From 5d0bf7d5b650ce524727cdc6411d5bdab4ac2a7c Mon Sep 17 00:00:00 2001
From: Tim O'Donnell <timodonnell@gmail.com>
Date: Fri, 17 Mar 2017 00:34:03 -0400
Subject: [PATCH] small fixes
---
examples/class1_allele_specific_models.ipynb | 14 ++-------
.../mhcflurry_released.py | 20 +++++++++----
mhcflurry/class1_allele_specific/__init__.py | 8 ++++-
...ss1_single_model_multi_allele_predictor.py | 8 +++--
.../__init__.py | 2 ++
.../class1_ensemble_multi_allele_predictor.py | 30 +++++++++++++++++++
mhcflurry/downloads.yml | 2 +-
7 files changed, 62 insertions(+), 22 deletions(-)
diff --git a/examples/class1_allele_specific_models.ipynb b/examples/class1_allele_specific_models.ipynb
index 0fda9cd6..f9942936 100644
--- a/examples/class1_allele_specific_models.ipynb
+++ b/examples/class1_allele_specific_models.ipynb
@@ -2,21 +2,11 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": null,
"metadata": {
"collapsed": false
},
- "outputs": [
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "Using Theano backend.\n",
- "/Users/tim/miniconda3/envs/py3k/lib/python3.5/site-packages/matplotlib/__init__.py:872: UserWarning: axes.color_cycle is deprecated and replaced with axes.prop_cycle; please use the latter.\n",
- " warnings.warn(self.msg_depr % (key, alt_key))\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"import mhcflurry\n",
"import numpy\n",
diff --git a/mhcflurry/antigen_presentation/presentation_component_models/mhcflurry_released.py b/mhcflurry/antigen_presentation/presentation_component_models/mhcflurry_released.py
index fc401e32..cb08000d 100644
--- a/mhcflurry/antigen_presentation/presentation_component_models/mhcflurry_released.py
+++ b/mhcflurry/antigen_presentation/presentation_component_models/mhcflurry_released.py
@@ -21,15 +21,22 @@ class MHCflurryReleased(PresentationComponentModel):
random_peptides_for_percent_rank : list of string
If specified, then percentile rank will be calibrated and emitted
using the given peptides.
+
+ predictor : Class1EnsembleMultiAllelePredictor-like object
+ Predictor to use.
"""
def __init__(
self,
experiment_to_alleles,
random_peptides_for_percent_rank=None,
+ predictor=None,
+ predictor_name="mhcflurry_released",
**kwargs):
PresentationComponentModel.__init__(self, **kwargs)
self.experiment_to_alleles = experiment_to_alleles
+ self.predictor = predictor
+ self.predictor_name = predictor_name
if random_peptides_for_percent_rank is None:
self.percent_rank_transforms = None
self.random_peptides_for_percent_rank = None
@@ -39,9 +46,9 @@ class MHCflurryReleased(PresentationComponentModel):
random_peptides_for_percent_rank)
def column_names(self):
- columns = ['mhcflurry_released_affinity']
+ columns = [self.predictor_name + '_affinity']
if self.percent_rank_transforms is not None:
- columns.append('mhcflurry_released_percentile_rank')
+ columns.append(self.predictor_name + '_percentile_rank')
return columns
def requires_fitting(self):
@@ -63,11 +70,14 @@ class MHCflurryReleased(PresentationComponentModel):
normalize_allele_name(allele)
for allele in alleles
]
- df = predict(alleles, numpy.unique(numpy.array(peptides)))
+ df = predict(
+ alleles,
+ numpy.unique(numpy.array(peptides)),
+ predictor=self.predictor)
pivoted = df.pivot(index='Peptide', columns='Allele')
pivoted.columns = pivoted.columns.droplevel()
result = {
- 'mhcflurry_released_affinity': (
+ self.predictor_name + '_affinity': (
pivoted.min(axis=1).ix[peptides].values)
}
if self.percent_rank_transforms is not None:
@@ -77,7 +87,7 @@ class MHCflurryReleased(PresentationComponentModel):
percentile_ranks[allele] = (
self.percent_rank_transforms[allele]
.transform(pivoted[allele].values))
- result['mhcflurry_released_percentile_rank'] = (
+ result[self.predictor_name + '_percentile_rank'] = (
percentile_ranks.min(axis=1).ix[peptides].values)
return result
diff --git a/mhcflurry/class1_allele_specific/__init__.py b/mhcflurry/class1_allele_specific/__init__.py
index 55b703f3..228b33d9 100644
--- a/mhcflurry/class1_allele_specific/__init__.py
+++ b/mhcflurry/class1_allele_specific/__init__.py
@@ -3,7 +3,11 @@ from __future__ import absolute_import
from .class1_binding_predictor import Class1BindingPredictor
from .train import train_across_models_and_folds, AlleleSpecificTrainTestFold
from .cross_validation import cross_validation_folds
-from .class1_single_model_multi_allele_predictor import from_allele_name, supported_alleles
+from .class1_single_model_multi_allele_predictor import (
+ from_allele_name,
+ supported_alleles,
+ get_downloaded_predictor,
+ Class1SingleModelMultiAllelePredictor)
__all__ = [
'Class1BindingPredictor',
@@ -12,4 +16,6 @@ __all__ = [
'train_across_models_and_folds',
'from_allele_name',
'supported_alleles',
+ 'get_downloaded_predictor',
+ 'Class1SingleModelMultiAllelePredictor',
]
diff --git a/mhcflurry/class1_allele_specific/class1_single_model_multi_allele_predictor.py b/mhcflurry/class1_allele_specific/class1_single_model_multi_allele_predictor.py
index 30f53d3f..1dca8766 100644
--- a/mhcflurry/class1_allele_specific/class1_single_model_multi_allele_predictor.py
+++ b/mhcflurry/class1_allele_specific/class1_single_model_multi_allele_predictor.py
@@ -32,7 +32,7 @@ CACHED_PREDICTOR = None
def from_allele_name(allele_name):
"""
- Load a predictor for an allele using the default loader.
