Updates the documentation to the new API

Author: miguelgondu

docs/protein-optimization/contributing/a_new_problem.md

@@ -56,8 +56,8 @@ from your_local_dependency import ...
 
 
 class YourBlackBox(AbstractBlackBox):
-    def __init__(self, L: int = np.inf):
-        super().__init__(L=L)
+    def __init__(self, info: ProblemSetupInformation, batch_size: int = None):
+        super().__init__(info=info, batch_size=batch_size)
 
     # The only method you have to define
     def _black_box(self, x: np.ndarray, context: dict = None) -> np.ndarray:
@@ -66,11 +66,8 @@ class YourBlackBox(AbstractBlackBox):
 
 class YourProblemFactory(AbstractProblemFactory):
     def get_setup_information(self) -> ProblemSetupInformation:
-        # The tokens of your alphabet
-        alphabet_symbols = [...]
-        
-        # The encoding
-        alphabet = {symbol: i for i, symbol in enumerate(alphabet_symbols)}
+        # Your alphabet
+        alphabet = [...]
 
         # A description of the problem
         # See more in the chapter about defining
@@ -92,12 +89,12 @@ class YourProblemFactory(AbstractProblemFactory):
         ...
 
         # The maximum length you defined above
-        L = self.get_setup_information().get_max_sequence_length()
+        problem_info = self.get_setup_information()
 
         # Creating your black box function
-        f = YourBlackBox(L=L)
+        f = YourBlackBox(info=problem_info)
 
-        # Your first input (an np.array)
+        # Your first input (an np.array[str])
         x0 = ...
 
         return f, x0, f(x0)
@@ -145,6 +142,8 @@ dependencies:
 This environment will be created (if it doesn't exist yet), and will be used to run `register.py`.
 
 :::{admonition} Why `conda`?
+:class: dropdown
+
 Conda environments can be quite good! For example, the `super_mario_bros` environment contains a Java runtime. This is the `environment.yml` for said problem:
 
 ```yml
@@ -189,7 +188,7 @@ $ python -c "from poli.core.registry import get_problems; print(get_problems())"
 Your problem is not registered yet, so don't fret. You can check _if_ you can register it by running
 
 ```bash
-$ python -c "from poli.objective_repository import AVAILABLE_OBJECTIVES; print(AVAILABLE_OBJECTIVES)"
+$ python -c "from poli.core.registry import get_problems; print(get_problems(include_repository=True))"
 [..., "your_problem", ...]   # If all goes well, you should see "your_problem" here.
 ```
 

docs/protein-optimization/index.md

@@ -79,6 +79,12 @@ Solvent accessibility of mutations of a wildtype using `foldx`
 Rapid Stability Predictions of single mutations from a wildtype. [WIP]
 :::
 
+:::{grid-item-card} RFP Fluorescence Protein Stability (using `lambo`)
+:link: ./using_poli/objective_repository/foldx_rfp_lambo.html
+:columns: 6
+LaMBO Fluorescence (RFP) by stability and solvent-accessible surface area.
+:::
+
 ::::
 
 

docs/protein-optimization/using_poli/objective_repository/aloha.md

@@ -22,7 +22,7 @@ from poli import objective_factory
 problem_info, f, x0, y0, run_info = objective_factory.create(name="aloha")
 
 # Example input:
-x = np.array([["A", "L", "O", "O", "F"]])  # must be of shape [b, L], in this case [1, 3].
+x = np.array([["A", "L", "O", "O", "F"]])  # must be of shape [b, L], in this case [1, 5].
 
 # Querying:
 print(f(x))  # Should be 3 (A, L, and the first O).

docs/protein-optimization/using_poli/objective_repository/foldx_sasa.md

@@ -46,15 +46,13 @@ problem_info, f, x0, y0, run_info = objective_factory.create(
     wildtype_pdb_file=wildtype_pdb_file
 )
 
-# Example input:
+# Example input: (an array of strings)
 print(x0)
 
 # Querying:
 print(y0)  # The stability of your wildtype
 ```
 
