protac_degradation_predictor package

Subpackages

protac_degradation_predictor.optuna package

Submodules

protac_degradation_predictor.config module

class protac_degradation_predictor.config.Config(morgan_radius: int = 10, fingerprint_size: int = 256, protein_embedding_size: int = 1024, cell_embedding_size: int = 768, dmax_threshold: float = 0.6, pdc50_threshold: float = 6.0, active_label: str = 'Active (Dmax 0.6, pDC50 6.0)', e3_ligase2uniprot: dict = <factory>)

Bases: object

Parameters:

morgan_radius (int)
fingerprint_size (int)
protein_embedding_size (int)
cell_embedding_size (int)
dmax_threshold (float)
pdc50_threshold (float)
active_label (str)
e3_ligase2uniprot (dict)

morgan_radius: int = 10

fingerprint_size: int = 256

protein_embedding_size: int = 1024

cell_embedding_size: int = 768

dmax_threshold: float = 0.6

pdc50_threshold: float = 6.0

active_label: str = 'Active (Dmax 0.6, pDC50 6.0)'

e3_ligase2uniprot: dict

protac_degradation_predictor.data_utils module

protac_degradation_predictor.data_utils.avail_e3_ligases()

Get the available E3 ligases.

Returns:: The available E3 ligases.
Return type:: List[str]

protac_degradation_predictor.data_utils.avail_cell_lines()

Get the available cell lines.

Returns:: The available cell lines.
Return type:: List[str]

protac_degradation_predictor.data_utils.avail_uniprots()

Get the available Uniprot IDs.

Returns:: The available Uniprot IDs.
Return type:: List[str]

protac_degradation_predictor.data_utils.get_fingerprint(smiles, morgan_fpgen=None)

Get the Morgan fingerprint of a molecule.

Parameters:

smiles (str) – The SMILES string of the molecule.
morgan_fpgen – The Morgan fingerprint generator.

Returns:

The Morgan fingerprint.

Return type:

np.ndarray

protac_degradation_predictor.data_utils.is_active(DC50, Dmax, pDC50_threshold=7.0, Dmax_threshold=0.8, oring=False)

Check if a PROTAC is active based on DC50 and Dmax. :param DC50: DC50 in nM :type DC50: float :param Dmax: Dmax in % :type Dmax: float

Returns:

True if active, False if inactive, np.nan if either DC50 or Dmax is NaN

Return type:

bool

Parameters:

DC50 (float)
Dmax (float)
pDC50_threshold (float)
Dmax_threshold (float)
oring (bool)

protac_degradation_predictor.data_utils.load_curated_dataset()

Load the curated PROTAC dataset as described in the paper: https://arxiv.org/abs/2406.02637

Returns:: The curated PROTAC dataset.
Return type:: pd.DataFrame

protac_degradation_predictor.optuna_utils module

protac_degradation_predictor.optuna_utils.get_dataframe_stats(train_df=None, val_df=None, test_df=None, active_label='Active')

Get some statistics from the dataframes.

Parameters:

train_df (pd.DataFrame) – The training set.
val_df (pd.DataFrame) – The validation set.
test_df (pd.DataFrame) – The test set.

Return type:

Dict

protac_degradation_predictor.optuna_utils.get_majority_vote_metrics(test_preds, test_df, active_label='Active')

Get the majority vote metrics.

Parameters:

test_preds (List)
test_df (DataFrame)
active_label (str)

Return type:

Dict

protac_degradation_predictor.optuna_utils.get_suggestion(trial, dtype, hparams_range)

protac_degradation_predictor.optuna_utils.pytorch_model_objective(trial, protein2embedding, cell2embedding, smiles2fp, train_val_df, kf, groups=None, test_df=None, hparams_ranges=None, fast_dev_run=False, active_label='Active', disabled_embeddings=[], max_epochs=100, use_logger=False, logger_save_dir='logs', logger_name='cv_model', enable_checkpointing=False)

Objective function for hyperparameter optimization.

Parameters:

trial (optuna.Trial) – The Optuna trial object.
train_df (pd.DataFrame) – The training set.
val_df (pd.DataFrame) – The validation set.
hparams_ranges (List[Dict[str, Any]]) – NOT IMPLEMENTED YET. Hyperparameters ranges. The list must be of a tuple of the type of hparam to suggest (‘int’, ‘float’, or ‘categorical’), and the dictionary must contain the arguments of the corresponding trial.suggest method.
fast_dev_run (bool) – Whether to run a fast development run.
active_label (str) – The active label column.
disabled_embeddings (List[str]) – The list of disabled embeddings.
protein2embedding (Dict)
cell2embedding (Dict)
smiles2fp (Dict)
train_val_df (DataFrame)
kf (StratifiedKFold | StratifiedGroupKFold)
groups (array | None)
test_df (DataFrame | None)
max_epochs (int)
use_logger (bool)
logger_save_dir (str)
logger_name (str)
enable_checkpointing (bool)

Return type:

float

protac_degradation_predictor.optuna_utils.hyperparameter_tuning_and_training(protein2embedding, cell2embedding, smiles2fp, train_val_df, test_df, kf, groups=None, split_type='standard', n_models_for_test=3, fast_dev_run=False, n_trials=50, logger_save_dir='logs', logger_name='protac_hparam_search', active_label='Active', max_epochs=100, study_filename=None, force_study=False)

Hyperparameter tuning and training of a PROTAC model.

Parameters:

protein2embedding (Dict) – The protein to embedding dictionary.
cell2embedding (Dict) – The cell to embedding dictionary.
smiles2fp (Dict) – The SMILES to fingerprint dictionary.
train_val_df (pd.DataFrame) – The training and validation set.
test_df (pd.DataFrame) – The test set.
kf (StratifiedKFold | StratifiedGroupKFold) – The KFold object.
groups (np.array) – The groups for the StratifiedGroupKFold.
split_type (str) – The split type of the current study. Used for reporting.
n_models_for_test (int) – The number of models to train for the test set.
fast_dev_run (bool) – Whether to run a fast development run.
n_trials (int) – The number of trials for the hyperparameter search.
logger_save_dir (str) – The logger save directory.
logger_name (str) – The logger name.
active_label (str) – The active label column.
max_epochs (int) – The maximum number of epochs.
study_filename (str) – The study filename.
force_study (bool) – Whether to force the study.

