Adds missing docs

src/poli/core/chemistry/tdc_black_box.py

@@ -36,6 +36,12 @@ class TDCBlackBox(AbstractBlackBox):
     string_representation : Literal["SMILES", "SELFIES"], optional
         A string (either "SMILES" or "SELFIES") specifying which
         molecule representation you plan to use.
+    alphabet : list[str] | None, optional
+        The alphabet to be used for the SMILES or SELFIES representation.
+        It is common that the alphabet depends on the dataset used, so
+        it is recommended to pass it as an argument. Default is None.
+    max_sequence_length : int, optional
+        The maximum length of the sequence. Default is infinity.
     batch_size : int, optional
         The batch size for simultaneous execution, by default None.
     parallelize : bool, optional

src/poli/objective_repository/albuterol_similarity/register.py

@@ -46,6 +46,12 @@ class AlbuterolSimilarityBlackBox(TDCBlackBox):
     string_representation : Literal["SMILES", "SELFIES"], optional
         A string (either "SMILES" or "SELFIES") specifying which
         molecule representation you plan to use.
+    alphabet : list[str] | None, optional
+        The alphabet to be used for the SMILES or SELFIES representation.
+        It is common that the alphabet depends on the dataset used, so
+        it is recommended to pass it as an argument. Default is None.
+    max_sequence_length : int, optional
+        The maximum length of the sequence. Default is infinity.
     batch_size : int, optional
         The batch size for simultaneous execution, by default None.
     parallelize : bool, optional
@@ -155,6 +161,12 @@ def create(
         ----------
         string_representation : str, optional
             The string representation of the molecules. Must be either 'SMILES' or 'SELFIES'. Default is 'SMILES'.
+        alphabet : list[str] | None, optional
+            The alphabet to be used for the SMILES or SELFIES representation.
+            It is common that the alphabet depends on the dataset used, so
+            it is recommended to pass it as an argument. Default is None.
+        max_sequence_length : int, optional
+            The maximum length of the sequence. Default is infinity.
         seed : int, optional
             Seed for random number generators. If None, no seed is set.
         batch_size : int, optional

src/poli/objective_repository/amlodipine_mpo/register.py

@@ -42,6 +42,12 @@ class AmlodipineMPOBlackBox(TDCBlackBox):
     string_representation : Literal["SMILES", "SELFIES"], optional
         A string (either "SMILES" or "SELFIES") specifying which
         molecule representation you plan to use.
+    alphabet : list[str] | None, optional
+        The alphabet to be used for the SMILES or SELFIES representation.
+        It is common that the alphabet depends on the dataset used, so
+        it is recommended to pass it as an argument. Default is None.
+    max_sequence_length : int, optional
+        The maximum length of the sequence. Default is infinity.
     batch_size : int, optional
         The batch size for simultaneous execution, by default None.
     parallelize : bool, optional
@@ -152,6 +158,12 @@ def create(
         ----------
         string_representation : str, optional
             The string representation of the molecules. Must be either 'SMILES' or 'SELFIES'. Default is 'SMILES'.
+        alphabet : list[str] | None, optional
+            The alphabet to be used for the SMILES or SELFIES representation.
+            It is common that the alphabet depends on the dataset used, so
+            it is recommended to pass it as an argument. Default is None.
+        max_sequence_length : int, optional
+            The maximum length of the sequence. Default is infinity.
         seed : int, optional
             Seed for random number generators. If None, no seed is set.
         batch_size : int, optional

src/poli/objective_repository/celecoxib_rediscovery/register.py

@@ -43,6 +43,12 @@ class CelecoxibRediscoveryBlackBox(TDCBlackBox):
     string_representation : Literal["SMILES", "SELFIES"], optional
         A string (either "SMILES" or "SELFIES") specifying which
         molecule representation you plan to use.
+    alphabet : list[str] | None, optional
+        The alphabet to be used for the SMILES or SELFIES representation.
+        It is common that the alphabet depends on the dataset used, so
+        it is recommended to pass it as an argument. Default is None.
+    max_sequence_length : int, optional
+        The maximum length of the sequence. Default is infinity.
     batch_size : int, optional
         The batch size for simultaneous execution, by default None.
     parallelize : bool, optional
@@ -153,6 +159,12 @@ def create(
         ----------
         string_representation : str, optional
             The string representation of the molecules. Must be either 'SMILES' or 'SELFIES'. Default is 'SMILES'.
+        alphabet : list[str] | None, optional
+            The alphabet to be used for the SMILES or SELFIES representation.
+            It is common that the alphabet depends on the dataset used, so
+            it is recommended to pass it as an argument. Default is None.
+        max_sequence_length : int, optional
+            The maximum length of the sequence. Default is infinity.
         seed : int, optional
             Seed for random number generators. If None, no seed is set.
         batch_size : int, optional

