search

openvax / mhcflurry

Peptide-MHC I binding affinity prediction
http://openvax.github.io/mhcflurry/
Apache License 2.0
191 stars 57 forks source link

Project dependencies may have API risk issues #209

Closed PyDeps closed 11 months ago

PyDeps commented 1 year ago

Hi, In mhcflurry, inappropriate dependency versioning constraints can cause risks.

Below are the dependencies and version constraints that the project is using

six
pandas>=0.20.3
tensorflow>=2.2.0
appdirs
scikit-learn
mhcgnomes
pyyaml
tqdm
np_utils

The version constraint == will introduce the risk of dependency conflicts because the scope of dependencies is too strict. The version constraint No Upper Bound and * will introduce the risk of the missing API Error because the latest version of the dependencies may remove some APIs.

After further analysis, in this project, The version constraint of dependency scikit-learn can be changed to >=0.14,<=0.21.3. The version constraint of dependency tqdm can be changed to >=4.42.0,<=4.64.0.

The above modification suggestions can reduce the dependency conflicts as much as possible, and introduce the latest version as much as possible without calling Error in the projects.

The invocation of the current project includes all the following methods.

The calling methods from the scikit-learn 
sklearn.linear_model.LogisticRegression
sklearn.metrics.pairwise.cosine_similarity
sklearn.metrics.f1_score
sklearn.metrics.roc_auc_score
The calling methods from the tqdm 
tqdm.trange
itertools.product
tqdm.tqdm
The calling methods from the all methods 
class1_affinity_predictor.Class1AffinityPredictor.load.save
AlleleEncoding
alleles.pandas.Series.map
argparse.ArgumentParser.parse_args
load_data_abelin_mass_spec
all_peptides_df.peptide.str.len
ALLELE_SEQUENCES.index.isin.to_dict
hit_df.protein_ensembl.isnull.iterrows
high_peptides.pandas.Series.sample
reference_df.set_index.set_index
df.allele.isin.to_csv
iedb_df.isnull.iedb_df.loc.copy.map
multiprocessing.Queue
col.startswith
flat_shape.numpy.random.standard_normal.astype
exclude_dfs.append
self.allele_to_percent_rank_transform.items
shutil.move
pandas.concat.drop_duplicates
train_df.groupby.measurement_value.count.to_dict
self.clear_cache
locals.items
eval
y_true.sum.int.df.sort_values.y_true.mean
pandas.DataFrame.head
tqdm.tqdm
iedb_df.iedb_df.loc.copy
all
collections.Counter.peptides.map.sum
fold_cols.data_df.sum
iedb_df.Description.str.match.isnull
df.ensembl.fillna
df.accession.map
peptides.pandas.DataFrame.to_csv
encodable_sequences.EncodableSequences.create.variable_length_to_fixed_length_vector_encoding
mse
dict.items
tensorflow.keras.backend.sum
df.n_flank.str.len.unique
result_generator
class1_neural_network.Class1NeuralNetwork.from_config
get_current_release
columns.df.mean
numpy.exp
args.input.lower.split
model.clear_allele_representations
comparison_quantity.endswith
os.path.exists
c.endswith
collections.OrderedDict
self.get_total_count
pandas.concat.isnull
precomputed_dfs.items
names.append
sorted.pop
class1_presentation_predictor.Class1PresentationPredictor.predict_affinity
json.loads
predictor.allele_to_percent_rank_transform.update
urls.append
allele_similarity.columns.to_series.sample
shellinford.FMIndex.read
value.groupby
numpy.random.choice.append
class1_affinity_predictor.Class1AffinityPredictor.load.calibrate_percentile_ranks
tensorflow.keras.backend.flatten
gene.gene_to_alleles.append
Class1AffinityPredictor.weights_path
position1_scores.possible_additional_positions_scores.negative_position1_distances.position3s.position2s.position1s.pandas.DataFrame.sort_values
self.score_function
hit_df.groupby.peptide.nunique
sample_info.index.isin.isnull
sample_id_to_expression_dataset.items.add
numpy.maximum
sub_df.peptide.map
input_matrix.fillna.fillna
self.wrapped_loss.loss
expression_df.columns.tolist
amino_acid.index_encoding
iedb_df.str.findall
kind.LOADERS
layer
self.models.append
alleles.data_size_by_allele.loc.sum
allele_similarity.columns.to_series
x.split
result_df.copy.drop_duplicates
progress_callback
train_models
set.remove
jobs.append
q.reshape.reshape
tensorflow.keras.backend.int_shape
tensorflow.keras.models.Model.network
downloads.get_default_class1_presentation_models_dir
tensorflow.reduce_max
os.path.abspath
df.length.value_counts
class_ii_cols.df.fillna.sum
predictor.model_select
row.allele.allele_to_allele_specific_models.append
first_pass_plan.iterrows
dfs.append
numpy.random.permutation
allele_sequences.pseudosequence.to_dict.allele_sequences.index.values.AlleleEncoding.fixed_length_vector_encoded_sequences
ms_df.sample_id.str.replace
pandas.read_csv.apply
urllib.urlretrieve
hashlib.sha1.hexdigest
column_to_sample.x1.x1.index.map.value_counts
remove_mask.df.loc.copy.to_csv
traceback.print_stack
args.subparser_name.command_functions
data.allele.value_counts
collections.defaultdict.values
class1_affinity_predictor.Class1AffinityPredictor.merge_in_place
class1_affinity_calibrate_percentile_ranks
tensorflow.keras.backend.not_equal
df.groupby.measurement_value.count.unstack.fillna
get
lengths.length_distribution.set_index.reindex.fillna.reset_index.plot
self.predict_affinity
c.startswith.info_df.c.c.info_df.fillna.apply
check_shape
fold_cols.len.fold_cols.data_df.sum.data_df.loc.copy.groupby
allele_table.applymap.iterrows
sklearn.model_selection.StratifiedKFold.split
numpy.zeros
sub_df.groupby.measurement_value.median
name.replace
mix.replace
df.peptide.min
decoys_df.append
new_hit_df.copy.drop_duplicates
pandas.DataFrame.idxmin
missing.sample_table.loc.dropna.drop_duplicates.tolist
peptides_affinities_inequalities_per_round.append
compile_hyperparameter_defaults.early_stopping_hyperparameter_defaults.fit_hyperparameter_defaults.network_hyperparameter_defaults.extend.extend.extend.extend
idx.replace.replace
tensorflow.keras.layers.Activation