Returns:

The trained model, the trainer, and the best metrics.

Return type:

tuple

protac_degradation_predictor.optuna_utils_xgboost module

protac_degradation_predictor.optuna_utils_xgboost.get_confidence_scores(y, y_pred, threshold=0.5)

protac_degradation_predictor.optuna_utils_xgboost.train_and_evaluate_xgboost(protein2embedding, cell2embedding, smiles2fp, train_df, val_df, params, test_df=None, active_label='Active', num_boost_round=100, shuffle_train_data=False)

Train and evaluate an XGBoost model with the given parameters.

Parameters:

train_df (pd.DataFrame) – The training and validation data.
test_df (pd.DataFrame) – The test data.
params (dict) – Hyperparameters for the XGBoost model.
active_label (str) – The active label column.
num_boost_round (int) – Maximum number of epochs.
protein2embedding (Dict)
cell2embedding (Dict)
smiles2fp (Dict)
val_df (DataFrame)
shuffle_train_data (bool)

Returns:

The trained model, test predictions, and metrics.

Return type:

tuple

protac_degradation_predictor.optuna_utils_xgboost.xgboost_model_objective(trial, protein2embedding, cell2embedding, smiles2fp, train_val_df, kf, groups=None, active_label='Active', num_boost_round=100, model_name=None)

Objective function for hyperparameter optimization with XGBoost.

Parameters:

trial (optuna.Trial) – The Optuna trial object.
train_val_df (pd.DataFrame) – The training and validation data.
kf (StratifiedKFold) – Stratified K-Folds cross-validator.
test_df (Optional[pd.DataFrame]) – The test data.
active_label (str) – The active label column.
num_boost_round (int) – Maximum number of epochs.
model_name (Optional[str]) – The prefix name of the CV models to save, if supplied. Used as: f”{model_name}_fold_{k}.json”
protein2embedding (Dict)
cell2embedding (Dict)
smiles2fp (Dict)
groups (array | None)

Return type:

float

protac_degradation_predictor.optuna_utils_xgboost.xgboost_hyperparameter_tuning_and_training(protein2embedding, cell2embedding, smiles2fp, train_val_df, test_df, kf, groups=None, split_type='random', n_models_for_test=3, n_trials=50, active_label='Active', num_boost_round=100, study_filename=None, force_study=False, model_name=None)

Hyperparameter tuning and training of an XGBoost model.

Parameters:

train_val_df (pd.DataFrame) – The training and validation data.
test_df (pd.DataFrame) – The test data.
kf (StratifiedKFold) – Stratified K-Folds cross-validator.
groups (Optional[np.array]) – Group labels for the samples used while splitting the dataset into train/test set.
split_type (str) – Type of the data split. Used for reporting information.
n_models_for_test (int) – Number of models to train for testing.
fast_dev_run (bool) – Whether to run a fast development run.
n_trials (int) – Number of trials for hyperparameter optimization.
logger_save_dir (str) – Directory to save logs.
logger_name (str) – Name of the logger.
active_label (str) – The active label column.
num_boost_round (int) – Maximum number of epochs.
study_filename (Optional[str]) – File name to save/load the Optuna study.
force_study (bool) – Whether to force the study optimization even if the study file exists.
protein2embedding (Dict)
cell2embedding (Dict)
smiles2fp (Dict)
model_name (str | None)

Returns:

A dictionary containing reports from the CV and test.

Return type:

dict

protac_degradation_predictor.protac_dataset module

class protac_degradation_predictor.protac_dataset.PROTAC_Dataset(protac_df, protein2embedding, cell2embedding, smiles2fp, use_smote=False, oversampler=None, active_label='Active', disabled_embeddings=[], scaler=None, use_single_scaler=None, shuffle_embedding_prob=0.0)

Bases: Dataset

Parameters:

protac_df (DataFrame)
protein2embedding (Dict[str, ndarray])
cell2embedding (Dict[str, ndarray])
smiles2fp (Dict[str, ndarray])
use_smote (bool)
oversampler (SMOTE | ADASYN | None)
active_label (str)
disabled_embeddings (List[Literal['smiles', 'poi', 'e3', 'cell']])
scaler (StandardScaler | Dict[str, StandardScaler] | None)
use_single_scaler (bool | None)
shuffle_embedding_prob (float)

get_smiles_emb_dim()

get_protein_emb_dim()

get_cell_emb_dim()

apply_smote()

fit_scaling(use_single_scaler=False, **scaler_kwargs)

Fit the scalers for the data and save them in the dataset class.

Parameters:

use_single_scaler (bool) – Whether to use a single scaler for all features.
scaler_kwargs – Keyword arguments for the StandardScaler.

Returns:

The fitted scalers.

Return type:

dict

apply_scaling(scalers, use_single_scaler=False)

Apply scaling to the data.

Parameters:

scalers (dict) – The scalers for each feature.
use_single_scaler (bool) – Whether to use a single scaler for all features.

get_numpy_arrays(component=None)

Get the numpy arrays for the dataset.

Parameters:: component (str) – The component to get the numpy arrays for. Defaults to None, i.e., get a single stacked array.
Returns:: The numpy arrays for the dataset. The first element is the input array, and the second element is the output array.
Return type:: tuple

protac_degradation_predictor.protac_dataset.get_datasets(train_df, val_df, test_df=None, protein2embedding=None, cell2embedding=None, smiles2fp=None, smote_k_neighbors=5, active_label='Active', disabled_embeddings=[], scaler=None, use_single_scaler=None, apply_scaling=False, shuffle_embedding_prob=0.0)

Get the datasets for training the PROTAC model.

Parameters:

train_df (pd.DataFrame) – The training data.
val_df (pd.DataFrame) – The validation data.
test_df (pd.DataFrame) – The test data.
protein2embedding (dict) – Dictionary of protein embeddings.
cell2embedding (dict) – Dictionary of cell line embeddings.
smiles2fp (dict) – Dictionary of SMILES to fingerprint.
use_smote (bool) – Whether to use SMOTE for oversampling.
smote_k_neighbors (int) – The number of neighbors to use for SMOTE.
active_label (str) – The active label column.
disabled_embeddings (list) – The list of embeddings to disable.
scaler (StandardScaler | dict) – The scaler to use for the embeddings.
use_single_scaler (bool) – Whether to use a single scaler for all features.
apply_scaling (bool) – Whether to apply scaling to the data now. Defaults to False (the Pytorch Lightning model does that).
shuffle_embedding_prob (float)

Return type:

Tuple[PROTAC_Dataset, PROTAC_Dataset, PROTAC_Dataset | None]

class protac_degradation_predictor.protac_dataset.PROTAC_DataModule(*args, **kwargs)

Bases: LightningDataModule

PyTorch Lightning DataModule for the PROTAC dataset.

