diff --git a/mhcflurry/antigen_presentation/percent_rank_transform.py b/mhcflurry/antigen_presentation/percent_rank_transform.py
index 0b21298fa6329f4ac758ca6e1db1ac5a3faf873d..5d729f1c60a0ef23bf9b9a592014ce16123741c3 100644
--- a/mhcflurry/antigen_presentation/percent_rank_transform.py
+++ b/mhcflurry/antigen_presentation/percent_rank_transform.py
@@ -20,10 +20,11 @@ class PercentRankTransform(object):
assert self.bin_edges is None
assert len(values) > 0
(hist, self.bin_edges) = numpy.histogram(values, bins=self.n_bins)
- self.cdf = numpy.ones(len(hist) + 2) * numpy.nan
+ self.cdf = numpy.ones(len(hist) + 3) * numpy.nan
self.cdf[0] = 0.0
+ self.cdf[1] = 0.0
self.cdf[-1] = 100.0
- numpy.cumsum(hist / numpy.sum(hist) * 100.0, out=self.cdf[1:-1])
+ numpy.cumsum(hist / numpy.sum(hist) * 100.0, out=self.cdf[2:-1])
assert not numpy.isnan(self.cdf).any()
def transform(self, values):
diff --git a/mhcflurry/antigen_presentation/presentation_component_models/mhcflurry_trained_on_hits.py b/mhcflurry/antigen_presentation/presentation_component_models/mhcflurry_trained_on_hits.py
index 7ea2272f7f0238be70010ff98b45cadad6b33551..70f933c23727b8e739cc5da4813059a9c64f8a1f 100644
--- a/mhcflurry/antigen_presentation/presentation_component_models/mhcflurry_trained_on_hits.py
+++ b/mhcflurry/antigen_presentation/presentation_component_models/mhcflurry_trained_on_hits.py
@@ -144,6 +144,8 @@ class MHCflurryTrainedOnHits(PresentationComponentModel):
def fit(self, hits_df):
assert 'experiment_name' in hits_df.columns
assert 'peptide' in hits_df.columns
+ if 'hit' in hits_df.columns:
+ assert (hits_df.hit == 1).all()
grouped = hits_df.groupby("experiment_name")
for (experiment_name, sub_df) in grouped:
diff --git a/mhcflurry/antigen_presentation/presentation_component_models/presentation_component_model.py b/mhcflurry/antigen_presentation/presentation_component_models/presentation_component_model.py
index 76bcb7f7fe777fa2bada185675aef3f688804a55..388f1bf9b1424bb5d0cd71348e46833f21217215 100644
--- a/mhcflurry/antigen_presentation/presentation_component_models/presentation_component_model.py
+++ b/mhcflurry/antigen_presentation/presentation_component_models/presentation_component_model.py
@@ -53,7 +53,7 @@ class PresentationComponentModel(object):
"""
raise NotImplementedError(str(self))
- def clone_and_fit(self, peptides_df):
+ def clone_and_fit(self, hits_df):
"""
Clone the object and fit to given dataset with a weakref cache.
