Social recommendation leverages social information to solve data sparsity and cold-start problems in traditional collaborative ltering methods. However, most existing models assume that social e ects from friend users are static and under the forms of constant weights or xed constraints. To relax this strong assumption, in this paper, we propose dual graph a ention networks to collaboratively learn representations for two-fold social e ects, where one is modeled by a user-speci c a ention weight and the other is modeled by a dynamic and context-aware a ention weight. We also extend the social e ects in user domain to item domain, so that information from related items can be leveraged to further alleviate the data sparsity problem. Furthermore, considering that di erent social e ects in two domains could interact with each other and jointly inuence users' preferences for items, we propose a new policy-based fusion strategy based on contextual multi-armed bandit to weigh interactions of various social e ects. Experiments on one benchmark dataset and a commercial dataset verify the e cacy of the key components in our model. e results show that our model achieves great improvement for recommendation accuracy compared with other state-of-the-art social recommendation methods.

Endophthalmitis, derived from the infections of pathogens, is a common complication during the use of ophthalmology‐related biomaterials and after ophthalmic surgery. Herein, aiming at efficient photodynamic therapy (PDT) of bacterial infections and biofilm eradication of endophthalmitis, a pH‐responsive zeolitic imidazolate framework‐8‐polyacrylic acid (ZIF‐8‐PAA) material is constructed for bacterial infection–targeted delivery of ammonium methylbenzene blue (MB), a broad‐spectrum photosensitizer antibacterial agent. Polyacrylic acid (PAA) is incorporated into the system to achieve higher pH responsiveness and better drug loading capacity. MB‐loaded ZIF‐8‐PAA nanoparticles are modified with AgNO3/dopamine for in situ reduction of AgNO3 to silver nanoparticles (AgNPs), followed by a secondary modification with vancomycin/NH2‐polyethylene glycol (Van/NH2‐PEG), leading to the formation of a composite nanomaterial, ZIF‐8‐PAA‐MB@AgNPs@Van‐PEG. Dynamic light scattering, transmission electron microscopy, and UV–vis spectral analysis are used to explore the nanoparticles synthesis, drug loading and release, and related material properties. In terms of biological performance, in vitro antibacterial studies against three kinds of bacteria, i.e., Escherichia coli, Staphylococcus aureus, and methicillin‐resistant S. aureus, suggest an obvious superiority of PDT/AgNPs to any single strategy. Both in vitro retinal pigment epithelium cellular biocompatibility experiments and in vivo mice endophthalmitis models verify the biocompatibility and antibacterial function of the composite nanomaterials.

In recent decades, bacterial and viral infections and chronic inflammatory response have emerged as important causes of cancer. Also, infections remain a significant cause of morbidity and mortality in cancer patients. In this work, carboxymethyl chitosan nanoparticles (CMC NPs) were synthesized in a facile and green way and further combined with ammonium methylbenzene blue (MB) as a cross-linking agent as well as a fluorescent molecule and a photosensitizer for self-imaging photodynamic therapy (PDT). The obtained CMC−MB NPs exhibited an apparent pH-responsive release behavior of MB, which was released for a prolonged period in a simulated physiological environment (pH 7.4) for more than 15 days and the time reduced to only 3.5 h in acidic conditions (pH 5.5). When irradiated by a 650 nm laser at 202 mW/cm 2 for 5 min, the CMC−MB NPs showed efficient bactericidal and biofilm eradication properties as well as suppression of tumor cell growth in a similar acidified microenvironment. Furthermore, in an in vivo rabbit wound bacterial infection model, the rapid sterilization of CMC−MB NPs played a crucial role in bacterial infections, inflammation inhibition, and wound healing. As a PDT treatment against cancer, the CMC−MB NPs also exhibited an efficient antitumor therapeutic effect in a subcutaneous tumor mice model.