bblean 0.7.5__tar.gz → 0.7.7__tar.gz

{bblean-0.7.5 → bblean-0.7.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bblean
-Version: 0.7.5
+Version: 0.7.7
 Summary: BitBirch-Lean Python package
 Author: The Miranda-Quintana Lab and other BitBirch developers
 Author-email: Ramon Alain Miranda Quintana <quintana@chem.ufl.edu>, Krisztina Zsigmond <kzsigmond@ufl.edu>, Ignacio Pickering <ipickering@ufl.edu>, Kenneth Lopez Perez <klopezperez@chem.ufl.edu>, Miroslav Lzicar <miroslav.lzicar@deepmedchem.com>

{bblean-0.7.5 → bblean-0.7.7}/bblean/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.7.5'
-__version_tuple__ = version_tuple = (0, 7, 5)
+__version__ = version = '0.7.7'
+__version_tuple__ = version_tuple = (0, 7, 7)
 
 __commit_id__ = commit_id = None

{bblean-0.7.5 → bblean-0.7.7}/bblean/bitbirch.py

@@ -532,6 +532,7 @@ class _CentroidsMolIds(tp.TypedDict):
 
 
 class _MedoidsMolIds(tp.TypedDict):
+    medoid_idxs: NDArray[np.int64]
     medoids: NDArray[np.uint8]
     mol_ids: list[list[int]]
 
@@ -926,32 +927,42 @@ class BitBirch:
         input_is_packed: bool = True,
         n_features: int | None = None,
     ) -> _MedoidsMolIds:
-        """Get a dict with medoids and mol indices of the leaves"""
+        r"""Get a dict with medoid idxs, medoids and mol indices of the leaves
+
+        The medoid indices are indices into the cluster mol ids, not into the fps array
+        """
         cluster_members = self.get_cluster_mol_ids(
             sort=sort, global_clusters=global_clusters
         )
 
         if input_is_packed:
             fps = _unpack_fingerprints(fps, n_features=n_features)
-        cluster_medoids = self._unpacked_medoids_from_members(fps, cluster_members)
+        cluster_medoid_idxs, cluster_medoids = self._unpacked_medoids_from_members(
+            fps, cluster_members
+        )
         if pack:
             cluster_medoids = pack_fingerprints(cluster_medoids)
-        return {"medoids": cluster_medoids, "mol_ids": cluster_members}
+        return {
+            "medoid_idxs": cluster_medoid_idxs,
+            "medoids": cluster_medoids,
+            "mol_ids": cluster_members,
+        }
 
     @staticmethod
     def _unpacked_medoids_from_members(
         unpacked_fps: NDArray[np.uint8], cluster_members: tp.Sequence[list[int]]
-    ) -> NDArray[np.uint8]:
+    ) -> tuple[NDArray[np.int64], NDArray[np.uint8]]:
         cluster_medoids = np.zeros(
             (len(cluster_members), unpacked_fps.shape[1]), dtype=np.uint8
         )
+        cluster_medoid_idxs = np.zeros((len(cluster_members),), dtype=np.int64)
         for idx, members in enumerate(cluster_members):
-            cluster_medoids[idx, :] = jt_isim_medoid(
+            cluster_medoid_idxs[idx], cluster_medoids[idx, :] = jt_isim_medoid(
                 unpacked_fps[members],
                 input_is_packed=False,
                 pack=False,
-            )[1]
-        return cluster_medoids
+            )
+        return cluster_medoid_idxs, cluster_medoids
 
     def get_medoids(
         self,

{bblean-0.7.5 → bblean-0.7.7}/bblean/cli.py

@@ -1550,6 +1550,14 @@ def _fps_from_smiles(
             help="Whether the smiles file has the format <smiles><tab><field><tab>...",
         ),
     ] = False,
+    replace_dummy_atoms: Annotated[
+        bool,
+        Option(
+            "--replace-dummy/--no-replace-dummy",
+            help="Whether to replace dummy atoms such as [U], [Np], etc. used in synthon spaces",  # noqa
+            hidden=True,
+        ),
+    ] = False,
 ) -> None:
     r"""Generate a `*.npy` fingerprints file from one or more `*.smi` smiles files
 
