Recent advancements in industrial anomaly detection (AD) have demonstrated that incorporating a small number of anomalous samples during training can significantly enhance accuracy. However, this improvement often comes at the cost of extensive annotation efforts, which are impractical for many real-world applications. In this paper, we introduce a novel framework, "Weakly-supervised RESidual $T$ ransformer" (WeakREST), designed to achieve high anomaly detection accuracy while minimizing the reliance on manual annotations. First, we reformulate the pixel-wise anomaly localization task into a block-wise classification problem. Second, we introduce a residual-based feature representation called "Positional $F$ ast $A$ nomaly $R$ esiduals" (PosFAR) which captures anomalous patterns more effectively. To leverage this feature, we adapt the Swin Transformer for enhanced anomaly detection and localization. Additionally, we propose a weak annotation approach utilizing bounding boxes and image tags to define anomalous regions. This approach establishes a semi-supervised learning context that reduces the dependency on precise pixel-level labels. To further improve the learning process, we develop a novel ResMixMatch algorithm, capable of handling the interplay between weak labels and residual-based representations. On the benchmark dataset MVTec-AD, our method achieves an Average Precision (AP) of 83.0%, surpassing the previous best result of 82.7% in the unsupervised setting. In the supervised AD setting, WeakREST attains an AP of 87.6%, outperforming the previous best of 86.0%. Notably, even when using weaker annotations such as bounding boxes, WeakREST exceeds the performance of leading methods relying on pixel-wise supervision, achieving an AP of 87.1% compared to the prior best of 86.0% on MVTec-AD. This superior performance is consistently replicated across other well-established AD datasets, including MVTec 3D, KSDD2 and Real-IAD. Code is available at: https://github.com/BeJane/Semi_REST.

This paper presents Gpl, a fast and accurate optimizer for query processing over knowledge graphs. Gpl is novel in three ways. First, Gpl proposes a type-centric approach to enhance the accuracy of cardinality estimation prominently, which naturally embeds the correlation of multiple query conditions into the existing type system of knowledge graphs. Second, to predict execution time accurately, Gpl constructs a specialized cost model for graph exploration scheme and tunes the coefficients with target hardware platform and graph data. Third, Gpl further uses a budget-aware strategy for plan enumeration with a greedy heuristic to boost the overall performance (i.e., optimization time and execution time) for various workloads. Evaluations with representative knowledge graphs and query benchmarks show that Gpl can select optimal plans for 33 of 39 queries and only incurs less than 5% slowdown on average compared to optimal results. In contrast, the state-of-the-art optimizer and manually tuned results will cause 100% and 36% slowdown, respectively.

The spatial position and interaction of drugs and their targets is the most important characteristics for understanding a drug's pharmacological effect, and it could help both in finding new and more precise treatment targets for diseases and in exploring the targeting effects of the new drugs. In this work, we develop a computational pipeline to confirm the spatial interaction relationship of the drugs and their targets and compare the drugs' efficacies based on the interaction centers. First, we produce a 100-sample set to reconstruct a stable docking model of the confirmed drug-target pairs. Second, we set 5.5 Å as the maximum distance threshold for the drug-amino acid residue atom interaction and construct 3-dimensional interaction surface models. Third, by calculating the spatial position of the 3-dimensional interaction surface center, we develop a comparison strategy for estimating the efficacy of different drug-target pairs. For the 1199 drug-target interactions of the 649 drugs and 355 targets, the drugs that have similar interaction center positions tend to have similar efficacies in disease treatment, especially in the analysis of the 37 targeted relationships between the 15 known anti-cancer drugs and 10 target molecules. Furthermore, the analysis of the unpaired anti-cancer drug and target molecules suggests that there is a potential application for discovering new drug actions using the sampling molecular docking and analyzing method. The comparison of the drug-target interaction center spatial position method better reflect the drug-target interaction situations and could support the discovery of new efficacies among the known anti-cancer drugs.

An increasing number of functional studies shows that long noncoding RNAs (lncRNAs) are involved in many aspects of cellular physiology and fulfills a wide variety of regulatory roles at almost every stage of gene expression. A major feature of lncRNAs is the highly folded modular domains in transcripts. With improved modeling and definition, it is now feasible to explore and gain novel insights into the structural-functional relationship of lncRNAs and their association with complex human diseases. In this study, we utilized an automatic computational pipeline to scan lncRNA architecture at the genome-wide scale and to obtain a landscape of functional domains. An accurate alignment algorithm was performed to identify 40 triple pairs between single-nucleotide polymorphisms (SNPs), lncRNAs and diseases. In order to detect the potential contribution of a lncRNA's modular character, we estimated and evaluated structural rearrangements, which were derived from disease-associated SNPs. In addition, we focused on annotating and comparing the global and local heterogeneity of the wild-type and mutant lncRNAs. Assessing lncRNA architecture has yielded how variations in structured regions impact the molecular mechanisms of lncRNAs and how SNPs disturb binding and recruiting ability. These observations are the first glimpse of the 'lncRNA structurome' and make it possible to robustly explore and assemble intricate space conformation and their stress variation. This result also successfully demonstrates that lncRNA transcripts contain a complex structural landscape and highlights the proposed contribution of lncRNA structure in controlling RNA functions and disease mechanisms.

The recent extensive application of next-generation sequencing has led to the rapid accumulation of multiple types of data for functional DNA elements. With the advent of precision medicine, the fine-mapping of risk loci based on these elements has become of paramount importance. In this study, we obtained the human reference genome (GRCh38) and the main DNA sequence elements, including protein-coding genes, miRNAs, lncRNAs and single nucleotide polymorphism flanking sequences, from different repositories. We then realigned these elements to identify their exact locations on the genome. Overall, 5%-20% of all sequence element locations deviated among databases, on the scale of kilobase-pair to megabase-pair. These deviations even affected the selection of genome-wide association study risk-associated genes. Our results implied that the location information for functional DNA elements may deviate among public databases. Researchers should take care when using cross-database sources and should perform pilot sequence alignments before element location-based studies.

In many medium access control (MAC) schemes for wireless networks, an Acknowledgment (ACK) packet is transmitted from the data receiver to the data sender to announce the successful reception of the data packet. Such a protocol requirement may become a system weakness when malicious nodes attack these wireless networks. In this paper, we demonstrate the effects of such a Jamming ACK (JACK) attack to networks employing the popular carrier sense multiple access with collision avoidance (CSMA/CA) scheme in IEEE 802.11 DCF. Our study shows that a JACK attacker can easily disrupt the traffic flow between two wireless nodes when it sends out JACK packets at the right time. The benefits of such a JACK attack include low energy consumption by the attacker, attack stealthiness, and great damage to the victim nodes. To mitigate the effects of JACK attacks, we propose in this paper an extended network allocation vector (ENAV) scheme. Our analysis and simulations show that the ENAV scheme recovers a significant portion of the lost throughput and reduces the energy drainage of the attacked nodes to 40%.