Recent advances in generative models, especially diffusion models, have significantly improved image restoration (IR) performance. However, existing problem-agnostic diffusion model-based image restoration (DMIR) methods face challenges in fully leveraging diffusion priors, resulting in suboptimal performance. In this paper, we address the limitations of current problem-agnostic DMIR methods by analyzing their sampling process and providing effective solutions. We introduce EquS, a DMIR method that imposes equivariant information through dual sampling trajectories. To further boost EquS, we propose the Timestep-Aware Schedule (TAS) and introduce EquS+. TAS prioritizes deterministic steps to enhance certainty and sampling efficiency. Extensive experiments on benchmarks demonstrate that our method is compatible with previous problem-agnostic DMIR methods and significantly boosts their performance without increasing computational costs. Our code is available in https://github.com/FouierL/EquS.

Anomaly detection (AD) identifies outliers for applications like defect and lesion detection. While CLIP shows promise for zero-shot AD tasks due to its strong generalization capabilities, its inherent Anomaly-Unawareness leads to limited discrimination between normal and abnormal features. To address this problem, we propose Anomaly-Aware CLIP (AA-CLIP), which enhances CLIP's anomaly discrimination ability in both text and visual spaces while preserving its generalization capability. AA-CLIP is achieved through a straightforward yet effective two-stage approach: it first creates anomaly-aware text anchors to differentiate normal and abnormal semantics clearly, then aligns patch-level visual features with these anchors for precise anomaly localization. This two-stage strategy, with the help of residual adapters, gradually adapts CLIP in a controlled manner, achieving effective AD while maintaining CLIP's class knowledge. Extensive experiments validate AA-CLIP as a resource-efficient solution for zero-shot AD tasks, achieving state-of-the-art results in industrial and medical applications. The code is available at https://github.com/Mwxinnn/AA-CLIP.

Magnetic Resonance Imaging (MRI), including diffusion MRI (dMRI), serves as a ``microscope'' for anatomical structures and routinely mitigates the influence of low signal-to-noise ratio scans by compromising temporal or spatial resolution. However, these compromises fail to meet clinical demands for both efficiency and precision. Consequently, denoising is a vital preprocessing step, particularly for dMRI, where clean data is unavailable. In this paper, we introduce Di-Fusion, a fully self-supervised denoising method that leverages the latter diffusion steps and an adaptive sampling process. Unlike previous approaches, our single-stage framework achieves efficient and stable training without extra noise model training and offers adaptive and controllable results in the sampling process. Our thorough experiments on real and simulated data demonstrate that Di-Fusion achieves state-of-the-art performance in microstructure modeling, tractography tracking, and other downstream tasks. Code is available at https://github.com/FouierL/Di-Fusion.

Over the past decades, pansharpening has contributed greatly to numerous remote sensing applications, with methods evolving from theoretically grounded models to deep learning approaches and their hybrids. Though promising, existing methods rarely address pansharpening through the lens of underlying physical imaging processes. In this work, we revisit the spectral imaging mechanism and propose a novel physics‐informed neural operator framework for pansharpening, termed PINO, which faithfully models the end‐to‐end electro‐optical sensor process. Specifically, PINO operates as: (1) First, a spatial-spectral encoder pair is introduced to aggregate multi-granularity high-resolution panchromatic (PAN) and low-resolution multispectral (LRMS) features. (2) Subsequently, an iterative neural integral process utilizes these fused spatial-spectral characteristics to learn a continuous radiance field $L_i(x, y, \lambda)$ over spatial coordinates and wavelength, effectively emulating band-wise spectral integration. (3) Finally, the learned radiance field is modulated by the sensor’s spectral responsivity $R_b(\lambda)$ to produce physically consistent spatial–spectral fusion products. This physics-grounded fusion paradigm offers a principled solution for reconstructing high-resolution multispectral and hyperspectral images in accordance with sensor imaging physics, effectively harnessing the unique advantages of spectral data to better uncover real-world characteristics. Experiments on multiple benchmark datasets show that our method surpasses state-of-the-art fusion algorithms, achieving reduced spectral aberrations and finer spatial textures. Furthermore, extension to hyperspectral (HS) data demonstrates its generalizability and universality. The code will be available upon potential acceptance.

Accurate calling of parental-child SNPs and Indels in family trios is very helpful for understanding genetic traits and diseases. Indel calling is even more important than SNP calling, as Indels may have led to substantial changes in protein structures that affect more of the traits of the organism. However, the best Indel calling methods have recall rates below 85%, precision below 92%, and F1 below 88% on $60\times $ ONT Q20 data, much lower than their SNP calling's recall performance of 99.87%, precision of 99.86%, and F1 of 99.86%. Difficulties in Indels calling include how to distinguish sequencing errors from genuine Indels and how to optimize the Mendelian genetic model. This work proposes sparse attention learning for high-performance calling of Indels from family-trios' ONT long-read sequencing data, while still maintaining exceptional performance on SNP calling. Key steps include a sparsely connected attention network to convert fully aligned data cubes into essential features, and a deep learning on these features via ResNet and 3D convolutional blocks to enable accurate detection of family-trio variants. This attention network is in fact a dual attention network to aggregate both channel and spatial information, capable of selecting sub-cubes of critical channels and base locations that are resistant to the confounding effects of sequencing errors. Comparing with the current best-performing trio-variant detection method, our F1 is 5.6%-14.19% higher, recall is 7.07%-18.67% higher, and precision is 3.85%-7.87% higher on ONT Q20 datasets. Case studies of indel-dense regions in chromosome 20, including the centromere and disease-associated genes, demonstrate the significant impact of indel variations on disease pathogenesis, providing novel perspectives for future personalized and targeted therapies.

