As large language models (LLMs) become increasingly capable, concerns over the unauthorized use of copyrighted and licensed content in their training data have grown, especially in the context of code. Open-source code, often protected by open source licenses (e.g, GPL), poses legal and ethical challenges when used in pretraining. Detecting whether specific code samples were included in LLM training data is thus critical for transparency, accountability, and copyright compliance. We propose SynPrune, a syntax-pruned membership inference attack method tailored for code. Unlike prior MIA approaches that treat code as plain text, SynPrune leverages the structured and rule-governed nature of programming languages. Specifically, it identifies and excludes consequent tokens that are syntactically required and not reflective of authorship, from attribution when computing membership scores. Experimental results show that SynPrune consistently outperforms the state-of-the-arts. Our method is also robust across varying function lengths and syntax categories.

In this study, we investigate the performance of nine protein structure alignment tools on three tasks: superposition derivation, structural classification, and function inference. These tools include (1) traditional sequential methods using both 3D and 2D structure representations, (2) non-sequential methods, (3) flexible methods, and (4) deep-learning methods. We also include two canonical sequence alignment methods the Needleman-Wunsch algorithm and BLASTp, as baselines. We have the following results: In deriving superposition, deep learning methods, which focus on library search, produce less accurate patterns than traditional pairwise methods, but are more precise than sequence alignment; In structural classification, structure-based methods are much better than sequence alignment, with DALI performing the best; In function inference, structure-based methods recover more functional homology hits than sequence alignment, with KPAX recovering the most. We identify key factors that affect performance, including scoring metrics, the ability to capture side-chain information, and partial alignment mechanisms. Notably, deep learning methods, such as Foldseek, perform well on large-scale queries, in terms of both speed and accuracy. Our findings highlight the importance of integrating structural and sequence data for performance benefits, providing insight into the development of protein structure alignment tools in the future. Code and data are available at https://github.com/georgedashen/StructAlign

The High-Fidelity (HiFi) sequencing technology produces long, highly accurate reads, leading to higher-quality results in genome assembly. All-vs-all overlap detection is an important task for de novo assembly and other genomics applications. However, existing methods remain inefficient for HiFi reads, as they lack optimizations for long read length and high accuracy. To improve efficiency, we introduce RapidAVA, a new method for all-vs-all overlap detection in HiFi reads. First, we identify a set of representative subsequences, or minimizers, from all reads as indices for overlap detection; we keep the total number of minimizers small while ensuring their coverage of the reads. Second, we develop a fast seed-chaining algorithm to link the common minimizers (seeds) between a pair of reads. Last, to align a pair of reads to identify overlap, we adopt the wavefront alignment (WFA) algorithm for its lower complexity than other dynamic programming algorithms, and improve the algorithm with heuristics suitable for HiFi reads. Our experiments show that RapidAVA outperforms existing tools, achieving speedups of$4.7 \times$and$2.3 \times$over Minimap 2 and Hifiasm, respectively, with its peak memory consumption at 13 - 50 % of the other systems.

MOTIVATION: The three-dimensional protein tertiary structure alignment is a fundamental problem that seeks insights into functions and evolution. Previous structure alignment algorithms have adopted the sequential assumption and used dynamic programming solvers. However, many distantly related structures exhibit non-sequential similarities, and non-sequential alignment tools are less efficient and accurate than sequential ones. In this paper, we formulate the non-sequential alignment as the Entropy-regularized Partial Linear Sum Assignment Problem (epLSAP) and propose a solver based on Sinkhorn algorithms, referred to as epLSAP-Align. RESULTS: Compared with existing non-sequential alignment solvers, our epLSAP-Align can explicitly model the gap penalty, efficiently achieve global optimality and balance coverage and fidelity. We show that epLSAP-Align can be easily integrated into the existing frameworks, such as TM-align and MICAN, resulting in the non-sequential alignment tool epLSAP-TM and epLSAP-MICAN, respectively. Both epLSAP-TM and epLSAP-MICAN achieve better performance than the existing non-sequential alignment tools in terms of biologically meaningful structure overlaps on two sequential alignment test sets MALIDUP and MALISAM, and four non-sequential alignment test sets MALIDUP-ns, MALISAM-ns, 64-difficult-case and RIPC datasets. Also, compared with the most recent non-sequential alignment tool USalign2, our epLSAP-TM is at least 22% faster under the same setting. AVAILABILITY AND IMPLEMENTATION: Our source code is available at https://github.com/xzhangem/epLSAP-align.

