MolCodon: A Codon-Based Molecular Language for InterpretableStructural Representation and Similarity Search (opens in new tab)

Molecular representation determines which aspects of chemical structure can be learned, com-pared, and interpreted in computational drug discovery. Existing encodings typically emphasize either compact string description, as in SMILES and SELFIES, or efficient similarity search, as in circular fingerprints, but they may not simultaneously provide deterministic sequence structure, graph-level interpretability, pharmacophore annotation, and high-fidelity molecular reconstruction. Here, we intro...