Tandem Mass Spectrometry is a cornerstone technique for identifying unknown small molecules in fields such as metabolomics, natural product discovery and environmental analysis. However, certain aspects, such as the probabilistic fragmentation process and size of the chemical space, make structure elucidation from such spectra highly challenging, particularly when there is a shift between the deployment and training conditions. Current methods rely on database matching of previously observed spectra of known molecules and multi-step pipelines that require intermediate fingerprint prediction or expensive fragment annotations. We introduce a novel end-to-end framework based on a transformer model that directly generates molecular structures from an input tandem mass spectrum and its corresponding molecular formula, thereby eliminating the need for manual annotations and intermediate steps, while leveraging transfer learning from simulated data. To further address the challenge of out-of-distribution spectra, we introduce a test-time tuning strategy that dynamically adapts the pre-trained model to novel experimental data. Our approach achieves a Top-1 accuracy of 3.16% on the MassSpecGym benchmark and 12.88% on the NPLIB1 datasets, considerably outperforming conventional fine-tuning. Baseline approaches are also surpassed by 27% and 67% respectively. Even when the exact reference structure is not recovered, the generated candidates are chemically informative, exhibiting high structural plausibility as reflected by strong Tanimoto similarity to the ground truth. Notably, we observe a relative improvement in average Tanimoto similarity of 83% on NPLIB1 and 64% on MassSpecGym compared to state-of-the-art methods. Our framework combines simplicity with adaptability, generating accurate molecular candidates that offer valuable guidance for expert interpretation of unseen spectra.
MolRGen: A Training and Evaluation Setting for De Novo Molecular Generation with Reasonning Models
Université Paris-Saclay(巴黎萨克雷大学);ÉTS Montréal(蒙特利尔ÉTS);ILLS – International Laboratory on Learning Systems(学习系统国际实验室);Mila – Quebec AI Institute(魁北克人工智能研究所);Mistral AI;LIVIA;CNRS, CentraleSupélec(国家科学研究中心,中央超导大学)
De Novo Molecular Generation via Connection-aware Motif Mining
University of Science and Technology of China(中国科学技术大学);Renmin University of China(中国人民大学);Microsoft Research AI4Science(微软研究院AI4Science);Hefei Comprehensive National Science Center(合肥综合性国家科学中心)
Artificial Intelligence Advances for De Novo Molecular Structure Modeling in Cryo-EM
University of Washington Bothell(华盛顿大学博塞尔分校);University of Washington Seattle(华盛顿大学西雅图分校);Saint Louis University(圣路易斯大学);Pacific Lutheran University(太平洋路德大学);University of Chicago(芝加哥大学)
Scalable and Cost-Efficient de Novo Template-Based Molecular Generation
Jagiellonian University, Faculty of Mathematics and Computer Science(雅盖隆大学数学与计算机科学学院);Mila – Québec AI Institute(魁北克AI研究所);Université de Montréal(蒙特利尔大学);University of Toronto(多伦多大学);The Hospital for Sick Children Research Institute(儿童医院研究所在);Acceleration Consortium(加速联盟);Vector Institute(向量研究所)
t-SMILES: A Scalable Fragment-based Molecular Representation Framework for De Novo Molecule Generation
State Key Laboratory of Chemo/Biosensing and Chemometrics, College of Chemistry and Chemical Engineering, Hunan University(湖南大学化学生物传感与计量学国家重点实验室,化学化工学院)
Proteo-R1: Reasoning Foundation Models for De Novo Protein Design
Stanford University(斯坦福大学);Shanghai Jiao Tong University(上海交通大学);Yale University(耶鲁大学);University of Notre Dame(圣母大学);University of Waterloo(滑铁卢大学);University of Chicago, USA(美国芝加哥大学);University of Hamburg, Germany(德国汉堡大学);University of New South Wales(新南威尔士大学);University of Tokyo(东京大学);Harvard University(哈佛大学);AWS AI, Amazon (work outside of Amazon)(亚马逊AWS人工智能(亚马逊外工作));Chinese University of Hong Kong(香港中文大学)
Deep Lead Optimization: Leveraging Generative AI for Structural Modification
College of Pharmaceutical Sciences, Zhejiang University(浙江大学药学院);AI Lab, Research Center for Industries of the Future, Westlake University(西湖大学未来产业研究中心AI实验室)
Human-level molecular optimization driven by mol-gene evolution
Hainan Institute of Zhejiang University(浙江大学海南研究院);Institute of Marine Biology and Pharmacology, Ocean College, Zhejiang University(浙江大学海洋学院海洋生物与药理研究所);College of Pharmaceutical Sciences and Cancer Center, Zhejiang University(浙江大学药学院与癌症中心)
Molecular Generative Adversarial Network with Multi-Property Optimization
Cloud Computing Technology and Application Department, Shandong Institute of Commerce and Technology(山东商业科技学院云计算技术与应用系);Graduate School of Advanced Science and Engineering, Hiroshima University(广岛大学研究生院);D3 Center, The University of Osaka(大阪大学D3中心);Graduate School of Informatics, Nagoya University(名古屋大学研究生院)
MolSculpt: Sculpting 3D Molecular Geometries from Chemical Syntax
AI for Science (AI4S)-Preferred Program, Peking University Shenzhen Graduate School, China(人工智能科学(AI4S)优选计划,北京大学深圳研究生院,中国);Faculty of Materials Science, Shenzhen MSU-BIT University, Shenzhen, China(材料科学学院,深圳MSU-BIT大学,中国)
MODA: A Unified 3D Diffusion Framework for Multi-Task Target-Aware Molecular Generation
School of Artificial Intelligence, Shenzhen University, Shenzhen, China(深圳大学人工智能学院);School of Computer Science, University of Nottingham Ningbo, Ningbo, China(诺丁汉大学宁波校区计算机科学学院);Biology Department, University of California San Diego, California, USA(加州大学圣地亚哥分校生物系)
Generative Active Learning for the Search of Small-molecule Protein Binders
Mila – Québec AI Institute(米拉-魁北克人工智能研究所);Dreamfold;McGill University(麦吉尔大学);Université de Montréal(蒙特利尔大学);IRIC, Université de Montréal(蒙特利尔大学IRIC研究所);Valence Labs(Valence实验室);X-Chem(X-Chem公司);MIT(麻省理工学院);AI Redefined
DiffSpectra: Molecular Structure Elucidation from Spectra using Diffusion Models
NLPR, MAIS, Institute of Automation(NLPR、MAIS、自动化研究所);School of Artificial Intelligence(人工智能学院);University of Chinese Academy of Sciences(中国科学院大学);Alibaba Group(阿里巴巴集团);Hupan Lab(华普实验室);College of Intelligence and Computing(智能与计算学院);National University of Singapore(新加坡国立大学);Cancer Science Institute of Singapore(新加坡癌症科学研究所)