Nanomedicine uses nanotechnology-based strategies for precision tumor therapy, including passive and ligand-mediated active tumor targeting by nanocarriers. However, the possible biotoxicity of chemosynthetic nanovectors limits their clinical applications. A novel natural egg yolk lipid nanovector (EYLN) was developed for effective loading and delivery of therapeutic agents. Lipids were extracted from egg yolks and reassembled into nanosized particles. EYLNs’ stability, cellular uptake, toxicity, and delivery capacity for therapeutic agents were evaluated in vitro. The systemic toxicity and biodistribution of EYLNs were analyzed in normal mice, and the therapeutic effects of doxorubicin (Dox)-loaded EYLNs were evaluated in mouse breast cancer and hepatoma models. EYLNs had a particle size of ∼40 nm and a surface ζ-potential of −45 mV and were effectively internalized by tumor cells, without showing toxicity and side effects in vitro and in vivo. Importantly, their excellent permeability and retention effect significantly enhanced the distribution of EYLNs at tumor sites, and EYLN-Dox effectively inhibited the tumor growth in both mouse models. Targeted modification with folic acid further promoted vector-mediated drug distribution in tumors. This study demonstrates that lipids with specific proportions in the egg yolk can be used to construct natural drug vectors, providing a new strategy for nano-oncology research.

Aiming at the problem that traditional heuristic algorithm is difficult to extract the empirical model in time from large sample terrain data, a multi-UAV collaborative path planning method based on attention reinforcement learning is proposed. The method draws on a combined consideration of influencing factors, such as survival probability, path length, and load balancing and endurance constraints, and works as a support system for multimachine collaborative optimizing. The attention neural network is used to generate the cooperative reconnaissance strategy of the UAV, and a large amount of simulation data is tested to optimize the attention network using the REINFORCE algorithm. Experimental results show that the proposed method is effective in solving the multi-UAV path planning issue with high real-time requirements, and the solving time is less than the traditional algorithms.

No abstract