Script documentation¶
BioCompoundML’s primary script is
bcml.py
BioCompoundML’s primary script is
bcml.py
--input
: Training File Input¶--datain
: Saved Data Input¶--test_input
: Testing File Input¶--train
: Train the model¶--test
: Test the model¶--model
: Output the model to a file¶--dataout
: Output all data structures¶--pred
: Prediction feature¶--proxy
: URL of http/s proxy¶--cluster
: Cluster the training data¶--split_value
: Threshold for classification of prediction feature¶--random
: User defined random seed¶--verbose
: Verbose output¶--experimental
: Extract experimental/computed features from PubChem¶--fingerprint
: Extract CACTVS fingerprints from PubChem¶--chemofeatures
: Run PaDEL-Descriptors¶--user
: User features are provided in training and/or test files¶--distance
: Calculate compound vs. compound distance matrix¶--impute
: Impute missing data using K Nearest Neighbors Imputation¶--selection
: Run Boruta Feature Selection to reduce uninformative features¶--cv
: Run 50% hold-out Cross-Validation 100 times¶