In radio astronomy, visibility data, which are measurements of wave signals from radio telescopes, are transformed into images for observation of distant celestial objects. However, these resultant images usually contain both real sources and artifacts, due to signal sparsity and other factors. One way to obtain cleaner images is to reconstruct samples into dense forms before imaging. Unfortunately, existing reconstruction methods often miss some components of visibility in frequency domain, so blurred object edges and persistent artifacts remain in the images. Furthermore, the computation overhead is high on irregular visibility samples due to the data skew. To address these problems, we propose PolarRec, a transformer-encoder-conditioned reconstruction pipeline with visibility samples converted into the polar coordinate system. This coordinate system matches the way in which radio telescopes observe a celestial area as the Earth rotates. As a result, visibility samples distribute in the polar system more uniformly than in the Cartesian space. Therefore, we propose to use radial distance in the loss function, to help reconstruct complete visibility effectively. Also, we group visibility samples by their polar angles and propose a group-based encoding scheme to improve the efficiency. Our experiments demonstrate that PolarRec markedly improves imaging results by faithfully reconstructing all frequency components in the visibility domain while significantly reducing the computation cost in visibility data encoding. The code is available at https://github.com/RapidsAtHKUSTIPolarRec.

MOTIVATION: Protein-protein interaction (PPI) networks are crucial for automatically annotating protein functions. As multiple PPI networks exist for the same set of proteins that capture properties from different aspects, it is a challenging task to effectively utilize these heterogeneous networks. Recently, several deep learning models have combined PPI networks from all evidence, or concatenated all graph embeddings for protein function prediction. However, the lack of a judicious selection procedure prevents the effective harness of information from different PPI networks, as these networks vary in densities, structures, and noise levels. Consequently, combining protein features indiscriminately could increase the noise level, leading to decreased model performance. RESULTS: We develop DualNetGO, a dual-network model comprised of a Classifier and a Selector, to predict protein functions by effectively selecting features from different sources including graph embeddings of PPI networks, protein domain, and subcellular location information. Evaluation of DualNetGO on human and mouse datasets in comparison with other network-based models shows at least 4.5%, 6.2%, and 14.2% improvement on Fmax in BP, MF, and CC gene ontology categories, respectively, for human, and 3.3%, 10.6%, and 7.7% improvement on Fmax for mouse. We demonstrate the generalization capability of our model by training and testing on the CAFA3 data, and show its versatility by incorporating Esm2 embeddings. We further show that our model is insensitive to the choice of graph embedding method and is time- and memory-saving. These results demonstrate that combining a subset of features including PPI networks and protein attributes selected by our model is more effective in utilizing PPI network information than only using one kind of or concatenating graph embeddings from all kinds of PPI networks. AVAILABILITY AND IMPLEMENTATION: The source code of DualNetGO and some of the experiment data are available at: https://github.com/georgedashen/DualNetGO.

In radio astronomy, signals from radio telescopes are transformed into images of observed celestial objects, or sources. However, these images, called dirty images, contain real sources as well as artifacts due to signal sparsity and other factors. Therefore, radio interferometric image reconstruction is performed on dirty images, aiming to produce clean images in which artifacts are reduced and real sources are recovered. So far, existing methods have limited success on recovering faint sources, preserving detailed structures, and eliminating artifacts. In this paper, we present VIC-DDPM, a Visibility and Image Conditioned Denoising Diffusion Probabilistic Model. Our main idea is to use both the original visibility data in the spectral domain and dirty images in the spatial domain to guide the image generation process with DDPM. This way, we can leverage DDPM to generate fine details and eliminate noise, while utilizing visibility data to separate signals from noise and retaining spatial information in dirty images. We have conducted experiments in comparison with both traditional methods and recent deep learning based approaches. Our results show that our method significantly improves the resulting images by reducing artifacts, preserving fine details, and recovering dim sources. This advancement further facilitates radio astronomical data analysis tasks on celestial phenomena. Our code is available at https://github.com/RapidsAtHKUST/VIC-DDPM.