Predicting the drug response of cancer cell lines is crucial for advancing personalized cancer treatment, yet remains challenging due to tumor heterogeneity and individual diversity. In this study, we present a deep learning-based framework named Deep neural network Integrating Prior Knowledge (DIPK) (DIPK), which adopts self-supervised techniques to integrate multiple valuable information, including gene interaction relationships, gene expression profiles and molecular topologies, to enhance prediction accuracy and robustness. We demonstrated the superior performance of DIPK compared to existing methods on both known and novel cells and drugs, underscoring the importance of gene interaction relationships in drug response prediction. In addition, DIPK extends its applicability to single-cell RNA sequencing data, showcasing its capability for single-cell-level response prediction and cell identification. Further, we assess the applicability of DIPK on clinical data. DIPK accurately predicted a higher response to paclitaxel in the pathological complete response (pCR) group compared to the residual disease group, affirming the better response of the pCR group to the chemotherapy compound. We believe that the integration of DIPK into clinical decision-making processes has the potential to enhance individualized treatment strategies for cancer patients.

Some life transitions can be difficult to discuss on social media, especially with networks of known ties, due to challenges such as stigmatization. Separate online networks can provide alternative spaces to discuss life transitions. To understand why and how people turn to separate networks, we interviewed 28 participants who had recently experienced life transitions. While prior research tends to focus on one life transition in isolation, this work examines social media sharing behaviors across a wide variety of life transitions. We describe how people often turn to separate networks during life transitions due to challenges faced in networks of known ties, yet encounter new challenges such as difficulty locating these networks. We describe support from waiting contributors and virtual friends. Finally, we provide insight into how online separate networks can be better designed through enhancing search functionality, promoting contribution, and providing context-sensitive templates for sharing in online spaces.

Abstract When people experience major life changes, this often impacts their self‐presentation, networks, and online behavior in substantial ways. To effectively study major life transitions and events, we surveyed a large U.S. sample (n = 554) to create the Major Life Events Taxonomy, a list of 121 life events in 12 categories. We then applied this taxonomy to a second large U.S. survey sample (n = 775) to understand on average how much social readjustment each event required, how likely each event was to be shared on social media with different types of audiences, and how much online network separation each involved. We found that social readjustment is positively correlated with sharing on social media, with both broad audiences and close ties as well as in online spaces separate from one's network of known ties. Some life transitions involve high levels of sharing with both separate audiences and broad audiences on social media, providing evidence for what previous research has called social media as social transition machinery. Researchers can use the Major Life Events Taxonomy to examine how people's life transition experiences relate to their behaviors, technology use, and health and well‐being outcomes.

People often strive to present themselves authentically on social media, but this may not be possible for everyone. To understand how people view online authenticity, how it relates to social media sharing behaviors, and whether it is achievable, we interviewed 28 social media users who had recently experienced major life transitions. We found that to many participants, online authenticity required presenting a consistent, positive, and "true" self across online and offline contexts. Though most stated that they considered online authenticity achievable, their social media self-disclosure behaviors around life transitions revealed what we call the online authenticity paradox: people strive to achieve online authenticity, yet because doing so requires sharing negative experiences on social media, online authenticity is often unreachable, or is possible only at great personal cost - especially for those with marginalized identities and difficult life experiences.

MapReduce is the most widely used distributed computing framework due to its excellent parallelism and scalability in dealing with large-scale data. It is one of the most important research point in distributed computing field to improve the performance of MapReduce application in data center network. OpenFlow protocol makes it possible to schedule network resource dynamically to provide better link bandwidth for shuffle traffic. Current OpenFlow-based scheduling method runs on a single controller, which cannot meet the needs of excessive switch requests in large scale data center networks. The performance of those scheduling method will decrease obviously due to some conflict problem when they run on distributed controllers. This paper proposed DScheduler, a dynamic network scheduling method for distributed controllers. DScheduler is running as an application on each SDN controller and avoid a majority of conflict problems in scheduling with small cost by using lock and communication between each controller. We implement a prototype system on Floodlight to demonstrate our design and test the performance. Experimental results show that DScheduler has a significant effect on decreasing the occurrence times of conflict situations and improving the performance of openflow-based scheduling method on distributed controllers.