Release 4.0.0

CHANGELOG.md

@@ -1,5 +1,41 @@
 # CHANGELOG
 
+## Version 4.0.0 2023-11-30
+
+### Features
+
+- `Configuration` now supports a `rescale_prior` property which rescales the priors in `TemplateBasedExpansionStrategy`.
+- Functionality of `ScorerCollection` has been extended.
+- Pricing is now supported in `InMemoryInchiKeyQuery`.
+- Reward scorer has been added to Configuration scorers as `search_reward` item.
+- `MaxTransformScorerer` and `FractionInStockScorer` have been created to separate scores in `StateScorer`.
+- Reaction routes are scored with all reward scorers after the search is complete.
+- `StockAvailabilityScorer` and `ReactionClassMembershipScorer` have been added to the scorers.
+- Atom mapping existing in target molecule can be inherited.
+- A caching feature has been add to the expansion strategies.
+- Degenerate states can now be grouped in the MCTS algorithm.
+- `ChemformerBasedExpansionStrategy` and `ModelZooExpansionStrategy` can be found under plugins and used as additional expansion strategies.
+- Support for the stereocenter model has been added with to support chiral fingerprints for molecules and reactions.
+- The `Configuration` format has been entirely revamped to a more easy-to-use format.
+- A `MolbloomFilterQuery` has been created as a stock query class.
+
+### Trivial changes
+
+- Python version requirements have been updated to versions 3.9 - 3.11.
+- `MoleculeCost` has been moved from aizynthfinder.context.cost.collection to the Retro* package.
+
+### Deprecations
+
+- Graphviz has been removed from aizynthfinder.utils.image.
+- `Reaction` class has been removed from aizynthfinder.chem.reaction.
+- aizynthfinder.context.cost package has been removed.
+
+### Bug-fixes
+
+- Fixed an issue with `max_transforms` to ensure only the given number of maximum depth is considered.
+- Pinned Jupyter notebook version to ^6.5.3 to avoid errors when displaying widgets.
+- Rollout child has been removed from the MCTS search algorithm.
+
 ## Version 3.7.0 2023-06-01 (2023-04-11)
 
 ### Features
@@ -289,4 +325,4 @@
 
 ## Version 1.0.0 - 2020-06-11
 
-- First public version
+- First public version

README.md

@@ -1,4 +1,4 @@
-# AiZynthFinder 
+# AiZynthFinder
 
 [![License](https://img.shields.io/github/license/MolecularAI/aizynthfinder)](https://github.com/MolecularAI/aizynthfinder/blob/master/LICENSE)
 [![Tests](https://github.com/MolecularAI/aizynthfinder/workflows/tests/badge.svg)](https://github.com/MolecularAI/aizynthfinder/actions?workflow=tests)
@@ -7,8 +7,8 @@
 [![version](https://img.shields.io/github/v/release/MolecularAI/aizynthfinder)](https://github.com/MolecularAI/aizynthfinder/releases)
 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/MolecularAI/aizynthfinder/blob/master/contrib/notebook.ipynb)
 
-
-AiZynthFinder is a tool for retrosynthetic planning. The algorithm is based on a Monte Carlo tree search that recursively breaks down a molecule to purchasable precursors. The tree search is guided by a policy that suggests possible precursors by utilizing a neural network trained on a library of known reaction templates.
+AiZynthFinder is a tool for retrosynthetic planning. The default algorithm is based on a Monte Carlo tree search that recursively breaks down a molecule to purchasable precursors. The tree search is guided by a policy that suggests possible precursors by utilizing a neural network trained on a library of known reaction templates. This setup is completely customizable as the tool
+supports multiple search algorithms and expansion policies.
 
 An introduction video can be found here: [https://youtu.be/r9Dsxm-mcgA](https://youtu.be/r9Dsxm-mcgA)
 
@@ -18,19 +18,18 @@ Before you begin, ensure you have met the following requirements:
 
 * Linux, Windows or macOS platforms are supported - as long as the dependencies are supported on these platforms.
 
