While language models (LMs) have demonstrated remarkable general-purpose capabilities across domains, including molecule generation using line notations such as SMILES and SELFIES, their direct application to 3D structure design remains constrained by two interdependent challenges. First, the difficulty in designing a 3D line notation that ensures SE(3)-invariant atomic coordinates and supports autoregressive generation. Second, the incompatibility between continuous spatial coordinates and the discrete token inputs required by LMs. To address this, we propose Mol-StrucTok, a unified framework for tokenizing 3D molecular structures. Our approach comprises two key innovations: (1) a 3D line notation—Spherical Coordinate Notation—that encodes local atomic environments in spherical coordinates, agnostic to 2D notations and inherently SE(3)-invariant; and (2) a structure-aware Vector Quantized Variational Autoencoder (VQ-VAE) for discretizing these coordinates into chemically valid tokens suitable for language model processing. Leveraging this tokenization framework, we train a GPT-2 style model for end-to-end 3D molecular generation. Empirical results demonstrate strong, task-dependent performance: in unconditional generation, Mol-StrucTok achieves diffusion-level stability with ~28× faster inference; in conditional generation, it reduces property-matching mean absolute error (MAE) by 5–8× compared to diffusion-based methods, highlighting the advantage of autoregressive contextual modeling for precise control of molecular attributes. Our code is available at https://github.com/KyGao/Mol-StrucTok.

The integration of molecular and natural language representations has emerged as a focal point in molecular science, with recent advancements in Language Models (LMs) demonstrating significant potential for comprehensive modeling of both domains. However, existing approaches face notable limitations, particularly in their neglect of three-dimensional (3D) information, which is crucial for understanding molecular structures and functions. While some efforts have been made to incorporate 3D molecular information into LMs using external structure encoding modules, significant difficulties remain, such as insufficient interaction across modalities in pre-training and challenges in modality alignment. To address the limitations, we propose \textbf{3D-MolT5}, a unified framework designed to model molecule in both sequence and 3D structure spaces. The key innovation of our approach lies in mapping fine-grained 3D substructure representations into a specialized 3D token vocabulary. This methodology facilitates the seamless integration of sequence and structure representations in a tokenized format, enabling 3D-MolT5 to encode molecular sequences, molecular structures, and text sequences within a unified architecture. Leveraging this tokenized input strategy, we build a foundation model that unifies the sequence and structure data formats. We then conduct joint pre-training with multi-task objectives to enhance the model's comprehension of these diverse modalities within a shared representation space. Thus, our approach significantly improves cross-modal interaction and alignment, addressing key challenges in previous work. Further instruction tuning demonstrated that our 3D-MolT5 has strong generalization ability and surpasses existing methods with superior performance in multiple downstream tasks, such as nearly 70\% improvement on the molecular property prediction task compared to state-of-the-art methods. Our code is available at \url{https://github.com/QizhiPei/3D-MolT5}.

Molecular docking that predicts the bound structures of small molecules (ligands) to their protein targets, plays a vital role in drug discovery. However, existing docking methods often face limitations: they either overlook crucial structural changes by assuming protein rigidity or suffer from low computational efficiency due to their reliance on generative models for structure sampling. To address these challenges, we propose FABFlex, a fast and accurate regression-based multi-task learning model designed for realistic blind flexible docking scenarios, where proteins exhibit flexibility and binding pocket sites are unknown (blind). Specifically, FABFlex's architecture comprises three specialized modules working in concert: (1) A pocket prediction module that identifies potential binding sites, addressing the challenges inherent in blind docking scenarios. (2) A ligand docking module that predicts the bound (holo) structures of ligands from their unbound (apo) states. (3) A pocket docking module that forecasts the holo structures of protein pockets from their apo conformations. Notably, FABFlex incorporates an iterative update mechanism that serves as a conduit between the ligand and pocket docking modules, enabling continuous structural refinements. This approach effectively integrates the three subtasks of blind flexible docking—pocket identification, ligand conformation prediction, and protein flexibility modeling—into a unified, coherent framework. Extensive experiments on public benchmark datasets demonstrate that FABFlex not only achieves superior effectiveness in predicting accurate binding modes but also exhibits a significant speed advantage (208$\times$) compared to existing state-of-the-art methods. Our code is released at~\url{https://github.com/tmlr-group/FABFlex}.

