Large Language Model (LLM)-based agents are increasingly deployed for complex, toolbased tasks where long-term memory is critical to driving actions.Existing benchmarks, however, primarily test an agent's ability to passively retrieve isolated facts in response to explicit questions.They fail to evaluate the more crucial capability of actively applying memory to execute tasks.To address this gap, we introduce MEM2ACTBENCH, a benchmark for evaluating whether agents can proactively leverage long-term memory to execute tool-based actions by selecting appropriate tools and grounding their parameters.The benchmark simulates persistent assistant usage, where users mention the same topic across long, interrupted interactions and expect previously established preferences and task states to be implicitly applied.We build the dataset with an automated pipeline that merges heterogeneous sources (ToolACE, BFCL, OASST1), resolves conflicts via consistency modeling, and synthesizes 2,029 sessions with 12 user-assistant-tool turns on average.From these memory chains, a reverse-generation method produces 400 tooluse tasks, with human evaluation confirming 91.3% are strongly memory-dependent.Experiments on seven memory frameworks show that current systems remain inadequate at actively utilizing memory for parameter grounding, highlighting the need for more effective approaches to evaluate and improve memory application in task execution.

Salmonella infections pose a significant global public health threat, and the emergence of multi-drug resistant strains has left traditional antibiotic agents in a predicament of ineffectiveness. Since the development of traditional antibiotic drugs is costly and time-consuming, the global research and development of novel antibiotics has nearly stagnated at present. Although several generative molecular design models have been proposed, their application in generating antibiotics targeting specific pathogens suffers from undesirable antibacterial efficacy and poor diversity due to limited training data. In this paper, we propose an effective Variational AutoEncoder (VAE) framework for generating antibiotic molecules targeting Salmonella bacteria, in which a triple-stage training strategy is utilized to address the issues of poor efficacy and low diversity for existing molecule generation models. More specifically, a set of all available small molecule drugs is first used to pre-train the VAE-based framework to capture the general semantics contained in various types of small molecules. Then, a mediumsize set of all antibiotic molecules is employed to fine-tune the pre-trained VAE framework to learn the fine-grained semantics among antibiotic agents. Finally, a small-size set of all antibiotics treating Salmonella pathogens is utilized to optimize further the generated molecules with specific anti-Salmonella activity. In addition, introducing several key molecular properties as conditional input can effectively guide the VAE model to generate molecules with ideal absorption and metabolic properties. Results of comprehensive experiments show that the proposed framework is able to generate highly effective and structurally diverse antibacterial candidate molecules, providing a feasible solution to the development of antibiotics against drug-resistant Salmonella pathogens.

MOTIVATION: The widespread use of antibiotics has led to the emergence of resistant pathogens. Antimicrobial peptides (AMPs) combat bacterial infections by disrupting the integrity of cell membranes, making it challenging for bacteria to develop resistance. Consequently, AMPs offer a promising solution to addressing antibiotic resistance. However, the limited availability of natural AMPs cannot meet the growing demand. While deep learning technologies have advanced AMP generation, conventional models often lack stability and may introduce unforeseen side effects. RESULTS: This study presents a novel denoising VAE-based model guided by desirable physicochemical properties for AMP generation. The model integrates key features (e.g. molecular weight, isoelectric point, hydrophobicity, etc.), and employs position encoding along with a Transformer architecture to enhance generation accuracy. A customized loss function, combining reconstruction loss, KL divergence, and property preserving loss ensure effective model training. Additionally, the model incorporates a denoising mechanism, enabling it to learn from perturbed inputs, thus maintaining performance under limited training data. Experimental results demonstrate that the proposed model can generate AMPs with desirable functional properties, offering a viable approach for AMP design and analysis, which ultimately contributes to the fight against antibiotic resistance. AVAILABILITY AND IMPLEMENTATION: The data and source codes are available both in GitHub (https://github.com/David-WZhao/PPGC-DVAE) and Zenodo (DOI 10.5281/zenodo.14730711).

Antimicrobial peptides (AMPs) are crucial in addressing the global crisis of bacterial resistance. However, there are still significant limitations in existing methods on de novo AMPs design, especially in designing AMPs with desirable physicochemical properties for specific bacterial pathogens. In this study, we propose a novel generative framework for designing pathogen-targeted antimicrobial peptides with programmable physicochemical properties. More specifically, a conditional Variational Autoencoder is first pretrained for generating AMPs with editable physicochemical properties. We then develop a conditional diffusion model to learn hidden representations of AMPs for targeting pathogens of interest, and construct corresponding MIC predictors for specific bacterial strains. Through comprehensive simulation experiments, we demonstrate that the proposed framework outperforms most existing models in terms of antimicrobial efficacy against specific bacterial targets. Moreover, through systematic screening and analysis, we have identified two star AMPs for each of the two target bacterial species (i.e., E. coli or S. aureus), both of which exhibit excellent performance in antibacterial activity, hemolytic properties, toxicity profiles, etc. Overall, this study provides the key technological support for developing next-generation intelligent platforms for antimicrobial agents design.