-* You have installed [anaconda](https://www.anaconda.com/) or [miniconda](https://docs.conda.io/en/latest/miniconda.html) with python 3.8 - 3.9
+* You have installed [anaconda](https://www.anaconda.com/) or [miniconda](https://docs.conda.io/en/latest/miniconda.html) with python 3.9 - 3.11
 
 The tool has been developed on a Linux platform, but the software has been tested on Windows 10 and macOS Catalina.
 
-
 ## Installation
 
 ### For end-users
 
 First time, execute the following command in a console or an Anaconda prompt
 
     conda create "python>=3.8,<3.10" -n aizynth-env
-    
+
 To install, activate the environment and install the package using pypi
 
     conda activate aizynth-env
@@ -48,28 +47,28 @@ Then execute the following commands in the root of the repository
 
     conda env create -f env-dev.yml
     conda activate aizynth-dev
-    poetry install -E all
+    poetry install --all-extras
 
 the `aizynthfinder` package is now installed in editable mode.
 
+
 ## Usage
 
-The tool will install the ``aizynthcli`` and ``aizynthapp`` tools
+The tool will install the `aizynthcli` and `aizynthapp` tools
 as interfaces to the algorithm:
 
-```
-aizynthcli --config config.yml --smiles smiles.txt
-aizynthapp --config config.yml
-```
+    aizynthcli --config config_local.yml --smiles smiles.txt
+    aizynthapp --config config_local.yml
+
 
 Consult the documentation [here](https://molecularai.github.io/aizynthfinder/) for more information.
 
