molclaw-mol-basic-metrics

What problem does it solve?

Provide reliable, per-molecule basic property calculations from SMILES strings to support data curation, quality control, and downstream screening or optimization workflows, while detecting inconsistencies between reported formula and computed mass.

Core Features & Use Cases

• Batch SMILES processing: Accepts a list of SMILES strings and returns per-molecule metrics.
• Key metrics computed: molecular formula, exact and average molecular weights, heavy and total atom counts, bond counts, valence electrons, and formal charge.
• Validation guidance: Includes a molecular weight vs formula consistency check to flag parsing errors and prompt SMILES re-validation.
• Use Cases: Dataset QC before model training, preprocessing for virtual screening, and sanity-checking molecules produced by generative models.

Quick Start

Use molclaw-mol-basic-metrics to compute formulas, exact and average molecular weights, atom and bond counts, valence electrons, and formal charge for the provided list of SMILES and report any MW/formula inconsistencies.