fpembed 0.1.3__tar.gz → 0.1.4__tar.gz

{fpembed-0.1.3/src/fpembed.egg-info → fpembed-0.1.4}/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.4
 Name: fpembed
-Version: 0.1.3
+Version: 0.1.4
 Summary: Generalized fingerprint embedding library
 License-Expression: MIT
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: scikit-fingerprints>=2.0.0
+Requires-Dist: scikit-fingerprints==2.0.0
 Requires-Dist: selfies>=2.2.0
 Provides-Extra: app
 Requires-Dist: nicegui>=3.8.0; extra == "app"
@@ -20,7 +20,7 @@ Dynamic: license-file
 
 # FPembed - Generalized Molecular Fingerprint Embeddings
 
-A lightweight Python package for generating compressed molecular fingerprint embeddings, backed by [scikit-fingerprints](https://github.com/scikit-fingerprints/scikit-fingerprints). Supports six binary fingerprint types through a single unified class.
+A lightweight Python package for generating compressed molecular fingerprint embeddings, backed by [scikit-fingerprints](https://github.com/scikit-fingerprints/scikit-fingerprints). Supports ten binary fingerprint types through a single unified class.
 
 FPembed compresses standard molecular fingerprints using weighted binary masking, producing compact float vectors suitable for machine-learning models. The package accepts SMILES, SELFIES, and RDKit Mol objects as input.
 
@@ -53,6 +53,10 @@ Original concept repository: [MMLabCodes/eMFP](https://github.com/MMLabCodes/eMF
 | RDKit | `rdkit` | `min_path` (1), `max_path` (7) |
 | Layered | `layered` | `min_path` (1), `max_path` (7) |
 | Pattern | `pattern` | (none) |
+| Avalon | `avalon` | (none) |
+| SECFP | `secfp` | `radius` (default 3) |
+| MHFP | `mhfp` | `radius` (default 3) |
+| MAP4 | `map` | `radius` (default 2) |
 
 ## Compression Methods
 

{fpembed-0.1.3 → fpembed-0.1.4}/README.md

@@ -1,6 +1,6 @@
 # FPembed - Generalized Molecular Fingerprint Embeddings
 
-A lightweight Python package for generating compressed molecular fingerprint embeddings, backed by [scikit-fingerprints](https://github.com/scikit-fingerprints/scikit-fingerprints). Supports six binary fingerprint types through a single unified class.
+A lightweight Python package for generating compressed molecular fingerprint embeddings, backed by [scikit-fingerprints](https://github.com/scikit-fingerprints/scikit-fingerprints). Supports ten binary fingerprint types through a single unified class.
 
 FPembed compresses standard molecular fingerprints using weighted binary masking, producing compact float vectors suitable for machine-learning models. The package accepts SMILES, SELFIES, and RDKit Mol objects as input.
 
@@ -33,6 +33,10 @@ Original concept repository: [MMLabCodes/eMFP](https://github.com/MMLabCodes/eMF
 | RDKit | `rdkit` | `min_path` (1), `max_path` (7) |
 | Layered | `layered` | `min_path` (1), `max_path` (7) |
 | Pattern | `pattern` | (none) |
+| Avalon | `avalon` | (none) |
+| SECFP | `secfp` | `radius` (default 3) |
+| MHFP | `mhfp` | `radius` (default 3) |
+| MAP4 | `map` | `radius` (default 2) |
 
 ## Compression Methods
 

{fpembed-0.1.3 → fpembed-0.1.4}/pyproject.toml

@@ -4,11 +4,11 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "fpembed"
-version = "0.1.3"
+version = "0.1.4"
 description = "Generalized fingerprint embedding library"
 requires-python = ">=3.9"
 dependencies = [
-    "scikit-fingerprints>=2.0.0",
+    "scikit-fingerprints==2.0.0",
     "selfies>=2.2.0",
 ]
 readme = "README.md"

{fpembed-0.1.3 → fpembed-0.1.4}/src/fpembed/__init__.py

@@ -20,7 +20,7 @@ from fpembed.compression import compress_fingerprint
 from fpembed.smiles_utils import parse_smiles, canonicalize_smiles
 from fpembed.hashing import fp_params_hash
 
