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.

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.

Accurate prediction of drug-target affinity (DTA) is of vital importance in early-stage drug discovery, facilitating the identification of drugs that can effectively interact with specific targets and regulate their activities. While wet experiments remain the most reliable method, they are time-consuming and resource-intensive, resulting in limited data availability that poses challenges for deep learning approaches. Existing methods have primarily focused on developing techniques based on the available DTA data, without adequately addressing the data scarcity issue. To overcome this challenge, we present the Semi-Supervised Multi-task training (SSM) framework for DTA prediction, which incorporates three simple yet highly effective strategies: (1) A multi-task training approach that combines DTA prediction with masked language modeling using paired drug-target data. (2) A semi-supervised training method that leverages large-scale unpaired molecules and proteins to enhance drug and target representations. This approach differs from previous methods that only employed molecules or proteins in pre-training. (3) The integration of a lightweight cross-attention module to improve the interaction between drugs and targets, further enhancing prediction accuracy. Through extensive experiments on benchmark datasets such as BindingDB, DAVIS and KIBA, we demonstrate the superior performance of our framework. Additionally, we conduct case studies on specific drug-target binding activities, virtual screening experiments, drug feature visualizations and real-world applications, all of which showcase the significant potential of our work. In conclusion, our proposed SSM-DTA framework addresses the data limitation challenge in DTA prediction and yields promising results, paving the way for more efficient and accurate drug discovery processes.

In this paper, we propose the Variance Reduced Randomized Kaczmarz (VR-RK) algorithm for XFEL signal particle imaging phase retrieval. The VR-RK algorithm is inspired by the randomized Kaczmarz algorithm and the variance reduction in stochastic gradient methods. The formulations of the VR-RK algorithm under the L1and L2constraints are also presented. Numerical simulations demonstrate that the VR-RK method has a faster convergence rate compared with the randomized Kaczmarz method. Tests on the synthetic signal particle imaging data and the PR772 XFEL real imaging data show that the VR-RK algorithm can recover information with higher accuracy. It is useful for biological data processing.

BACKGROUND: Interactions between ions and proteins have been extensively studied, yet most of the studies focus on the ion binding site. The binding mechanism for many ion binding sites can be clearly described from high resolution structures. Although knowledge accumulated on a case-by-case basis is valuable, it is also important to study the ion-protein interaction statistically. From experimentally determined structures, it is possible to examine the ion distribution around each amino acid. Such distributions can reveal relation between ions and amino acids, so it is desirable to carry out a systematic survey of 'ion-amino acid' pairing interaction and share the information with a publicly available database. RESULTS: The survey in the Protein Data Bank (PDB) revealed that approximately 40% of molecules records contain at least one ion. To reduce the bias resulted from protein redundancy, the statistics were extracted from a non-redundant dataset by excluding the proteins with similar sequences. Based on the structures of protein molecules and the location of ions, the statistical distributions of ions around each proteinogenic amino acid type were investigated and further summarized in a database. To systematically quantify the interactions between ions and each amino acid, the positions of ions were mapped to the coordinate system centered at each neighboring amino acid. It was found that the distribution of ions follows the expected rules governed by the physicochemical interactions in general. Large variations were observed, reflecting the preference in 'ion-amino acid' interactions. The analysis program is written in the Python programming language. The statistical results and program are available from the online database: ion distribution in protein molecules (IDPM) at http://liulab.csrc.ac.cn/idpm/ . CONCLUSION: The spatial distribution of ions around amino acids is documented and analyzed. The statistics can be useful for identifying ion types for a given site in biomolecules, and can be potentially used in ion position prediction for given structures.

Open source rendering engine OpenSceneGraph (OSG) is introduced, a virtual reality platform is made by integrating OSG with other open source software. Method that integrating OSG with Cal3d and the developing process of the platform in Microsoft Visual Studio.net is brought out, as well as character animation in OSG environment. The platform developed is applied into a virtual reality runner training electronics treadmill. Feasibility of the method is proven.