TODO: Work in progress. It would be nice to wrap all information into a single class, but it is not clear how to do it yet due to cross-validation and the need to split the data into training, validation, and test sets accordingly.

Parameters:

protac_csv_filepath (str) – The path to the PROTAC CSV file.
protein2embedding_filepath (str) – The path to the protein to embedding dictionary.
cell2embedding_filepath (str) – The path to the cell line to embedding dictionary.
pDC50_threshold (float) – The threshold for the pDC50 value to consider a PROTAC active.
Dmax_threshold (float) – The threshold for the Dmax value to consider a PROTAC active.
use_smote (bool) – Whether to use SMOTE for oversampling.
smote_k_neighbors (int) – The number of neighbors to use for SMOTE.
active_label (str) – The column containing the active/inactive information.
disabled_embeddings (list) – The list of embeddings to disable.
scaler (StandardScaler | dict) – The scaler to use for the embeddings.
use_single_scaler (bool) – Whether to use a single scaler for all features.

setup(stage)

Parameters:: stage (str)

train_dataloader()

val_dataloader()

test_dataloader()

static get_random_split_indices(active_df, test_split)

Get the indices of the test set using a random split.

Parameters:

active_df (pd.DataFrame) – The DataFrame containing the active PROTACs.
test_split (float) – The percentage of the active PROTACs to use as the test set.

Returns:

The indices of the test set.

Return type:

pd.Index

static get_e3_ligase_split_indices(active_df)

Get the indices of the test set using the E3 ligase split.

Parameters:: active_df (pd.DataFrame) – The DataFrame containing the active PROTACs.
Returns:: The indices of the test set.
Return type:: pd.Index

static get_smiles2fp_and_avg_tanimoto(protac_df)

Get the SMILES to fingerprint dictionary and the average Tanimoto similarity.

Parameters:: protac_df (pd.DataFrame) – The DataFrame containing the PROTACs.
Returns:: The SMILES to fingerprint dictionary and the average Tanimoto similarity.
Return type:: tuple

static get_tanimoto_split_indices(active_df, active_label, test_split, n_bins_tanimoto=200)

Get the indices of the test set using the Tanimoto-based split.

Parameters:

active_df (pd.DataFrame) – The DataFrame containing the active PROTACs.
n_bins_tanimoto (int) – The number of bins to use for the Tanimoto similarity.
active_label (str)
test_split (float)

Returns:

The indices of the test set.

Return type:

pd.Index

static get_target_split_indices(active_df, active_label, test_split)

Get the indices of the test set using the target-based split.

Parameters:

active_df (pd.DataFrame) – The DataFrame containing the active PROTACs.
active_label (str) – The column containing the active/inactive information.
test_split (float) – The percentage of the active PROTACs to use as the test set.

Returns:

The indices of the test set.

Return type:

pd.Index

protac_degradation_predictor.protac_degradation_predictor module

protac_degradation_predictor.protac_degradation_predictor.get_protac_active_proba(protac_smiles, e3_ligase, target_uniprot, cell_line, device='cpu', use_models_from_cv=False, use_xgboost_models=False, study_type='standard')

Predict the probability of a PROTAC being active.

Parameters:

protac_smiles (str | List[str]) – The SMILES of the PROTAC.
e3_ligase (str | List[str]) – The Uniprot ID of the E3 ligase.
target_uniprot (str | List[str]) – The Uniprot ID of the target protein.
cell_line (str | List[str]) – The cell line identifier.
device (str) – The device to run the model on.
use_models_from_cv (bool) – Whether to use the models from cross-validation.
use_xgb_models (bool) – Whether to use the XGBoost models.
study_type (str) – Use models trained on the specified study. Options are ‘standard’, ‘similarity’, ‘target’.
use_xgboost_models (bool)

Returns:

The predictions of the model. The dictionary contains the following: ‘preds’, ‘mean’, ‘majority_vote’. The ‘preds’ key contains the predictions of all models with shape: (n_models, batch_size), ‘mean’ contains the mean prediction, and ‘majority_vote’ contains the majority vote.

Return type:

Dict[str, np.ndarray]

protac_degradation_predictor.protac_degradation_predictor.is_protac_active(protac_smiles, e3_ligase, target_uniprot, cell_line, device='cpu', proba_threshold=0.5, use_majority_vote=False, use_models_from_cv=False, use_xgboost_models=False, study_type='standard')

Predict whether a PROTAC is active or not.

Parameters:

protac_smiles (str) – The SMILES of the PROTAC.
e3_ligase (str) – The Uniprot ID of the E3 ligase.
target_uniprot (str) – The Uniprot ID of the target protein.
cell_line (str) – The cell line identifier.
device (str) – The device to run the model on.
proba_threshold (float) – The probability threshold.
use_majority_vote (bool) – Whether to use the majority vote.
use_models_from_cv (bool) – Whether to use the models from cross-validation.
use_xgboost_models (bool) – Whether to use the XGBoost models.
study_type (str) – Use models trained on the specified study. Options are ‘standard’, ‘similarity’, ‘target’.

Returns:

Whether the PROTAC is active or not.

Return type:

bool

protac_degradation_predictor.protac_degradation_predictor.get_protac_embedding(protac_smiles, e3_ligase, target_uniprot, cell_line, device='cpu', use_models_from_cv=False, study_type='standard')

Get the embeddings of a PROTAC or a list of PROTACs.

Parameters:

protac_smiles (str | List[str]) – The SMILES of the PROTAC.
e3_ligase (str | List[str]) – The Uniprot ID of the E3 ligase.
target_uniprot (str | List[str]) – The Uniprot ID of the target protein.
cell_line (str | List[str]) – The cell line identifier.
device (str) – The device to run the model on.
use_models_from_cv (bool) – Whether to use the models from cross-validation.
study_type (str) – Use models trained on the specified study. Options are ‘standard’, ‘similarity’, ‘target’.

