Optical chemical structure recognition from scientific publications is essential for rediscovering a chemical structure. It is an extremely challenging problem, and current rule-based and deep-learning methods cannot achieve satisfactory recognition rates. Herein, we propose SwinOCSR, an end-to-end model based on a Swin Transformer. This model uses the Swin Transformer as the backbone to extract image features and introduces Transformer models to convert chemical information from publications into DeepSMILES. A novel chemical structure dataset was constructed to train and verify our method. Our proposed Swin Transformer-based model was extensively tested against the backbone of existing publicly available deep learning methods. The experimental results show that our model significantly outperforms the compared methods, demonstrating the model’s effectiveness. Moreover, we used a focal loss to address the token imbalance problem in the text representation of the chemical structure diagram, and our model achieved an accuracy of 98.58%.

Purpose: To observe the apoptotic effects of NSMF on human hepatoma cells and to investigate the mechanisms. Materials and methods: Human hepatoma cell line Bel-7402 and Hep G-2 were treated by 0.2 T rotary NSMF (30 min/d) with 250 Hz, 400 Hz and 500 Hz for 3 d and 6 d, respectively. Apoptosis was analyzed with flow cytometry. Cell proliferation was measured with XTT assay. Expression of Bcl-2, caspase3/8/9 was analyzed with ELISA. Results: After 6 d treatment, significant apoptosis was induced by 400 Hz in Bel-7402 cells. Slight cell apoptosis was observed at 250 Hz, while Hep G-2 cells exhibited slight apoptosis at 250 Hz and 400 Hz. After 3 d treatment, no apoptosis exhibited in both cell types. Compared with control group, expression of Bcl-2 and Caspase 8 in treated Bel-7402 cells were significantly reduced (p < 0.01), while Caspase 3 and Caspase 9 were significantly upregulated (p < 0.01). Conclusions: NSMF upregulates caspase 9 and downregulates Bel-2 expression, which results in higher level of active caspase 3 to trigger apoptosis in cells. Different cell types require different NSMF factors like rotary frequency and treatment time to induce apoptosis.

Dynamic Opinion Maximization (DOM) is a significant optimization issue, whose target is to select some nodes in the network and prorogate the opinions of network nodes, and produce the optimum node opinions. Until now, the node opinions of related researches are unchanged and seldom focus on social relationships. In the real scenario, the dynamic process of network nodes over time and user preference have existed. Therefore, this paper proposes the Q-learning-based Dynamic Opinion Maximization framework (QDOM) in signed social networks to solve the OM problem, which is made up of two phases: activated dynamic opinion model and Qlearning-based seeding process. We propose the activated dynamic opinion model based on stateless Q-learning theory to derive the opinion propagation process. Moreover, we design the Q-learningbased seeding algorithm to obtain the seed nodes. Experimental results on the four signed social network datasets demonstrate that the proposed framework outperforms the state-of-the-art approaches on positive opinions, the ratio of positive opinions, and activated nodes.