Language Models Can Understand Spectra: A Multimodal Model for Molecular Structure Elucidation
By: Yunyue Su , Jiahui Chen , Zao Jiang and more
Potential Business Impact:
Helps scientists figure out what things are made of.
Structure elucidation is a fundamental technique for understanding the microscopic composition of matter and is widely applied across various disciplines in the natural sciences and engineering. However, existing methods often rely heavily on prior databases or known structural information, making it difficult to resolve unknown structures. In addition, complex structures typically require the joint analysis of multiple spectroscopic modalities. This process heavily depends on expert domain knowledge and is often accompanied by high costs in terms of both time and instrumentation. To address these challenges, we propose SpectraLLM, the first large language model designed to support multi-modal spectroscopic joint reasoning. SpectraLLM is capable of processing either single or multiple spectroscopic inputs and performing end-to-end structure elucidation. By integrating continuous and discrete spectroscopic modalities into a shared semantic space, SpectraLLM learns to uncover substructural patterns that are consistent and complementary across spectra, enabling precise molecular structure elucidation. We pretrain and fine-tune SpectraLLM in the domain of small molecules, and evaluate it on six standardized, publicly available chemical datasets. The model achieves state-of-the-art performance, significantly outperforming existing approaches trained on single modalities. Notably, SpectraLLM demonstrates strong robustness and generalization even for single-spectrum inference, while its multi-modal reasoning capability further improves the accuracy of structural prediction.
Similar Papers
DiffSpectra: Molecular Structure Elucidation from Spectra using Diffusion Models
Machine Learning (CS)
**Finds molecule shapes from sound and light.**
Breaking the Modality Barrier: Generative Modeling for Accurate Molecule Retrieval from Mass Spectra
Machine Learning (CS)
Finds hidden molecule shapes from chemical fingerprints.
Test-Time Tuned Language Models Enable End-to-end De Novo Molecular Structure Generation from MS/MS Spectra
Artificial Intelligence
Finds new chemicals from their broken pieces.