Returns:

The embeddings of the given PROTAC. Each key is the name of the model and the value is the embedding, of shape: (batch_size, model_hidden_size). NOTE: Each model has its own hidden size, so the embeddings might have different dimensions.

Return type:

Dict[str, np.ndarray]

protac_degradation_predictor.pytorch_models module

class protac_degradation_predictor.pytorch_models.PROTAC_Predictor(hidden_dim, smiles_emb_dim=256, poi_emb_dim=1024, e3_emb_dim=1024, cell_emb_dim=768, dropout=0.2, join_embeddings='sum', use_batch_norm=False, disabled_embeddings=[])

Bases: Module

Parameters:

hidden_dim (int)
smiles_emb_dim (int)
poi_emb_dim (int)
e3_emb_dim (int)
cell_emb_dim (int)
dropout (float)
join_embeddings (Literal['beginning', 'concat', 'sum'])
use_batch_norm (bool)
disabled_embeddings (List[Literal['smiles', 'poi', 'e3', 'cell']])

forward(poi_emb, e3_emb, cell_emb, smiles_emb, return_embeddings=False)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

T_destination = ~T_destination

add_module(name, module)

Adds a child module to the current module.

The module can be accessed as an attribute using the given name.

Parameters:

name (str) – name of the child module. The child module can be accessed from this module using the given name
module (Module) – child module to be added to the module.

Return type:

None

apply(fn)

Applies fn recursively to every submodule (as returned by .children()) as well as self. Typical use includes initializing the parameters of a model (see also nn-init-doc).

Parameters:

fn (Module -> None) – function to be applied to each submodule
self (T)

Returns:

self

Return type:

Module

Example:

>>> @torch.no_grad()
>>> def init_weights(m):
>>>     print(m)
>>>     if type(m) == nn.Linear:
>>>         m.weight.fill_(1.0)
>>>         print(m.weight)
>>> net = nn.Sequential(nn.Linear(2, 2), nn.Linear(2, 2))
>>> net.apply(init_weights)
Linear(in_features=2, out_features=2, bias=True)
Parameter containing:
tensor([[1., 1.],
        [1., 1.]], requires_grad=True)
Linear(in_features=2, out_features=2, bias=True)
Parameter containing:
tensor([[1., 1.],
        [1., 1.]], requires_grad=True)
Sequential(
  (0): Linear(in_features=2, out_features=2, bias=True)
  (1): Linear(in_features=2, out_features=2, bias=True)
)

bfloat16()

Casts all floating point parameters and buffers to bfloat16 datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module
Parameters:: self (T)

buffers(recurse=True)

Returns an iterator over module buffers.

Parameters:: recurse (bool) – if True, then yields buffers of this module and all submodules. Otherwise, yields only buffers that are direct members of this module.
Yields:: torch.Tensor – module buffer
Return type:: Iterator[Tensor]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for buf in model.buffers():
>>>     print(type(buf), buf.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)

call_super_init: bool = False

children()

Returns an iterator over immediate children modules.

Yields:: Module – a child module
Return type:: Iterator[Module]

cpu()

Moves all model parameters and buffers to the CPU.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module
Parameters:: self (T)

cuda(device=None)

Moves all model parameters and buffers to the GPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on GPU while being optimized.

Note

This method modifies the module in-place.

Parameters:

device (int, optional) – if specified, all parameters will be copied to that device
self (T)

Returns:

self

Return type:

Module

double()

Casts all floating point parameters and buffers to double datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module
Parameters:: self (T)

dump_patches: bool = False

eval()

Sets the module in evaluation mode.

This has any effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g. Dropout, BatchNorm, etc.

This is equivalent with self.train(False).

See locally-disable-grad-doc for a comparison between .eval() and several similar mechanisms that may be confused with it.

Returns:: self
Return type:: Module
Parameters:: self (T)

extra_repr()

Set the extra representation of the module

To print customized extra information, you should re-implement this method in your own modules. Both single-line and multi-line strings are acceptable.

Return type:: str

float()

Casts all floating point parameters and buffers to float datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module
Parameters:: self (T)

get_buffer(target)

Returns the buffer given by target if it exists, otherwise throws an error.

See the docstring for get_submodule for a more detailed explanation of this method’s functionality as well as how to correctly specify target.

Parameters:: target (str) – The fully-qualified string name of the buffer to look for. (See get_submodule for how to specify a fully-qualified string.)
Returns:: The buffer referenced by target
Return type:: torch.Tensor
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not a buffer

get_extra_state()

Returns any extra state to include in the module’s state_dict. Implement this and a corresponding set_extra_state() for your module if you need to store extra state. This function is called when building the module’s state_dict().

Note that extra state should be picklable to ensure working serialization of the state_dict. We only provide provide backwards compatibility guarantees for serializing Tensors; other objects may break backwards compatibility if their serialized pickled form changes.

Returns:: Any extra state to store in the module’s state_dict
Return type:: object

get_parameter(target)

Returns the parameter given by target if it exists, otherwise throws an error.

See the docstring for get_submodule for a more detailed explanation of this method’s functionality as well as how to correctly specify target.

Parameters:: target (str) – The fully-qualified string name of the Parameter to look for. (See get_submodule for how to specify a fully-qualified string.)
Returns:: The Parameter referenced by target
Return type:: torch.nn.Parameter
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not an nn.Parameter

get_submodule(target)

Returns the submodule given by target if it exists, otherwise throws an error.

For example, let’s say you have an nn.Module A that looks like this:

A(
    (net_b): Module(
        (net_c): Module(
            (conv): Conv2d(16, 33, kernel_size=(3, 3), stride=(2, 2))
        )
        (linear): Linear(in_features=100, out_features=200, bias=True)
    )
)

(The diagram shows an nn.Module A. A has a nested submodule net_b, which itself has two submodules net_c and linear. net_c then has a submodule conv.)

To check whether or not we have the linear submodule, we would call get_submodule("net_b.linear"). To check whether we have the conv submodule, we would call get_submodule("net_b.net_c.conv").

The runtime of get_submodule is bounded by the degree of module nesting in target. A query against named_modules achieves the same result, but it is O(N) in the number of transitive modules. So, for a simple check to see if some submodule exists, get_submodule should always be used.

