QuantumChem-200K: A Large-Scale Open Organic Molecular Dataset for Quantum-Chemistry Property Screening and Language Model Benchmarking

TL;DR

QuantumChem-200K is a comprehensive large-scale dataset of over 200,000 organic molecules with detailed quantum-chemical properties, enabling AI-driven screening and discovery of photoinitiators and related materials.

Contribution

The paper introduces QuantumChem-200K, the first extensive dataset with diverse quantum-chemical properties for organic molecules, and demonstrates fine-tuning of a language model for property prediction.

Findings

Fine-tuned language model outperforms baselines in property prediction.

QuantumChem-200K enables high-throughput screening of photoinitiators.

Benchmarking shows improved accuracy for TPA and ISC predictions.

Abstract

The discovery of next-generation photoinitiators for two-photon polymerization (TPP) is hindered by the absence of large, open datasets containing the quantum-chemical and photophysical properties required to model photodissociation and excited-state behavior. Existing molecular datasets typically provide only basic physicochemical descriptors and therefore cannot support data-driven screening or AI-assisted design of photoinitiators. To address this gap, we introduce QuantumChem-200K, a large-scale dataset of over 200,000 organic molecules annotated with eleven quantum-chemical properties, including two-photon absorption (TPA) cross sections, TPA spectral ranges, singlet-triplet intersystem crossing (ISC) energies, toxicity and synthetic accessibility scores, hydrophilicity, solubility, boiling point, molecular weight, and aromaticity. These values are computed using a hybrid workflow that integrates density function theory (DFT), semi-empirical excited-state methods, atomistic quantum solvers, and neural-network predictors. Using QuantumChem-200K, we fine tune the open-source Qwen2.5-32B large language model to create a chemistry AI assistant capable of forward property prediction from SMILES. Benchmarking on 3000 unseen molecules from VQM24 and ZINC20 demonstrates that domain-specific fine-tuning significantly improves accuracy over GPT-4o, Llama-3.1-70B, and the base Qwen2.5-32B model, particularly for TPA and ISC predictions central to photoinitiator design. QuantumChem-200K and the corresponding AI assistant together provide the first scalable platform for high-throughput, LLM-driven photoinitiator screening and accelerated discovery of photosensitive materials.