allele_sequences_with_target.recapitulate_target.str.len.max
class1_presentation_predictor.Class1PresentationPredictor.predict
ms_df.groupby.pmid.nunique.sort_values
df.peptide.str.upper.str.match
args.only_format.hit_df.format.hit_df.loc.copy
re.search
length.strip
allele.allele_similarity.index.allele.allele_similarity.sort_values
task_results.pandas.DataFrame.T.set_index
warnings.warn
load_data_systemhc_atlas
appdirs.user_data_dir
instance.__dict__.update
lengths.length_distribution.set_index.reindex.fillna.reset_index
self.weights_path
pieces.str.get
frequency_matrices_df.allele.unique
tensorflow.keras.layers.Conv1D
allele.self.df.allele.sum
df.set_index.iterrows
predictions.encoded_peptides.sequences.pandas.DataFrame.drop_duplicates
length_distribution.set_index.reindex
logging.warning
df.peptide.unique
FULL_TRAIN_DF.peptide.str.len
matplotlib.pyplot.close
full_matrix.sample.astype
a.strip.strip
multiprocessing.util.Finalize
mhcflurry.Class1AffinityPredictor.load.predict_peptides_dataframe
reference_df.columns.tolist
key.startswith
pandas.read_csv
tensorflow.expand_dims
self.network.get_layer.get_weights.numpy.array.flatten
print
index_encoded_sequences.reshape
self.apply_hyperparameter_renames
subparsers.add_parser.add_argument
endswith
peptides.self._predictions.sample
sample_table.expression_dataset.to_dict
df.peptide.unique.isin
scipy.stats.kendalltau
col.sub_df.values.astype
i.dropout_probability.Dropout
class_ii_cols.df.fillna.sum.df.loc.Sequence.unique
mhcflurry.local_parallelism.worker_pool_with_gpu_assignments_from_args.close
row.expression_dataset.row.protein_ensembl.split.expression_df.reindex.sum
WrapException
prev_score_col.df.max
df.supported_peptide.any
class1_pan_allele_models.extend
df.length.value_counts.to_dict.get
components.append
class1_neural_network.Class1NeuralNetwork.clear_allele_representations
self.processing_predictor_with_flanks.save
current_models.append
possible_additional_positions_scores.append
numpy.searchsorted
uuid.uuid4
downloads.get_downloads_dir
df.sample_id.unique
join_df.pandas.DataFrame.drop_duplicates
sub_hit_df.protein_accession.unique.universe.protein_accession.isin.sub_hit_df.peptide.unique.universe.peptide.isin.universe.loc.sample
matplotlib.pyplot.xticks
a.strip.split
threshold.eq_df.measurement_value.nunique
int.strip
qualitative.str.contains.qualitative.ix.copy
alleles_by_similarity.pop
common.positional_frequency_matrix
eval_df.ensemble_key.value_counts
c.sheet.c.c.sheet.fillna
numpy.ones
self.update_network_description
assign_folds
updated_network_config_jsons.append
sub_df.col.values.result_df.isnull
unsaved_predictors.append
result_df.copy.copy
iedb_df.isnull.iedb_df.loc.copy
pandas.concat.append
mhcflurry.Class1AffinityPredictor.load
min_val_loss_iteration.min_val_loss.str.fit_info.epoch_time.self.hyperparameters.i.progress_preamble.strip
svd_orthonormal
cluster_parallelism.cluster_results_from_args
os.path.join.format
self._network.to_json
patience_epoch_threshold.mutable_generator_state.min_val_loss_iteration.min_val_loss.val_loss.fit_info.epoch_time.epochs.epoch.strip
load
self._cache.clear
remove_mask.df.loc.copy
row.items
new_hit_df.copy.iterrows
lengths.eval_df.peptide.str.len.isin.eval_df.loc.copy
f.read
result_items.remove
ms_df.isnull.any
allele_indices.tuple.allele_indices_to_peptides.append
int.allele_representations.shape.numpy.product.allele_representations.shape.Embedding
self.indices.isnull.any
do_predictions_function
tensorflow.keras.layers.concatenate
cutoff.normalized_frequency_matrices.cutoff_fraction.length.normalized_frequency_matrices.length.allele.normalized_frequency_matrices.allele.normalized_frequency_matrices.loc.set_index
allele_sequences.dropna.set_index.dropna
tarfile.open.extractall
join_df.pandas.DataFrame.drop_duplicates.append
worker_pool_with_gpu_assignments
pandas.merge.to_csv
df.sample_name.nunique
allele.precomputed_df.isnull.all
mhcflurry.class1_presentation_predictor.Class1PresentationPredictor.load
debug
model.predict
allele_sequences.dropna.set_index.to_csv
result_df.hit.result_df.loc.groupby.hit.count
cluster_results
common.normalize_allele_name.upper
self.allele_to_allele_specific_models.values
df.copy.copy
urls.pandas.DataFrame.to_csv
class1_processing_neural_network.Class1ProcessingNeuralNetwork.predict
fd.read
lengths.len.args.ppv_multiplier.sub_hit_df.len.int.sub_hit_df.protein_accession.unique.universe.protein_accession.isin.sub_hit_df.peptide.unique.universe.peptide.isin.universe.loc.sample.drop_duplicates
numpy.testing.assert_array_less
tarfile.open
df.protein_primary_ensembl_contig.isin
sub_hit_df.copy.copy
class1_affinity_predictor.Class1AffinityPredictor
df.normalized_allele.isin.all
encodable_sequences.EncodableSequences.create.append
allele_sequences.pseudosequence.to_dict.allele_sequences.index.values.AlleleEncoding.fixed_length_vector_encoded_sequences.reshape
medians.index.to_series.sample
self.affinity_predictor.save
self.y_pred_transform
filtered_sub_df.Sequence.unique
class1_presentation_predictor.Class1PresentationPredictor.save
peptides.str.len
pandas.DataFrame.drop_duplicates
backup_arg_queue.put
self.save
tqdm.trange
result.restrict_allele_fields.to_string
setuptools.setup
yes_no
columns_to_keep.num_to_take.merged_df.head.sample.copy
amino_acid.fixed_vectors_encoding
ALLELE_SEQUENCES.index.isin
self.cdf.numpy.isnan.any
encodable_sequences.EncodableSequences.create.extend
worker_result.groupby
total_nonbinders_by_length.max
time.asctime
predictor_for_ensemble_key
self.open_file
differentiate_alleles.allele_sequences.index.isin.allele_sequences.loc.copy
raw_predictions.numpy.squeeze.astype
flanking_length.end_pos.end_pos.seq.ljust
pandas.DataFrame.map
hit_df.sample_id.isin
self.allele_to_allele_specific_models.get
parse_peptide_lengths
peptides.str.slice.map
