The identification of drug-target interactions (DTIs) is a key task in drug discovery, where drugs are chemical compounds and targets are proteins. Traditional DTI prediction methods are either time consuming (simulation-based methods) or heavily dependent on domain expertise (similarity-based and feature-based methods). In this work, we propose an end-to-end neural network model that predicts DTIs directly from low level representations. In addition to making predictions, our model provides biological interpretation using two-way attention mechanism. Instead of using simplified settings where a dataset is evaluated as a whole, we designed an evaluation dataset from BindingDB following more realistic settings where predictions of unobserved examples (proteins and drugs) have to be made. We experimentally compared our model with matrix factorization, similarity-based methods, and a previous deep learning approach. Overall, the results show that our model outperforms other approaches without requiring domain knowledge and feature engineering. In a case study, we illustrated the ability of our approach to provide biological insights to interpret the predictions.
This paperpresents a new approach for consistently caching dynamic Web data in order to improve pegormanee. Our algorithm, which we call Data Update Propagation (DUP), maintains data dependence information between cached objects and the underlying data which affect their values in a graph. When the system becomes aware of a change to underlying data, graph traversal algorithms are applied to determine which cached objects are affected by the change. Cached objects which are found to be highly obsolete are then either invalidated or updated. DUP was a critical component at the ojjicial Web site for the 1998 Olympic Winter Games. By using DUE we were able to achieve cache hit rates close to 100% compared with 80% f o r an earlier version of our system which did not employ DUE As a result of the high cache hit rates, the Olympic Games Web site was able to serve data quickly even during peak request periods.
Quantification of heart valve leaflet deformation during the cardiac cycle is essential in understanding normal and pathological valvular function, as well as in the design of replacement heart valves. Due to the technical complexities involved, little work to date has been performed on dynamic valve leaflet motion. We have developed a novel experimental method utilizing a noncontacting structured laser-light projection technique to investigate dynamic leaflet motion. Using a simulated circulatory loop, a matrix of 150-200 laser light points were projected over the entire leaflet surface. To obtain unobstructed views of the leaflet surface, a stereo system of high-resolution boroscopes was used to track the light points at discrete temporal points during the cardiac cycle. The leaflet surface at each temporal point was reconstructed in three dimensions, and fit using our biquintic hermite finite element approach (Smith et al., Ann. Biomed. Eng. 26:598-611, 2001). To demonstrate our approach, we utilized a bovine pericardial bioprosthetic heart valve, which revealed regions of complex flexural deformation and substantially different shapes during the opening and closing phases. In conclusion, the current method has high spatial and temporal resolution and can reconstruct the entire surface of the cusp simultaneously. Because it is completely noncontacting, this approach is applicable to studies of fatigue and bioreactor technology for tissue engineered heart valves.
Abstract-Disruption Tolerant Networks (DTNs) are characterized by the low node density, unpredictable node mobility and lack of global network information. Most of current research efforts in DTNs focus on data forwarding, but only limited work has been done on providing effective data access to mobile users. In this paper, we propose a novel approach to support cooperative caching in DTNs, which enables the sharing and coordination of cached data among multiple nodes and reduces data access delay. Our basic idea is to intentionally cache data at a set of Network Central Locations (NCLs), which can be easily accessed by other nodes in the network. We propose an effective scheme which ensures appropriate NCL selection based on a probabilistic selection metric, and coordinate multiple caching nodes to optimize tradeoff between data accessibility and caching overhead. Extensive trace-driven simulations show that our scheme significantly improves data access performance compared to existing schemes.
Location-based services (LBSs) provide enhanced functionality and convenience of ubiquitous computing, but they open up new vulnerabilities that can be utilized to violate the users’ privacy. The leakage of private location data in the LBS context has drawn significant attention from academics and industry due to its importance, leading to numerous research efforts aiming to confront the related challenges. However, to the best of our knowledge, none of relevant studies have performed a qualitative and quantitative comparison and analysis of the complex topic of designing countermeasures and discussed the viability of their use with different kinds of services and the potential elements that could be deployed to meet new challenges. Accordingly, the purpose of this survey is to examine the privacy-preserving techniques in LBSs. We categorize and provide an inside-out review of the existing techniques. Performing a retrospective analysis of several typical studies in each category, we summarize their basic principles and recent advances. Additionally, we highlight the use of privacy-preserving techniques in LBSs for enabling new research opportunities. Providing an up-to-date and comprehensive overview of existing studies, this survey may further stimulate new research efforts into this promising field.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.