diff --git a/downloads-generation/data_curated/curate.py b/downloads-generation/data_curated/curate.py
index 49eb75c50cd1827c40ad49c2d38d960101c6c43c..2650a5bb67c4d19d11d506318c2afe1115f7fc27 100755
--- a/downloads-generation/data_curated/curate.py
+++ b/downloads-generation/data_curated/curate.py
@@ -4,9 +4,6 @@ Train single allele models
"""
import sys
import argparse
-import json
-import os
-import pickle
import pandas
@@ -37,13 +34,20 @@ parser.add_argument(
required=True,
help="Result file")
-QUALITATIVE_TO_AFFINITY = {
- "Negative": 50000.0,
- "Positive": 100.0,
- "Positive-High": 50.0,
- "Positive-Intermediate": 500.0,
- "Positive-Low": 5000.0,
+QUALITATIVE_TO_AFFINITY_AND_INEQUALITY = {
+ "Negative": (20000.0, ">"),
+ "Positive": (500.0, "<"),
+ "Positive-High": (100.0, "<"),
+ "Positive-Intermediate": (1000.0, "<"),
+ "Positive-Low": (5000.0, "<"),
}
+QUALITATIVE_TO_AFFINITY = dict(
+ (key, value[0]) for (key, value)
+ in QUALITATIVE_TO_AFFINITY_AND_INEQUALITY.items())
+QUALITATIVE_TO_INEQUALITY = dict(
+ (key, value[1]) for (key, value)
+ in QUALITATIVE_TO_AFFINITY_AND_INEQUALITY.items())
+
EXCLUDE_IEDB_ALLELES = [
"HLA class I",
@@ -60,6 +64,7 @@ def load_data_kim2014(filename):
True: "quantitative",
False: "qualitative",
})
+ df["measurement_inequality"] = df.inequality
df["original_allele"] = df.mhc
df["peptide"] = df.sequence
df["allele"] = df.mhc.map(normalize_allele_name)
@@ -99,24 +104,28 @@ def load_data_iedb(iedb_csv, include_qualitative=True):
quantitative = iedb_df.ix[iedb_df["Units"] == "nM"].copy()
quantitative["measurement_type"] = "quantitative"
+ quantitative["measurement_inequality"] = "="
print("Quantitative measurements: %d" % len(quantitative))
qualitative = iedb_df.ix[iedb_df["Units"] != "nM"].copy()
qualitative["measurement_type"] = "qualitative"
print("Qualitative measurements: %d" % len(qualitative))
- non_mass_spec_qualitative = qualitative.ix[
- (~qualitative["Method/Technique"].str.contains("mass spec"))
- ].copy()
- non_mass_spec_qualitative["Quantitative measurement"] = (
- non_mass_spec_qualitative["Qualitative Measure"].map(
- QUALITATIVE_TO_AFFINITY))
- print("Qualitative measurements after dropping MS: %d" % (
- len(non_mass_spec_qualitative)))
+ #qualitative = qualitative.ix[
+ # (~qualitative["Method/Technique"].str.contains("mass spec"))
+ #].copy()
+
+ qualitative["Quantitative measurement"] = (
+ qualitative["Qualitative Measure"].map(QUALITATIVE_TO_AFFINITY))
+ qualitative["measurement_inequality"] = (
+ qualitative["Qualitative Measure"].map(QUALITATIVE_TO_INEQUALITY))
+
+ print("Qualitative measurements (possibly after dropping MS): %d" % (
+ len(qualitative)))
iedb_df = pandas.concat(
(
([quantitative]) +
- ([non_mass_spec_qualitative] if include_qualitative else [])),
+ ([qualitative] if include_qualitative else [])),
ignore_index=True)
print("IEDB measurements per allele:\n%s" % iedb_df.allele.value_counts())
@@ -145,6 +154,7 @@ def load_data_iedb(iedb_csv, include_qualitative=True):
"Quantitative measurement"
].values
train_data["measurement_source"] = iedb_df.category.values
+ train_data["measurement_inequality"] = iedb_df.measurement_inequality.values
train_data["allele"] = iedb_df["allele"].values
train_data["original_allele"] = iedb_df["Allele Name"].values
@@ -181,6 +191,7 @@ def run():
"allele",
"peptide",
"measurement_value",
+ "measurement_inequality",
"measurement_type",
"measurement_source",
"original_allele",
diff --git a/mhcflurry/class1_affinity_predictor.py b/mhcflurry/class1_affinity_predictor.py
index f56865ebf9efacb619791fde6b34db906199d045..ffd9744b1ba3c6d5077d12c0cc652936c118a412 100644
--- a/mhcflurry/class1_affinity_predictor.py
+++ b/mhcflurry/class1_affinity_predictor.py
@@ -14,12 +14,12 @@ import pandas
from numpy.testing import assert_equal
from six import string_types
-from mhcflurry.class1_neural_network import Class1NeuralNetwork
-from mhcflurry.common import random_peptides
-from mhcflurry.downloads import get_path
-from mhcflurry.encodable_sequences import EncodableSequences
-from mhcflurry.percent_rank_transform import PercentRankTransform
-from mhcflurry.regression_target import to_ic50
+from .class1_neural_network import Class1NeuralNetwork
+from .common import random_peptides