self.class1_pan_allele_models.append
abs
current_layer.get_shape.int.dropout_rate.Dropout
Class1AffinityPredictor.optimize
self.network.set_weights
fold_cols.df.mean
ms_df.groupby.peptide.nunique
numpy.random.choice
outputs_for_final_dense.append
yaml.safe_load
Class1AffinityPredictor
self.borrow_from.allele_representations
numpy.array.append
self.allele_to_sequence.items
item.summary_results_lists.append
tensorflow.reduce_mean
recapitulate_df.dropna.drop_duplicates
klass.keras_network_cache_key
collections.defaultdict
args.match_amino_acid_distribution_data.pandas.read_csv.peptide.unique
item.mapping_df.key.mapping_df.loc.groupby
f.endswith
tensorflow.keras.layers.Dropout
sheets.update
network.predict_encoded
gtf_df.feature.gtf_df.loc.set_index
max
zip
pandas.DataFrame.sort_values
common.configure_tensorflow
range
df.allele.map.drop_duplicates
pandas.DataFrame.groupby
tensorflow.keras.models.model_from_json
get_amino_acid_index
tensorflow.keras.backend.maximum
letter.lower
argparse.ArgumentParser.add_argument
df.c_flank.str.pad
result_df.sample.groupby
allele_sequences.index.map
mkdir_p
numpy.var
ipdb.set_trace
hit_df.pmid.isin
sub_df.to_csv
subselect_df_held_out
result_args.values
tensorflow.keras.layers.Dense
result_df.hit.result_df.loc.groupby.hit.count.sort_values
tasks.append
self.network
sub_df.prediction.nsmallest
pprint.pprint
numpy.array.sum
compile_hyperparameter_defaults.network_hyperparameter_defaults.extend.extend
run
numpy.array
len
class1_presentation_predictor.Class1PresentationPredictor.load
row.join.replace
worker_pool.imap_unordered.append
tensorflow.reduce_sum
pandas.concat.groupby
s.replace.strip
BLOSUM62_MATRIX.T.BLOSUM62_MATRIX.all
result_df.hit.result_df.loc.groupby
self.data_dependent_weights_initialization
scoring.split.split
urls.extend
allele_sequences_with_target.aligned.str.len
tensorflow.gather_nd
percent_rank_transform.PercentRankTransform.fit
pandas.Series.sum
s.replace.replace
numpy.load
early_stopping_hyperparameter_defaults.fit_hyperparameter_defaults.network_hyperparameter_defaults.extend.extend.extend
shellinford.FMIndex.build
constant_data.clear
itertools.product
self.class1_pan_allele_models.predict
write
fit_hyperparameter_defaults.compile_hyperparameter_defaults.network_hyperparameter_defaults.extend.extend.extend
sub_df.Sequence.unique
result.hyperparameters.get
numpy.stack
qprint
row.model.get_config
pandas.concat.fillna
new_hit_df.copy.groupby
numpy.nanpercentile
self.get_model.predict_proba
class1_affinity_predictor.Class1AffinityPredictor.load.optimize
cls.weights_path
sub_df.groupby
Exception.__str__
hit_df.protein_accession.unique
args.allele_column.args.allele_column.args.allele_column.df.drop_duplicates.set_index.str.split.to_dict
downloads.get_current_release_downloads
self.plan_df.sum.sum
df.target.astype
self.peptides_to_network_input
fold.fold_to_ensemble.append
enumerate
numpy.savez
os.path.basename
peptides.str.slice
pandas.read_table
df.fillna.iterrows
allele_sequences.pseudosequence.to_dict
pickle.load
signal.signal
df1.rename
percent_rank_transform.PercentRankTransform.to_series
models.len.numpy.arange.individual_model_scores.pandas.Series.to_frame.reset_index
df.groupby.count.unstack.fillna.astype.to_csv
EXPRESSION_GROUPS_ROWS.append
n.strip.startswith
new_model_names.append
fd.write
log_values.numpy.nanpercentile.reshape.sum
fold_cols.len.fold_cols.data_df.sum.data_df.loc.copy
urlparse.urlsplit
numpy.testing.assert_equal
layer.get_weights
hit_df.groupby.tpm.max.hit_df.hit_id.map.hit_df.tpm.hit_df.loc.sample
type
order.append
hit_df.protein_ensembl.isnull.groupby
tensorflow.squeeze
col.replace
go
sample_info.index.map
score_col.df.max.score_col.df.df.loc.sample
string.split
result_df.hla.isnull
df.groupby.measurement_value.count.unstack
predictions.encoded_peptides.sequences.pandas.DataFrame.drop_duplicates.set_index.groupby
hit_df.allele.isin
result_df.groupby.binder.mean
filename.endswith
names.pandas.Series.to_csv
numpy.full
mhcflurry.amino_acid.COMMON_AMINO_ACIDS.join.all_peptides_df.peptide.str.match.hit_df.protein_accession.unique.all_peptides_df.protein_accession.isin.all_peptides_df.loc.copy
sub_networks.append
y_true.sum
numpy.cumsum
index_encoded_sequences.reshape.letter_to_vector_df.iloc.values.reshape
matches.items
EncodingResult
iedb_df.str.strip
decoy_universe.str.len
reference_df.set_index.iterrows
position2s.append
hit_df.peptide.str.match
score_function
HyperparameterDefaults
mhcflurry.cluster_parallelism.cluster_results_from_args
allele.self.df.allele.self.df.loc.reset_index
copy.deepcopy
IOError
os.remove
model_selection_dfs.append
self.manifest_df.model_name.isin
sample_info.index.isin
up_to_date
mhcflurry.common.normalize_allele_name
list.append
df.normalized_allele.isin
merged_df.sort_values.head
tensorflow.compat.v1.ConfigProto
mhcflurry.encodable_sequences.EncodableSequences.create.unique
self.ppv
pandas.DataFrame
ConsensusModelSelector.usable_for_allele
result_df.sample_id.unique
mhcflurry.cluster_parallelism.add_cluster_parallelism_args
dict
alleles.pandas.DataFrame.to_csv
iter
hit_df.hla.str.split.map
df.measurement_value.isnull
CombinedModelSelector
class1_neural_network.Class1NeuralNetwork.update_network_description
sample_info.isnull.any
float
self.predict_processing
sub_train.to_csv
pandas.read_excel.isnull
allele_before_normalization.startswith
df.normalized_allele.unique
shellinford.FMIndex.search
self.wrapped_loss.encode_y
sub_df.aligned.nunique
yaml.load
numpy.sum
intensity_col.df.fillna
argparse.ArgumentParser.exit
flank.max_pool_over_peptide_extractor.Lambda
s.endswith
df.columns.tolist
df.allele.map
hit_df.allele.str.match
sorted
ms_df.groupby.pmid.nunique
pandas.DataFrame.set_index
numpy.nan_to_num
sample_id.df.map
class1_neural_network.Class1NeuralNetwork.get_config
mhcgnomes.parse
local_parallelism.worker_pool_with_gpu_assignments_from_args.close
