gt4sd.algorithms.conditional_generation.guacamol.implementation.smiles_lstm_hc module

Recurrent Neural Networks with Hill Climbing algorithm implementation.

Summary

Classes:

SMILESLSTMHC

Reference

class SMILESLSTMHC(model_path, smi_file, max_len, n_jobs, keep_top, n_epochs, mols_to_sample, optimize_n_epochs, benchmark_num_samples, optimize_batch_size, random_start)[source]

Bases: object

__init__(model_path, smi_file, max_len, n_jobs, keep_top, n_epochs, mols_to_sample, optimize_n_epochs, benchmark_num_samples, optimize_batch_size, random_start)[source]

Initialize SMILESLSTMHC.

Parameters

  • model_path (str) – path to load the model.

  • smi_file – path to load the hypothesis, candidate labels and, optionally, the smiles file.

  • max_len (int) – maximum length of a SMILES string.

  • n_jobs (int) – number of concurrently running jobs.

  • keep_top (int) – molecules kept each step.

  • n_epochs (int) – number of epochs to sample.

  • mols_to_sample (int) – molecules sampled at each step.

  • optimize_n_epochs (int) – number of epochs for the optimization.

  • benchmark_num_samples (int) – number of molecules to generate from final model for the benchmark.

  • optimize_batch_size (int) – batch size for the optimization.

  • random_start (bool) – set to True to randomly choose list of SMILES for generating optimized molecules.

get_generator()[source]

Create an instance of the SmilesRnnDirectedGenerator.

Return type

SmilesRnnDirectedGenerator

Returns

an instance of SmilesRnnDirectedGenerator.

__dict__ = mappingproxy({'__module__': 'gt4sd.algorithms.conditional_generation.guacamol.implementation.smiles_lstm_hc', '__init__': <function SMILESLSTMHC.__init__>, 'get_generator': <function SMILESLSTMHC.get_generator>, '__dict__': <attribute '__dict__' of 'SMILESLSTMHC' objects>, '__weakref__': <attribute '__weakref__' of 'SMILESLSTMHC' objects>, '__doc__': None, '__annotations__': {}})
__doc__ = None
__module__ = 'gt4sd.algorithms.conditional_generation.guacamol.implementation.smiles_lstm_hc'
__weakref__

list of weak references to the object (if defined)