The biomedical literature suggests that drug interventions can affect microbial communities of the human body and thereby treat disease. Screening of microbe-drug associations is therefore a key research topic in the field of antimicrobial drug development and drug repositioning. Existing models have not adequately integrated the multimodal representations of biomedical entities and the microbe-drug association networks from different sources. In addition, the positive negative sample imbalance of the heterogeneous networks and the sparsity of the association matrices decrease the accuracy of the prediction results. In this paper, we proposed a multimodal joint representation framework (MJRFMDA) for microbe-drug association prediction. First, we represented microbial and drug features through multimodal attributes. Secondly, we aggregated neighbor information and updated node attributes through GCN and GAT in microbe-drug association networks. Then we aggregated the embedded representations of multimodal networks through a joint representation layer based on a graph-level attention mechanism. Finally, we employed neural inductive matrix completion to capture the nonlinear associations between microbes and drugs, and reconstructed the association score matrix. The experimental results show that MJRFMDA outperforms the six selected state-of-the-art models.

In intensity-modulation and direct-detection (IM/DD) multiple-input and multiple-output (MIMO) visible light communication (VLC) systems, spatial subchannels are usually correlated, and spatial modulation is a good choice to achieve the advantages of MIMO technology. Peak-to-average power ratio (PAPR) is a key issue in VLCs due to the limited linear dynamic range of light emitting diodes (LEDs). Single-carrier communication systems have a lower PAPR than orthogonal frequency division multiplexing (OFDM) communication systems. However, it is challenging to design a single-carrier spatial modulation for high-rate transmissions because of the time domain intersymbol interference. This paper develops an optical spatial modulation (OSM) scheme based on bipolar pulse amplitude modulation (PAM) and spatial elements for high-rate indoor VLC systems. Multiple data streams can be transmitted simultaneously in the proposed scheme. Based on the transmit strategy, we develop a low-complexity receiver algorithm that achieves better bit-error rate performance than reference schemes, and the proposed OSM scheme has a much lower PAPR than OFDM based OSM schemes. When the spatial subchannels are highly correlated, a spatial area division strategy is applied, and the receiver algorithm is investigated. The symbol-error rate expression of the proposed OSM scheme is derived, and the computational complexity is analyzed.

Spatial modulation is a promising transmission scheme for massive multiple‐input multiple‐output (MIMO) systems to improve energy efficiency. In this study, considering the low‐complexity hybrid structure, the authors propose a joint spatial modulation and beamforming scheme for a hybrid massive MIMO system in both single user and multi‐user scenarios. Specifically, a design criterion of the channel control parameter is provided to reduce the high correlation among different channel coefficients in the hybrid massive MIMO system. In addition, with the statistical channel state information acquired at the base station, the optimum analogue beamforming vectors are designed with the goal of maximising the signal to leakage and noise ratio in the multi‐user scenario. Furthermore, the upper bound, the lower bound as well as the closed form approximation of achievable spectral efficiency of the proposed scheme are derived for both single user and multi‐user scenarios. Numerical simulation results demonstrate that the proposed scheme outperforms the conventional MIMO scheme.

BACKGROUND: Target identification is necessary for the comprehensive inference of the mechanism of action of a compound. The application of computational methods to predict the targets of bioactive compounds saves cost and time in drug research and development. Therefore, we designed an integrated strategy consisting of ligand-protein docking, network analysis, enrichment analysis, and an experimental surface plasmon resonance (SPR) method to identify and validate new targets, and then used enriched pathways to elucidate the underlying pharmacological mechanisms. Here, we used rhein, a compound with various pharmacological activities, as an example to find some of its previously unknown targets and to determine its pharmacological activity. RESULTS: A total of nine candidate targets were discovered, including LCK, HSP90AA1, RAB5A, EGFR, CDK2, CDK6, GSK3B, p38, and JNK. LCK was confirmed through SPR experiments, and HSP90AA1, EGFR, CDK6, p38, and JNK were validated through previous reports. Rhein network regulations are complex and interconnected. The therapeutic effect of rhein is the synergistic and comprehensive result of this vast and complex network, and the perturbation of multiple targets gives rhein its various pharmacological activities. CONCLUSIONS: This study provided a new integrated strategy to identify new targets of bioactive compounds and reveal their molecular mechanisms of action.