mhcflurry.common.random_peptides
class1_processing_predictor.Class1ProcessingPredictor.load
df.original_allele.map
next
args.allele_column.args.allele_column.args.allele_column.df.drop_duplicates.set_index.str.split
tarfile.open.getnames
numpy.histogram
iedb_df.str.upper.str.startswith
counts.counts.sum
hyperparameters.HyperparameterDefaults
pandas.DataFrame.to_csv
self._network.summary
pandas.read_csv.iterrows
do_predict
argparse.ArgumentParser.error
sample_to_peptides.items
length_distribution.sort_values.to_frame
position3s.append
unpadded.str.len.max
rows.pandas.DataFrame.to_csv
self.check_valid_keys
write_manifest_df.to_csv
df.allele.isin.stack
six.StringIO
sample_id_to_cell_line.items
pandas.DataFrame.replace
argparse.ArgumentParser
scipy.stats.pearsonr
df.ensembl_primary.mean
re.MULTILINE.f.read.re.search.group
args.alleles.pandas.Series.str.split.to_dict
matplotlib.pyplot.gcf.clear
self.predict_encoded
df.drop_duplicates.allele.to_csv
hit_df.drop_duplicates.set_index
intensity_cols.df.sum
local_parallelism.worker_pool_with_gpu_assignments_from_args.join
args.expression.pandas.read_csv.fillna.reindex
df.groupby.peptide.count
c.startswith
locally_connected_params.i.keras.layers.LocallyConnected1D
make_expression_groups
train_df.groupby.peptide.unique
tempfile.NamedTemporaryFile
seaborn.despine
numpy.nanmean
data.allele.isin
key_string.split
tensorflow.keras.models.Model
gzip.open
functools.partial
mhcflurry.local_parallelism.worker_pool_with_gpu_assignments_from_args.join
list
df.index.map
self.metadata_dataframes.items
bool
x.split.split
sklearn.metrics.pairwise.cosine_similarity
class1_neural_network.Class1NeuralNetwork.network
to_remove.allele.map
df.allele_peptide.isin.sum
work_items.pop
densenet_layers.append
random_negative_peptides.RandomNegativePeptides.get_alleles
mix.replace.upper
ConsensusModelSelector
reference_df.index.to_series.reset_index
tensorflow.stack
layer.get_output_at
int.random_negative_output_indices.pandas.Series.sample
self.current_lines.append
col.result_df.isnull
peptides.len.counts.fillna
QUALITATIVE_TO_AFFINITY_AND_INEQUALITY.items
array.astype.astype
with_flanks_list.append
downloads.get_current_release_downloads.items
peptides.self.prediction_cache.copy
shellinford.FMIndex
df.groupby.peptide.count.sort_values
df.sort_values.dropna
model_names_to_write.self.manifest_df.model_name.isin.self.manifest_df.loc.copy.iterrows
sub_df.peptide.unique
allele.predictor.allele_to_sequence.sequence_to_allele.add
matplotlib.pyplot.gca.get_legend
get_path
startswith
df.copy.iterrows
klass.KERAS_MODELS_CACHE.clear
c_flank_length.df.c_flank.str.pad.str.slice
tensorflow.keras.layers.add
df.protein_ensembl_primary.isnull
x.startswith
class1_affinity_predictor.Class1AffinityPredictor.load.predict
sample_id_to_expression_dataset.pandas.Series.value_counts
predictions_df.prediction.nsmallest
numpy.tile
regression_target.to_ic50
row.protein_ensembl.split
six.moves.StringIO
FastaParser.iterate_over_file
iedb_df.iedb_df.ix.copy
make_worker_pool
df.format.df.loc.copy
missing.sample_table.loc.dropna
write_train_data
peptides.len.counts.fillna.restrict_allele_fields
percent_rank_transform.PercentRankTransform
numpy.minimum
allele_representations.reshape
pandas.Series.value_counts
pandas.merge
df.experiment_id.unique
df.peptide.str.upper.str.match.sum
FastaParser
sklearn.metrics.f1_score
write_length_distribution
fit_history.history.items
offsets.isnan.any
peptides.str.match
mhcflurry.local_parallelism.worker_pool_with_gpu_assignments_from_args
socket.gethostname
encodable_sequences.EncodableSequences.create
new_hit_df.copy.astype
hit_df.format.hit_df.loc.copy
sequence.decode.decode
allele_encoding.AlleleEncoding
allele_sequences.recapitulate_target.isnull
self.network.get_layer.get_weights
handler
allele.df_nonbinders.allele.df_nonbinders.loc.length.value_counts
subprocess.check_call
self.check_consistency
position_identities.max.min
class1_presentation_predictor.Class1PresentationPredictor
numpy.object_.self.sequences.pandas.Series.str.len.max
args.expression.pandas.read_csv.fillna
tensorflow.keras.layers.Embedding
allele_info.apply.get
df.measurement_type.df.loc.allele.value_counts
slice
cutoff_count.predictions_df.prediction.nsmallest.index.str.len.value_counts
df.selected.all
manifest_df.col.isin.iterrows
self._parse_header_id
parser.add_argument_group.add_argument
parser.add_subparsers.add_parser
dict.update
sample_info.index.isnull.sample_info.loc.fillna
ms_df.drop_duplicates.set_index
allele.allele_to_allele_specific_models.extend
result_df.drop_duplicates.sort_values
mhcflurry.local_parallelism.worker_pool_with_gpu_assignments_from_args.imap_unordered
m.get_config
pandas.Series.update
df.fillna.fillna
tarfile.open.close
matrix.sum.sum
hyperparameters.pop
do_process_samples
self.network.get_layer
run_class1_presentation_predictor
selector_to_max_weighted_score.values
tensorflow.size
MSEWithInequalities
dict.pop
unpadded.str.pad
self.function
df.peptide.str.len
label.replace.replace
class1_processing_neural_network.Class1ProcessingNeuralNetwork.fit
numpy.sqrt
logging.getLogger
set.update
getattr
df.index.isin
df.n_flank.max
convolutional_activation.convolutional_kernel_l1_l2.regularizers.l1_l2.convolutional_kernel_size.convolutional_filters.Conv1D
summary_df.index.map
value.split
grid.append
df.hla.nunique
self.borrow_cached_network
normalize_allele_name_or_return_unknown
df.groupby.count.unstack
numpy.array_split
numpy.linalg.svd
df.mhc.map
result_df.groupby.hit.mean
tensorflow.compat.v1.disable_v2_behavior
pandas.Series.map
pandas.read_csv.to_csv
universe.peptide.isin
mixmhcpred_usable_alleles.append
common.configure_logging
self.network_hyperparameter_defaults.subselect
input_matrix.fillna.isnull
sklearn.linear_model.LogisticRegression
position1_scores.append
