In this paper, an automatic approach for 3D pose reconstruction from a single image is proposed. The presence of human body articulation, hallucinated parts and cluttered background leads to ambiguity during the pose inference, which makes the problem non-trivial. Researchers have explored various methods based on motion and shading in order to reduce the ambiguity and reconstruct the 3D pose. The key idea of our algorithm is to impose both kinematic and orientation constraints. The former is imposed by projecting a 3D model onto the input image and pruning the parts, which are incompatible with the anthropomorphism. The latter is applied by creating synthetic views via regressing the input view to multiple oriented views. After applying the constraints, the 3D model is projected onto the initial and synthetic views, which further reduces the ambiguity. Finally, we borrow the direction of the unambiguous parts from the synthetic views to the initial one, which results in the 3D pose. Quantitative experiments are performed on the Human Eva-I dataset and qualitatively on unconstrained images from the Image Parse dataset. The results show the robustness of the proposed approach to accurately reconstruct the 3D pose form a single image.

The combination of natural products with standard chemotherapeutic agents offers a promising strategy to enhance the efficacy or reduce the side effects of standard chemotherapy. Doxorubicin (DOX), a standard drug for breast cancer, has several disadvantages, including severe side effects and the development of drug resistance. Recently, we reported the potential bioactive markers of Australian propolis extract (AP-1) and their broad spectrum of pharmacological activities. In the present study, we explored the synergistic interactions between AP-1 and DOX in the MCF7 breast adenocarcinoma cells using different synergy quantitation models. Biochemometric and metabolomics-driven analysis was performed to identify the potential anticancer metabolites in AP-1. The molecular mechanisms of synergy were studied by analysing the apoptotic profile via flow cytometry, apoptotic proteome array and measuring the oxidative status of the MCF7 cells treated with the most synergistic combination. Furthermore, label-free quantification proteomics analysis was performed to decipher the underlying synergistic mechanisms. Five prenylated stilbenes were identified as the key metabolites in the most active AP-1 fraction. Strong synergy was observed when AP-1 was combined with DOX in the ratio of 100:0.29 (w/w) as validated by different synergy quantitation models implemented. AP-1 significantly enhanced the inhibitory effect of DOX against MCF7 cell proliferation in a dose-dependent manner with significant inhibition of the reactive oxygen species (p < 0.0001) compared to DOX alone. AP-1 enabled the reversal of DOX-mediated necrosis to programmed cell death, which may be advantageous to decline DOX-related side effects. AP-1 also significantly enhanced the apoptotic effect of DOX after 24 h of treatment with significant upregulation of catalase, HTRA2/Omi, FADD together with DR5 and DR4 TRAIL-mediated apoptosis (p < 0.05), contributing to the antiproliferative activity of AP-1. Significant upregulation of pro-apoptotic p27, PON2 and catalase with downregulated anti-apoptotic XIAP, HSP60 and HIF-1α, and increased antioxidant proteins (catalase and PON2) may be associated with the improved apoptosis and oxidative status of the synergistic combination-treated MCF7 cells compared to the mono treatments. Shotgun proteomics identified 21 significantly dysregulated proteins in the synergistic combination-treated cells versus the mono treatments. These proteins were involved in the TP53/ATM-regulated non-homologous end-joining pathway and double-strand breaks repairs, recruiting the overexpressed BRCA1 and suppressed RIF1 encoded proteins. The overexpression of UPF2 was noticed in the synergistic combination treatment, which could assist in overcoming doxorubicin resistance-associated long non-coding RNA and metastasis of the MCF7 cells. In conclusion, we identified the significant synergy and highlighted the key molecular pathways in the interaction between AP-1 and DOX in the MCF7 cells together with the AP-1 anticancer metabolites. Further in vivo and clinical studies are warranted on this synergistic combination.

The lack of a gold standard synergy quantification method for chemotherapeutic drug combinations warrants the consideration of different synergy metrics to develop efficient predictive models. Furthermore, neglecting combination sensitivity may lead to biased synergistic combinations, which are ineffective in cancer treatment. In this paper, we propose a deep learning-based model, SynPredict, which effectively predicts synergy in five synergy metrics together with the combination sensitivity score. SynPredict assesses the impact of multimodal fusion architectures of the input data, including the gene expression data of cancer cells, along with the representative chemical features of drugs in pairwise combinations. Both ONEIL and ALMANAC anticancer combination datasets are employed comparatively. The impact of the training datasets was more significant and consistent across most synergy models than input data fusion architectures. Synpredict outperforms the state-of-the-art predictive models, including DeepSynergy, AuDNN synergy, TranSynergy and DrugComb, with up to 74% decline in the mean square error. We highlight the pivotal need to consider a multiplex of synergy metrics and the combined sensitivity in the predictive models.