src/poli/objective_repository/drd2_docking/register.py

@@ -43,6 +43,12 @@ class DRD2BlackBox(TDCBlackBox):
     string_representation : Literal["SMILES", "SELFIES"], optional
         A string (either "SMILES" or "SELFIES") specifying which
         molecule representation you plan to use.
+    alphabet : list[str] | None, optional
+        The alphabet to be used for the SMILES or SELFIES representation.
+        It is common that the alphabet depends on the dataset used, so
+        it is recommended to pass it as an argument. Default is None.
+    max_sequence_length : int, optional
+        The maximum length of the sequence. Default is infinity.
     batch_size : int, optional
         The batch size for simultaneous execution, by default None.
     parallelize : bool, optional
@@ -153,6 +159,12 @@ def create(
         ----------
         string_representation : str, optional
             The string representation of the molecules. Must be either 'SMILES' or 'SELFIES'. Default is 'SMILES'.
+        alphabet : list[str] | None, optional
+            The alphabet to be used for the SMILES or SELFIES representation.
+            It is common that the alphabet depends on the dataset used, so
+            it is recommended to pass it as an argument. Default is None.
+        max_sequence_length : int, optional
+            The maximum length of the sequence. Default is infinity.
         seed : int, optional
             Seed for random number generators. If None, no seed is set.
         batch_size : int, optional

src/poli/objective_repository/drd3_docking/register.py

@@ -31,6 +31,12 @@ class DRD3BlackBox(TDCBlackBox):
     string_representation : Literal["SMILES", "SELFIES"], optional
         A string (either "SMILES" or "SELFIES") specifying which
         molecule representation you plan to use.
+    alphabet : list[str] | None, optional
+        The alphabet to be used for the SMILES or SELFIES representation.
+        It is common that the alphabet depends on the dataset used, so
+        it is recommended to pass it as an argument. Default is None.
+    max_sequence_length : int, optional
+        The maximum length of the sequence. Default is infinity.
     batch_size : int, optional
         The batch size for simultaneous execution, by default None.
     parallelize : bool, optional
@@ -121,6 +127,12 @@ def create(
         ----------
         string_representation : str, optional
             The string representation of the molecules. Must be either 'SMILES' or 'SELFIES'. Default is 'SMILES'.
+        alphabet : list[str] | None, optional
+            The alphabet to be used for the SMILES or SELFIES representation.
+            It is common that the alphabet depends on the dataset used, so
+            it is recommended to pass it as an argument. Default is None.
+        max_sequence_length : int, optional
+            The maximum length of the sequence. Default is infinity.
         seed : int, optional
             Seed for random number generators. If None, no seed is set.
         batch_size : int, optional

src/poli/objective_repository/fexofenadine_mpo/register.py

@@ -42,6 +42,12 @@ class FexofenadineMPOBlackBox(TDCBlackBox):
     string_representation : Literal["SMILES", "SELFIES"], optional
         A string (either "SMILES" or "SELFIES") specifying which
         molecule representation you plan to use.
+    alphabet : list[str] | None, optional
+        The alphabet to be used for the SMILES or SELFIES representation.
+        It is common that the alphabet depends on the dataset used, so
+        it is recommended to pass it as an argument. Default is None.
+    max_sequence_length : int, optional
+        The maximum length of the sequence. Default is infinity.
     batch_size : int, optional
         The batch size for simultaneous execution, by default None.
     parallelize : bool, optional
@@ -150,6 +156,12 @@ def create(
         ----------
         string_representation : str, optional
             The string representation of the molecules. Must be either 'SMILES' or 'SELFIES'. Default is 'SMILES'.
+        alphabet : list[str] | None, optional
+            The alphabet to be used for the SMILES or SELFIES representation.
+            It is common that the alphabet depends on the dataset used, so
+            it is recommended to pass it as an argument. Default is None.
+        max_sequence_length : int, optional
+            The maximum length of the sequence. Default is infinity.
         seed : int, optional
             Seed for random number generators. If None, no seed is set.
         batch_size : int, optional