args.alleles_file.pandas.read_csv.allele.unique
main
result_args.items
args.max_peptides.args.input_peptides.pandas.read_csv.peptide.drop_duplicates
key.split
train_df.groupby.measurement_value.count.to_dict.get
join_df.protein_accession.map
json.JSONEncoder.default
i.BatchNormalization
get_downloads_dir
c.sheet.c.c.sheet.fillna.sum
peptides.pandas.Series.sample.extend
peptides.pandas.Series.sample
mix.upper
tensorflow.keras.models.Model.predict
self.sequences_to_fixed_length_index_encoded_array
random.shuffle
layer.get_output_shape_at
self.make_network
df.peptide.str.upper.str.match.any
self.predict_to_dataframe_encoded
flanking_encoding.FlankingEncoding.vector_encode
numpy.repeat
tensorflow.keras.initializers.Ones.Dense
df.top_allele.map
lengths.allele.df_nonbinders.allele.df_nonbinders.loc.length.value_counts.reindex.fillna
layer.set_weights
allele_sequences.index.recapitulate_df.index.isin.recapitulate_df.index.tolist
additional_metadata.items
removed.append
PMID_31495665_SAMPLE_TYPES.values
allele_table.applymap.applymap
hit_df.allele.isin.copy
logomaker.Logo
traceback.format_exception
allele_table.index.isnull
tensorflow.keras.losses.LossFunctionWrapper
pipes.quote
df.sort_values.dropna.drop_duplicates
manifest_df.set_index.path.map
local_parallelism.call_wrapped_kwargs
item.lower
iedb_df.allele.iedb_df.ix.unique
tensorflow.keras.backend.get_value
script_prefix.format.append
local_parallelism.worker_pool_with_gpu_assignments_from_args
matches
download.get
self.defaults.items
tensorflow.keras.regularizers.l1_l2
peptide.encode
random_negative_peptides.RandomNegativePeptides.plan
mhcflurry.amino_acid.COMMON_AMINO_ACIDS.join.all_peptides_df.peptide.str.match.hit_df.protein_accession.unique.all_peptides_df.protein_accession.isin.all_peptides_df.loc.copy.groupby
ScoreFunction
expression_dfs.extend
n_flank_length.df.n_flank.str.pad.str.slice
logging.info
df.allele.df.ix.unique
col.replace.replace
df.allele.any
str
ConsensusModelSelector.score_function
klass
fasta.read_fasta_to_dataframe
args.allele_column.args.allele_column.args.allele_column.df.drop_duplicates.set_index.str.split.to_dict.values
iedb_df.str.findall.str.len.sum
predictions_df.index.str.len
self.affinity_predictor.percentile_ranks
iedb_df.Description.str.strip
peptides.p.i.p.pandas.Series.value_counts
insuffient_mask.iedb_df.loc.value_counts
parser.add_argument_group
df.sort_values.dropna.to_csv
fd.numpy.load.astype
isinstance
args.alleles.pandas.Series.str.split
low_peptides.pandas.Series.sample
recapitulate_df.allele.map
selected_df.hit.value_counts
universe.protein_accession.isin
hit_df.groupby.tpm.max.hit_df.hit_id.map.hit_df.tpm.hit_df.loc.sample.drop_duplicates
allele.allele_similarity.index.allele.allele_similarity.sort_values.index.tolist
sorted.append
sub_hit_df.protein_accession.unique
tensorflow.shape
info.isnull.info.loc.set_index
self.fit_info.append
df.n_flank.str.pad
scipy.stats.percentileofscore
self.alleles.unique
genotypes.index.map
random_negative_peptides.RandomNegativePeptides.get_peptides
peptide.strip
y_dict_with_random_negatives.numpy.isnan.sum
self._network.set_weights
run_class1_affinity_predictor
a.startswith
write_df.to_csv
numpy.random.randint
df.allele.unique
random_negative_peptides.RandomNegativePeptides.hyperparameter_defaults.subselect
collections.defaultdict.items
BLOSUM62_MATRIX.T.BLOSUM62_MATRIX.all.all
reference_df.index.to_series
function
allele.data.allele.astype
posixpath.basename
peptide_has_valid_amino_acids.df.loc.peptide.unique
cls.hyperparameter_renames.items
lengths.length_distribution.set_index.reindex.fillna.reset_index.set_index
get_train_param
ConsensusModelSelector.plan_summary
df_all.allele.unique
allele.df_nonbinders.allele.df_nonbinders.loc.length.value_counts.reindex
df.groupby.measurement_value.count.unstack.fillna.astype
df.groupby.count
df.length.value_counts.to_dict
model.predict_encoded
self.aa_distribution.to_dict
mhcflurry.common.configure_logging
some.split
class1_pan_allele_models.append
any
decoy_universe.seq.unique
pandas.concat.iterrows
AMINO_ACIDS.AMINO_ACIDS.StringIO.pandas.read_csv.loc.astype
tensorflow.boolean_mask
scoring.split
numpy.linspace
cell_line_df.pivot.pivot
pandas.set_option
recapitulate_df.dropna.drop_duplicates.set_index
item.pop
series_k.series_i.mean
train_df.groupby.peptide.unique.iteritems
hla_text.split
make_selector
pandas.read_csv.groupby
iedb_df.allele.iedb_df.loc.unique
pickle.dump
tuple
fold_num.folds_df.df.loc.sample
tensorflow.keras.backend.cast
df.hla.unique
models_dir.join.pandas.read_csv.iloc.to_dict
os.makedirs
hit_df.hit_id.map
exists_string
line.rstrip.rstrip
matplotlib.pyplot.savefig
Loss.__init__
result_dict.update
iedb_df.allele.value_counts
pandas.concat.applymap
peptides.extend
yaml.dump
self.encode
allele_sequences.index.isin
os.getpid
possible_universe.sample.copy
mhcflurry.encodable_sequences.EncodableSequences.create
sub_hit_df.peptide.unique
numpy.mean
itertools.chain
df.n_flank.str.len.unique.set.union
do_job
fd.read.format
hla_set.split
ms_df.str.strip.str.replace
configure
predictor.predict
tensorflow.reshape
self.allele_encoding_to_network_input
load_data_iedb
recapitulate_df.dropna.drop_duplicates.set_index.dropna
model.model.get_config.json.dumps.allele.model_name.collections.OrderedDict.pandas.Series.to_frame
df.measurement_source.value_counts
amino_acid.AMINO_ACID_INDEX.get
targets.numpy.isnan.sum
manifest_df.col.map
model.get_input_at
weakref.WeakKeyDictionary
sub_df.copy
common.load_weights
col.split
input_serialization_module.load
re.sub
sample_alleles.predictions_df.min
self.predict_to_dataframe
unusable_alleles.append
df2.rename
items
common.amino_acid_distribution
copy.deepcopy.append
str.fold_cols.eval_df.astype.sum.str.strip
df.allele.isin.groupby
ms_dfs.append
numpy.array.any
multiprocessing.Queue.put
