From 6cac6ebd5fd870257dd7f77b73af94d5a2b2a6d9 Mon Sep 17 00:00:00 2001
From: Tim O'Donnell <timodonnell@gmail.com>
Date: Sun, 21 May 2017 21:16:30 -0400
Subject: [PATCH] updates
---
.../class1_affinity_predictor.py | 96 ++++++++++---------
.../scoring.py | 2 +-
test/test_class1_binding_predictor_A0205.py | 64 +++++++++----
test/test_ensemble.py | 35 ++++---
4 files changed, 110 insertions(+), 87 deletions(-)
rename mhcflurry/{class1_affinity_prediction => }/scoring.py (95%)
diff --git a/mhcflurry/class1_affinity_prediction/class1_affinity_predictor.py b/mhcflurry/class1_affinity_prediction/class1_affinity_predictor.py
index 223ff08a..42305241 100644
--- a/mhcflurry/class1_affinity_prediction/class1_affinity_predictor.py
+++ b/mhcflurry/class1_affinity_prediction/class1_affinity_predictor.py
@@ -3,6 +3,7 @@ import time
import hashlib
import json
from os.path import join, exists
+from six import string_types
import numpy
import pandas
@@ -80,7 +81,7 @@ class Class1AffinityPredictor(object):
def weights_path(models_dir, model_name):
return join(
models_dir,
- "%s.%s" % (
+ "weights_%s.%s" % (
model_name, Class1NeuralNetwork.weights_filename_extension))
@@ -228,66 +229,67 @@ class Class1AffinityPredictor(object):
verbose=verbose)
yield model
- def predict(
+ def predict(self, peptides, alleles=None, allele=None):
+ df = self.predict_to_dataframe(
+ peptides=peptides,
+ alleles=alleles,
+ allele=allele
+ )
+ return df.prediction.values
+
+ def predict_to_dataframe(
self,
peptides,
- alleles,
- include_mean=True,
- include_peptides_and_alleles=True):
- input_df = pandas.DataFrame({
+ alleles=None,
+ allele=None,
+ include_individual_model_predictions=False):
+ if isinstance(peptides, string_types):
+ raise TypeError("peptides must be a list or array, not a string")
+ if isinstance(alleles, string_types):
+ raise TypeError("alleles must be a list or array, not a string")
+ if allele is not None:
+ if alleles is not None:
+ raise ValueError("Specify exactly one of allele or alleles")
+ alleles = [allele] * len(peptides)
+
+ df = pandas.DataFrame({
'peptide': peptides,
'allele': alleles,
})
- input_df["allele"] = input_df.allele.map(
+ df["normalized_allele"] = input_df.allele.map(
mhcnames.normalize_allele_name)
- result_dataframes = []
-
if self.class1_pan_allele_models:
- allele_pseudosequences = input_df.allele.map(
+ allele_pseudosequences = df.normalized_allele.map(
self.allele_to_pseudosequence)
encodable_peptides = EncodableSequences.create(
- input_df.peptide.values)
- for model in self.class1_pan_allele_models:
- result_df = pandas.DataFrame(
- model.predict(
- encodable_peptides,
- allele_pseudosequences=allele_pseudosequences))
- result_dataframes.append(result_df)
+ df.peptide.values)
+ for (i, model) in enumerate(self.class1_pan_allele_models):
+ df["model_pan_%d" % i] = model.predict(
+ encodable_peptides,
+ allele_pseudosequences=allele_pseudosequences)
if self.allele_to_allele_specific_models:
- for allele in input_df.allele.unique():
- mask = (input_df.allele == allele).values
+ for allele in df.normalized_allele.unique():
+ mask = (df.normalized_allele == allele).values
allele_peptides = EncodableSequences.create(
- input_df.ix[mask].peptide.values)
+ df.ix[mask].peptide.values)
models = self.allele_to_allele_specific_models.get(allele, [])
- for model in models:
- result_df = pandas.DataFrame(
- model.predict(allele_peptides),
- index=input_df.index[mask].values)
- result_dataframes.append(result_df)
-
- model_predictions = pandas.Panel(
- dict(enumerate(result_dataframes)),
- major_axis=input_df.index)
+ for (i, model) in enumerate(models):
+ df.loc[mask, "model_single_%d" % i] = model.predict(
+ allele_peptides)
# Geometric mean
- log_means = numpy.log(model_predictions).mean(0)
- first_columns = []
- if include_mean:
- log_means["mean"] = log_means.mean(1)
- first_columns.append("mean")
-
- result = numpy.exp(log_means)
-
- if include_peptides_and_alleles:
- result["peptide"] = input_df.peptide.values
- result["allele"] = input_df.allele.values
- first_columns.append("allele")
- first_columns.append("peptide")
-
- assert len(result) == len(peptides), result.shape
- return result[
- list(reversed(first_columns)) +
- [c for c in result.columns if c not in first_columns]
+ df_predictions = df[
+ [c for c in df.columns if c.startswith("model_")]