Parameters:: target (str) – The fully-qualified string name of the submodule to look for. (See above example for how to specify a fully-qualified string.)
Returns:: The submodule referenced by target
Return type:: torch.nn.Module
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not an nn.Module

half()

Casts all floating point parameters and buffers to half datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module
Parameters:: self (T)

ipu(device=None)

Moves all model parameters and buffers to the IPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on IPU while being optimized.

Note

This method modifies the module in-place.

Parameters:

device (int, optional) – if specified, all parameters will be copied to that device
self (T)

Returns:

self

Return type:

Module

load_state_dict(state_dict, strict=True)

Copies parameters and buffers from state_dict into this module and its descendants. If strict is True, then the keys of state_dict must exactly match the keys returned by this module’s state_dict() function.

Parameters:

state_dict (dict) – a dict containing parameters and persistent buffers.
strict (bool, optional) – whether to strictly enforce that the keys in state_dict match the keys returned by this module’s state_dict() function. Default: True

Returns:

missing_keys is a list of str containing the missing keys
unexpected_keys is a list of str containing the unexpected keys

Return type:

NamedTuple with missing_keys and unexpected_keys fields

Note

If a parameter or buffer is registered as None and its corresponding key exists in state_dict, load_state_dict() will raise a RuntimeError.

modules()

Returns an iterator over all modules in the network.

Yields:: Module – a module in the network
Return type:: Iterator[Module]

Note

Duplicate modules are returned only once. In the following example, l will be returned only once.

Example:

>>> l = nn.Linear(2, 2)
>>> net = nn.Sequential(l, l)
>>> for idx, m in enumerate(net.modules()):
...     print(idx, '->', m)

0 -> Sequential(
  (0): Linear(in_features=2, out_features=2, bias=True)
  (1): Linear(in_features=2, out_features=2, bias=True)
)
1 -> Linear(in_features=2, out_features=2, bias=True)

named_buffers(prefix='', recurse=True, remove_duplicate=True)

Returns an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.

Parameters:

prefix (str) – prefix to prepend to all buffer names.
recurse (bool, optional) – if True, then yields buffers of this module and all submodules. Otherwise, yields only buffers that are direct members of this module. Defaults to True.
remove_duplicate (bool, optional) – whether to remove the duplicated buffers in the result. Defaults to True.

Yields:

(str, torch.Tensor) – Tuple containing the name and buffer

Return type:

Iterator[Tuple[str, Tensor]]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, buf in self.named_buffers():
>>>     if name in ['running_var']:
>>>         print(buf.size())

named_children()

Returns an iterator over immediate children modules, yielding both the name of the module as well as the module itself.

Yields:: (str, Module) – Tuple containing a name and child module
Return type:: Iterator[Tuple[str, Module]]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, module in model.named_children():
>>>     if name in ['conv4', 'conv5']:
>>>         print(module)

named_modules(memo=None, prefix='', remove_duplicate=True)

Returns an iterator over all modules in the network, yielding both the name of the module as well as the module itself.

Parameters:

memo (Set[Module] | None) – a memo to store the set of modules already added to the result
prefix (str) – a prefix that will be added to the name of the module
remove_duplicate (bool) – whether to remove the duplicated module instances in the result or not

Yields:

(str, Module) – Tuple of name and module

Note

Duplicate modules are returned only once. In the following example, l will be returned only once.

Example:

>>> l = nn.Linear(2, 2)
>>> net = nn.Sequential(l, l)
>>> for idx, m in enumerate(net.named_modules()):
...     print(idx, '->', m)

0 -> ('', Sequential(
  (0): Linear(in_features=2, out_features=2, bias=True)
  (1): Linear(in_features=2, out_features=2, bias=True)
))
1 -> ('0', Linear(in_features=2, out_features=2, bias=True))

named_parameters(prefix='', recurse=True, remove_duplicate=True)

Returns an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.

Parameters:

prefix (str) – prefix to prepend to all parameter names.
recurse (bool) – if True, then yields parameters of this module and all submodules. Otherwise, yields only parameters that are direct members of this module.
remove_duplicate (bool, optional) – whether to remove the duplicated parameters in the result. Defaults to True.

Yields:

(str, Parameter) – Tuple containing the name and parameter

Return type:

Iterator[Tuple[str, Parameter]]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, param in self.named_parameters():
>>>     if name in ['bias']:
>>>         print(param.size())

parameters(recurse=True)

Returns an iterator over module parameters.

This is typically passed to an optimizer.

Parameters:: recurse (bool) – if True, then yields parameters of this module and all submodules. Otherwise, yields only parameters that are direct members of this module.
Yields:: Parameter – module parameter
Return type:: Iterator[Parameter]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for param in model.parameters():
>>>     print(type(param), param.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)

register_backward_hook(hook)

Registers a backward hook on the module.

This function is deprecated in favor of register_full_backward_hook() and the behavior of this function will change in future versions.

Returns:: a handle that can be used to remove the added hook by calling handle.remove()
Return type:: torch.utils.hooks.RemovableHandle
Parameters:: hook (Callable[[Module, Tuple[Tensor, ...] | Tensor, Tuple[Tensor, ...] | Tensor], None | Tuple[Tensor, ...] | Tensor])

register_buffer(name, tensor, persistent=True)

Adds a buffer to the module.

This is typically used to register a buffer that should not to be considered a model parameter. For example, BatchNorm’s running_mean is not a parameter, but is part of the module’s state. Buffers, by default, are persistent and will be saved alongside parameters. This behavior can be changed by setting persistent to False. The only difference between a persistent buffer and a non-persistent buffer is that the latter will not be a part of this module’s state_dict.

Buffers can be accessed as attributes using given names.

Parameters:

name (str) – name of the buffer. The buffer can be accessed from this module using the given name
tensor (Tensor or None) – buffer to be registered. If None, then operations that run on buffers, such as cuda, are ignored. If None, the buffer is not included in the module’s state_dict.
persistent (bool) – whether the buffer is part of this module’s state_dict.

Return type:

None

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> self.register_buffer('running_mean', torch.zeros(num_features))

register_forward_hook(hook, *, prepend=False, with_kwargs=False)

Registers a forward hook on the module.

The hook will be called every time after forward() has computed an output.