hit_df.protein_primary_ensembl_contig.astype
df.columns.str.lower
Bio.SeqIO.write
selected.positional_frequency_matrix.reset_index
allele_sequences_with_target.recapitulate_target.str.len
col.grouped.any
ensemble.extend
percent_rank_transform.PercentRankTransform.from_series
RuntimeError
iedb_df.str.strip.str.upper
numpy.testing.assert_array_almost_equal
self.predict
allele.allele_to_excluded_peptides.update
class1_affinity_predictor.Class1AffinityPredictor.load
result_df.copy.insert
df.measurement_kind.value_counts
pandas.read_csv.copy
model.model.get_config.json.dumps.model_name.collections.OrderedDict.pandas.Series.to_frame
Class1AffinityPredictor.extend
activation.kernel_regularizer.i.layer_size.Dense
write_logo
pandas.DataFrame.sum
NotImplementedError
hit_df.protein_ensembl.isnull
ms_df.str.strip
mhcflurry.local_parallelism.add_local_parallelism_args
selected_positions.set.union
df.ensembl.fillna.str.split
inequalities.pandas.Series.map
backup_arg_queue.get.update
tarfile.open.getmembers
allele_sequences_with_target.recapitulate_target.str.get
new_hit_df.copy
qualitative.str.contains
flank.Dense
exclude_df.allele.unique
lst.append
sys.exc_info
df.inequality.map
centrality_function
inputs.append
predictor.predict_sequences.to_csv
gtex_df.pivot.pivot
logging.debug
self.update
x.split.split.split.strip
hyperparrameters_grid
pandas.Series.extend
models.append
df.measurement_kind.df.loc.copy
col_to_predictions.items
argparse.ArgumentParser.add_subparsers
iedb_df.iedb_df.loc.copy.fillna
make_expression_mixtures
y_values.numpy.isnan.sum
getpass.getuser
tensorflow.maximum
ValueError
tensorflow.keras.layers.Lambda
class1_neural_network.Class1NeuralNetwork.fit
cache_encoding
self.indices.isnull
id
train_data.drop_duplicates.reset_index
hit_df.hla.str.split
decoy_universe.str.match.sample
args.input.lower
pandas.DataFrame.append
class1_neural_network.Class1NeuralNetwork
hashlib.sha1.update
quantitative.fillna.map
iedb_df.Description.str.match
self.plan_df.iterrows
math.floor
init_function
transform
tensorflow.less
result_df.copy.sort_values
df.allele.isin
mhcflurry.downloads.get_path
allele.precomputed_df.isnull
sample_names.append
first_pass_plan.copy
mhctools.NetMHCpan4
train_model
qualitative.str.contains.qualitative.ix.copy.map
self.allele_representations
collections.OrderedDict.items
iedb_df.str.findall.str.len
args.sequence_column.df.to_dict
iedb_df.str.contains
item.mapping_df.key.mapping_df.loc.groupby.value.unique
class1_processing_predictor.Class1ProcessingPredictor
df.groupby.count.unstack.fillna.astype.sum
Class1NeuralNetwork.update_network_description
gtfparse.read_gtf
current_sequences.value_counts.max
GLOBAL_DATA.update
tensorflow.keras.models.clone_model.get_layer
sub_df.groupby.measurement_value.median.median
args.allele_column.df.drop_duplicates.set_index
self.processing_predictor_without_flanks.save
json.load
alleles.df.allele.isin.df.loc.dropna
json.dumps
train.df.iloc.allele_peptide.unique
to_differentiate.aligned.str.get
self.network.predict
matches.values
df.c_flank.max
len.append
MSEWithInequalities.encode_y
get_activations
df._key.isin
pandas.Series.to_csv
ms_df.expression_dataset.unique
numpy.random.standard_normal
aa_counts.sum.sum
numpy.where
amino_acids.frequency_matrices_df.cutoff_fraction.frequency_matrices_df.loc.mean
df.allele.df.loc.hla.unique
pandas.Series.sample
summary_dfs.append
self._network.get_weights
df.sort_values.dropna.map
info_path.pandas.read_csv.iloc.to_dict
peptide_allele_merge_activation.peptide_allele_merge_activation.keras.layers.Activation
merged_df.peptide.unique
self.network_weights_loader
make_selector.score_function
hyperparameters.HyperparameterDefaults.with_defaults
pandas.concat
df.measurement_inequality.value_counts
custom_loss.get_loss.encode_y
shellinford.FMIndex.write
x.x.get.sample_id.df.map.astype
class1_affinity_predictor.Class1AffinityPredictor.clear_cache
locals
self.set_allele_representations
current_sample.sample_to_peptides.append
numpy.ones.mean
float.mask.astype.without_nans.sum
ensembl_primary.append
df.protein_accession.unique
regression_target.from_ic50
tensorflow.keras.models.clone_model
numpy.ceil
tensorflow.gather
pkg_resources.resource_string
open
sys.path.insert
allele_sequences.str.replace
tensorflow.compat.v1.Session
differentiate_alleles.allele_sequences.index.isin.allele_sequences.loc.copy.groupby
allele.replace.replace
allele_sequences.index.isin.to_dict
make_train_peptide_hash
df.allele_peptide.isin
tensorflow.keras.initializers.Ones
local_parallelism.add_local_parallelism_args
self.plan_by_allele
tensorflow.keras.layers.multiply
allele_sequences_with_target.aligned.str.len.max
loaded.keys
matplotlib.pyplot.title
iedb_df.Description.str.match.map
tensorflow.cast
args.mhcflurry_batch_size.allele.peptides.predictor.predict.astype
start.flanking_length.start.max.seq.rjust
round_mask.any
df.allele.nunique
columns_to_keep.num_to_take.merged_df.head.sample.copy.fillna
idx.replace
sklearn.metrics.roc_auc_score
result_df.sample.to_csv
set
class1_neural_network.Class1NeuralNetwork.predict
fold_cols.eval_df.astype
mhcflurry.allele_encoding.AlleleEncoding
gtf_df.gene_id.unique
model_selection_df.allele.map
random.seed
predictor.calibrate_percentile_ranks.items
hyperparameters.get
ConsensusModelSelector.max_absolute_value
n_flank_length.n_flank_length.df.n_flank.str.pad.str.slice.str.upper
numpy.isnan
cluster_parallelism.add_cluster_parallelism_args
allele.replace
self.network_input
MassSpecModelSelector
pandas.DataFrame.max
df.sort_values.dropna.groupby
negative_position1_distances.append
intensity_cols.df.sum.dropna
df.supported_peptide.df.loc.peptide.unique
model.hyperparameters.items
initialize_training
full_matrix.sample.astype.sample
sample_info.index.isin.any
self.hyperparameter_defaults.with_defaults
df.groupby.count.unstack.fillna
time.sleep
