Structure-based drug design (SBDD) is crucial for developing specific and effective therapeutics against protein targets but remains challenging due to complex protein-ligand interactions and vast chemical space. Although language models (LMs) have excelled in natural language processing, their application in SBDD is underexplored. To bridge this gap, we introduce a method, known as Frag2Seq, to apply LMs to SBDD by generating molecules in a fragment-based manner in which fragments correspond to functional modules. We transform 3D molecules into fragment-informed sequences using SE(3)-equivariant molecule and fragment local frames, extracting SE(3)-invariant sequences that preserve geometric information of 3D fragments. Furthermore, we incorporate protein pocket embeddings obtained from a pre-trained inverse folding model into the LMs via cross-attention to capture protein-ligand interaction, enabling effective target-aware molecule generation. Benefiting from employing LMs with fragment-based generation and effective protein context encoding, our model achieves the best performance on binding vina score and chemical properties such as QED and Lipinski, which shows our model's efficacy in generating drug-like ligands with higher binding affinity against target proteins. Moreover, our method also exhibits higher sampling efficiency compared to atom-based autoregressive and diffusion baselines with at most ~300x speedup.
Molexar: A Unified Multimodal Molecular Foundation Model for Drug Design
Center for Quantitative Biology, Academy for Advanced Interdisciplinary Studies, Peking University（北京大学前沿交叉学科研究院定量生物学中心）；School of Life Sciences, Peking University（北京大学生命科学学院）；Department of Pathology, The First Affiliated Hospital of Shantou University Medical College（汕头大学医学院第一附属医院病理科）；BNLMS, College of Chemistry and Molecular Engineering, Peking University（北京大学化学与分子工程学院北京分子科学国家研究中心）；Peking-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies, Peking University（北京大学前沿交叉学科研究院清华-北大生命科学中心）；Peking University Chengdu Academy for Advanced Interdisciplinary Biotechnologies（北京大学成都前沿交叉生物技术研究院）
A Foundation Chemical Language Model for Comprehensive Fragment-Based Drug Discovery
Advanced Technology Core for Macromolecular X-Ray Crystallography（宏分子X射线衍射先进技术核心）；Verna and Marrs McLean Dept. of Biochemistry and Molecular Pharmacology（韦纳和玛里斯麦克莱恩生物化学与分子药理学系）；Dept. of Molecular & Cellular Biology（分子与细胞生物学系）；Dept. of Molecular Virology & Microbiology（分子病毒学与微生物学系）；Baylor College of Medicine（贝勒医学院）
Fragment-Masked Diffusion for Molecular Optimization
School of Computer Science, Wuhan University（武汉大学计算机学院）；Department of Computing, Macquarie University（麦考瑞大学计算机系）；School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院）；Department of Abdominal Oncology, Hubei Cancer Hospital（湖北癌症医院腹部肿瘤科）
Flow-Based Fragment Identification via Binding Site-Specific Latent Representations
Ecole Polytechnique Fédérale de Lausanne（瑞士联邦理工学院）；Oxford University（牛津大学）；VantAI；Aithyra Research Institute for Biomedical Artificial Intelligence（Aithyra生物医学人工智能研究所）；National Centre of Competence in Research (NCCR) Catalysis EPFL, Switzerland（瑞士国家研究能力中心（NCCR）催化EPFL，瑞士）
FragmentGPT: A Unified GPT Model for Fragment Growing, Linking, and Merging in Molecular Design
Department of Computer Science, University of Chicago（芝加哥大学计算机科学系）；Pritzker School of Molecular Engineering, University of Chicago（芝加哥大学分子工程学院）；Department of Chemistry, University of Chicago（芝加哥大学化学系）；Argonne National Laboratory（阿贡国家实验室）；AI Lab, Princeton University（普林斯顿大学人工智能实验室）
Character-level Tokenizations as Powerful Inductive Biases for RNA Foundational Models
Nostrum Biodiscovery（诺斯特伦生物发现公司）；Institute for Research in Biomedicine (IRB Barcelona), The Barcelona Institute of Science and Technology（巴塞罗那科学技术研究所生物医药研究所（IRB巴塞罗那））；Barcelona Supercomputing Center（巴塞罗那超级计算中心）
FusionDTI: Fine-grained Binding Discovery with Token-level Fusion for Drug-Target Interaction
School of Computing Science（计算科学学院）；School of Cancer Sciences（癌症科学学院）；Cancer Research UK Scotland Institute（英国癌症研究苏格兰研究所）；University of Glasgow（格拉斯哥大学）
AutoBinder Agent: An MCP-Based Agent for End-to-End Protein Binder Design
Guangzhou Institutes of Biomedicine and Health（广州生物医学研究院）；Chinese Academy of Sciences（中国科学院）；Renmin University of China（中国人民大学）；South China University of Technology（华南理工大学）；RIKEN, Japan（日本理化学研究所）；Westlake University（西湖大学）
Structure-Based Drug Design via 3D Molecular Generative Pre-training and Sampling
ByteDance Research（字节跳动研究院）；Carnegie Mellon University（卡内基梅隆大学）；Guanghua Law School（光华法学院）；Zhejiang University（浙江大学）；Shanghai Institute of Materia Medica（上海药物研究所）；Chinese Academy of Sciences（中国科学院）；Institute of AI Industrial Research（人工智能产业研究院）；Tsinghua University（清华大学）
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）
READ: A Retrieval-Alignment Diffusion Framework for Structure-based Drug Design
School of Artificial Intelligence（人工智能学院）；Shenzhen University（深圳大学）；National Engineering Laboratory for Big Data System Computing Technology（大数据系统计算技术国家工程实验室）；School of Computer Science（计算机科学学院）；University of Nottingham Ningbo（诺丁汉大学宁波校区）；Department of Computing（计算学院）
Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension
Tsinghua University（清华大学）；University of Washington（华盛顿大学）；Massachusetts Institute of Technology（麻省理工学院）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；ByteDance Inc.（字节跳动公司）；Helixon Inc.（Helixon公司）