src/poli/objective_repository/gsk3_beta/register.py

@@ -48,6 +48,12 @@ class GSK3BetaBlackBox(TDCBlackBox):
     string_representation : Literal["SMILES", "SELFIES"], optional
         A string (either "SMILES" or "SELFIES") specifying which
         molecule representation you plan to use.
+    alphabet : list[str] | None, optional
+        The alphabet to be used for the SMILES or SELFIES representation.
+        It is common that the alphabet depends on the dataset used, so
+        it is recommended to pass it as an argument. Default is None.
+    max_sequence_length : int, optional
+        The maximum length of the sequence. Default is infinity.
     batch_size : int, optional
         The batch size for simultaneous execution, by default None.
     parallelize : bool, optional
@@ -170,6 +176,12 @@ def create(
         ----------
         string_representation : str, optional
             The string representation of the molecules. Must be either 'SMILES' or 'SELFIES'. Default is 'SMILES'.
+        alphabet : list[str] | None, optional
+            The alphabet to be used for the SMILES or SELFIES representation.
+            It is common that the alphabet depends on the dataset used, so
+            it is recommended to pass it as an argument. Default is None.
+        max_sequence_length : int, optional
+            The maximum length of the sequence. Default is infinity.
         seed : int, optional
             Seed for random number generators. If None, no seed is set.
         batch_size : int, optional

src/poli/objective_repository/isomer_c7h8n2o2/register.py

@@ -42,6 +42,12 @@ class IsomerC7H8N2O2BlackBox(TDCBlackBox):
     string_representation : Literal["SMILES", "SELFIES"], optional
         A string (either "SMILES" or "SELFIES") specifying which
         molecule representation you plan to use.
+    alphabet : list[str] | None, optional
+        The alphabet to be used for the SMILES or SELFIES representation.
+        It is common that the alphabet depends on the dataset used, so
+        it is recommended to pass it as an argument. Default is None.
+    max_sequence_length : int, optional
+        The maximum length of the sequence. Default is infinity.
     batch_size : int, optional
         The batch size for simultaneous execution, by default None.
     parallelize : bool, optional
@@ -150,6 +156,12 @@ def create(
         ----------
         string_representation : str, optional
             The string representation of the molecules. Must be either 'SMILES' or 'SELFIES'. Default is 'SMILES'.
+        alphabet : list[str] | None, optional
+            The alphabet to be used for the SMILES or SELFIES representation.
+            It is common that the alphabet depends on the dataset used, so
+            it is recommended to pass it as an argument. Default is None.
+        max_sequence_length : int, optional
+            The maximum length of the sequence. Default is infinity.
         seed : int, optional
             Seed for random number generators. If None, no seed is set.
         batch_size : int, optional

src/poli/objective_repository/isomer_c9h10n2o2pf2cl/register.py

@@ -43,6 +43,12 @@ class IsomerC9H10N2O2PF2ClBlackBox(TDCBlackBox):
     string_representation : Literal["SMILES", "SELFIES"], optional
         A string (either "SMILES" or "SELFIES") specifying which
         molecule representation you plan to use.
+    alphabet : list[str] | None, optional
+        The alphabet to be used for the SMILES or SELFIES representation.
+        It is common that the alphabet depends on the dataset used, so
+        it is recommended to pass it as an argument. Default is None.
+    max_sequence_length : int, optional
+        The maximum length of the sequence. Default is infinity.
     batch_size : int, optional
         The batch size for simultaneous execution, by default None.
     parallelize : bool, optional
@@ -153,6 +159,12 @@ def create(
         ----------
         string_representation : str, optional
             The string representation of the molecules. Must be either 'SMILES' or 'SELFIES'. Default is 'SMILES'.
+        alphabet : list[str] | None, optional
+            The alphabet to be used for the SMILES or SELFIES representation.
+            It is common that the alphabet depends on the dataset used, so
+            it is recommended to pass it as an argument. Default is None.
+        max_sequence_length : int, optional
+            The maximum length of the sequence. Default is infinity.
         seed : int, optional
             Seed for random number generators. If None, no seed is set.
         batch_size : int, optional

src/poli/objective_repository/jnk3/register.py

@@ -46,6 +46,12 @@ class JNK3BlackBox(TDCBlackBox):
     string_representation : Literal["SMILES", "SELFIES"], optional
         A string (either "SMILES" or "SELFIES") specifying which
         molecule representation you plan to use.
+    alphabet : list[str] | None, optional
+        The alphabet to be used for the SMILES or SELFIES representation.
+        It is common that the alphabet depends on the dataset used, so
+        it is recommended to pass it as an argument. Default is None.
+    max_sequence_length : int, optional
+        The maximum length of the sequence. Default is infinity.
     batch_size : int, optional
         The batch size for simultaneous execution, by default None.
     parallelize : bool, optional
@@ -166,6 +172,12 @@ def create(
         ----------
         string_representation : str, optional
             The string representation of the molecules. Must be either 'SMILES' or 'SELFIES'. Default is 'SMILES'.
+        alphabet : list[str] | None, optional
+            The alphabet to be used for the SMILES or SELFIES representation.
+            It is common that the alphabet depends on the dataset used, so
+            it is recommended to pass it as an argument. Default is None.
+        max_sequence_length : int, optional
+            The maximum length of the sequence. Default is infinity.
         seed : int, optional
             Seed for random number generators. If None, no seed is set.
         batch_size : int, optional