Molecular docking is a pivotal process in drug discovery. While traditional techniques rely on extensive sampling and simulation governed by physical principles, deep learning has emerged as a promising alternative, offering improvements in both accuracy and efficiency. Building upon the foundational work of FABind, a model focused on speed and accuracy, we introduce FABind+, an enhanced iteration that significantly elevates the performance of its predecessor. We identify pocket prediction as a critical bottleneck in molecular docking and introduce an enhanced approach. In addition to the pocket prediction module, the docking module has also been upgraded with permutation loss and a more refined model design. These designs enable the regression-based FABind+ to surpass most of the generative models. In contrast, while sampling-based models often struggle with inefficiency, they excel in capturing a wide range of potential docking poses, leading to better overall performance. To bridge the gap between sampling and regression docking models, we incorporate a simple yet effective sampling technique coupled with a lightweight confidence model, transforming the regression-based FABind+ into a sampling version without requiring additional training. This involves the introduction of pocket clustering to capture multiple binding sites and dropout sampling for various conformations. The combination of a classification loss and a ranking loss enables the lightweight confidence model to select the most accurate prediction. Experimental results and analysis demonstrate that FABind+ (both the regression and sampling versions) not only significantly outperforms the original FABind, but also achieves competitive state-of-the-art performance. Our code is available at https://github.com/QizhiPei/FABind.

Molecular docking plays a crucial role in predicting the binding mode of ligands to target proteins, and covalent interactions, which involve the formation of a covalent bond between the ligand and the target, are particularly valuable due to their strong, enduring binding nature. However, most existing docking methods and deep learning approaches hardly account for the formation of covalent bonds and the associated structural changes. To address this gap, we introduce a comprehensive benchmark for covalent docking, CovDocker, which is designed to better capture the complexities of covalent binding. We decompose the covalent docking process into three main tasks: reactive location prediction, covalent reaction prediction, and covalent docking. By adapting state-of-the-art models, such as Uni-Mol and Chemformer, we establish baseline performances and demonstrate the effectiveness of the benchmark in accurately predicting interaction sites and modeling the molecular transformations involved in covalent binding. These results confirm the role of the benchmark as a rigorous framework for advancing research in covalent drug design. It underscores the potential of data-driven approaches to accelerate the discovery of selective covalent inhibitors and addresses critical challenges in therapeutic development.

Graph Transformers, emerging as a new architecture for graph representation learning, suffer from the quadratic complexity and can only handle graphs with at most thousands of nodes. To this end, we propose a Neighborhood Aggregation Graph Transformer (NAGphormer) that treats each node as a sequence containing a series of tokens constructed by our proposed Hop2Token module. For each node, Hop2Token aggregates the neighborhood features from different hops into different representations, producing a sequence of token vectors as one input. In this way, NAGphormer could be trained in a mini-batch manner and thus could scale to large graphs with millions of nodes. To further enhance the model's generalization, we propose NAGphormer+, an extended model of NAGphormer with a novel data augmentation method called Neighborhood Augmentation (NrAug). Based on the output of Hop2Token, NrAug simultaneously augments the features of neighborhoods from global as well as local views. In this way, NAGphormer+ can fully utilize the neighborhood information of multiple nodes, thereby undergoing more comprehensive training and improving the model's generalization capability. Extensive experiments on benchmark datasets from small to large demonstrate the superiority of NAGphormer+ against existing graph Transformers and mainstream GNNs, as well as the original NAGphormer.

Recent advancements in biological research leverage the integration of molecules, proteins, and natural language to enhance drug discovery.However, current models exhibit several limitations, such as the generation of invalid molecular SMILES, underutilization of contextual information, and equal treatment of structured and unstructured knowledge.To address these issues, we propose BioT5, a comprehensive pretraining framework that enriches cross-modal integration in biology with chemical knowledge and natural language associations.BioT5 utilizes SELFIES for 100% robust molecular representations and extracts knowledge from the surrounding context of bio-entities in unstructured biological literature.Furthermore, BioT5 distinguishes between structured and unstructured knowledge, leading to more effective utilization of information.After fine-tuning, BioT5 shows superior performance across a wide range of tasks, demonstrating its strong capability of capturing underlying relations and properties of bio-entities.Our code is available at https://github.com/QizhiPei/BioT5.

Antibodies are proteins that effectively protect the human body by binding to pathogens. Recently, deep learning-based computational antibody design has attracted popular attention since it automatically mines the antibody patterns from data that could be complementary to human experiences. However, the computational methods heavily rely on high-quality antibody structure data, which is quite limited. Besides, the complementarity-determining region (CDR), which is the key component of an antibody that determines the specificity and binding affinity, is highly variable and hard to predict. Therefore, the limited availability of high-quality antibody structure data exacerbates the difficulty of CDR generation. Fortunately, there is a large amount of sequence data for antibodies that can help model the CDR and reduce reliance on structure data. By witnessing the success of pre-training models for protein modeling, in this paper, we develop the antibody pre-training language model and incorporate it into the antigen-specific antibody design model in a systemic way. Specifically, we first pre-train a novel antibody language model based on the sequence data, then propose a one-shot way for sequence and structure generation of CDR to mitigate the high cost and error propagation associated with autoregressive methods, and finally leverage the pre-trained antibody model for the antigen-specific antibody generation model with some carefully designed modules. Our experiments demonstrate the superiority of our method over previous baselines in tasks such as sequence and structure generation, CDR-H3 design for antigen binding, and antibody optimization1. The code is available at https://github.com/KyGao/ABGNN.

