor(object):
for (key, value) in fit_history.history.items():
self.fit_history[key].extend(value)
+ logging.info(
+ "Epoch %3d / %3d: loss=%g. Min val loss at epoch %s" % (
+ i,
+ self.hyperparameters['max_epochs'],
+ self.fit_history['loss'][-1],
+ min_val_loss_iteration))
+
if self.hyperparameters['validation_split']:
val_loss = fit_history.history['val_loss'][-1]
val_losses.append(val_loss)
@@ -273,7 +277,8 @@ class Class1BindingPredictor(object):
pseudosequences_input = self.pseudosequence_to_network_input(
allele_pseudosequences)
x_dict['pseudosequence'] = pseudosequences_input
- return numpy.array(self.network.predict(x_dict))
+ (predictions,) = numpy.array(self.network.predict(x_dict)).T
+ return to_ic50(predictions)
@staticmethod
def make_network(
diff --git a/mhcflurry/downloads.yml b/mhcflurry/downloads.yml
index 76f420fb..703ca938 100644
--- a/mhcflurry/downloads.yml
+++ b/mhcflurry/downloads.yml
@@ -20,6 +20,14 @@ releases:
1.0.0:
compatibility-version: 2
downloads:
+ - name: models_class1
+ url: http://github.com/hammerlab/mhcflurry/releases/download/pre-1.0.0-alpha/models_class1.tar.bz2
+ default: true
+
+ - name: data_curated
+ url: https://github.com/hammerlab/mhcflurry/releases/download/pre-1.0.0-alpha/data_curated.tar.bz2
+ default: true
+
- name: data_kim2014
url: http://github.com/hammerlab/mhcflurry/releases/download/0.0.8/data_kim2014.tar.bz2
default: false
@@ -28,10 +36,6 @@ releases:
url: https://github.com/hammerlab/mhcflurry/releases/download/pre-1.0.0-alpha/data_iedb.tar.bz2
default: false
- - name: data_curated
- url: https://github.com/hammerlab/mhcflurry/releases/download/pre-1.0.0-alpha/data_curated.tar.bz2
- default: true
-
0.2.0:
compatibility-version: 1
downloads:
diff --git a/test/test_class1_binding_predictor_A0205.py b/test/test_class1_binding_predictor_A0205.py
index fb3df4a7..451d3ca7 100644
--- a/test/test_class1_binding_predictor_A0205.py
+++ b/test/test_class1_binding_predictor_A0205.py
@@ -1,7 +1,7 @@
-import numpy as np
-np.random.seed(0)
+import numpy
+import pandas
+numpy.random.seed(0)
-from mhcflurry.affinity_measurement_dataset import AffinityMeasurementDataset
from mhcflurry import Class1BindingPredictor
from nose.tools import eq_
@@ -11,27 +11,32 @@ from mhcflurry.downloads import get_path
def test_class1_binding_predictor_A0205_training_accuracy():
- dataset = AffinityMeasurementDataset.from_csv(get_path(
- "data_combined_iedb_kim2014", "combined_human_class1_dataset.csv"))
- dataset_a0205_all_lengths = dataset.get_allele("HLA-A0205")
- dataset_a0205 = AffinityMeasurementDataset(
- dataset_a0205_all_lengths._df.ix[
- dataset_a0205_all_lengths._df.peptide.str.len() == 9])
+ df = pandas.read_csv(
+ get_path(
+ "data_curated", "curated_training_data.csv.bz2"))
+ df = df.ix[df.allele == "HLA-A*02:05"]
+ df = df.ix[
+ df.peptide.str.len() == 9
+ ]
+ df = df.ix[
+ df.measurement_type == "quantitative"
+ ]
+ df = df.ix[
+ df.measurement_source == "kim2014"
+ ]
predictor = Class1BindingPredictor(
- name="A0205",
- embedding_output_dim=32,
activation="tanh",
layer_sizes=[64],
- optimizer="adam",
+ max_epochs=1000, # Memorize the dataset.
+ early_stopping=False,
dropout_probability=0.0)
- predictor.fit_dataset(dataset_a0205, n_training_epochs=1000)
- peptides = dataset_a0205.peptides
- ic50_pred = predictor.predict(peptides)
- ic50_true = dataset_a0205.affinities
+ 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(
- np.log(ic50_pred),
- np.log(ic50_true),
+ numpy.log(ic50_pred),
+ numpy.log(ic50_true),
rtol=0.2,
atol=0.2)
--
GitLab