 To use the tool you need
 
     1. A stock file
-    2. A trained rollout policy network (including the Keras model and the list of unique templates)
-    3. A trained filer policy network (optional)
-
+    2. A trained expansion policy network
+    3. A trained filter policy network (optional)
+    
 Such files can be downloaded from [figshare](https://figshare.com/articles/AiZynthFinder_a_fast_robust_and_flexible_open-source_software_for_retrosynthetic_planning/12334577) and [here](https://figshare.com/articles/dataset/A_quick_policy_to_filter_reactions_based_on_feasibility_in_AI-guided_retrosynthetic_planning/13280507) or they can be downloaded automatically using
 
 ```
@@ -122,6 +121,8 @@ Please use ``black`` package for formatting, and follow ``pep8`` style guide.
 ## Contributors
 
 * [@SGenheden](https://www.github.com/SGenheden)
+* [@lakshidaa](https://github.com/Lakshidaa)
+* [@helenlai](https://github.com/helenlai)
 * [@EBjerrum](https://www.github.com/EBjerrum)
 * [@A-Thakkar](https://www.github.com/A-Thakkar)
 * [@benteb](https://www.github.com/benteb)
@@ -135,7 +136,4 @@ The software is licensed under the MIT license (see LICENSE file), and is free a
 ## References
 
 1. Thakkar A, Kogej T, Reymond J-L, et al (2019) Datasets and their influence on the development of computer assisted synthesis planning tools in the pharmaceutical domain. Chem Sci. https://doi.org/10.1039/C9SC04944D
-2. Genheden S, Thakkar A, Chadimova V, et al (2020) AiZynthFinder: a fast, robust and flexible open-source software for retrosynthetic planning. J. Cheminf. https://jcheminf.biomedcentral.com/articles/10.1186/s13321-020-00472-1
-3. Genheden S, Engkvist O, Bjerrum E (2020) A Quick Policy to Filter Reactions Based on Feasibility in AI-Guided Retrosynthetic Planning. ChemRxiv. Preprint. https://doi.org/10.26434/chemrxiv.13280495.v1 
-4. Genheden S, Engkvist O, Bjerrum E (2021) Clustering of synthetic routes using tree edit distance. J. Chem. Inf. Model. 61:3899–3907 [https://doi.org/10.1021/acs.jcim.1c00232](https://doi.org/10.1021/acs.jcim.1c00232)
-5. Genheden S, Engkvist O, Bjerrum E (2022) Fast prediction of distances between synthetic routes with deep learning. Mach. Learn. Sci. Technol. 3:015018 [https://doi.org/10.1088/2632-2153/ac4a91](https://doi.org/10.1088/2632-2153/ac4a91) 
+2. Genheden S, Thakkar A, Chadimova V, et al (2020) AiZynthFinder: a fast, robust and flexible open-source software for retrosynthetic planning. ChemRxiv. Preprint. https://doi.org/10.26434/chemrxiv.12465371.v1

aizynthfinder/aizynthfinder.py

@@ -15,6 +15,7 @@
 )
 from aizynthfinder.chem import FixedRetroReaction, Molecule, TreeMolecule
 from aizynthfinder.context.config import Configuration
+from aizynthfinder.context.scoring import CombinedScorer
 from aizynthfinder.reactiontree import ReactionTreeFromExpansion
 from aizynthfinder.search.andor_trees import AndOrSearchTreeBase
 from aizynthfinder.search.mcts import MctsSearchTree
@@ -60,7 +61,9 @@ class AiZynthFinder:
     :param configdict: the config as a dictionary source, defaults to None
     """
 
-    def __init__(self, configfile: str = None, configdict: StrDict = None) -> None:
+    def __init__(
+        self, configfile: Optional[str] = None, configdict: Optional[StrDict] = None
+    ) -> None:
         self._logger = logger()
 
         if configfile:
@@ -102,7 +105,9 @@ def target_mol(self, mol: Molecule) -> None:
         self._target_mol = mol
 
     def build_routes(
-        self, selection: RouteSelectionArguments = None, scorer: str = "state score"
+        self,
+        selection: Optional[RouteSelectionArguments] = None,
+        scorer: Optional[str] = None,
     ) -> None:
         """
         Build reaction routes
@@ -114,10 +119,15 @@ def build_routes(
         :param scorer: a reference to the object used to score the nodes
         :raises ValueError: if the search tree not initialized
         """
+
+        scorer = scorer or self.config.post_processing.route_scorer
+
         if not self.tree:
             raise ValueError("Search tree not initialized")
 
-        self.analysis = TreeAnalysis(self.tree, scorer=self.scorers[scorer])
+        _scorer = self.scorers[scorer]
+
+        self.analysis = TreeAnalysis(self.tree, scorer=_scorer)
         config_selection = RouteSelectionArguments(
             nmin=self.config.post_processing.min_routes,
             nmax=self.config.post_processing.max_routes,
@@ -157,13 +167,17 @@ def prepare_tree(self) -> None:
             raise ValueError("Target molecule unsanitizable")
 
         self.stock.reset_exclusion_list()
-        if self.config.exclude_target_from_stock and self.target_mol in self.stock:
+        if (
+            self.config.search.exclude_target_from_stock
+            and self.target_mol in self.stock
+        ):
             self.stock.exclude(self.target_mol)
             self._logger.debug("Excluding the target compound from the stock")
 