shellinford.FMIndex.push_back
encodable_sequences.EncodingError
line.rstrip.find
alleles.extend
length_distribution.sort_values.reset_index
self.percent_rank_transform.fit
allele_to_sequence.pandas.Series.to_frame
os.environ.get
c.startswith.info_df.c.c.info_df.fillna
self.percent_rank_transform.transform
fold_num.folds_df.df.loc.sample.copy
position_identities.idxmax.tolist
position_in_sequence.append
train_data.drop_duplicates.reset_index.drop_duplicates
pan_allele_layer_initial_names.index
unselected_score_function
str.ms_df.applymap.applymap
numpy.append
pandas.DataFrame.idxmax
decoys.extend
predictor.allele_to_allele_specific_models.items
qualitative.str.contains.map
key.replace
pandas.DataFrame.astype
argparse.ArgumentParser.add_argument_group
first_pass_plan.copy.astype
encodable_sequences.EncodableSequences
Bio.SeqIO.parse
self.load_weights
recapitulate_df.index.isin
result_items.append
name.startswith
Class1AffinityPredictor.union
result.append
pandas.read_csv.to_dict
self.allele_to_allele_specific_models.get.append
self.affinity_predictor.predict
key.fit_info.extend
tensorflow.compat.v1.keras.backend.set_session
allele.upper.replace.replace
masked_allele_encoding.compact.compact
columns_to_keep.num_to_take.merged_df.head.sample
data_dependent_weights_initialization.lsuv_init
identifier.decode
EncodingError
result_df.peptide_num.map
numpy.object_.self.sequences.pandas.Series.str.len
predictions.encoded_peptides.sequences.pandas.DataFrame.drop_duplicates.set_index
flank.flanking_extractor.Lambda
numpy.abs
collections.namedtuple
id.append
args.flanking_length.end_pos.end_pos.reference_row.seq.ljust
sub_df.Sequence.isin
df.peptide_num.map
time.asctime.append
df.normalized_allele.isin.sum
self.percent_rank_transform.to_series
sample_info.index.isnull
numpy.product
col.df.fillna.df.loc.Sequence.unique
join
re.finditer
selected.append
callable
matplotlib.pyplot.ylabel
df.groupby.count.unstack.fillna.astype
models.len.numpy.arange.individual_model_scores.pandas.Series.to_frame
result_chunks.append
tempfile.NamedTemporaryFile.close
length_distribution.sort_values.sort_values
sequences.pandas.Series.value_counts
common.normalize_allele_name
self.weights_dataframe.to_csv
flank.cleavage_extractor.Lambda
models_dir.join.pandas.read_csv.iloc.to_dict.items
mhcflurry.Class1AffinityPredictor
disambiguation_score
new_manifest_rows.append
i.kernel_regularizer.activation.layer_size.Dense
sum
class1_processing_predictor.Class1ProcessingPredictor.save
mhcflurry.train_pan_allele_models_command.train_model
df.set_index.set_index
pandas.DataFrame.insert
matplotlib.pyplot.gcf
call_wrapped
model.fit_info.setdefault
predictor.predict_peptides_dataframe.groupby
os.path.dirname
missing.sample_table.loc.dropna.drop_duplicates
obj.tolist
ms_df.groupby.pmid.nunique.max
early_stopping_hyperparameter_defaults.fit_hyperparameter_defaults.compile_hyperparameter_defaults.network_hyperparameter_defaults.extend.extend.extend.extend
item.mapping_df.key.mapping_df.loc.groupby.value.unique.map
hashlib.sha1
result.copy
decoy_universe.str.match
pandas.concat.to_csv
df.groupby._excluded.mean
n.strip
local_parallelism.call_wrapped_kwargs.save
copy.copy
record.seq.str.upper
fit_hyperparameter_defaults.network_hyperparameter_defaults.extend.extend
df.allele.df.loc.unique
x.split.split.split.strip.replace
wrapped_generator
data.allele.isin.sample
work_items.append
os.mkdir
tensorflow.keras.layers.average
sample_alleles.predictions_df.idxmin
x.split.split.split
model.intercept_.flatten
peptide.startswith
flanking_encoding.FlankingEncoding
fold_num.folds_df.df.loc.copy
result_df.groupby.hit.mean.sort_values
fold_cols.len.fold_cols.data_df.sum.data_df.loc.copy.to_csv
load_data_kim2014
class1_presentation_predictor.Class1PresentationPredictor.load.predict_sequences
all_peptides_df.peptide.str.match
allele.upper.replace
numpy.random.uniform
m.start
TypeError
train_df.groupby.measurement_value.count
logging.disable
alleles.a.a.peptides.numpy.float32.pandas.DataFrame.get_path.load_results.rename
tensorflow.keras.layers.Flatten
multiprocessing.cpu_count
info.isnull.info.loc.set_index.map
do_task
col.df.fillna
allele_sequences_with_target.recapitulate_target.allele_sequences_with_target.recapitulated.mean
hit_df.sample_id.nunique
length_distribution.sort_values.sum
hit_df.hit_id.nunique
unselected_summary.append
logging.basicConfig
class1_neural_network.Class1NeuralNetwork.merge
custom_loss.get_loss
eval_df.peptide.str.len.isin
json.dump
numpy.object_.self.sequences.pandas.Series.str.len.min
metadata.drop_duplicates.set_index
start.args.flanking_length.start.max.reference_row.seq.rjust
matplotlib.pyplot.tight_layout
pandas.read_excel
score_col.df.max
PercentRankTransform
str.fold_cols.eval_df.astype.sum
df.ensembl_primary.map
layer.name.original_model.get_layer.get_weights
pandas.DataFrame.iterrows
hit_df.peptide.str.len
num.decoy_universe.sample.map
result_df.sample_id.map
allele.self.df.sum
hit_df.sample_id.unique
tensorflow.math.equal
make_selector.plan_summary
TRAIN_DF.allele.isin
downloads.get_default_class1_models_dir
math.ceil
numpy.array.mean
result_df.groupby.peptide.nunique
bad.index.df.index.isin.df.loc.copy
log_values.numpy.nanpercentile.reshape
sub_df.col.values.result_df.isnull.any
input_matrix.isnull.any
s.startswith
ms_df.sample_id.map
alleles_by_similarity
tensorflow.compat.v1.keras.backend.backend
allele_sequences_with_target.aligned.str.get
mhcflurry.Class1AffinityPredictor.load.predict
sub_df.peptide.isin
tensorflow.keras.layers.LocallyConnected1D
set.add
tensorflow.keras.layers.Input
matplotlib.pyplot.ylim
c_flank_length.c_flank_length.df.c_flank.str.pad.str.slice.str.upper
int
allele_info.index.str.strip
row.append
allele.self.allele_to_allele_specific_models.append
c_flanks.append
multiprocessing.Pool
matplotlib.pyplot.gca.get_legend.remove
