diff --git a/mhcflurry/class1_affinity_predictor.py b/mhcflurry/class1_affinity_predictor.py
index 1638075e365a13b4c1d6fcbc4b68abc5805e968f..63cf796076324a9cfcd4ba4064ddb5c68a19ad14 100644
--- a/mhcflurry/class1_affinity_predictor.py
+++ b/mhcflurry/class1_affinity_predictor.py
@@ -86,8 +86,20 @@ class Class1AffinityPredictor(object):
self.allele_to_allele_specific_models = allele_to_allele_specific_models
self.class1_pan_allele_models = class1_pan_allele_models
self.allele_to_fixed_length_sequence = allele_to_fixed_length_sequence
+ self._manifest_df = manifest_df
- if manifest_df is None:
+ if not allele_to_percent_rank_transform:
+ allele_to_percent_rank_transform = {}
+ self.allele_to_percent_rank_transform = allele_to_percent_rank_transform
+ self.metadata_dataframes = metadata_dataframes
+ self._cache = {}
+
+ @property
+ def manifest_df(self):
+ if self._manifest_df is None:
+ # Make a manifest based on
+ # - self.class1_pan_allele_models
+ # - self.allele_to_allele_specific_models
rows = []
for (i, model) in enumerate(self.class1_pan_allele_models):
rows.append((
@@ -96,7 +108,8 @@ class Class1AffinityPredictor(object):
json.dumps(model.get_config()),
model
))
- for (allele, models) in self.allele_to_allele_specific_models.items():
+ for (allele,
+ models) in self.allele_to_allele_specific_models.items():
for (i, model) in enumerate(models):
rows.append((
self.model_name(allele, i),
@@ -104,16 +117,10 @@ class Class1AffinityPredictor(object):
json.dumps(model.get_config()),
model
))
- manifest_df = pandas.DataFrame(
+ self._manifest_df = pandas.DataFrame(
rows,
columns=["model_name", "allele", "config_json", "model"])
- self.manifest_df = manifest_df
-
- if not allele_to_percent_rank_transform:
- allele_to_percent_rank_transform = {}
- self.allele_to_percent_rank_transform = allele_to_percent_rank_transform
- self.metadata_dataframes = metadata_dataframes
- self._cache = {}
+ return self._manifest_df
def clear_cache(self):
"""
@@ -209,7 +216,7 @@ class Class1AffinityPredictor(object):
("config_json", json.dumps(model.get_config())),
("model", model),
])).to_frame().T
- self.manifest_df = pandas.concat(
+ self._manifest_df = pandas.concat(
[self.manifest_df, row], ignore_index=True)
new_model_names.append(model_name)
@@ -225,7 +232,7 @@ class Class1AffinityPredictor(object):
("config_json", json.dumps(model.get_config())),
("model", model),
])).to_frame().T
- self.manifest_df = pandas.concat(
+ self._manifest_df = pandas.concat(
[self.manifest_df, row], ignore_index=True)
current_models.append(model)
new_model_names.append(model_name)
@@ -609,7 +616,7 @@ class Class1AffinityPredictor(object):
("config_json", json.dumps(model.get_config())),
("model", model),
])).to_frame().T
- self.manifest_df = pandas.concat(
+ self._manifest_df = pandas.concat(
[self.manifest_df, row], ignore_index=True)
self.allele_to_allele_specific_models[allele].append(model)
if models_dir_for_save:
@@ -702,7 +709,7 @@ class Class1AffinityPredictor(object):
("config_json", json.dumps(model.get_config())),
("model", model),
])).to_frame().T
- self.manifest_df = pandas.concat(
+ self._manifest_df = pandas.concat(
[self.manifest_df, row], ignore_index=True)
if models_dir_for_save:
self.save(
@@ -1207,7 +1214,9 @@ class Class1AffinityPredictor(object):
Class1AffinityPredictor(
allele_to_allele_specific_models={
allele: [row.model] + existing_selected
- }))
+ }
+ )
+ )
for (_, row) in df.iterrows()
]
diff --git a/mhcflurry/select_allele_specific_models_command.py b/mhcflurry/select_allele_specific_models_command.py
index 01587d7614b0d90f4b95715d3139830be03bffe3..336756193c732896d47296c95af92b1aa2469093 100644
--- a/mhcflurry/select_allele_specific_models_command.py
+++ b/mhcflurry/select_allele_specific_models_command.py
@@ -146,7 +146,7 @@ parser.add_argument(
parser.add_argument(
"--consensus-num-peptides-per-length",
type=int,
- default=100000,
+ default=10000,
help="Num peptides per length to use for consensus scoring")
parser.add_argument(
"--mass-spec-regex",
@@ -364,6 +364,13 @@ def model_select(allele):
**model_selection_kwargs)
+def cache_encoding(predictor, peptides):
+ # Encode the peptides for each neural network, so the encoding
+ # becomes cached.
+ for network in predictor.neural_networks:
+ network.peptides_to_network_input(peptides)
+
+
class CombinedModelSelector(object):
def __init__(self, model_selectors, weights=None):
if weights is None:
@@ -396,7 +403,7 @@ class ConsensusModelSelector(object):
def __init__(
self,
predictor,
- num_peptides_per_length=100000,
+ num_peptides_per_length=10000,
multiply_score_by_value=10.0):
(min_length, max_length) = predictor.supported_peptide_lengths
@@ -408,11 +415,7 @@ class ConsensusModelSelector(object):
self.peptides = EncodableSequences.create(peptides)
self.predictor = predictor
self.multiply_score_by_value = multiply_score_by_value
-
- # Encode the peptides for each neural network, so the encoding
- # becomes cached.
- for network in predictor.neural_networks:
- network.peptides_to_network_input(self.peptides)
+ cache_encoding(self.predictor, self.peptides)
def usable_for_allele(self, allele):
return True
@@ -513,11 +516,7 @@ class MassSpecModelSelector(object):
self.multiply_score_by_data_size = multiply_score_by_data_size
self.peptides = EncodableSequences.create(full_matrix.index.values)
-
- # Encode the peptides for each neural network, so the encoding
- # becomes cached.
- for network in predictor.neural_networks:
- network.peptides_to_network_input(self.peptides)
+ cache_encoding(self.predictor, self.peptides)
@staticmethod
def ppv(y_true, predictions):