In the process of targeted drug molecule design, models that incorporate three-dimensional structures show better performance than target-free models. This is because the interactions between atoms can be explicitly modeled in three-dimensional space, thereby improving the accuracy and effectiveness of drug design. In previous studies, researchers usually used static or semi-flexible crystal structures to simplify the dynamic interactions between active sites and small molecules, only calculating limited system dynamics information. However, this simplification leads to an inadequate understanding of the dynamic characteristics of active sites, neglecting the consideration of the binding dynamics during molecule generation, which impacts the generation of high-quality 3D molecules. To this end, we proposed a 3D molecule generation method based on a target-aware guided diffusion model. This method uses target structure as a condition, introducing a diffusion model to simulate the dynamic evolution of molecular structures, and further refines and optimizes ligand through the structure of target-ligand complexes. Additionally, the continuous distribution of atomic coordinates and the discrete distribution of molecular features are introduced in the molecular latent space through the equivariant graph neural network, which facilitates the representation of the parameterized reverse generation process. Experimental results show that this method can continuously achieve better performance on multiple molecular generation benchmarks and can generate more realistic multiple 3D structure molecules with high binding affinity to protein targets.

Using amino acid residues in peptide generation has solved several key problems, including precise control of amino acid sequence order, customized peptides for property modification, and large-scale peptide synthesis. Proteins contain unknown amino acid residues. Extracting them for the synthesis of drug-like peptides can create novel structures with unique properties, driving drug development. Computer-aided design of novel peptide drug molecules can solve the high-cost and low-efficiency problems in the traditional drug discovery process. Previous studies faced limitations in enhancing the bioactivity and drug-likeness of polypeptide drugs due to less emphasis on the connection relationships in amino acid structures. Thus, we proposed a reinforcement learning-driven generation model based on graph attention mechanisms for peptide generation. By harnessing the advantages of graph attention mechanisms, this model effectively captured the connectivity structures between amino acid residues in peptides. Simultaneously, leveraging reinforcement learning's strength in guiding optimal sequence searches provided a novel approach to peptide design and optimization. This model introduces an actor-critic framework with real-time feedback loops to achieve dynamic balance between attributes, which can customize the generation of multiple peptides for specific targets and enhance the affinity between peptides and targets. Experimental results demonstrate that the generated drug-like peptides meet specified absorption, distribution, metabolism, excretion, and toxicity properties and bioactivity with a success rate of over 90$\%$, thereby significantly accelerating the process of drug-like peptide generation.

MOTIVATION: In the field of pharmacochemistry, it is a time-consuming and expensive process for the new drug development. The existing drug design methods face a significant challenge in terms of generation efficiency and quality. RESULTS: In this paper, we proposed a novel molecular generation strategy and optimization based on A2C reinforcement learning. In molecular generation strategy, we adopted transformer-DNN to retain the scaffolds advantages, while accounting for the generated molecules' similarity and internal diversity by dynamic parameter adjustment, further improving the overall quality of molecule generation. In molecular optimization, we introduced heterogeneous parallel supercomputing for large-scale molecular docking based on message passing interface communication technology to rapidly obtain bioactive information, thereby enhancing the efficiency of drug design. Experiments show that our model can generate high-quality molecules with multi-objective properties at a high generation efficiency, with effectiveness and novelty close to 100%. Moreover, we used our method to assist shandong university school of pharmacy to find several candidate drugs molecules of anti-PEDV. AVAILABILITY AND IMPLEMENTATION: The datasets involved in this method and the source code are freely available to academic users at https://github.com/wq-sunshine/MomdTDSRL.git.

With the increasing complexity of continuous optimization problems, the requirement of solving algorithms is higher and higher. To improve the performance of brain storm optimization algorithm, an elitist guided parameter adaptive BSO (EGBSO) is proposed in this paper. The population is sorted in the objective space based on the fitness. The top M individuals are regarded as elitists to guide the ordinary individuals to cluster, which accelerates the convergence speed of the algorithm. The updating mechanism of elite guidance is introduced, which utilizes the cooperation between global optimal individual and elitists to guide the population to a better direction. An adaptive selection parameter is set to make the algorithm more inclined to global search in the early stage and local search in the later stage, balancing the exploration and exploitation capabilities. The proposed EGBSO algorithm and three comparison algorithms are tested on the CEC2017 benchmark test suit, and the experimental results show that the EGBSO has good performance in solving complex optimization problems.

Backtracking search algorithm (BSA) has been applied to solve the various optimization problems in recent years. However, BSA is difficult to solve non-separable problems due to its single search mechanism. In this paper, backtracking search algorithm based on knowledge of different populations, named DKBSA, is proposed to solve continuous optimization problems. In DKBSA, sub-population partitioning method is used to enhance the local search ability and alleviate the loss rate of the diversity of population. Afterwards, a mutation strategy with knowledge guidance and rotation invariance, which is based on the current sub-population information and historical information, is designed to improve the convergence speed of the DKBSA. Furthermore, a control parameter of adaptive search factor is embedded in the mutation strategy to balance the exploitation and exploration of the proposed algorithm. Finally, a probabilistic model-based strategy is proposed to generate dominant individuals to further improve the search ability of the proposed algorithm. The experimental results of the state-of-the-art algorithms in the CEC2017 benchmark test suit reveal that the DKBSA is effective for solving non-separable problems.

In medicinal chemistry programs, it is key to design and make compounds that are efficacious and safe. In this study, we developed a new deep Reinforcement learning-based compounds molecular generation method. Because chemical space is impractically large, and many existing generation models generate molecules that lack effectiveness, novelty and unsatisfactory molecular properties. Our proposed method-DeepRLDS, which integrates transformer network, balanced binary tree search and docking simulation based on super large-scale supercomputing, can solve these problems well. Experiments show that more than 96 of the generated molecules are chemically valid, 99 of the generated molecules are chemically novelty, the generated molecules have satisfactory molecular properties and possess a broader chemical space distribution.

The image restoration is the technology to restore the damaged part in the image automatically. In this paper we proposed a new restoration method based on the eigensubspace for image structure. After the regions need to be restored are selected, the proposed method use the undamaged part to make up the eigenspace, and then, search different set of image blocks that have high similarity with for each damaged image block, to make up eigensubspace for image structure. At the end, the damaged image blocks can be restored according to their eigensubspace. Experiments result indicates that the proposed method can restore damaged image accurately,