SUMMARY: We present needLR, a structural variant (SV) annotation tool that can be used for filtering and prioritization of candidate pathogenic SVs from long-read sequencing data using population allele frequencies, annotations for genomic context, and gene-phenotype associations. When using population data from 500 presumably healthy individuals to evaluate nine test cases with known pathogenic SVs, needLR assigned allele frequencies to over 97.5% of all detected SVs and reduced the average number of novel genic SVs to 121 per case while retaining all known pathogenic variants. AVAILABILITY AND IMPLEMENTATION: needLR is implemented in bash with dependencies including Truvari v4.2.2, BEDTools v2.31.1, and BCFtools v1.19. Source code, documentation, and pre-computed population allele frequency data are freely available at https://github.com/jgust1/needLR under an MIT license and archived on Zenodo at https://zenodo.org/records/19463479.

Signal Modulation Classification (SMC) is a fundamental technique in wireless communications. However, the prevalence of label noise in practical scenarios severely constrains the advancement of SMC technology. Existing SMC methods heavily rely on high-quality labeled data and often underutilize the inherent physical prior knowledge of signals. To address these issues, this article proposes a Physics-Aware Collaborative Framework with Prototype Consistency (PhyCo-PC), designed for noisy label environments and operating without requiring reliable labels. Firstly, the framework leverages co-teaching for noise identification and incorporates a collaborative consensus-guided module for prototype learning and pseudo-label generation. Secondly, it constructs physics-guided downstream decision module that fuses deep learning features with instantaneous physical signal characteristics to enhance decision robustness. Thirdly, a Domain Knowledge-guided Adaptive Sample Selection (DKASS) strategy is introduced. DKASS parameterizes the selection rate scheduling function, incorporates domain knowledge to constrain the search space, and utilizes automated search for optimization. This enables the model to adaptively determine the optimal training strategy for varying noise environments. Finally, experimental results demonstrate that PhyCo-PC significantly improves SMC classification performance under complex label noise scenarios on the RML2016.10a/04c datasets, exhibiting excellent robustness and significant advantages.

Representational state transfer (REST) is a widely employed architecture by web applications and cloud. Users can invoke such services according to the specification of their application interfaces, namely RESTful APIs. Existing approaches for fuzzing RESTful APIs are generally based on classic API-dependency graphs. However, such dependencies are inefficient for REST services due to the explosion of dependencies among APIs. In this paper, we propose a novel tree-based approach that can better capture the essential dependencies and largely improve the efficiency of RESTful API fuzzing. In particular, the hierarchical information of the endpoints across multiple APIs enables us to construct an API tree, and the relationships of tree nodes can indicate the priority of resource dependencies, e.g., it’s more likely that a node depends on its parent node rather than its offspring or siblings. We employ two real-world REST projects and the REST-Go benchmark for evaluation and compare the performance of foREST with two state-of-the-art fuzzing tools, RESTler and EvoMaster (black-box mode). Results show that foREST can achieve substantial coverage improvement in most experiments. Besides, foREST finds 20 new bugs previously unknown.

Structural variant (SV) detection is essential for genomic studies, and long-read sequencing technologies have advanced our capacity to detect SVs directly from read or de novo assembly, also known as read-based and assembly-based strategy. However, to date, no independent studies have compared and benchmarked the two strategies. Here, on the basis of SVs detected by 20 read-based and eight assembly-based detection pipelines from six datasets of HG002 genome, we investigated the factors that influence the two strategies and assessed their performance with well-curated SVs. We found that up to 80% of the SVs could be detected by both strategies among different long-read datasets, whereas variant type, size, and breakpoint detected by read-based strategy were greatly affected by aligners. For the high-confident insertions and deletions at non-tandem repeat regions, a remarkable subset of them (82% in assembly-based calls and 93% in read-based calls), accounting for around 4000 SVs, could be captured by both reads and assemblies. However, discordance between two strategies was largely caused by complex SVs and inversions, which resulted from inconsistent alignment of reads and assemblies at these loci. Finally, benchmarking with SVs at medically relevant genes, the recall of read-based strategy reached 77% on 5X coverage data, whereas assembly-based strategy required 20X coverage data to achieve similar performance. Therefore, integrating SVs from read and assembly is suggested for general-purpose detection because of inconsistently detected complex SVs and inversions, whereas assembly-based strategy is optional for applications with limited resources.

The black-box adversarial attack has attracted impressive attention for its practical use in the field of deep learning security. Meanwhile, it is very challenging as there is no access to the network architecture or internal weights of the target model. Based on the hypothesis that if an example remains adversarial for multiple models, then it is more likely to transfer the attack capability to other models, the ensemble-based adversarial attack methods are efficient and widely used for black-box attacks. However, ways of ensemble attack are rather less investigated, and existing ensemble attacks simply fuse the outputs of all the models evenly. In this work, we treat the iterative ensemble attack as a stochastic gradient descent optimization process, in which the variance of the gradients on different models may lead to poor local optima. To this end, we propose a novel attack method called the stochastic variance reduced ensemble (SVRE) attack, which could reduce the gradient variance of the ensemble models and take full advantage of the ensemble attack. Empirical results on the standard ImageNet dataset demonstrate that the proposed method could boost the adversarial transferability and outperforms existing ensemble attacks significantly. Code is available at https://github.com/JHL-HUST/SVRE.

MOTIVATION: Tumor purity is a fundamental property of each cancer sample and affects downstream investigations. Current tumor purity estimation methods either require matched normal sample or report moderately high tumor purity even on normal samples. It is critical to develop a novel computational approach to estimate tumor purity with sufficient precision based on tumor-only sample. RESULTS: In this study, we developed MEpurity, a beta mixture model-based algorithm, to estimate the tumor purity based on tumor-only Illumina Infinium 450k methylation microarray data. We applied MEpurity to both The Cancer Genome Atlas (TCGA) cancer data and cancer cell line data, demonstrating that MEpurity reports low tumor purity on normal samples and comparable results on tumor samples with other state-of-art methods. AVAILABILITY AND IMPLEMENTATION: MEpurity is a C++ program which is available at https://github.com/xjtu-omics/MEpurity. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.