Pansharpening is the critical technology for generating high-resolution (HR) multispectral (MS) images by learning the cross-modality complementary representations between the panchromatic (PAN) images and low-resolution (LR) MS images. Though methods based on convolutional neural networks (CNNs) have dominated the pansharpening community, they still suffer from the limited global modeling capability due to the inherent property of the convolutional operator. To remedy this common limitation, the transformer family has recently gained great popularity in this field. However, existing cascaded transformer designs inevitably introduce a heavy memory footprint and computational cost due to the dense dot-product self-attention (SA) computation. More importantly, these paradigms simply ignore the innate sparsity of remote sensing images, leading to information redundancy and a challenging optimization process. To alleviate these issues, we propose the bilateral adaptive evolution transformer (BAEFormer), which is built upon two core mechanisms: bilateral attention computation and adaptive attention evolution. Specifically, we first decompose the conventional quadratic complexity SA into linear-degree height and width computing at the first stage, respectively, which significantly reduces the computational complexity. Given the data-specific properties, furthermore, we devise a novel yet effective neighboring layer-dependent strategy to adaptively update the attention map of two spatial dimensions, thereby avoiding the repetitive SA computation while taking into account the dynamics toward the evolution of attention weights. Our model, called BAEFormer, outperforms other state-of-the-art pansharpening methods on various remote sensing datasets while showing fewer network parameters and computational requirements. The code is available athttps://github.com/coder-JMHou/BAEFormer.

Pan-sharpening essentially to boost the spatial resolution of a multispectral (MS) image guided by its paired panchromatic (PAN) image. In other words, this process intricately integrates the high-frequency components extracted from texture-rich PAN images into the low-resolution (LR) MS images, resulting in texture-rich MS images. Though existing deep learning (DL)-based techniques have made impressive performance compared with traditional algorithms, they still face challenges in accurately restoring high-frequency details in MS images, thus limiting overall pan-sharpening performance. In addition, reference high-resolution (HR) MS images are often underutilized, typically serving only as training labels. In this work, we present a general high-frequency enhancement framework for pan-sharpening, which is implemented through a cooperative optimization strategy using mutual information (MI) maximization and contrastive learning. Specifically, our model comprises two fundamental modules: the high-frequency feature alignment (HFFA) module and the high-frequency detail calibration (HFDC) module. The first employs MI maximization to align the high-frequency semantic statistical distribution between PAN images and reference HRMS images. The latter is designed to calibrate the high-frequency components of MS modality under the guidance of the PAN counterparts through the contrastive learning constraint, thereby producing more accurate high-frequency information on MS modality. By integrating the calibrated high-frequency features of MS modality and those of PAN modality, we can obtain a more comprehensive and precise high-frequency feature representation of these two modalities, facilitating the reconstruction of LRMS images. Our model, incorporating the aforementioned key elements, significantly surpasses other state-of-the-art (SOTA) techniques across multiple satellite datasets in both quantitative and qualitative experiments. Moreover, the real-world full-resolution and cross-sensor assessments testify to its exceptional generalization capabilities. The code is available athttps://github.com/Vcocoi/CONet.

Copy number alterations (CNAs) are a predominant source of genetic alterations in human cancer and play an important role in cancer progression. However comprehensive understanding of the mutational processes and signatures of CNA is still lacking. Here we developed a mechanism-agnostic method to categorize CNA based on various fragment properties, which reflect the consequences of mutagenic processes and can be extracted from different types of data, including whole genome sequencing (WGS) and single nucleotide polymorphism (SNP) array. The 14 signatures of CNA have been extracted from 2778 pan-cancer analysis of whole genomes WGS samples, and further validated with 10 851 the cancer genome atlas SNP array dataset. Novel patterns of CNA have been revealed through this study. The activities of some CNA signatures consistently predict cancer patients' prognosis. This study provides a repertoire for understanding the signatures of CNA in cancer, with potential implications for cancer prognosis, evolution and etiology.

Major histocompatibility complex (MHC) class II molecules play a pivotal role in antigen presentation and CD4+ T cell response. Accurate prediction of the immunogenicity of MHC class II-associated antigens is critical for vaccine design and cancer immunotherapies. However, current computational methods are limited by insufficient training data and algorithmic constraints, and the rules that govern which peptides are truly recognized by existing T cell receptors remain poorly understood. Here, we build a transfer learning-based, long short-term memory model named 'TLimmuno2' to predict whether epitope-MHC class II complex can elicit T cell response. Through leveraging binding affinity data, TLimmuno2 shows superior performance compared with existing models on independent validation datasets. TLimmuno2 can find real immunogenic neoantigen in real-world cancer immunotherapy data. The identification of significant MHC class II neoantigen-mediated immunoediting signal in the cancer genome atlas pan-cancer dataset further suggests the robustness of TLimmuno2 in identifying really immunogenic neoantigens that are undergoing negative selection during cancer evolution. Overall, TLimmuno2 is a powerful tool for the immunogenicity prediction of MHC class II presented epitopes and could promote the development of personalized immunotherapies.