-__version__ = "0.1.3"
+__version__ = "0.1.4"
 
 __all__ = [
     "EmbeddedFingerprintGenerator",

{fpembed-0.1.3 → fpembed-0.1.4}/src/fpembed/generator.py

@@ -11,10 +11,14 @@ import numpy.typing as npt
 from rdkit import Chem
 from skfp.fingerprints import (
     AtomPairFingerprint,
+    AvalonFingerprint,
     ECFPFingerprint,
     LayeredFingerprint,
+    MAPFingerprint,
+    MHFPFingerprint,
     PatternFingerprint,
     RDKitFingerprint,
+    SECFPFingerprint,
     TopologicalTorsionFingerprint,
 )
 
@@ -22,6 +26,8 @@ from fpembed.compression import (
     compress_fingerprint,
     _is_power_of_two,
     _ALL_METHODS,
+    _BLOCKWISE_METHODS,
+    _VALID_PARAMS,
     _validate_method_params,
     _DEFAULT_SEED,
 )
@@ -42,6 +48,7 @@ _EMPTY_CACHE_INFO = CacheInfo(hits=0, misses=0, maxsize=0, currsize=0)
 
 _SUPPORTED_FP_TYPES = (
     "ecfp", "atom_pair", "topological_torsion", "rdkit", "layered", "pattern",
+    "avalon", "secfp", "mhfp", "map",
 )
 
 
@@ -74,14 +81,33 @@ def _build_skfp(fp_type: str, fp_size: int, fp_params: dict) -> Any:
             fp_size=fp_size, min_path=fp_params.get("min_path", 1),
             max_path=fp_params.get("max_path", 7), n_jobs=1,
         )
+    if fp_type == "avalon":
+        return AvalonFingerprint(fp_size=fp_size, count=False, n_jobs=1)
+    if fp_type == "secfp":
+        return SECFPFingerprint(
+            fp_size=fp_size, radius=fp_params.get("radius", 3),
+            min_radius=fp_params.get("min_radius", 1), n_jobs=1,
+        )
+    if fp_type == "mhfp":
+        return MHFPFingerprint(
+            fp_size=fp_size, radius=fp_params.get("radius", 3),
+            min_radius=fp_params.get("min_radius", 1),
+            variant="bit", n_jobs=1,
+        )
+    if fp_type == "map":
+        return MAPFingerprint(
+            fp_size=fp_size, radius=fp_params.get("radius", 2),
+            variant="binary", n_jobs=1,
+        )
     return PatternFingerprint(fp_size=fp_size, n_jobs=1)
 
 
 class EmbeddedFingerprintGenerator:
     """Unified fingerprint generator backed by scikit-fingerprints.
 
-    Supports six fp_types: ecfp, atom_pair, topological_torsion,
-    rdkit, layered, pattern. Compression via log-space weighted mask.
+    Supports ten fp_types: ecfp, atom_pair, topological_torsion,
+    rdkit, layered, pattern, avalon, secfp, mhfp, map.
+    Compression via log-space weighted mask.
     """
 
     __slots__ = (

{fpembed-0.1.3 → fpembed-0.1.4/src/fpembed.egg-info}/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.4
 Name: fpembed
-Version: 0.1.3
+Version: 0.1.4
 Summary: Generalized fingerprint embedding library
 License-Expression: MIT
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: scikit-fingerprints>=2.0.0
+Requires-Dist: scikit-fingerprints==2.0.0
 Requires-Dist: selfies>=2.2.0
 Provides-Extra: app
 Requires-Dist: nicegui>=3.8.0; extra == "app"
@@ -20,7 +20,7 @@ Dynamic: license-file
 
 # FPembed - Generalized Molecular Fingerprint Embeddings
 
-A lightweight Python package for generating compressed molecular fingerprint embeddings, backed by [scikit-fingerprints](https://github.com/scikit-fingerprints/scikit-fingerprints). Supports six binary fingerprint types through a single unified class.
+A lightweight Python package for generating compressed molecular fingerprint embeddings, backed by [scikit-fingerprints](https://github.com/scikit-fingerprints/scikit-fingerprints). Supports ten binary fingerprint types through a single unified class.
 