"""
@@ -65,12 +65,12 @@ class PresentationComponentModel(object):
result = None
else:
key = dataframe_cryptographic_hash(
- peptides_df[["experiment_name", "peptide"]])
+ hits_df[["experiment_name", "peptide"]])
result = self.cached_fits.get(key)
if result is None:
print("Cache miss in clone_and_fit: %s" % str(self))
result = self.clone()
- result.fit(peptides_df)
+ result.fit(hits_df)
if self.cached_fits is not None:
self.cached_fits[key] = result
else:
@@ -229,6 +229,9 @@ class PresentationComponentModel(object):
self.cached_predictions[cache_key] = return_value
return return_value
+ def fit_ensemble_and_predict(peptides_df):
+ raise NotImplementedError
+
def reset_cache(self):
for key in PresentationComponentModel.cache_fields:
obj_type = type(getattr(self, key))
diff --git a/mhcflurry/antigen_presentation/presentation_model.py b/mhcflurry/antigen_presentation/presentation_model.py
index 7f6bc651b16694ab11685d8b7ec21aa6a57e6d05..f538ac2e77b9ea8ce479ea82a999b9424a3385d3 100644
--- a/mhcflurry/antigen_presentation/presentation_model.py
+++ b/mhcflurry/antigen_presentation/presentation_model.py
@@ -321,7 +321,6 @@ class PresentationModel(object):
assert len(self.presentation_models_predictors) == \
len(self.trained_component_models)
- # peptides_df = peptides_df.reset_index(drop=True)
prediction_cols = []
presentation_model_predictions = {}
zipped = enumerate(
@@ -343,20 +342,6 @@ class PresentationModel(object):
x_df = self.evaluate_expressions(df)
assert_no_null(x_df)
- """
- with pandas.option_context('mode.use_inf_as_null', True):
- null_x = x_df.ix[x_df.isnull().sum(axis=1) > 0]
- if len(null_x) > 0:
- null_x = null_x.copy()
- null_x["peptide"] = peptides_df.ix[null_x.index, "peptide"]
- null_x["experiment_name"] = peptides_df.ix[
- null_x.index, "experiment_name"
- ]
- raise ValueError(
- "Null values in features:\n%s\ninputs:\n%s" % (
- str(null_x), str(df.iloc[null_x.index])))
- """
-
prediction_col = "Prediction (Model %d)" % (i + 1)
assert prediction_col not in presentation_model_predictions
presentation_model_predictions[prediction_col] = (
@@ -370,7 +355,10 @@ class PresentationModel(object):
del presentation_model_predictions[prediction_cols[0]]
else:
presentation_model_predictions["Prediction"] = numpy.mean(
- [presentation_model_predictions[col] for col in prediction_cols],
+ [
+ presentation_model_predictions[col]
+ for col in prediction_cols
+ ],
axis=0)
return pandas.DataFrame(presentation_model_predictions)
diff --git a/test/test_antigen_presentation.py b/test/test_antigen_presentation.py
index 1f69f2f78278179af5704f2596f684e40b7a0673..16d31bc0b688072d1327089209390885f2547edd 100644
--- a/test/test_antigen_presentation.py
+++ b/test/test_antigen_presentation.py
@@ -1,10 +1,12 @@
from nose.tools import eq_, assert_less
import numpy
+from numpy.testing import assert_almost_equal
import pandas
from mhcflurry import amino_acid
from mhcflurry.antigen_presentation import (
decoy_strategies,
+ percent_rank_transform,
presentation_component_models,
presentation_model)
@@ -62,6 +64,7 @@ PEPTIDES_DF["hit"] = [
for _, row in
PEPTIDES_DF.iterrows()
]
+print("Hit rate: %0.3f" % PEPTIDES_DF.hit.mean())
HITS_DF = PEPTIDES_DF.ix[PEPTIDES_DF.hit].reset_index().copy()
del HITS_DF["hit"]
@@ -70,6 +73,14 @@ del HITS_DF["hit"]
# Tests
+def test_percent_rank_transform():
+ model = percent_rank_transform.PercentRankTransform()
+ model.fit(numpy.arange(1000))
+ assert_almost_equal(
+ model.transform([-2, 0, 50, 100, 2000]),
+ [0.0, 0.0, 5.0, 10.0, 100.0])
+
+
def test_mhcflurry_trained_on_hits():
mhcflurry_model = presentation_component_models.MHCflurryTrainedOnHits(
"basic",
@@ -100,11 +111,11 @@ def test_presentation_model():
experiment_to_expression_group=EXPERIMENT_TO_EXPRESSION_GROUP,
transcripts=TRANSCIPTS_DF,
peptides_and_transcripts=PEPTIDES_AND_TRANSCRIPTS_DF,
- random_peptides_for_percent_rank=make_random_peptides(10000, 9),
+ random_peptides_for_percent_rank=make_random_peptides(1000, 9),
)
decoys = decoy_strategies.UniformRandom(
- make_random_peptides(10000, 9),
+ make_random_peptides(1000, 9),
decoys_per_hit=50)
terms = {