+from .downloads import get_path
+from .encodable_sequences import EncodableSequences
+from .percent_rank_transform import PercentRankTransform
+from .regression_target import to_ic50
class Class1AffinityPredictor(object):
@@ -368,7 +368,7 @@ class Class1AffinityPredictor(object):
affinities,
inequalities=None,
models_dir_for_save=None,
- verbose=1,
+ verbose=0,
progress_preamble=""):
"""
Fit one or more allele specific predictors for a single allele using a
@@ -425,7 +425,7 @@ class Class1AffinityPredictor(object):
if n_architectures > 1:
pieces.append(
"Architecture {architecture_num:2d} / {n_architectures:2d}"
- " (best so far: {best_num:2d)")
+ " (best so far: {best_num})")
progress_preamble_template = "[ %s ] {user_progress_preamble}" % (
", ".join(pieces))
else:
@@ -450,13 +450,12 @@ class Class1AffinityPredictor(object):
verbose=verbose,
progress_preamble=progress_preamble_template.format(
user_progress_preamble=progress_preamble,
- best_num=best_num,
- model_num=model_num,
+ best_num="n/a" if best_num is None else best_num + 1,
+ model_num=model_num + 1,
n_models=n_models,
- architecture_num=architecture_num,
+ architecture_num=architecture_num + 1,
n_architectures=n_architectures))
-
if n_architectures > 1:
# We require val_loss (i.e. a validation set) if we have
# multiple architectures.
@@ -464,11 +463,14 @@ class Class1AffinityPredictor(object):
else:
loss = None
if loss is None or best_loss is None or best_loss > loss:
- best_loss = best_loss
+ best_loss = loss
best_num = architecture_num
best_model = model
del model
+ if n_architectures > 1:
+ print("Selected architecture %d." % (best_num + 1))
+
model_name = self.model_name(allele, model_num)
row = pandas.Series(collections.OrderedDict([
("model_name", model_name),
diff --git a/mhcflurry/class1_neural_network.py b/mhcflurry/class1_neural_network.py
index c8e674b2ab211df1417c76593f607bcd91190cbc..583499878c6adc152f6ce18171c911374ac342c5 100644
--- a/mhcflurry/class1_neural_network.py
+++ b/mhcflurry/class1_neural_network.py
@@ -444,9 +444,17 @@ class Class1NeuralNetwork(object):
if sample_weights is not None:
sample_weights = sample_weights[shuffle_permutation]
- if self.hyperparameters['loss'] in LOSSES:
+ if self.hyperparameters['loss'].startswith("custom:"):
# Using a custom loss that supports inequalities
- loss_name_or_function = LOSSES[self.hyperparameters['loss']]
+ try:
+ loss_name_or_function = LOSSES[
+ self.hyperparameters['loss'].replace("custom:", "")
+ ]
+ except KeyError:
+ raise ValueError(
+ "No such custom loss function: %s. Supported losses are: %s" % (
+ self.hyperparameters['loss'],
+ ", ".join(["custom:" + loss_name for loss_name in LOSSES])))
loss_supports_inequalities = True
else:
# Using a regular keras loss. No inequalities supported.
diff --git a/mhcflurry/loss_with_inequalities.py b/mhcflurry/loss_with_inequalities.py
index a1efe0682b28b7c62028a5f4bdaf0d581ef7cb39..98a0383e36a75a820efef0bf3924e7ecabb6bc5a 100644
--- a/mhcflurry/loss_with_inequalities.py
+++ b/mhcflurry/loss_with_inequalities.py
@@ -25,14 +25,14 @@ between 4 - 5:
from keras import backend as K
import pandas
-import numpy
+from numpy import isnan, array
LOSSES = {}
def encode_y(y, inequalities=None):
- y = numpy.array(y, dtype="float32")
- if y.isnan().any():
+ y = array(y, dtype="float32")
+ if isnan(y).any():
raise ValueError("y contains NaN")
if (y > 1.0).any():
raise ValueError("y contains values > 1.0")
@@ -47,14 +47,14 @@ def encode_y(y, inequalities=None):
'<': 2,
'>': 4,
}).values
- if offsets.isnan().any():
+ if isnan(offsets).any():
raise ValueError("Invalid inequality. Must be =, <, or >")
encoded = y + offsets
- assert not encoded.isnan().any()
+ assert not isnan(encoded).any()
return encoded
-def mse_with_ineqalities(y_true, y_pred):
+def mse_with_inequalities(y_true, y_pred):
# Handle (=) inequalities
diff1 = y_pred - y_true
diff1 *= K.cast(y_true >= 0.0, "float32")
@@ -75,4 +75,4 @@ def mse_with_ineqalities(y_true, y_pred):
K.sum(K.square(diff1), axis=-1) +
K.sum(K.square(diff2), axis=-1) +
K.sum(K.square(diff3), axis=-1))
-LOSSES["mse_with_ineqalities"] = mse_with_ineqalities
\ No newline at end of file
+LOSSES["mse_with_inequalities"] = mse_with_inequalities
\ No newline at end of file