selfies
=======

.. py:module:: selfies

.. autoapi-nested-parse::

   Class to represent SELFIES molecules.



Attributes
----------

.. autoapisummary::

   selfies.SELFIES_VOCAB_SMALL
   selfies.PAD_TOKEN


Classes
-------

.. autoapisummary::

   selfies.Selfies


Module Contents
---------------

.. py:data:: SELFIES_VOCAB_SMALL
   :value: ['[#Branch1]', '[#Branch2]', '[#C]', '[#N]', '[=Branch1]', '[=Branch2]', '[=C]', '[=N]', '[=O]',...


.. py:data:: PAD_TOKEN
   :value: '[nop]'


.. py:class:: Selfies(selfies_vocab = None, **kwargs)

   Bases: :py:obj:`gflownet.envs.sequences.base.SequenceBase`


   :param selfies_vocab: The list of SELFIES tokens to use as the vocabulary.
                         If None (default), the small vocabulary defined in
                         SELFIES_VOCAB_SMALL is used.
   :type selfies_vocab: List[str] | None


   .. py:attribute:: selfies_vocab
      :value: None



   .. py:method:: states2proxy(states)

      Prepare a batch of states for a SELFIES-string proxy.

      The proxy representation is the compact SELFIES string obtained by
      concatenating all non-padding tokens in the sequence.

      :param states: A batch of states in environment format, either as a list of states or as a
                     single tensor.
      :type states: list or tensor

      :returns: *A list containing one SELFIES string per state.*