-You could also pass an `alphabet: Dict[str, int]` to the create method. By default, [we use this encoding](https://github.com/MachineLearningLifeScience/poli/blob/44cad2a5c95f209aeb24d4893d162b3359ca91a3/src/poli/core/util/proteins/defaults.py#L1).
-
 :::
 
 :::{tab-item} In isolation
@@ -94,4 +92,7 @@ Registering the objective function in this way will create a `conda` environment
 
 :::
 
-::::
+::::
+
+You could also pass an `alphabet: List[str]` to the create method. By default, [we use this encoding](https://github.com/MachineLearningLifeScience/poli/blob/44cad2a5c95f209aeb24d4893d162b3359ca91a3/src/poli/core/util/proteins/defaults.py#L1).
+

docs/protein-optimization/using_poli/objective_repository/foldx_stability.md

@@ -46,15 +46,13 @@ problem_info, f, x0, y0, run_info = objective_factory.create(
     wildtype_pdb_file=wildtype_pdb_file
 )
 
-# Example input:
+# Example input: (an array of strings)
 print(x0)
 
 # Querying:
 print(y0)  # The stability of your wildtype
 ```
 
-You could also pass an `alphabet: Dict[str, int]` to the create method. By default, [we use this encoding](https://github.com/MachineLearningLifeScience/poli/blob/44cad2a5c95f209aeb24d4893d162b3359ca91a3/src/poli/core/util/proteins/defaults.py#L1).
-
 :::
 
 :::{tab-item} In isolation
@@ -94,4 +92,6 @@ Registering the objective function in this way will create a `conda` environment
 
 :::
 
-::::
+::::
+
+You could also pass an `alphabet: List[str]` to the create method. By default, [we use this encoding](https://github.com/MachineLearningLifeScience/poli/blob/44cad2a5c95f209aeb24d4893d162b3359ca91a3/src/poli/core/util/proteins/defaults.py#L1).

docs/protein-optimization/using_poli/objective_repository/rdkit_logp.md

@@ -5,19 +5,11 @@
 
 ## About
 
-This objective function returns the Quantitative Estimate of Druglikeness (QED) using `RDKit`. During creation, you can specify whether you are measuring the QED of a SMILES string, or a SELFIES.
+This objective function returns the partition coefficient of a solute between octanol and water (known as logP) using `RDKit`. You can specify whether you are measuring the logP of a SMILES string, or a SELFIES.
 
 ## Prerequisites
 
-- An alphabet of tokens `{str: int}` as a json file. For example, in the case of SELFIES, this file would be
-```json
-# alphabet_selfies.json
-{
-    "": 0,       # an empty padding
-    "[C]": 1,
-    ...
-}
-```
+- You will need to specify an alphabet `List[str]`.
 
 ## How to run
 
@@ -36,24 +28,23 @@ pip install rdkit selfies
 Then run
 
 ```python
-from pathlib import Path
-
 import numpy as np
 
 from poli import objective_factory
 
-# The path to your alphabet
-path_to_alphabet = Path("path/to/alphabet_selfies.json")
+# Your alphabet
+alphabet = ["", "[C]", ...]
 
 # How to create
 problem_info, f, x0, y0, run_info = objective_factory.create(
     name="rdkit_logp",
-    path_to_alphabet=path_to_alphabet,
-    string_representation="SELFIES"  # it is "SMILES" by default.
-    )
+    alphabet=alphabet,
+    string_representation="SELFIES",  # it is "SMILES" by default.
+    force_register=True, 
+)
 
 # Example input: a single carbon
-x = np.array([[1]])
+x = np.array(["[C]"]).reshape(1, -1)
 
 # Querying:
 print(f(x))  # Should be close to 0.6361
@@ -73,19 +64,19 @@ import numpy as np
 from poli import objective_factory
 
 
-# The path to your alphabet
-path_to_alphabet = Path("path/to/alphabet_selfies.json")
+# Your alphabet
+alphabet = ["", "[C]", ...]
 