If with_kwargs is False or not specified, the input contains only the positional arguments given to the module. Keyword arguments won’t be passed to the hooks and only to the forward. The hook can modify the output. It can modify the input inplace but it will not have effect on forward since this is called after forward() is called. The hook should have the following signature:

hook(module, args, output) -> None or modified output

If with_kwargs is True, the forward hook will be passed the kwargs given to the forward function and be expected to return the output possibly modified. The hook should have the following signature:

hook(module, args, kwargs, output) -> None or modified output

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If True, the provided hook will be fired before all existing forward hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing forward hooks on this torch.nn.modules.Module. Note that global forward hooks registered with register_module_forward_hook() will fire before all hooks registered by this method. Default: False
with_kwargs (bool) – If True, the hook will be passed the kwargs given to the forward function. Default: False

Returns:

a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_forward_pre_hook(hook, *, prepend=False, with_kwargs=False)

Registers a forward pre-hook on the module.

The hook will be called every time before forward() is invoked.

If with_kwargs is false or not specified, the input contains only the positional arguments given to the module. Keyword arguments won’t be passed to the hooks and only to the forward. The hook can modify the input. User can either return a tuple or a single modified value in the hook. We will wrap the value into a tuple if a single value is returned (unless that value is already a tuple). The hook should have the following signature:

hook(module, args) -> None or modified input

If with_kwargs is true, the forward pre-hook will be passed the kwargs given to the forward function. And if the hook modifies the input, both the args and kwargs should be returned. The hook should have the following signature:

hook(module, args, kwargs) -> None or a tuple of modified input and kwargs

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing forward_pre hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing forward_pre hooks on this torch.nn.modules.Module. Note that global forward_pre hooks registered with register_module_forward_pre_hook() will fire before all hooks registered by this method. Default: False
with_kwargs (bool) – If true, the hook will be passed the kwargs given to the forward function. Default: False

Returns:

a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_full_backward_hook(hook, prepend=False)

Registers a backward hook on the module.

The hook will be called every time the gradients with respect to a module are computed, i.e. the hook will execute if and only if the gradients with respect to module outputs are computed. The hook should have the following signature:

hook(module, grad_input, grad_output) -> tuple(Tensor) or None

The grad_input and grad_output are tuples that contain the gradients with respect to the inputs and outputs respectively. The hook should not modify its arguments, but it can optionally return a new gradient with respect to the input that will be used in place of grad_input in subsequent computations. grad_input will only correspond to the inputs given as positional arguments and all kwarg arguments are ignored. Entries in grad_input and grad_output will be None for all non-Tensor arguments.

For technical reasons, when this hook is applied to a Module, its forward function will receive a view of each Tensor passed to the Module. Similarly the caller will receive a view of each Tensor returned by the Module’s forward function.

Warning

Modifying inputs or outputs inplace is not allowed when using backward hooks and will raise an error.

Parameters:

hook (Callable) – The user-defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing backward hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing backward hooks on this torch.nn.modules.Module. Note that global backward hooks registered with register_module_full_backward_hook() will fire before all hooks registered by this method.

Returns:

a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_full_backward_pre_hook(hook, prepend=False)

Registers a backward pre-hook on the module.

The hook will be called every time the gradients for the module are computed. The hook should have the following signature:

hook(module, grad_output) -> Tensor or None

The grad_output is a tuple. The hook should not modify its arguments, but it can optionally return a new gradient with respect to the output that will be used in place of grad_output in subsequent computations. Entries in grad_output will be None for all non-Tensor arguments.

For technical reasons, when this hook is applied to a Module, its forward function will receive a view of each Tensor passed to the Module. Similarly the caller will receive a view of each Tensor returned by the Module’s forward function.

Warning

Modifying inputs inplace is not allowed when using backward hooks and will raise an error.

Parameters:

hook (Callable) – The user-defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing backward_pre hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing backward_pre hooks on this torch.nn.modules.Module. Note that global backward_pre hooks registered with register_module_full_backward_pre_hook() will fire before all hooks registered by this method.

Returns:

a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_load_state_dict_post_hook(hook)

Registers a post hook to be run after module’s load_state_dict is called.

It should have the following signature::: hook(module, incompatible_keys) -> None

The module argument is the current module that this hook is registered on, and the incompatible_keys argument is a NamedTuple consisting of attributes missing_keys and unexpected_keys. missing_keys is a list of str containing the missing keys and unexpected_keys is a list of str containing the unexpected keys.

The given incompatible_keys can be modified inplace if needed.

Note that the checks performed when calling load_state_dict() with strict=True are affected by modifications the hook makes to missing_keys or unexpected_keys, as expected. Additions to either set of keys will result in an error being thrown when strict=True, and clearing out both missing and unexpected keys will avoid an error.

Returns:: a handle that can be used to remove the added hook by calling handle.remove()
Return type:: torch.utils.hooks.RemovableHandle

register_module(name, module)

Alias for add_module().

Parameters:

name (str)
module (Module | None)

Return type:

None

register_parameter(name, param)

Adds a parameter to the module.

The parameter can be accessed as an attribute using given name.

Parameters:

name (str) – name of the parameter. The parameter can be accessed from this module using the given name
param (Parameter or None) – parameter to be added to the module. If None, then operations that run on parameters, such as cuda, are ignored. If None, the parameter is not included in the module’s state_dict.

Return type:

None

register_state_dict_pre_hook(hook): These hooks will be called with arguments: self, prefix, and keep_vars before calling state_dict on self. The registered hooks can be used to perform pre-processing before the state_dict call is made.

requires_grad_(requires_grad=True)

Change if autograd should record operations on parameters in this module.

This method sets the parameters’ requires_grad attributes in-place.

This method is helpful for freezing part of the module for finetuning or training parts of a model individually (e.g., GAN training).

See locally-disable-grad-doc for a comparison between .requires_grad_() and several similar mechanisms that may be confused with it.

Parameters:

requires_grad (bool) – whether autograd should record operations on parameters in this module. Default: True.
self (T)

Returns:

self

Return type:

Module

set_extra_state(state)

This function is called from load_state_dict() to handle any extra state found within the state_dict. Implement this function and a corresponding get_extra_state() for your module if you need to store extra state within its state_dict.

Parameters:: state (dict) – Extra state from the state_dict

share_memory()

See torch.Tensor.share_memory_()

Parameters:: self (T)
Return type:: T

state_dict(*args, destination=None, prefix='', keep_vars=False)

Returns a dictionary containing references to the whole state of the module.

