生成式 AI 如何助力蛋白质科学研究-郑在翔.pdf

1、生成式AI如何助力蛋白质科学研究ByteDance Research/郑在翔 How Generative AI Accelerates Protein ResearchWere doing AI for Science at ByteDance ResearchAI Protein Modeling&DesignLearning Harmonic Molecular Representations on Riemannian Manifold.In ICLR 2023On Pre-training Language Model for Antibody.In ICLR 2023Structu

2、re-informed Language Models Are Protein Designers.In ICML 2023(oral)Diffusion Language Models Are Versatile Protein Learners.In ICML 2024.Protein Conformation Generation via Force-Guided SE(3)Diffusion Models.In ICML 2024.Antigen-Specific Antibody Design via Direct Energy-based Preference Optimizati

3、on.preprint.2024Small Molecule DesignRegularized Molecular Conformation Fields.In NeurIPS 2022Zero-Shot 3D Drug Design by Sketching and Generating.In NeurIPS 2022Diffusion Models with Decomposed Priors for Structure-Based Drug Design.In ICML 2023DecompOpt:Controllable and Decomposed Diffusion Models

4、 for Structure-based Molecular Optimization.In ICLR 2024Cryo-EMCryoSTAR:Leveraging Structural Prior and Constraints for Cryo-EM Heterogeneous Reconstruction.preprint.2023_Structure-informed Language Models Are Protein Designers.In ICML 2023(oral)LM-DESIGN:steering large protein LMs to design protein

5、 sequencesas structure-conditioned sequence generative modelsDPLM:A Versatile Protein Foundation Model_Diffusion Language Models Are Versatile Protein Learners.In ICML 2024.AbDPO:designing antibodies with energy-based DPO _Antigen-Specific Antibody Design via Direct Energy-based Preference Optimizat

6、ion.2024(under review)Small Molecule Drug Design:DecompDiff_Diffusion Models with Decomposed Priors for Structure-Based Drug Design.In ICML 2023ConDiff:Protein Dynamic Conformation Generation with Physics-guided SE(3)Diffusion Model_Protein Conformation Generation via Force-Guided SE(3)Diffusion Mod