Related Experiment Video
Updated: Jul 17, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Can Large Language Models Translate MS/MS into Molecular Caption?
Menglin Zhou1,2, Chenhao Gong3, Shan Cong3
1Shenzhen Branch, Guangdong Laboratory for Lingnan Modern Agriculture, Genome Analysis Laboratory, Ministry of Agriculture and Rural Affairs, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, Shenzhen518120, People's Republic of China.
Abstract:
Mass spectrometry (MS) is central to molecular discovery, yet the interpretation of tandem mass spectra (MS/MS) remains limited by database dependence and an incomplete structural resolution. Here, we explore whether large language models (LLMs) can directly translate MS/MS spectra to chemically meaningful molecular descriptions. We introduce MS2LLM, a framework that represents spectra and molecular structures as natural languages and learns their correspondence through instruction tuning. MS2LLM generates hierarchical molecular descriptions, including functional groups, substructures, and chemical classes, directly from the spectral input. Across multiple datasets, it outperforms general-purpose LLMs and conventional spectral learning methods in both descriptive accuracy and chemical classification. Importantly, the model produces interpretable outputs that capture structural semantics rather than exact structures, offering a complementary paradigm for structural inference of unknowns.
Related Concept Videos
Molecular Models
Improving Translational Accuracy
Improving Translational Accuracy
Predicting Molecular Geometry
Tandem Mass Spectrometry
Genetic Lingo