القائمة
Datamol for molecular manipulation, SMILES processing, and cheminformatics
Shared operational contract for all MedSci agents: sequential execution, planning phase, retry limits, evidence standards.
Isolated exploratory code execution with medsci-sandbox tools. Use when analysis requires custom code beyond existing domain MCP tools.
AlphaFold DB for predicted protein structures and pLDDT confidence scores
Molecular biology toolkit. Use for FASTA parsing, sequence analysis, and translation.
ChEMBL database access for bioactivity data and target search
Molecular ML with DeepChem - featurizers, models, and molecular property prediction
| name | datamol |
| description | Datamol for molecular manipulation, SMILES processing, and cheminformatics |
Datamol is a lightweight Python library built on top of RDKit that simplifies molecular manipulation. It provides a clean API for SMILES parsing, standardization, fingerprints, scaffolds, and visualization.
import datamol as dm
# Parse and standardize SMILES
mol = dm.to_mol("CC(=O)Oc1ccccc1C(=O)O")
std_mol = dm.standardize_mol(mol)
smiles = dm.to_smiles(std_mol, canonical=True)
# Fix and sanitize
mol = dm.to_mol("bad_smiles", ordered=True) # returns None if invalid
fixed = dm.fix_mol(mol)
sanitized = dm.sanitize_mol(fixed)
# Molecular properties
dm.descriptors.mw(mol) # molecular weight
dm.descriptors.logp(mol) # cLogP
dm.descriptors.tpsa(mol) # topological polar surface area
dm.descriptors.n_hba(mol) # H-bond acceptors
dm.descriptors.n_hbd(mol) # H-bond donors
# Fingerprints
fp = dm.to_fp(mol, fp_type="ecfp", n_bits=2048) # numpy array
dm.to_scaffold_murcko(mol), dm.fragment.brics(mol).None inputs (return None).dm.to_smiles returns canonical SMILES by default.dm.to_mol(["CCO", "c1ccccc1"]) accepts lists.dm.cluster.cluster_mols(mols, cutoff=0.7).pip install datamol.