Command Line Interface¶
seffnet¶
Side Effects Knowledge Graph Embeddings.
seffnet [OPTIONS] COMMAND [ARGS]...
optimize¶
Run the optimization pipeline for a given method and graph.
seffnet optimize [OPTIONS]
Options
-
--input-path
<input_path>
¶ Input graph file. Only accepted edgelist format.
-
--training-path
<training_path>
¶ training graph file. Only accepted edgelist format.
-
--testing-path
<testing_path>
¶ testing graph file. Only accepted edgelist format.
-
--method
<method>
¶ The NRL method to train the model [required]
- Options
node2vec|DeepWalk|HOPE|GraRep|LINE|SDNE
-
--seed
<seed>
¶
-
--prediction-task
<prediction_task>
¶ The prediction task for the model [required]
- Options
link_prediction|node_classification
-
--labels-file
<labels_file>
¶ The labels file for node classification
-
--trials
<trials>
¶ the number of trials done to optimize hyperparameters
-
--dimensions-range
<dimensions_range>
¶ the range of dimensions to be optimized
-
--storage
<storage>
¶ SQL connection string for study database. Example: sqlite:///optuna.db
-
--name
<name>
¶ Name for the study
-
-o
,
--output
<output>
¶ Output study summary
-
--weighted
¶
True if graph is weighted.
-
--classifier-type
<classifier_type>
¶ Choose type of classifier for predictive model
- Options
LR|EN|SVM|RF|ENCV
predict¶
Predict for a given entity.
seffnet predict [OPTIONS] CURIE
Options
-
-n
,
--number-predictions
<number_predictions>
¶
-
-t
,
--result-type
<result_type>
¶ - Options
chemical|phenotype|target
Arguments
-
CURIE
¶
Required argument
predictc¶
Predict for a chemical by SMILES string.
seffnet predictc [OPTIONS] SMILES
Options
-
-n
,
--number-predictions
<number_predictions>
¶
-
-t
,
--result-type
<result_type>
¶ - Options
chemical|phenotype|target
Arguments
-
SMILES
¶
Required argument
repeat¶
Repeat training n times.
seffnet repeat [OPTIONS]
Options
-
--input-path
<input_path>
¶ Input graph file. Only accepted edgelist format.
-
--training-path
<training_path>
¶ training graph file. Only accepted edgelist format.
-
--testing-path
<testing_path>
¶ testing graph file. Only accepted edgelist format.
-
--method
<method>
¶ The NRL method to train the model [required]
- Options
node2vec|DeepWalk|HOPE|GraRep|LINE|SDNE
-
--evaluation-file
<evaluation_file>
¶ The path to save evaluation results.
-
--dimensions
<dimensions>
¶ The dimensions of embeddings.
-
--number-walks
<number_walks>
¶ The number of walks for random-walk methods.
-
--walk-length
<walk_length>
¶ The walk length for random-walk methods.
-
--window-size
<window_size>
¶ The window size for random-walk methods.
-
--p
<p>
¶ The p parameter for node2vec.
-
--q
<q>
¶ The q parameter for node2vec.
-
--alpha
<alpha>
¶ The alpha parameter for SDNE
-
--beta
<beta>
¶ The beta parameter for SDNE
-
--epochs
<epochs>
¶ The epochs for deep learning methods
-
--kstep
<kstep>
¶ The kstep parameter for GraRep
-
--order
<order>
¶ The order parameter for LINE. Could be 1, 2 or 3
-
--n
<n>
¶ number of repeats.
-
--seed
<seed>
¶
-
--weighted
¶
True if graph is weighted.
-
--prediction-task
<prediction_task>
¶ The prediction task for the model [required]
- Options
link_prediction|node_classification
-
--classifier-type
<classifier_type>
¶ Choose type of classifier for predictive model
- Options
LR|EN|SVM|RF|ENCV
-
--randomization
<randomization>
¶ - Options
xswap|random|node_shuffle
train¶
Train my model.
seffnet train [OPTIONS]
Options
-
--input-path
<input_path>
¶ Input graph file. Only accepted edgelist format.
-
--training-path
<training_path>
¶ training graph file. Only accepted edgelist format.
-
--testing-path
<testing_path>
¶ testing graph file. Only accepted edgelist format.
-
--seed
<seed>
¶
-
--method
<method>
¶ The NRL method to train the model [required]
- Options
node2vec|DeepWalk|HOPE|GraRep|LINE|SDNE
-
--evaluation
¶
If true, a testing set will be used to evaluate model.
-
--evaluation-file
<evaluation_file>
¶ The path to save evaluation results.
-
--embeddings-path
<embeddings_path>
¶ The path to save the embeddings file
-
--predictive-model-path
<predictive_model_path>
¶ The path to save the prediction model
-
--training-model-path
<training_model_path>
¶ The path to save the model used for training
-
--dimensions
<dimensions>
¶ The dimensions of embeddings.
-
--number-walks
<number_walks>
¶ The number of walks for random-walk methods.
-
--walk-length
<walk_length>
¶ The walk length for random-walk methods.
-
--window-size
<window_size>
¶ The window size for random-walk methods.
-
--p
<p>
¶ The p parameter for node2vec.
-
--q
<q>
¶ The q parameter for node2vec.
-
--alpha
<alpha>
¶ The alpha parameter for SDNE
-
--beta
<beta>
¶ The beta parameter for SDNE
-
--epochs
<epochs>
¶ The epochs for deep learning methods
-
--kstep
<kstep>
¶ The kstep parameter for GraRep
-
--order
<order>
¶ The order parameter for LINE. Could be 1, 2 or 3
-
--classifier-type
<classifier_type>
¶ Choose type of classifier for predictive model
- Options
LR|EN|SVM|RF|ENCV
-
--weighted
¶
True if graph is weighted.
-
--prediction-task
<prediction_task>
¶ The prediction task for the model [required]
- Options
link_prediction|node_classification
-
--labels-file
<labels_file>
¶ The labels file for node classification
update¶
Update node2vec training model.
seffnet update [OPTIONS]
Options
-
--updated-graph
<updated_graph>
¶ an edgelist containing the graph with new nodes
-
--chemicals-list
<chemicals_list>
¶ a file containing list of chemicals to update the model with
-
--old-graph
<old_graph>
¶ The graph needed to be updated. In pickle format
-
--updated-graph-path
<updated_graph_path>
¶ The path to save the updated fullgraph [required]
-
--chemsim-graph-path
<chemsim_graph_path>
¶ The path to save the chemical similarity graph [required]
-
--training-model-path
<training_model_path>
¶ The path to save the model used for training [required]
-
--new-training-model-path
<new_training_model_path>
¶ the path of the updated training model [required]
-
--embeddings-path
<embeddings_path>
¶ The path to save the embeddings file
-
--predictive-model-path
<predictive_model_path>
¶ The path to save the prediction model
-
--seed
<seed>
¶