 FPembed compresses standard molecular fingerprints using weighted binary masking, producing compact float vectors suitable for machine-learning models. The package accepts SMILES, SELFIES, and RDKit Mol objects as input.
 
@@ -53,6 +53,10 @@ Original concept repository: [MMLabCodes/eMFP](https://github.com/MMLabCodes/eMF
 | RDKit | `rdkit` | `min_path` (1), `max_path` (7) |
 | Layered | `layered` | `min_path` (1), `max_path` (7) |
 | Pattern | `pattern` | (none) |
+| Avalon | `avalon` | (none) |
+| SECFP | `secfp` | `radius` (default 3) |
+| MHFP | `mhfp` | `radius` (default 3) |
+| MAP4 | `map` | `radius` (default 2) |
 
 ## Compression Methods
 

{fpembed-0.1.3 → fpembed-0.1.4}/src/fpembed.egg-info/requires.txt

@@ -1,4 +1,4 @@
-scikit-fingerprints>=2.0.0
+scikit-fingerprints==2.0.0
 selfies>=2.2.0
 
 [app]

{fpembed-0.1.3 → fpembed-0.1.4}/tests/test_generator.py

@@ -17,7 +17,12 @@ VALID_SMILES = [
 ]
 INVALID_SMILES = ["not_a_molecule", "XYZ123", "C(C(C", "12345"]
 VALID_SELFIES = ["[C][C][O]", "[C][=C][C][=C][C][=C][Ring1][=Branch1]", "[C][C][=Branch1][C][=O][O]"]
-FP_TYPES = ["ecfp", "atom_pair", "topological_torsion", "rdkit", "layered", "pattern"]
+# @spec:049-T04.1
+# @spec:049-T04.3
+FP_TYPES = [
+    "ecfp", "atom_pair", "topological_torsion", "rdkit", "layered", "pattern",
+    "avalon", "secfp", "mhfp", "map",
+]
 
 
 # ===================================================================
@@ -114,6 +119,47 @@ class TestConstruction:
         assert gen._projection_cache is None
 
 
+# ===================================================================
+# New fingerprint types — targeted tests
+# @spec:049-T04.2
+# ===================================================================
+
+
+class TestNewFingerprintTypes:
+    @pytest.mark.fast
+    def test_avalon_no_params(self) -> None:
+        """Avalon with empty fp_params produces valid output."""
+        gen = EmbeddedFingerprintGenerator(fp_type="avalon", fp_size=2048, compression=16, fp_params={})
+        mol = Chem.MolFromSmiles("CCO")
+        fp = gen.GetFingerprintAsNumPy(mol)
+        assert fp.shape == (128,)
+        assert fp.dtype == np.float64
+
+    @pytest.mark.fast
+    def test_secfp_custom_radius(self) -> None:
+        """Non-default radius is actually passed through to the skfp instance."""
+        gen = EmbeddedFingerprintGenerator(
+            fp_type="secfp", fp_size=2048, compression=16, fp_params={"radius": 4}
+        )
+        assert gen._skfp_fp.radius == 4
+
+    @pytest.mark.fast
+    def test_mhfp_variant_hardcoded(self) -> None:
+        """variant='bit' is hardcoded — user-supplied variant in fp_params is ignored."""
+        gen = EmbeddedFingerprintGenerator(
+            fp_type="mhfp", fp_size=2048, compression=16, fp_params={"variant": "raw_hashes"}
+        )
+        assert gen._skfp_fp.variant == "bit"
+
+    @pytest.mark.fast
+    def test_map_variant_hardcoded(self) -> None:
+        """variant='binary' is hardcoded — user-supplied variant in fp_params is ignored."""
+        gen = EmbeddedFingerprintGenerator(
+            fp_type="map", fp_size=2048, compression=16, fp_params={"variant": "minhash"}
+        )
+        assert gen._skfp_fp.variant == "binary"
+
+
 # ===================================================================
 # Fingerprint methods
 # ===================================================================