OneProt: Towards Multi-Modal Protein Foundation Models
PriorLabs;Helmholtz AI(亥姆霍兹人工智能);Technical University of Munich(慕尼黑工业大学);Munich Data Science Institute(慕尼黑数据科学研究所);Munich Center for Machine Learning(慕尼黑机器学习中心);Institute of Bio- and Geosciences (IBG-4: Bioinformatics)(生物与地球科学研究所(IBG-4:生物信息学));Institute for Pharmaceutical and Medicinal Chemistry(药物与医药化学研究所);Helmholtz Munich(慕尼黑亥姆霍兹中心)
Klemens Flöge, Srisruthi Udayakumar, Johanna Sommer, Marie Piraud, Stefan Kesselheim, Vincent Fortuin, Stephan Günneman, Karel J van der Weg, Holger Gohlke, Eri… 展开作者
Klemens Flöge, Srisruthi Udayakumar, Johanna Sommer, Marie Piraud, Stefan Kesselheim, Vincent Fortuin, Stephan Günneman, Karel J van der Weg, Holger Gohlke, Erinc Merdivan, Alina Bazarova
Recent advances in Artificial Intelligence have enabled multi-modal systems to model and translate diverse information spaces. Extending beyond text and vision, we introduce OneProt, a multi-modal AI for proteins that integrates structural, sequence, text, and binding site data. Using the ImageBind framework, OneProt aligns the latent spaces of protein modality encoders in a lightweight fine-tuning scheme that focuses on pairwise alignment with sequence data rather than requiring full matches. This novel approach comprises a mix of Graph Neural Networks and transformer architectures. It demonstrates strong performance in retrieval tasks and showcases the efficacy of multi-modal systems in Protein Machine Learning through a broad spectrum of downstream baselines, including enzyme function prediction and binding site analysis. Furthermore, OneProt enables the transfer of representational information from specialized encoders to the sequence encoder, enhancing capabilities for distinguishing evolutionarily related and unrelated sequences and exhibiting representational properties where evolutionarily related proteins align in similar directions within the latent space. In addition, we extensively investigate modality ablations to identify the encoders that contribute most to predictive performance, highlighting the significance of the binding site encoder, which has not been used in similar models previously. This work expands the horizons of multi-modal protein models, paving the way for transformative applications in drug discovery, biocatalytic reaction planning, and protein engineering.
EvoLlama: Enhancing LLMs' Understanding of Proteins via Multimodal Structure and Sequence Representations
School of Computer Science and Technology, East China Normal University(华东师范大学计算机科学与技术学院);Institute of Artificial Intelligence (TeleAI), China Telecom(中国电信人工智能研究院(TeleAI));School of Computer Science, Fudan University(复旦大学计算机学院);Xiaohongshu Inc(小红书科技有限公司);Innovation Center for AI and Drug Discovery, School of Pharmacy, East China Normal University(华东师范大学药学院人工智能与药物发现创新中心)
Multi-modal Representation Learning Enables Accurate Protein Function Prediction in Low-Data Setting
Karadeniz Technical University(卡拉德尼兹技术大学);Middle East Technical University(中东技术大学);Health Sciences University Trabzon Kanuni Training and Research Hospital(特拉布宗卡努尼健康科学大学培训与研究医院);Hacettepe University(哈杰泰佩大学)
ProtCLIP: Function-Informed Protein Multi-Modal Learning
Zhejiang University(浙江大学);The Second Affiliated Hospital, School of Medicine, Zhejiang University(浙江大学医学院附属第二医院);Alibaba Cloud Computing(阿里云云计算);University of Science and Technology of China(中国科学技术大学);HKUST(Guangzhou)(香港科技大学(广州))
ProtCLIP 通过构建 ProtAnno 数据集和功能引导的分段预训练范式,学习功能感知的蛋白质多模态表示,在 22 个蛋白质基准上取得 SOTA 性能。
SE(3)-Equivariant Ternary Complex Prediction Towards Target Protein Degradation
University of Technology Sydney(悉尼科技大学);Nankai University(南开大学);Renmin University of China(中国人民大学);University of Chinese Academy of Sciences(中国科学院大学);Zhejiang University(浙江大学);University of California, Los Angeles(加利福尼亚大学洛杉矶分校)