]
+ log_means = numpy.log(df_predictions).mean(1)
+ df["prediction"] = numpy.exp(log_means)
+ df["prediction_low"] = numpy.exp(log_means.quantile(q=.05, axis=1))
+ df["prediction_high"] = numpy.exp(log_means.quantile(q=.05, axis=1))
+
+ if include_individual_model_predictions:
+ return df
+ return df[
+ [c for c in df.columns if c not in df_predictions.columns]
+ ]
\ No newline at end of file
diff --git a/mhcflurry/class1_affinity_prediction/scoring.py b/mhcflurry/scoring.py
similarity index 95%
rename from mhcflurry/class1_affinity_prediction/scoring.py
rename to mhcflurry/scoring.py
index 12cccc7f..ad904689 100644
--- a/mhcflurry/class1_affinity_prediction/scoring.py
+++ b/mhcflurry/scoring.py
@@ -8,7 +8,7 @@ import sklearn
import numpy
import scipy
-from ..regression_target import ic50_to_regression_target
+from mhcflurry.regression_target import ic50_to_regression_target
def make_scores(
diff --git a/test/test_class1_binding_predictor_A0205.py b/test/test_class1_binding_predictor_A0205.py
index 9010e99a..fc486469 100644
--- a/test/test_class1_binding_predictor_A0205.py
+++ b/test/test_class1_binding_predictor_A0205.py
@@ -2,35 +2,39 @@ import numpy
import pandas
numpy.random.seed(0)
-from mhcflurry import Class1NeuralNetwork
+from mhcflurry import Class1NeuralNetwork, Class1AffinityPredictor
from nose.tools import eq_
from numpy import testing
from mhcflurry.downloads import get_path
+allele = "HLA-A*02:05"
-def test_class1_binding_predictor_A0205_training_accuracy():
- df = pandas.read_csv(
+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 = Class1NeuralNetwork(
- activation="tanh",
- layer_sizes=[64],
- max_epochs=1000, # Memorize the dataset.
- early_stopping=False,
- dropout_probability=0.0)
+df = df.ix[df.allele == allele]
+df = df.ix[
+ df.peptide.str.len() == 9
+]
+df = df.ix[
+ df.measurement_type == "quantitative"
+]
+df = df.ix[
+ df.measurement_source == "kim2014"
+]
+
+hyperparameters = dict(
+ activation="tanh",
+ layer_sizes=[64],
+ max_epochs=1000, # Memorize the dataset.
+ early_stopping=False,
+ dropout_probability=0.0)
+
+
+def test_class1_neural_network_A0205_training_accuracy():
+ 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
@@ -40,3 +44,23 @@ def test_class1_binding_predictor_A0205_training_accuracy():
numpy.log(ic50_true),
rtol=0.2,
atol=0.2)
+
+
+def test_class1_neural_network_A0205_training_accuracy():
+ predictor = Class1AffinityPredictor()
+ predictor.fit_allele_specific_predictors(
+ n_models=1,
+ architecture_hyperparameters=hyperparameters,
+ allele=allele,
+ peptides=df.peptide.values,
+ affinities=df.measurement_value.values,
+ )
+ ic50_pred = predictor.predict(df.peptide.values, allele=allele)
+ 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)
+
diff --git a/test/test_ensemble.py b/test/test_ensemble.py
index 210989e3..127af7f1 100644
--- a/test/test_ensemble.py
+++ b/test/test_ensemble.py
@@ -1,31 +1,28 @@
-import tempfile
-import shutil
-import os
-import time
import cProfile
-
import json
-from os.path import join
+import os
+import shutil
+import tempfile
+import time
from os import mkdir
+from os.path import join
-from numpy.testing import assert_allclose, assert_equal
import numpy
-from nose.tools import eq_
-
-from . import make_random_peptides
-
-from mhcflurry.class1_affinity_prediction import scoring
-from mhcflurry.measurement_collection import MeasurementCollection
-from mhcflurry.class1_allele_specific_ensemble import train_command
+from mhcflurry import scoring
from mhcflurry.affinity_measurement_dataset import AffinityMeasurementDataset
-from mhcflurry.downloads import get_path
-from mhcflurry.amino_acid import common_amino_acid_letters
+from mhcflurry.class1_allele_specific_ensemble import train_command
from mhcflurry \
.class1_allele_specific_ensemble \
.class1_ensemble_multi_allele_predictor import (
- Class1EnsembleMultiAllelePredictor,
- get_downloaded_predictor,
- HYPERPARAMETER_DEFAULTS)
+ Class1EnsembleMultiAllelePredictor,
+ get_downloaded_predictor,
+ HYPERPARAMETER_DEFAULTS)
+from mhcflurry.downloads import get_path
+from mhcflurry.measurement_collection import MeasurementCollection
+from nose.tools import eq_
+from numpy.testing import assert_allclose, assert_equal
+
+from . import make_random_peptides
def test_single_allele():
--
GitLab