Aligned Manifold Property and Topology Point Clouds for Learning Molecular Properties

TL;DR

This paper introduces AMPTCR, a novel molecular surface representation combining local quantum and topological features within an aligned point cloud, enabling efficient and accurate prediction of molecular properties using standard neural architectures.

Contribution

AMPTCR is a new surface-based molecular representation that integrates quantum and topological data in an aligned point cloud format, improving property prediction efficiency and accuracy.

Findings

AMPTCR achieves a validation R^2 of 0.87 for molecular weight prediction.

AMPTCR enables classification with ROC AUC of 0.912 for bacterial inhibition.

AMPTCR provides a compact, expressive, and architecture-agnostic molecular representation.

Abstract

Machine learning models for molecular property prediction generally rely on representations -- such as SMILES strings and molecular graphs -- that overlook the surface-local phenomena driving intermolecular behavior. 3D-based approaches often reduce surface detail or require computationally expensive SE(3)-equivariant architectures to manage spatial variance. To overcome these limitations, this work introduces AMPTCR (Aligned Manifold Property and Topology Cloud Representation), a molecular surface representation that combines local quantum-derived scalar fields and custom topological descriptors within an aligned point cloud format. Each surface point includes a chemically meaningful scalar, geodesically derived topology vectors, and coordinates transformed into a canonical reference frame, enabling efficient learning with conventional SE(3)-sensitive architectures. AMPTCR is evaluated using a DGCNN framework on two tasks: molecular weight and bacterial growth inhibition. For molecular weight, results confirm that AMPTCR encodes physically meaningful data, with a validation R^2 of 0.87. In the bacterial inhibition task, AMPTCR enables both classification and direct regression of E. coli inhibition values using Dual Fukui functions as the electronic descriptor and Morgan Fingerprints as auxiliary data, achieving an ROC AUC of 0.912 on the classification task, and an R^2 of 0.54 on the regression task. These results help demonstrate that AMPTCR offers a compact, expressive, and architecture-agnostic representation for modeling surface-mediated molecular properties.