TourSynbio: A Multi-Modal Large Model and Agent Framework to Bridge Text and Protein Sequences for Protein Engineering
Toursun Synbio(拓荪合成生物);Johns Hopkins University(约翰斯·霍普金斯大学);University of Cambridge(剑桥大学);Shanghai AI Laboratory(上海人工智能实验室);Shanghai Jiao Tong University(上海交通大学);City University of Hong Kong(香港城市大学)
RIGA-Fold: A General Framework for Protein Inverse Folding via Recurrent Interaction and Geometric Awareness
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China(深圳大学计算机科学与软件工程学院);National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China(大数据系统计算技术国家工程实验室)
Multi-Scale Representation Learning for Protein Fitness Prediction
Mila - Québec AI Institute(米拉 - 魁北克人工智能研究所);Université de Montréal(蒙特利尔大学);Harvard Medical School(哈佛医学院);IBM Research(IBM研究院);Broad Institute(布罗德研究所);HEC Montréal(蒙特利尔高等商学院);CIFAR(加拿大高级研究所)
BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and Language
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);OpenDataLab, Shanghai Artificial Intelligence Laboratory(上海人工智能实验室 OpenDataLab);Zhejiang University(浙江大学);Shanghai Innovation Institute(上海创新研究院);East China Normal University(华东师范大学);Zhongguancun Academy(中关村学院);School of Artificial Intelligence, Wuhan University(武汉大学人工智能学院)
GastroDL-Fusion: A Dual-Modal Deep Learning Framework Integrating Protein-Ligand Complexes and Gene Sequences for Gastrointestinal Disease Drug Discovery
Technical University of Munich(慕尼黑工业大学);University of Michigan(密歇根大学);Georgia Institute of Technology(佐治亚理工学院)
Interpretable Multimodal Learning for Tumor Protein-Metal Binding: Progress, Challenges, and Perspectives
Institute of Big Data Science and Industry, Shanxi University, Taiyuan, China(山西大学大数据科学与产业研究院);School of Computer and Information Technology, Shanxi University, Taiyuan, China(山西大学计算机与信息学院);Key Laboratory of Evolutionary Science Intelligence of Shanxi Province, Taiyuan, Shanxi, China(山西省进化科学智能重点实验室);Faculty of Computer Engineering, University of Isfahan, Isfahan, Iran(伊斯法罕大学计算机工程学院);The First Clinical Medical School, Shanxi Medical University, Taiyuan, China(山西医科大学第一临床医学院);School of Medicine & Population Health, University of Sheffield, Sheffield, UK(谢菲尔德大学医学院与人口健康学院);School of Computer Science, University of Sheffield, Sheffield, UK(谢菲尔德大学计算机科学学院);Centre for Machine Intelligence, University of Sheffield, Sheffield, UK(谢菲尔德大学智能中心)
Full-Atom Peptide Design based on Multi-modal Flow Matching
Helixon Research(Helixon研究院);Institute for AI Industry Research, Tsinghua University(清华大学人工智能产业研究院);Department of Computer Science, University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校计算机科学系)
Leveraging generative hallucination and biophysics-informed modeling for unified biomolecular sequence-structure co-design
University of Florida(佛罗里达大学);University of Chicago(芝加哥大学);Data Science Institute, University of Chicago(芝加哥大学数据科学研究所);Toyota Technological Institute at Chicago(芝加哥丰田技术研究所);Mayo Clinic(梅奥诊所);Argonne National Laboratory(阿贡国家实验室)
ZeroFold: Protein-RNA Binding Affinity Predictions from Pre-Structural Embeddings
Centre for Misfolding Diseases, Yusuf Hamied Department of Chemistry, University of Cambridge(错误折叠疾病中心,尤斯夫·哈米埃德化学系,剑桥大学);Medicinal Chemistry, Research and Early Development, Respiratory and Immunology, BioPharmaceuticals R&D, AstraZeneca(药物化学,研发与早期开发,呼吸与免疫学,生物制药研发,阿斯利康)
RosettaSearch: Multi-Objective Inference-Time Search for Protein Sequence Design
AI for Good, Microsoft Redmond(微软红mond AI for Good);Google DeepMind(谷歌DeepMind);Google Research(谷歌研究);Institute for Protein Design University of Washington(蛋白质设计研究所华盛顿大学);Microsoft Research New England(微软新英格兰研究);Department of Biochemistry Institute for Protein Design University of Washington(生物化学系蛋白质设计研究所华盛顿大学)