self.network.compile
make_decoys
self.get_model.fit
common.save_weights
lengths.length_distribution.set_index.reindex.fillna
s.replace
row.sum
numpy.arange
df.allele.value_counts
df.measurement_kind.df.loc.copy.to_csv
tensorflow.logical_and
tensorflow.keras.layers.Concatenate
component_selectors.append
numpy.prod
eval_df.peptide.str.len
tensorflow.keras.layers.Concatenate.get_shape
model_select
matplotlib.pyplot.gca
os.path.join
df.sample_id.isin
os.path.isdir
input_layer_names.append
merged_df.peptide.map
do_class1_affinity_calibrate_percentile_ranks
verify_optimizable
self.network.summary
real_df.binder.real_df.loc.copy
downloads.get_default_class1_processing_models_dir
numpy.log
pretrain_data_iterator
percent_rank_transform.PercentRankTransform.transform
merged_df.sort_values.sort_values
matplotlib.pyplot.figure
df.index.astype
intensity_col_to_sample_id.items
sample_table.expression_dataset.to_dict.items
log_values.numpy.nanpercentile.reshape.astype
time.time.str.encode.hashlib.sha1.hexdigest
time.time.str.encode
all_peptides_df.protein_accession.isin
regression_target.from_ic50.mean
model.NumpyJSONEncoder.model.get_config.json.dumps.model_name.collections.OrderedDict.pandas.Series.to_frame
y.isnan.any
result_df.copy.reset_index
hit_df.groupby.tpm.max
class1_affinity_predictor.Class1AffinityPredictor.fit_allele_specific_predictors
ScrambledPredictor
self.__dict__.update
row.model.get_weights
df.supported_peptide.sum
numpy.random.seed
gzip.GzipFile
numpy.expand_dims
random_negative_peptides.RandomNegativePeptides
fasta_path.endswith
mix.replace.upper.split
df.name.str.split
random_negative_peptides.RandomNegativePeptides.get_total_count
position1s.append
self.percentile_ranks
arg_queue.get
tensorflow.greater_equal
write_col
manifest_df.col.isin
shutil.copyfileobj
pandas.DataFrame.min
x1.x1.index.map
metadata.drop_duplicates
self.optimization_info.get
model_names_to_write.self.manifest_df.model_name.isin.self.manifest_df.loc.copy
sample_id.df.dropna
to_differentiate.aligned.str.get.value_counts
col.result_df.isnull.mean
rows.append
unpadded.str.len
new_model.get_layer.set_weights
iedb_df.Authors.map
mhcflurry.encodable_sequences.EncodableSequences.create.isin
collections.OrderedDict.values
join_df.match_index.map
info_df.index.str.strip
result_df.sample.append
tensorflow.math.divide_no_nan
self.allele_to_allele_specific_models.items
df.groupby._excluded.sum
class1_processing_neural_network.Class1ProcessingNeuralNetwork.from_config.get_config
MSEWithInequalities.loss
hla_df.hla.items
self.plan_df.sum
self.plan_summary
class1_neural_network.Class1NeuralNetwork.fit_generator
hit_df.pmid.unique
possible_ensemble.predictions_df.mean
pandas.read_excel.items
class1_processing_neural_network.Class1ProcessingNeuralNetwork
sample_info.index.isin.map
copy.copy.keys
matplotlib.pyplot.subplot
task_results.pandas.DataFrame.T.set_index.to_csv
medians.index.to_series
tensorflow.keras.backend.square
allele_sequences.dropna.set_index
df.allele.isin.copy
input_serialization_module.dump
ValueError.__init__
TqdmUpTo
exclude_df._key.unique
to_differentiate.aligned.str.get.map
df.n_flank.str.len
eval_df.groupby.binder.mean
sub_df.sample_id.unique
numpy.concatenate
mhctools.MixMHCpred
argparse.ArgumentParser.print_help
sklearn.model_selection.StratifiedKFold
downloads.get_current_release
allele_encoding.allele_representations
kwargs.items
df.peptide.str.upper
plan_df.index.map
cls
model.fit_info.setdefault.update
hit_df.groupby.tpm.max.hit_df.hit_id.map.hit_df.tpm.hit_df.loc.sample.drop_duplicates.to_csv
mhcflurry.flanking_encoding.FlankingEncoding
class1_processing_predictor.Class1ProcessingPredictor.add_models
output_activation.init.num_outputs.Dense
load_data_additional_ms
results.append
class1_processing_neural_network.Class1ProcessingNeuralNetwork.from_config
pandas.DataFrame.copy
tensorflow.range
cutoff_count.predictions_df.prediction.nsmallest.index.str.len
pandas.Series
encoded.isnan.any
all_models.append
min
convolutional_activation.size.convolutional_kernel_l1_l2.regularizers.l1_l2.size.i.flank.Conv1D
record.description.split
result_df.peptide.str.upper
df.groupby.measurement_value.count
Class1NeuralNetwork
tensorflow.keras.layers.BatchNormalization
allele_sequences.aligned.map
df.sort_values.dropna.sort_values
df.measurement_source.str.contains
numpy.squeeze
network.peptides_to_network_input
hit_df.groupby.nunique
iedb_df.Description.str.match.isin
time.time
sequence_names.append
pieces.append
self.network.fit
hyperparameters.get.get
backup_arg_queue.get
min_val_loss_iteration.numpy.nan.min_val_loss.min_val_loss.fit_info.self.hyperparameters.i.progress_preamble.strip
self.get_model
sorted.remove
scoring.startswith
hyperparameters.HyperparameterDefaults.extend
held_out_low.set.union
local_parallelism.worker_pool_with_gpu_assignments_from_args.imap_unordered
iedb_df.str.upper
matplotlib.pyplot.xlabel
class1_presentation_predictor.Class1PresentationPredictor.fit
self._current_entry
load_results
sorted.update
MSEModelSelector
peptide.strip.upper
StandardKerasLoss
universe.protein_accession.isin.sample
result_df.sample.sample
sub_df.protein_accession.unique
self.model_name
self.network.make_predict_function
class1_affinity_predictor.Class1AffinityPredictor.add_pan_allele_model
get_downloads_metadata
class1_affinity_predictor.Class1AffinityPredictor.save
common.random_peptides
tensorflow.keras.backend.set_value
result_list.append
class_ii_cols.df.fillna
downloads.get_path
possible_selector.selectors.usable_for_allele
self.predictor.predict

@developer Could please help me check this issue? May I pull a request to fix it? Thank you very much.

timodonnell commented 11 months ago

We just updated a bunch of dependencies so I'm closing this for now but if you are still hitting issues here we would welcome a PR. Thanks.