+ Load a single-allele predictor.
Parameters
----------
@@ -42,7 +42,7 @@ def from_allele_name(allele_name):
----------
Class1BindingPredictor
"""
- return get_downloaded_predictor().from_allele_name(allele_name)
+ return get_downloaded_predictor().predictor_for_allele(allele_name)
def supported_alleles():
@@ -65,7 +65,9 @@ def get_downloaded_predictor():
# different.
path = get_path("models_class1_allele_specific_single")
if CACHED_PREDICTOR is None or path != CACHED_PREDICTOR.path:
- CACHED_PREDICTOR = Class1SingleModelMultiAllelePredictor(path)
+ CACHED_PREDICTOR = (
+ Class1SingleModelMultiAllelePredictor
+ .load_from_download_directory(path))
return CACHED_PREDICTOR
diff --git a/mhcflurry/class1_allele_specific_ensemble/__init__.py b/mhcflurry/class1_allele_specific_ensemble/__init__.py
index c262840a..c9dd8949 100644
--- a/mhcflurry/class1_allele_specific_ensemble/__init__.py
+++ b/mhcflurry/class1_allele_specific_ensemble/__init__.py
@@ -1,8 +1,10 @@
from .class1_ensemble_multi_allele_predictor import (
Class1EnsembleMultiAllelePredictor,
+ get_downloaded_predictor,
HYPERPARAMETER_DEFAULTS)
__all__ = [
"Class1EnsembleMultiAllelePredictor",
+ "get_downloaded_predictor",
"HYPERPARAMETER_DEFAULTS",
]
diff --git a/mhcflurry/class1_allele_specific_ensemble/class1_ensemble_multi_allele_predictor.py b/mhcflurry/class1_allele_specific_ensemble/class1_ensemble_multi_allele_predictor.py
index 8058b7c2..3192fbd1 100644
--- a/mhcflurry/class1_allele_specific_ensemble/class1_ensemble_multi_allele_predictor.py
+++ b/mhcflurry/class1_allele_specific_ensemble/class1_ensemble_multi_allele_predictor.py
@@ -34,6 +34,7 @@ import pandas
from ..hyperparameters import HyperparameterDefaults
from ..class1_allele_specific import Class1BindingPredictor, scoring
+from ..downloads import get_path
from .. import parallelism, common
MEASUREMENT_COLLECTION_HYPERPARAMETER_DEFAULTS = HyperparameterDefaults(
@@ -56,6 +57,35 @@ HYPERPARAMETER_DEFAULTS = (
.extend(Class1BindingPredictor.hyperparameter_defaults))
+CACHED_PREDICTOR = None
+
+
+def supported_alleles():
+ """
+ Return a list of the names of the alleles for which there are trained
+ predictors in the default laoder.
+ """
+ return get_downloaded_predictor().supported_alleles
+
+
+def get_downloaded_predictor():
+ """
+ Return a Class1AlleleSpecificPredictorLoader that uses downloaded models.
+ """
+ global CACHED_PREDICTOR
+
+ # Some of the unit tests manipulate the downloads directory configuration
+ # so get_path here may return different results in the same Python process.
+ # For this reason we check the path and invalidate the loader if it's
+ # different.
+ path = get_path("models_class1_allele_specific_ensemble")
+ if CACHED_PREDICTOR is None or path != CACHED_PREDICTOR.path:
+ CACHED_PREDICTOR = (
+ Class1EnsembleMultiAllelePredictor
+ .load_from_download_directory(path))
+ return CACHED_PREDICTOR
+
+
def call_fit_and_test(args):
return fit_and_test(*args)
diff --git a/mhcflurry/downloads.yml b/mhcflurry/downloads.yml
index 98b08ee6..aa8ad6b1 100644
--- a/mhcflurry/downloads.yml
+++ b/mhcflurry/downloads.yml
@@ -8,7 +8,7 @@
# by name, the downloads with "default=true" are downloaded.
# This should usually be the latest release.
-current-release: 0.0.8
+current-release: 0.1.0
# An integer indicating what models the current MHCflurry code base is compatible
# with. Increment this integer when changes are made to MHCflurry that would break
--
GitLab