Qifeng Wu, Zhengzhe Liu, Han Zhu, Yizhou Zhao, Daisuke Kihara, Min Xu
备注：
4 pages for body, 3 pages for appendix, 11 figures. Accepted to CVPR 2025 Workshop on Multimodal Foundation Models for Biomedicine: Challenges and Opportunities(MMFM-BIOMED)
本文旨在从大规模蛋白质数据集中检索具有相似结构和语义的蛋白质，以促进对通过冷冻电子显微镜（cryo-EM）等结构测定方法获得的蛋白质结构进行功能解释。受视觉-语言模型（VLMs）最新进展的启发，我们提出了一种 CLIP 风格的框架，通过对比学习将三维蛋白质结构与功能注释对齐。在模型训练方面，我们构建了一个包含约200,000个蛋白质-描述对、具有丰富功能描述符的大规模数据集。我们分别在 Protein Data Bank（PDB）和 Electron Microscopy Data Bank（EMDB）数据集上评估了模型的域内检索以及更具挑战性的跨数据库检索性能。在两种情况下，我们的方法均展现出良好的零样本检索性能，凸显了多模态基础模型在蛋白质生物学中结构-功能理解方面的潜力。
英文摘要：
This paper aims to retrieve proteins with similar structures and semantics from large-scale protein dataset, facilitating the functional interpretation of protein structures derived by structural determination methods like cryo-Electron Microscopy (cryo-EM). Motivated by the recent progress of vision-language models (VLMs), we propose a CLIP-style framework for aligning 3D protein structures with functional annotations using contrastive learning. For model training, we propose a large-scale dataset of approximately 200,000 protein-caption pairs with rich functional descriptors. We evaluate our model in both in-domain and more challenging cross-database retrieval on Protein Data Bank (PDB) and Electron Microscopy Data Bank (EMDB) dataset, respectively. In both cases, our approach demonstrates promising zero-shot retrieval performance, highlighting the potential of multimodal foundation models for structure-function understanding in protein biology.
Aligning Large Language Models and Geometric Deep Models for Protein Representation
Northwestern University（西北大学）；University of Pittsburgh（匹兹堡大学）；Michigan State University（密歇根州立大学）；North Carolina State University（北卡罗来纳州立大学）；New Jersey Institute of Technology（新泽西理工学院）
Aligning Extraction and Generation for Robust Retrieval-Augmented Generation
Meta；Institute for Clarity in Documentation（清晰文档研究所）；Inria Paris-Rocquencourt（Inria 巴黎-罗克quencourt 分所）；Rajiv Gandhi University（拉朱·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕勒尔研究实验室）
Multilingual Text-to-Image Person Retrieval via Bidirectional Relation Reasoning and Aligning
School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）；School of Computer Science, Wuhan University（武汉大学计算机学院）；Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新 generation 人工智能技术及交叉应用重点实验室（东南大学），教育部，中国）
DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval
Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China（数据科学与人工智能系，香港理工大学，香港特别行政区，中国）；Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong SAR, China（应用数学系，香港理工大学，香港特别行政区，中国）
The University of Hong Kong（香港大学）；Peking University（北京大学）；Microsoft Research Asia（微软亚洲研究院）；University of Waterloo（滑铁卢大学）
Protein language models have excelled in a variety of tasks, ranging from structure prediction to protein engineering. However, proteins are highly diverse in functions and structures, and current state-of-the-art models including the latest version of AlphaFold rely on Multiple Sequence Alignments (MSA) to feed in the evolutionary knowledge. Despite their success, heavy computational overheads, as well as the de novo and orphan proteins remain great challenges in protein representation learning. In this work, we show that MSAaugmented models inherently belong to retrievalaugmented methods. Mo…
RCSB PDB AI Help Desk: retrieval-augmented generation for protein structure deposition support
RCSB Protein Data Bank, Rutgers, The State University of New Jersey（RCSB蛋白质数据银行，新泽西州立大学拉特格斯分校）；RCSB Protein Data Bank, San Diego Supercomputer Center, University of California San Diego（RCSB蛋白质数据银行，圣地亚哥超级计算机中心，加州大学圣地亚哥分校）