src/poli/objective_repository/median_1/register.py

@@ -41,6 +41,12 @@ class Median1BlackBox(TDCBlackBox):
     string_representation : Literal["SMILES", "SELFIES"], optional
         A string (either "SMILES" or "SELFIES") specifying which
         molecule representation you plan to use.
+    alphabet : list[str] | None, optional
+        The alphabet to be used for the SMILES or SELFIES representation.
+        It is common that the alphabet depends on the dataset used, so
+        it is recommended to pass it as an argument. Default is None.
+    max_sequence_length : int, optional
+        The maximum length of the sequence. Default is infinity.
     batch_size : int, optional
         The batch size for simultaneous execution, by default None.
     parallelize : bool, optional
@@ -149,6 +155,12 @@ def create(
         ----------
         string_representation : str, optional
             The string representation of the molecules. Must be either 'SMILES' or 'SELFIES'. Default is 'SMILES'.
+        alphabet : list[str] | None, optional
+            The alphabet to be used for the SMILES or SELFIES representation.
+            It is common that the alphabet depends on the dataset used, so
+            it is recommended to pass it as an argument. Default is None.
+        max_sequence_length : int, optional
+            The maximum length of the sequence. Default is infinity.
         seed : int, optional
             Seed for random number generators. If None, no seed is set.
         batch_size : int, optional

src/poli/objective_repository/median_2/register.py

@@ -40,6 +40,12 @@ class Median2BlackBox(TDCBlackBox):
     string_representation : Literal["SMILES", "SELFIES"], optional
         A string (either "SMILES" or "SELFIES") specifying which
         molecule representation you plan to use.
+    alphabet : list[str] | None, optional
+        The alphabet to be used for the SMILES or SELFIES representation.
+        It is common that the alphabet depends on the dataset used, so
+        it is recommended to pass it as an argument. Default is None.
+    max_sequence_length : int, optional
+        The maximum length of the sequence. Default is infinity.
     batch_size : int, optional
         The batch size for simultaneous execution, by default None.
     parallelize : bool, optional
@@ -148,6 +154,12 @@ def create(
         ----------
         string_representation : str, optional
             The string representation of the molecules. Must be either 'SMILES' or 'SELFIES'. Default is 'SMILES'.
+        alphabet : list[str] | None, optional
+            The alphabet to be used for the SMILES or SELFIES representation.
+            It is common that the alphabet depends on the dataset used, so
+            it is recommended to pass it as an argument. Default is None.
+        max_sequence_length : int, optional
+            The maximum length of the sequence. Default is infinity.
         seed : int, optional
             Seed for random number generators. If None, no seed is set.
         batch_size : int, optional

src/poli/objective_repository/mestranol_similarity/register.py

@@ -45,6 +45,12 @@ class MestranolSimilarityBlackBox(TDCBlackBox):
     string_representation : Literal["SMILES", "SELFIES"], optional
         A string (either "SMILES" or "SELFIES") specifying which
         molecule representation you plan to use.
+    alphabet : list[str] | None, optional
+        The alphabet to be used for the SMILES or SELFIES representation.
+        It is common that the alphabet depends on the dataset used, so
+        it is recommended to pass it as an argument. Default is None.
+    max_sequence_length : int, optional
+        The maximum length of the sequence. Default is infinity.
     batch_size : int, optional
         The batch size for simultaneous execution, by default None.
     parallelize : bool, optional
@@ -153,6 +159,12 @@ def create(
         ----------
         string_representation : str, optional
             The string representation of the molecules. Must be either 'SMILES' or 'SELFIES'. Default is 'SMILES'.
+        alphabet : list[str] | None, optional
+            The alphabet to be used for the SMILES or SELFIES representation.
+            It is common that the alphabet depends on the dataset used, so
+            it is recommended to pass it as an argument. Default is None.
+        max_sequence_length : int, optional
+            The maximum length of the sequence. Default is infinity.
         seed : int, optional
             Seed for random number generators. If None, no seed is set.
         batch_size : int, optional