Modeling the interaction between proteins and ligands and accurately predicting their binding structures is a critical yet challenging task in drug discovery. Recent advancements in deep learning have shown promise in addressing this challenge, with sampling-based and regression-based methods emerging as two prominent approaches. However, these methods have notable limitations. Sampling-based methods often suffer from low efficiency due to the need for generating multiple candidate structures for selection. On the other hand, regression-based methods offer fast predictions but may experience decreased accuracy. Additionally, the variation in protein sizes often requires external modules for selecting suitable binding pockets, further impacting efficiency. In this work, we propose FABind, an end-to-end model that combines pocket prediction and docking to achieve accurate and fast protein-ligand binding. FABind incorporates a unique ligand-informed pocket prediction module, which is also leveraged for docking pose estimation. The model further enhances the docking process by incrementally integrating the predicted pocket to optimize protein-ligand binding, reducing discrepancies between training and inference. Through extensive experiments on benchmark datasets, our proposed FABind demonstrates strong advantages in terms of effectiveness and efficiency compared to existing methods. Our code is available at https://github.com/QizhiPei/FABind.

To tackle the poor localization accuracy of multimobile robots caused by non-line-of-sight (NLOS) errors in a complex indoor environment and to meet the real-time requirement, this article proposes a multimobile robot cooperative localization system using ultrawideband (UWB) sensor and GPU hardware acceleration. First, a UWB multinode ranging network is established to obtain the relative distance information between robots and anchors. Then, the line-of-sight (LOS) and NLOS errors in distance information are effectively mitigated by using the proposed UWB ranging error mitigation algorithm based on the Bayesian filter. A cooperative particle filter (PF) localization algorithm based on the Gibbs sampling is designed to estimate the position information of each robot at any time. Finally, in order to improve the real-time performance of the collaborative localization system, a parallel Gibbs collaborative localization algorithm that can be accelerated by GPU is proposed considering the characteristics of GPU hardware and CUDA programming model. The experimental results of three TurtleBot2 mobile robots in real scene show that the proposed multimobile robot cooperative localization system using UWB technology can estimate the position information of each robot robustly and accurately, and the localization accuracy is superior to that of the popular extended Kalman filter (EKF) and PF algorithms. It is shown through further evaluations that the proposed parallel algorithm achieves about 3.2 times acceleration effect in the scenarios of three mobile robots. The speed gain is found more significant with more robots, which substantially improves the real-time performance of the cooperative localization system. In the test with seven mobile robots, the speedup is as high as 11.9, that is, the execution time of the algorithm is only 8.39% of that of the original algorithm. Note to Practitioners—The purpose of this article is to improve the accuracy and real-time indoor multimobile robot cooperative localization, but the method proposed in this article is also applicable to outdoor multimobile robot cooperative localization. The existing methods for indoor cooperative localization of mobile robots usually use Bluetooth, infrared, RFID, and other technologies to establish a wireless sensor network (WSN) and then combine Karman filter or particle filter (PF) to achieve cooperative localization, which is difficult to achieve low-cost and high-precision real-time localization. In this article, a new method of cooperative localization is proposed, which uses ultrawideband (UWB) ranging network with high penetration and high precision to obtain accurate distance information, then weakens NLOS error by the Bayesian filtering to further improve the accuracy of distance information, and, finally, uses a novel cooperative localization approach to realize fast and high-precision indoor multimobile robot localization. In addition, by redesigning the collaborative localization algorithm in parallel, the real-time performance of the algorithm is improved while ensuring high accuracy. The collaborative localization experiment of three mobile robots in the real scene shows that the proposed algorithm can effectively improve the localization accuracy, and the real-time performance of collaborative localization is significantly improved. However, the algorithm still has some limitations when mitigating UWB ranging errors in highly obstructed environments, and the algorithm parallelization framework can be further improved for higher real-time performance. In the future, we will further improve the robustness of cooperative localization and apply this algorithm to cooperative control of multiple mobile robots, such as formation control and cooperative search.

Capacitance sensors are widely used for sensing physical parameters. Conventional capacitance to digital methods use complex analog ADC techniques which are power hungry. Recently a fully digital solution was proposed with improved power consumption. This paper describes a number of problems in that solution, analyzes these problems, and proposes a new design free of these problems. A voltage senor as an example was designed based on the proposed capacitance to digital conversion in this paper. The new method achieves the same accuracy with less than half the circuit size, and 25% and 33% savings on power and energy consumption.