         self._setup_search_tree()
         self.analysis = None
         self.routes = RouteCollection([])
+        self.expansion_policy.reset_cache()
 
     def stock_info(self) -> StrDict:
         """
@@ -202,9 +216,12 @@ def tree_search(self, show_progress: bool = False) -> float:
         time_past = time.time() - time0
 
         if show_progress:
-            pbar = tqdm(total=self.config.iteration_limit, leave=False)
+            pbar = tqdm(total=self.config.search.iteration_limit, leave=False)
 
-        while time_past < self.config.time_limit and i <= self.config.iteration_limit:
+        while (
+            time_past < self.config.search.time_limit
+            and i <= self.config.search.iteration_limit
+        ):
             if show_progress:
                 pbar.update(1)
             self.search_stats["iterations"] += 1
@@ -218,7 +235,7 @@ def tree_search(self, show_progress: bool = False) -> float:
                 self.search_stats["first_solution_time"] = time.time() - time0
                 self.search_stats["first_solution_iteration"] = i
 
-            if self.config.return_first and is_solved:
+            if self.config.search.return_first and is_solved:
                 self._logger.debug("Found first solved route")
                 self.search_stats["returned_first"] = True
                 break
@@ -234,12 +251,12 @@ def tree_search(self, show_progress: bool = False) -> float:
 
     def _setup_search_tree(self) -> None:
         self._logger.debug("Defining tree root: %s" % self.target_smiles)
-        if self.config.search_algorithm.lower() == "mcts":
+        if self.config.search.algorithm.lower() == "mcts":
             self.tree = MctsSearchTree(
                 root_smiles=self.target_smiles, config=self.config
             )
         else:
-            cls = load_dynamic_class(self.config.search_algorithm)
+            cls = load_dynamic_class(self.config.search.algorithm)
             self.tree = cls(root_smiles=self.target_smiles, config=self.config)
 
 
@@ -260,7 +277,9 @@ class AiZynthExpander:
     :param configdict: the config as a dictionary source, defaults to None
     """
 
-    def __init__(self, configfile: str = None, configdict: StrDict = None) -> None:
+    def __init__(
+        self, configfile: Optional[str] = None, configdict: Optional[StrDict] = None
+    ) -> None:
         self._logger = logger()
 
         if configfile:
@@ -278,7 +297,7 @@ def do_expansion(
         self,
         smiles: str,
         return_n: int = 5,
-        filter_func: Callable[[RetroReaction], bool] = None,
+        filter_func: Optional[Callable[[RetroReaction], bool]] = None,
     ) -> List[Tuple[FixedRetroReaction, ...]]:
         """
         Do the expansion of the given molecule returning a list of

aizynthfinder/analysis/tree_analysis.py

@@ -19,6 +19,7 @@
         Any,
         Iterable,
         List,
+        Optional,
         Sequence,
         StrDict,
         Tuple,
@@ -41,7 +42,7 @@ class TreeAnalysis:
     def __init__(
         self,
         search_tree: Union[MctsSearchTree, AndOrSearchTreeBase],
-        scorer: Scorer = None,
+        scorer: Optional[Scorer] = None,
     ) -> None:
         self.search_tree = search_tree
         if scorer is None:
@@ -65,7 +66,7 @@ def best(self) -> Union[MctsNode, ReactionTree]:
         return sorted_routes[0]
 
     def sort(
-        self, selection: RouteSelectionArguments = None
+        self, selection: Optional[RouteSelectionArguments] = None
     ) -> Tuple[Union[Sequence[MctsNode], Sequence[ReactionTree]], Sequence[float]]:
         """
         Sort and select the nodes or routes in the search tree.

aizynthfinder/analysis/utils.py

@@ -15,7 +15,13 @@
 from aizynthfinder.utils.image import make_visjs_page
 
 if TYPE_CHECKING:
-    from aizynthfinder.utils.type_utils import FrameColors, Sequence, StrDict, Tuple
+    from aizynthfinder.utils.type_utils import (
+        FrameColors,
+        Optional,
+        Sequence,
+        StrDict,
+        Tuple,
+    )
 
 
 @dataclass
@@ -69,7 +75,7 @@ def to_dict(self) -> StrDict:
     def to_visjs_page(
         self,
         filename: str,
-        in_stock_colors: FrameColors = None,
+        in_stock_colors: Optional[FrameColors] = None,
     ) -> None:
         """
         Create a visualization of the combined reaction tree using the vis.js network library.
@@ -93,7 +99,6 @@ def _add_reaction_trees_to_node(
         base_node: UniqueMolecule,
         rt_node_spec: Sequence[Tuple[UniqueMolecule, nx.DiGraph]],
     ) -> None:
-
         reaction_groups = defaultdict(list)
         # Group the reactions from the nodes at this level based on the reaction smiles
         for node, graph in rt_node_spec:

aizynthfinder/chem/__init__.py

@@ -9,7 +9,6 @@
 )
 from aizynthfinder.chem.reaction import (
     FixedRetroReaction,
-    Reaction,
     RetroReaction,
     SmilesBasedRetroReaction,
     TemplatedRetroReaction,