@@ -1656,7 +1664,7 @@ def _fps_from_smiles(
                 pool.map(
                     create_fp_file,
                     _iter_idxs_and_smiles_batches(
-                        smiles_paths, num_per_batch, tab_separated
+                        smiles_paths, num_per_batch, tab_separated, replace_dummy_atoms
                     ),
                 )
         timer.end_timing("total", console, indent=False)
@@ -1698,7 +1706,7 @@ def _fps_from_smiles(
             pool.starmap(
                 fps_array_filler,
                 _iter_ranges_and_smiles_batches(
-                    smiles_paths, num_per_batch, tab_separated
+                    smiles_paths, num_per_batch, tab_separated, replace_dummy_atoms
                 ),
             )
         fps = np.ndarray((smiles_num, out_dim), dtype=dtype, buffer=fps_shmem.buf)

{bblean-0.7.5 → bblean-0.7.7}/bblean/smiles.py

@@ -31,8 +31,12 @@ def calc_num_smiles(smiles_paths: SmilesPaths) -> int:
     return sum(1 for _ in iter_smiles_from_paths(smiles_paths))
 
 
+# NOTE: replace_dummy is the procedure used in RDKit as of Dec 2024 for Synthon spaces
+# synthons marked with [U], [Np], [Pu], [Am]. These need to be converted
 def iter_smiles_from_paths(
-    smiles_paths: SmilesPaths, tab_separated: bool = False
+    smiles_paths: SmilesPaths,
+    tab_separated: bool = False,
+    replace_dummy_atoms: bool = False,
 ) -> tp.Iterator[str]:
     r"""Iterate over smiles in a sequence of smiles paths
 
@@ -44,10 +48,21 @@ def iter_smiles_from_paths(
     for smi_path in smiles_paths:
         with open(smi_path, mode="rt", encoding="utf-8") as f:
             for smi in f:
-                smi = smi if not tab_separated else smi.split("\t")[0]
+                if tab_separated:
+                    smi = smi.split("\t")[0]
+
                 # Skip headers
                 if smi.lower().strip() == "smiles":
                     continue
+
+                # Replace 'dummy' atoms from synthon spaces
+                if replace_dummy_atoms:
+                    smi = (
+                        smi.replace("[U]", "[1*]")
+                        .replace("[Np]", "[2*]")
+                        .replace("[Pu]", "[3*]")
+                        .replace("[Am]", "[4*]")
+                    )
                 yield smi
 
 
@@ -55,10 +70,12 @@ def _iter_ranges_and_smiles_batches(
     smiles_paths: SmilesPaths,
     num_per_batch: int,
     tab_separated: bool = False,
+    replace_dummy_atoms: bool = False,
 ) -> tp.Iterable[tuple[tuple[int, int], tuple[str, ...]]]:
     start_idx = 0
     for batch in batched(
-        iter_smiles_from_paths(smiles_paths, tab_separated), num_per_batch
+        iter_smiles_from_paths(smiles_paths, tab_separated, replace_dummy_atoms),
+        num_per_batch,
     ):
         size = len(batch)
         end_idx = start_idx + size
@@ -70,7 +87,11 @@ def _iter_idxs_and_smiles_batches(
     smiles_paths: SmilesPaths,
     num_per_batch: int,
     tab_separated: bool = False,
+    replace_dummy_atoms: bool = False,
 ) -> tp.Iterable[tuple[int, tuple[str, ...]]]:
     yield from enumerate(
-        batched(iter_smiles_from_paths(smiles_paths, tab_separated), num_per_batch)
+        batched(
+            iter_smiles_from_paths(smiles_paths, tab_separated, replace_dummy_atoms),
+            num_per_batch,
+        )
     )

{bblean-0.7.5 → bblean-0.7.7}/bblean.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bblean
-Version: 0.7.5
+Version: 0.7.7
 Summary: BitBirch-Lean Python package
 Author: The Miranda-Quintana Lab and other BitBirch developers
 Author-email: Ramon Alain Miranda Quintana <quintana@chem.ufl.edu>, Krisztina Zsigmond <kzsigmond@ufl.edu>, Ignacio Pickering <ipickering@ufl.edu>, Kenneth Lopez Perez <klopezperez@chem.ufl.edu>, Miroslav Lzicar <miroslav.lzicar@deepmedchem.com>