chemap 0.1.0

Library for computing molecular fingerprint based similarities as well as dimensionality reduction based chemical space visualizations.

chemap - Chemical Mapping

Library for computing molecular fingerprint based similarities as well as dimensionality reduction based chemical space visualizations.

Fingerprint computations

Fingerprints can be computed using generators from RDKit or scikit-fingerprints. Here a code example:

import numpy as np
import scipy.sparse as sp
from rdkit.Chem import rdFingerprintGenerator
from skfp.fingerprints import MAPFingerprint, AtomPairFingerprint

from chemap import compute_fingerprints, DatasetLoader, FingerprintConfig


ds_loader = DatasetLoader()
smiles = ds_loader.load("tests/data/smiles.csv")

# ----------------------------
# RDKit: Morgan (folded, dense)
# ----------------------------
morgan = rdFingerprintGenerator.GetMorganGenerator(radius=3, fpSize=4096)
X_morgan = compute_fingerprints(
    smiles,
    morgan,
    config=FingerprintConfig(
        count=False,
        folded=True,
        return_csr=False,   # dense numpy
        invalid_policy="raise",
    ),
)
print("RDKit Morgan:", X_morgan.shape, X_morgan.dtype)

# -----------------------------------
# RDKit: RDKitFP (folded, CSR sparse)
# -----------------------------------
rdkitfp = rdFingerprintGenerator.GetRDKitFPGenerator(fpSize=4096)
X_rdkitfp_csr = compute_fingerprints(
    smiles,
    rdkitfp,
    config=FingerprintConfig(
        count=False,
        folded=True,
        return_csr=True,    # SciPy CSR
        invalid_policy="raise",
    ),
)
assert sp.issparse(X_rdkitfp_csr)
print("RDKit RDKitFP (CSR):", X_rdkitfp_csr.shape, X_rdkitfp_csr.dtype, "nnz=", X_rdkitfp_csr.nnz)

# --------------------------------------------------
# scikit-fingerprints: MAPFingerprint (folded, dense)
# --------------------------------------------------
# MAPFingerprint is a MinHash-like fingerprint (different from MAP4 lib).
map_fp = MAPFingerprint(fp_size=4096, count=False, sparse=False)
X_map = compute_fingerprints(
    smiles,
    map_fp,
    config=FingerprintConfig(
        count=False,
        folded=True,
        return_csr=False,
        invalid_policy="raise",
    ),
)
print("skfp MAPFingerprint:", X_map.shape, X_map.dtype)

# ----------------------------------------------------
# scikit-fingerprints: AtomPairFingerprint (folded, CSR)
# ----------------------------------------------------
atom_pair = AtomPairFingerprint(fp_size=4096, count=False, sparse=False, use_3D=False)
X_ap_csr = compute_fingerprints(
    smiles,
    atom_pair,
    config=FingerprintConfig(
        count=False,
        folded=True,
        return_csr=True,
        invalid_policy="raise",
    ),
)
assert sp.issparse(X_ap_csr)
print("skfp AtomPair (CSR):", X_ap_csr.shape, X_ap_csr.dtype, "nnz=", X_ap_csr.nnz)

# (Optional) convert CSR -> dense if you need a NumPy array downstream:
X_ap = X_ap_csr.toarray().astype(np.float32, copy=False)