Both parameters and persistent buffers (e.g. running averages) are included. Keys are corresponding parameter and buffer names. Parameters and buffers set to None are not included.

Note

The returned object is a shallow copy. It contains references to the module’s parameters and buffers.

Warning

Currently state_dict() also accepts positional arguments for destination, prefix and keep_vars in order. However, this is being deprecated and keyword arguments will be enforced in future releases.

Warning

Please avoid the use of argument destination as it is not designed for end-users.

Parameters:

destination (dict, optional) – If provided, the state of module will be updated into the dict and the same object is returned. Otherwise, an OrderedDict will be created and returned. Default: None.
prefix (str, optional) – a prefix added to parameter and buffer names to compose the keys in state_dict. Default: ''.
keep_vars (bool, optional) – by default the Tensor s returned in the state dict are detached from autograd. If it’s set to True, detaching will not be performed. Default: False.

Returns:

a dictionary containing a whole state of the module

Return type:

dict

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> module.state_dict().keys()
['bias', 'weight']

to(*args, **kwargs)

Moves and/or casts the parameters and buffers.

This can be called as

to(device=None, dtype=None, non_blocking=False)

to(dtype, non_blocking=False)

to(tensor, non_blocking=False)

to(memory_format=torch.channels_last)

Its signature is similar to torch.Tensor.to(), but only accepts floating point or complex dtypes. In addition, this method will only cast the floating point or complex parameters and buffers to dtype (if given). The integral parameters and buffers will be moved device, if that is given, but with dtypes unchanged. When non_blocking is set, it tries to convert/move asynchronously with respect to the host if possible, e.g., moving CPU Tensors with pinned memory to CUDA devices.

See below for examples.

Note

This method modifies the module in-place.

Parameters:

device (torch.device) – the desired device of the parameters and buffers in this module
dtype (torch.dtype) – the desired floating point or complex dtype of the parameters and buffers in this module
tensor (torch.Tensor) – Tensor whose dtype and device are the desired dtype and device for all parameters and buffers in this module
memory_format (torch.memory_format) – the desired memory format for 4D parameters and buffers in this module (keyword only argument)

Returns:

self

Return type:

Module

Examples:

>>> # xdoctest: +IGNORE_WANT("non-deterministic")
>>> linear = nn.Linear(2, 2)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
        [-0.5113, -0.2325]])
>>> linear.to(torch.double)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
        [-0.5113, -0.2325]], dtype=torch.float64)
>>> # xdoctest: +REQUIRES(env:TORCH_DOCTEST_CUDA1)
>>> gpu1 = torch.device("cuda:1")
>>> linear.to(gpu1, dtype=torch.half, non_blocking=True)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
        [-0.5112, -0.2324]], dtype=torch.float16, device='cuda:1')
>>> cpu = torch.device("cpu")
>>> linear.to(cpu)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
        [-0.5112, -0.2324]], dtype=torch.float16)

>>> linear = nn.Linear(2, 2, bias=None).to(torch.cdouble)
>>> linear.weight
Parameter containing:
tensor([[ 0.3741+0.j,  0.2382+0.j],
        [ 0.5593+0.j, -0.4443+0.j]], dtype=torch.complex128)
>>> linear(torch.ones(3, 2, dtype=torch.cdouble))
tensor([[0.6122+0.j, 0.1150+0.j],
        [0.6122+0.j, 0.1150+0.j],
        [0.6122+0.j, 0.1150+0.j]], dtype=torch.complex128)

to_empty(*, device)

Moves the parameters and buffers to the specified device without copying storage.

Parameters:

device (torch.device) – The desired device of the parameters and buffers in this module.
self (T)

Returns:

self

Return type:

Module

train(mode=True)

Sets the module in training mode.

This has any effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g. Dropout, BatchNorm, etc.

Parameters:

mode (bool) – whether to set training mode (True) or evaluation mode (False). Default: True.
self (T)

Returns:

self

Return type:

Module

type(dst_type)

Casts all parameters and buffers to dst_type.

Note

This method modifies the module in-place.

Parameters:

dst_type (type or string) – the desired type
self (T)

Returns:

self

Return type:

Module

xpu(device=None)

Moves all model parameters and buffers to the XPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on XPU while being optimized.

Note

This method modifies the module in-place.

Parameters:

device (int, optional) – if specified, all parameters will be copied to that device
self (T)

Returns:

self

Return type:

Module

zero_grad(set_to_none=True)

Sets gradients of all model parameters to zero. See similar function under torch.optim.Optimizer for more context.

Parameters:: set_to_none (bool) – instead of setting to zero, set the grads to None. See torch.optim.Optimizer.zero_grad() for details.
Return type:: None

training: bool

class protac_degradation_predictor.pytorch_models.PROTAC_Model(*args, **kwargs)

Bases: LightningModule

Parameters:

hidden_dim (int)
smiles_emb_dim (int)
poi_emb_dim (int)
e3_emb_dim (int)
cell_emb_dim (int)
batch_size (int)
learning_rate (float)
dropout (float)
use_batch_norm (bool)
join_embeddings (Literal['beginning', 'concat', 'sum'])
train_dataset (PROTAC_Dataset)
val_dataset (PROTAC_Dataset)
test_dataset (PROTAC_Dataset)
disabled_embeddings (List[Literal['smiles', 'poi', 'e3', 'cell']])
apply_scaling (bool)
extra_optim_params (dict | None)

initialize_scalers(): Initialize or reinitialize scalers based on dataset properties.

apply_scalers(): Apply scalers to all datasets.

scale_tensor(tensor, scaler, alpha=1e-10)

Scale a tensor using a scaler. This is done to avoid using numpy arrays (and stay on the same device).

Parameters:

tensor (torch.Tensor) – The tensor to scale.
scaler (StandardScaler) – The scaler to use.
alpha (float)

Returns:

The scaled tensor.

Return type:

torch.Tensor

forward(poi_emb, e3_emb, cell_emb, smiles_emb, prescaled_embeddings=True, return_embeddings=False)

step(batch, batch_idx, stage)

training_step(batch, batch_idx)

validation_step(batch, batch_idx)

test_step(batch, batch_idx)

configure_optimizers()

predict_step(batch, batch_idx)

train_dataloader()

val_dataloader()

test_dataloader()

on_save_checkpoint(checkpoint): Serialize the scalers to the checkpoint.

on_load_checkpoint(checkpoint): Deserialize the scalers from the checkpoint.

protac_degradation_predictor.pytorch_models.get_confidence_scores(true_ds, y_preds, threshold=0.5)

Get the mean value of the predictions for the false positives and false negatives.

