Search

• An effective end-to-end deep neural network for integration of multi-omics data. • Divergence-based regularization can capture consensus information among modalities. • The performances are varied when integrating different modalities of -omics data. • Improved performance in cancer type classification and survival prediction. • Visualized the better agreement among modalities after consensus learning. Breast and ovarian cancers are the second and the fifth leading causes of cancer death among women. Predicting the overall survival of breast and ovarian cancer patients can facilitate the therapeutics evaluation and treatment decision making. Multi-scale multi-omics data such as gene expression, DNA methylation, miRNA expression, and copy number variations can provide insights on personalized survival. However, how to effectively integrate multi-omics data remains a challenging task. In this paper, we develop multi-omics integration methods to improve the prediction of overall survival for breast cancer and ovarian cancer patients. Because multi-omics data for the same patient jointly impact the survival of cancer patients, features from different -omics modality are related and can be modeled by either association or causal relationship (e.g., pathways). By extracting these relationships among modalities, we can get rid of the irrelevant information from high-throughput multi-omics data. However, it is infeasible to use the Brute Force method to capture all possible multi-omics interactions. Thus, we use deep neural networks with novel divergence-based consensus regularization to capture multi-omics interactions implicitly by extracting modality-invariant representations. In comparing the concatenation-based integration networks with our new divergence-based consensus networks, the breast cancer overall survival C-index is improved from 0.655 ± 0.062 to 0.671 ± 0.046 when combing DNA methylation and miRNA expression, and from 0.627 ± 0.062 to 0.667 ± 0.073 when combing miRNA expression and copy number variations. In summary, our novel deep consensus neural network has successfully improved the prediction of overall survival for breast cancer and ovarian cancer patients by implicitly learning the multi-omics interactions. [ABSTRACT FROM AUTHOR]

Remanufacturing is widely considered a solution to environmental pollution and resource shortage but its progression is influenced by Original Equipment Manufacturers (OEMs), remanufacturers, consumers and public policy makers. This research studies the optimal price and production quantity of new and remanufactured products with a two-stage model under both scenarios under which the remanufacturing is conducted by the OEM or by the third-party remanufacturer (TPR). A non-cooperative game model is used at the second stage when the TPR conducts remanufacturing. The models consider both the impact of the product life cycle through the market growth factor at the second stage and the influence of consumers’ perceived value of new and remanufactured products, which depends on the identity of the remanufacturer. Both theoretical and numerical analyses show that both the life cycle phase and consumers’ perception have an impact on the OEM’s decision whether to allow the TPR in the remanufacturing business. The results also reveal that the market may not be efficient for maximizing the environmental sustainability and societal equity. Governments may need to interfere with the market in order to promote the TPR manufacturing, especially when the product is at the mature or declining phases of its life cycle. [ABSTRACT FROM AUTHOR]

We investigate how the diversity of consumers’ perceived value in different remanufacturing modes affects remanufacturing decision-making. We establish a two-stage optimal decision-making model of original equipment manufacturer (OEM) remanufacturing and a noncooperative game model of third party remanufacturer (TPR) remanufacturing and then analyze the optimal decisions of OEM and TPR. Comparing the effects of consumers’ perceived value on remanufacturing decision-making in different modes, we find that when OEM remanufactures products, consumers’ perceived value has a negative effect on new products’ price and quantity and has a positive effect on remanufactured products’ quantity and when TPR remanufactures products, consumers’ perceived value has a positive effect on new products price and quantity and has a negative effect on remanufactured products’ quantity. Compared with OEM remanufacturing, TPR remanufacturing can raise the profits of OEM and whole closed-loop supply chain, but it will lower the quantity of remanufacturing products. [ABSTRACT FROM AUTHOR]

This study examines experimental evidence showing how ethics power allocation mechanisms affect an individual's in-organization resource division and ethical behavior. We used two two-stage lab experiments to explore power seeking and usage; the experiments contained two stages of power contending and power usage. Stage one used two different power-seeking mechanisms in the honesty game. Stage two was based on the dictator game and the ultimatum game to measure an individual's power usage. The results show that the decisions taken by power-holders could influence the optimization of collective resources, and power-holders who gain power with unethical methods could result in collective resource allocation inequities. With more balanced in-organization power, members tend to be more honest. Subjects also adjust their unethical behavior to adapt to the environment, which could cause the diffusion of unethical behavior. This paper re-designed the dictator game and the ultimatum game by adding an ethically vulnerable power acquisition mechanism. For organizations to prevent the disproportionate dispersion of resources and achieve more public benefits, it is meaningful for managers to create a proper in-organization ethical power allocation mechanism. [ABSTRACT FROM AUTHOR]