Aligning multiple protein structures can yield valuable information about structural similarities among related proteins, as well as provide insight into evolutionary relationships between proteins in a family. We have developed an algorithm (msTALI) for aligning multiple protein structures using biochemical and biophysical properties, including torsion angles, secondary structure, hydrophobicity, and surface accessibility. The algorithm is a progressive alignment algorithm motivated by popular techniques from multiple sequence alignment. It has demonstrated success in aligning the major struc…
Aligning image and text encoders from scratch using contrastive learning requires large amounts of paired image-text data. We alleviate this need by aligning individually pre-trained language and vision representation models using a much smaller amount of paired data, augmented with a curriculum learning algorithm to learn fine-grained vision-language alignments. TOnICS (Training with Ontology-Informed Contrastive Sampling) initially samples minibatches whose image-text pairs contain a wide variety of objects to learn object-level alignment, and progressively samples minibatches where all imag…
ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback
Mila-Québec Artificial Intelligence Institute（米拉-魁北克人工智能研究所）；Arizona State University（亚利桑那州立大学）；Princeton University（普林斯顿大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Université de Montréal（蒙特利尔大学）；National Research Council Canada（加拿大国家研究委员会）
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Nanjing University（南京大学）
In this paper, we attempts to learn a single metric across two heterogeneous domains where source domain is fully labeled and has many samples while target domain has only a few labeled samples but abundant unlabeled samples. To the best of our knowledge, this task is seldom touched. The proposed learning model has a simple underlying motivation: all the samples in both the source and the target domains are mapped into a common space, where both their priors P(sample)s and their posteriors P(label|sample)s are forced to be respectively aligned as much as possible. We show that the two mappings…
ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning
Massachusetts Institute of Technology（麻省理工学院）；Laboratory for Atomistic and Molecular Mechanics (LAMM)（原子与分子力学实验室）；Center for Computational Science and Engineering（计算科学与工程中心）；Schwarzman College of Computing（施瓦茨曼计算学院）
DrugCLIP: Contrastive Protein-Molecule Representation Learning for Virtual Screening
Institute for AI Industry Research（人工智能产业研究院）；Tsinghua University（清华大学）；Peking University（北京大学）；Institute of Automation（自动化研究所）；Chinese Academy of Science（中国科学院）
Aligning Large Language Models with Searcher Preferences
School of Artificial Intelligence and Data Science, University of Science and Technology of China（中国科学技术大学人工智能与数据科学学院）；Xiaohongshu Inc.（小红书公司）；Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）人工智能研究所）；Department of Computer Science and Engineering, The Hong Kong University of Science and Technology（香港科技大学计算机科学与工程系）
Learning Protein-Ligand Binding in Hyperbolic Space
Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China（人工智能产业研究院（AIR），清华大学，北京，中国）；University of Electronic Science and Technology of China, Chengdu, China（电子科技大学，成都，中国）；Department of Computer Science and Technology, Tsinghua University, Beijing, China（计算机科学与技术系，清华大学，北京，中国）；Beijing Academy of Artificial Intelligence, Beijing, China（北京人工智能研究院，北京，中国）
Context-DPO: Aligning Language Models for Context-Faithfulness
University of Chinese Academy of Sciences（中国科学院大学）；Microsoft Corporation（微软公司）；University of California, Merced（加州大学默塞德分校）；National University of Singapore（新加坡国立大学）
In this paper we report on an algorithm for aligning multiple protein structures. The algorithm has been tested on a variety of inputs and it performs well in comparison to well-known algorithms for this problem.