Parameters:

true_ds (PROTAC_Dataset | torch.Tensor | np.ndarray) – The true labels
y_preds (torch.Tensor | np.ndarray) – The predictions
threshold (float) – The threshold to use for the predictions

Returns:

The mean value of the predictions for the false positives and false negatives.

Return type:

Tuple[float, float]

protac_degradation_predictor.pytorch_models.train_model(protein2embedding, cell2embedding, smiles2fp, train_df, val_df, test_df=None, hidden_dim=768, batch_size=128, learning_rate=2e-05, beta1=0.9, beta2=0.999, eps=1e-08, dropout=0.2, max_epochs=50, use_batch_norm=False, join_embeddings='sum', smote_k_neighbors=5, apply_scaling=True, active_label='Active', fast_dev_run=False, use_logger=True, logger_save_dir='../logs', logger_name='protac', enable_checkpointing=False, checkpoint_model_name='protac', disabled_embeddings=[], return_predictions=False, shuffle_embedding_prob=0.0, use_smote=False)

Train a PROTAC model using the given datasets and hyperparameters.

Parameters:

protein2embedding (dict) – A dictionary mapping protein identifiers to embeddings.
cell2embedding (dict) – A dictionary mapping cell line identifiers to embeddings.
smiles2fp (dict) – A dictionary mapping SMILES strings to fingerprints.
train_df (pd.DataFrame) – The training dataframe.
val_df (pd.DataFrame) – The validation dataframe.
test_df (Optional[pd.DataFrame]) – The test dataframe.
hidden_dim (int) – The hidden dimension of the model
batch_size (int) – The batch size
learning_rate (float) – The learning rate
dropout (float) – The dropout rate
max_epochs (int) – The maximum number of epochs
use_batch_norm (bool) – Whether to use batch normalization
join_embeddings (Literal['beginning', 'concat', 'sum']) – How to join the embeddings
smote_k_neighbors (int) – The number of neighbors to use in SMOTE
use_smote (bool) – Whether to use SMOTE
apply_scaling (bool) – Whether to apply scaling to the embeddings
active_label (str) – The name of the active label. Default: ‘Active’
fast_dev_run (bool) – Whether to run a fast development run (see PyTorch Lightning documentation)
use_logger (bool) – Whether to use a logger
logger_save_dir (str) – The directory to save the logs
logger_name (str) – The name of the logger
enable_checkpointing (bool) – Whether to enable checkpointing
checkpoint_model_name (str) – The name of the model for checkpointing
disabled_embeddings (list) – List of disabled embeddings. Can be ‘poi’, ‘e3’, ‘cell’, ‘smiles’
return_predictions (bool) – Whether to return predictions on the validation and test sets
beta1 (float)
beta2 (float)
eps (float)
shuffle_embedding_prob (float)

Returns:

The trained model, the trainer, and the metrics over the validation and test sets.

Return type:

tuple

protac_degradation_predictor.pytorch_models.evaluate_model(model, trainer, val_ds, test_ds=None, batch_size=128)

Evaluate a PROTAC model using the given datasets.

Parameters:

model (PROTAC_Model)
trainer (pytorch_lightning.Trainer)
val_ds (PROTAC_Dataset)
test_ds (PROTAC_Dataset | None)
batch_size (int)

Return type:

tuple

protac_degradation_predictor.pytorch_models.load_model(ckpt_path)

Load a PROTAC model from a checkpoint.

Parameters:: ckpt_path (str) – The path to the checkpoint.
Returns:: The loaded model.
Return type:: PROTAC_Model

protac_degradation_predictor.sklearn_models module

protac_degradation_predictor.sklearn_models.train_sklearn_model(clf, protein2embedding, cell2embedding, smiles2fp, train_df, val_df, test_df=None, active_label='Active', use_single_scaler=True)

Train a classifier model on train and val sets and evaluate it on a test set.

Parameters:

clf (ClassifierMixin) – The classifier model to train and evaluate.
train_df (pd.DataFrame) – The training set.
val_df (pd.DataFrame) – The validation set.
test_df (Optional[pd.DataFrame]) – The test set.
protein2embedding (Dict)
cell2embedding (Dict)
smiles2fp (Dict)
active_label (str)
use_single_scaler (bool)

Returns:

The trained model and the metrics.

Return type:

Tuple[ClassifierMixin, nn.ModuleDict]

protac_degradation_predictor.sklearn_models.suggest_random_forest(trial)

Suggest hyperparameters for a Random Forest classifier.

Parameters:: trial (optuna.Trial) – The Optuna trial object.
Returns:: The Random Forest classifier with the suggested hyperparameters.
Return type:: ClassifierMixin

protac_degradation_predictor.sklearn_models.suggest_logistic_regression(trial)

Suggest hyperparameters for a Logistic Regression classifier.

Parameters:: trial (optuna.Trial) – The Optuna trial object.
Returns:: The Logistic Regression classifier with the suggested hyperparameters.
Return type:: ClassifierMixin

protac_degradation_predictor.sklearn_models.suggest_svc(trial)

Suggest hyperparameters for an SVC classifier.

Parameters:: trial (optuna.Trial) – The Optuna trial object.
Returns:: The SVC classifier with the suggested hyperparameters.
Return type:: ClassifierMixin

protac_degradation_predictor.sklearn_models.suggest_gradient_boosting(trial)

Suggest hyperparameters for a Gradient Boosting classifier.

Parameters:: trial (optuna.Trial) – The Optuna trial object.
Returns:: The Gradient Boosting classifier with the suggested hyperparameters.
Return type:: ClassifierMixin

protac_degradation_predictor package

Subpackages

Submodules

protac_degradation_predictor.config module

protac_degradation_predictor.data_utils module

protac_degradation_predictor.optuna_utils module

protac_degradation_predictor.optuna_utils_xgboost module

protac_degradation_predictor.protac_dataset module

protac_degradation_predictor.protac_degradation_predictor module

protac_degradation_predictor.pytorch_models module

protac_degradation_predictor.sklearn_models module

Module contents