 # How to create
 problem_info, f, x0, y0, run_info = objective_factory.create(
     name="rdkit_logp",
-    path_to_alphabet=path_to_alphabet,
-    string_representation="SELFIES"  # it is "SMILES" by default.
+    alphabet=alphabet,
+    string_representation="SELFIES",  # it is "SMILES" by default.
     force_register=True, 
 )
 
 # Example input: a single carbon
-x = np.array([[1]])
+x = np.array(["[C]"]).reshape(1, -1)
 
 # Querying:
 print(f(x))  # Should be close to 0.6361

docs/protein-optimization/using_poli/objective_repository/rdkit_qed.md

@@ -5,19 +5,11 @@
 
 ## About
 
-This objective function returns the Quantitative Estimate of Druglikeness (QED) using `RDKit`. During creation, you can specify whether you are measuring the QED of a SMILES string, or a SELFIES.
+This objective function returns the Quantitative Estimate of Druglikeness (QED) using `RDKit`. You can specify whether you are measuring the QED of a SMILES string, or a SELFIES.
 
 ## Prerequisites
 
-- An alphabet of tokens `{str: int}` as a json file. For example, in the case of SELFIES, this file would be
-```json
-# alphabet_selfies.json
-{
-    "": 0,       # an empty padding
-    "[C]": 1,
-    ...
-}
-```
+- You will need to specify an alphabet `List[str]`.
 
 ## How to run
 
@@ -36,27 +28,27 @@ pip install rdkit selfies
 Then run
 
 ```python
-from pathlib import Path
-
 import numpy as np
-
 from poli import objective_factory
 
-# The path to your alphabet
-path_to_alphabet = Path("path/to/alphabet_selfies.json")
+# Your alphabet
+alphabet = ["", "[C]", ...]
 
 # How to create
 problem_info, f, x0, y0, run_info = objective_factory.create(
     name="rdkit_qed",
-    path_to_alphabet=path_to_alphabet,
-    string_representation="SELFIES"  # it is "SMILES" by default.
-    )
+    alphabet=alphabet,
+    string_representation="SELFIES",  # it is "SMILES" by default.
+    force_register=True,
+)
 
 # Example input: a single carbon
-x = np.array([[1]])
+x = np.array(["[C]"]).reshape(1, -1)
 
 # Querying:
-print(f(x))  # Should be close to 0.35978
+y = f(x)
+print(y)  # Should be close to 0.35978494
+assert np.isclose(y, 0.35978494).all()
 ```
 
 :::
@@ -66,29 +58,27 @@ print(f(x))  # Should be close to 0.35978
 If you want us to handle dependencies, run
 
 ```python
-from pathlib import Path
-
 import numpy as np
-
 from poli import objective_factory
 
-
-# The path to your alphabet
-path_to_alphabet = Path("path/to/alphabet_selfies.json")
+# Your alphabet
+alphabet = ["", "[C]", ...]
 
 # How to create
 problem_info, f, x0, y0, run_info = objective_factory.create(
     name="rdkit_qed",
-    path_to_alphabet=path_to_alphabet,
-    string_representation="SELFIES"  # it is "SMILES" by default.
-    force_register=True, 
+    alphabet=alphabet,
+    string_representation="SELFIES",  # it is "SMILES" by default.
+    force_register=True,
 )
 
 # Example input: a single carbon
-x = np.array([[1]])
+x = np.array(["[C]"]).reshape(1, -1)
 
 # Querying:
-print(f(x))  # Should be close to 0.35978
+y = f(x)
+print(y)  # Should be close to 0.35978494
+assert np.isclose(y, 0.35978494).all()
 
 # Terminate the process.
 f.terminate()