Endowing Molecular Language with Geometry Perception via Modality Compensation for High-Throughput Quantum Hamiltonian Prediction

TL;DR

This paper introduces a geometry-aware molecular language model that predicts quantum Hamiltonians efficiently using SMILES, employing modality compensation and weak supervision to bypass expensive geometric data, achieving significant speedups with maintained accuracy.

Contribution

The novel modality compensation strategy enables accurate Hamiltonian prediction from SMILES alone, reducing reliance on costly geometric data and improving data efficiency through weak supervision.

Findings

Achieves up to 100x speedup over traditional methods

Maintains comparable accuracy with reduced geometric data dependence

Proves theoretical bounds on prediction error without explicit geometry

Abstract

The quantum Hamiltonian is a fundamental property that governs a molecule's electronic structure and behavior, and its calculation and prediction are paramount in computational chemistry and materials science. Accurate prediction is highly reliant on extensive training data, including precise molecular geometries and the Hamiltonian matrices, which are expensive to acquire via either experimental or computational methods. Towards a fast yet accurate method for Hamiltonian prediction, we first introduce a geometry information-aware molecular language model to bypass the use of expensive molecular geometries by only using the readily available molecular language -- simplified molecular input line entry system (SMILES). Our method employs multimodal alignment to bridge the relationship between SMILES strings and their corresponding molecular geometries. Recognizing that the molecular language inherently lacks explicit geometric information, we propose a geometry modality compensation strategy to imbue molecular language representations with essential geometric features, thereby enabling accurate predictions using SMILES. In addition, given the high cost of acquiring Hamiltonian data, we devise a weakly supervised strategy to fine-tune the molecular language model, thus improving the data efficiency. Theoretically, we prove that the prediction generalization error without explicit molecular geometry can be bounded through our modality compensation scheme. Empirically, our method achieves superior computational efficiency, providing up to 100x speedup over conventional quantum mechanical methods while maintaining comparable prediction accuracy. We further demonstrate the practical case study of our approach in the screening of electrolyte formulations.