InstructProtein: Aligning Human and Protein Language via Knowledge Instruction
Zhejiang University（浙江大学）；ZJU-Hangzhou Global Scientific and Technological Innovation Center（浙江大学杭州国际科创中心）；AZFT Joint Lab for Knowledge Engine（AZFT知识引擎联合实验室）
Sequences of nucleotides (for DNA and RNA) or amino acids (for proteins) are central objects in biology. Among the most important computational problems is that of sequence alignment, i.e. arranging sequences from different organisms in such a way to identify similar regions, to detect evolutionary relationships between sequences, and to predict biomolecular structure and function. This is typically addressed through profile models, which capture position-specificities like conservation in sequences, but assume an independent evolution of different positions. Over the last years, it has been w…
This paper presents the methods that have participated in the SHREC 2021 contest on retrieval and classification of protein surfaces on the basis of their geometry and physicochemical properties. The goal of the contest is to assess the capability of different computational approaches to identify different conformations of the same protein, or the presence of common sub-parts, starting from a set of molecular surfaces. We addressed two problems: defining the similarity solely based on the surface geometry or with the inclusion of physicochemical information, such as electrostatic potential, am…
Retrieval and competition: how a protein foundation model starts a protein
Department of Biology, University of Oxford, Oxford, UK（牛津大学生物学系）；Kavli Institute for Nanoscience Discovery, University of Oxford, Oxford, UK（牛津大学纳科学发现研究所）；Department of Chemistry, University of Oxford, Oxford, UK（牛津大学化学系）
Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction
Department of Systems Biology, Harvard Medical School（系统生物学系，哈佛医学院）；Department of Computer Science, University of Oxford（计算机科学系，牛津大学）；Department of Computer Science, University of Copenhagen（计算机科学系，哥本哈根大学）；Enzyme research, Novonesis（酶研究，Novonesis）
SHREC 2025: Protein surface shape retrieval including electrostatic potential
organization= Laboratoire GBCM, EA7528, Conservatoire Nationale des Arts et Métiers , city= Paris , country= France；organization= National Institute of Technology, Tsuyama College , city= Tsuyama , country= Japan；organization= CONTACT AI Research, CONTACT Software GmbH , city= Bremen , country= Germany；organization= Changsha University of Science；organization= Department of Biological Sciences, Purdue University , city= West Lafayette, IN , country= USA；organization= Department of Computer Science, Purdue University , city= West Lafayette, IN , country= USA；organization= De Vinci Higher Education, De Vinci Research Center , city= Paris , country= France；organization= IMT Nord Europe, Institut Mines-Télécom, Université de Lille, Center for Digital Systems , city= Lille , country= France；organization= Yunnan Normal University , city= Kunming, Yunnan , country= China；organization= New York University Abu Dhabi , city= Abu Dhabi , country= UAE；organization= Department of Chemistry, Queen’s University , city= Kingston, ON , country= Canada；organization= University of Science, VNU-HCM , city= Ho Chi Minh City , country= Vietnam；organization= Vietnam National University , city= Ho Chi Minh City , country= Vietnam
Toyota Technological Institute at Chicago（芝加哥丰田工业大学）
Proteins are the basic building blocks of life. They usually perform functions by folding to a particular structure. Understanding the folding process could help the researchers to understand the functions of proteins and could also help to develop supplemental proteins for people with deficiencies and gain more insight into diseases associated with troublesome folding proteins. Experimental methods are both expensive and time consuming. In this thesis I introduce a new machine learning based method to predict the protein structure. The new method improves the performance from two directions: …
The flexibility in gap cost enjoyed by Hidden Markov Models (HMMs) is expected to afford them better retrieval accuracy than position-specific scoring matrices (PSSMs). We attempt to quantify the effect of more general gap parameters by separately examining the influence of position- and composition-specific gap scores, as well as by comparing the retrieval accuracy of the PSSMs constructed using an iterative procedure to that of the HMMs provided by Pfam and SUPERFAMILY, curated ensembles of multiple alignments. We found that position-specific gap penalties have an advantage over uniform gap …
Do Protein Transformers Have Biological Intelligence?
University of Delaware（德克萨斯大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Yale University（耶鲁大学）；University of Louisiana at Lafayette（路易斯安那州立大学）
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）
