Chee Keong Kwoh

The epitranscriptome comprises chemical modifications found on RNA molecules that play essential roles in co- and post-transcriptional gene regulation. Dysregulation of these modifications has been implicated in various diseases, fuelling interest in evaluating them as emerging biomarkers and therapeutic targets. Nanopore direct RNA sequencing provides a powerful platform for profiling diverse RNA modifications at single-molecule resolution, but the complexity of the signals requires advanced computational approaches for interpretation. Artificial intelligence, particularly deep learning (DL), has become central to this effort. While classical DL architectures such as convolutional and recurrent neural networks have been widely applied, more recent approaches employ specialized learning frameworks and ensemble strategies to address challenges of data scarcity, noise, and biological variability while providing higher resolution output. In this review, we summarize these developments and highlight future multidisciplinary opportunities at the intersection of artificial intelligence and biology for characterizing the epitranscriptome obtained with direct RNA nanopore sequencing.

Recent advances in spatial molecular imaging technologies have enabled gene expression profiling alongside high-resolution imaging, providing unprece dented opportunities to resolve molecular heterogeneity at subcellular resolution. However, these technologies fail to fully capture cellular characteristics due to the limited number of genes they can detect, which hinderdownstream analysis. Spatial imaging data provide high-resolution and fine-grained morphology information, developing computational methods that effectively integrate image features with transcriptomic profiles is crucial for enabling comprehensive subcellular data analysis. In this study, we present SIMMT, an image-enhanced multi-modal contrastivetrans former framework for identifying spatial domains and en hancing subcellular data. In the framework, we design a dual transformer architecture to learn multi-modal representations for cells by modeling transcriptomics and morphological images respectively. To fully capture modality interactions within spatial contexts, we introduce a contrastive learning module that enhances cell representation by aligning tissue morphology and gene expression at the cell level. We tested SIMMT on subcellular spatial transcriptomics datasets from human lung cancer tissue, mouse brain tissue, human colorectal cancer tissue, and human ovarian cancer tissue. The results demonstrated that SIMMT consistently outperformed state-of-the-art methods in spatial clustering and gene expression pattern analysis. Our method also effectively demonstrated its ability to identify tumor spatial heterogeneity and uncover potential gene biomarkers in the human bronchiolar adenoma (BA) dataset. The code and dataset of SIMMT can be downloaded from https://github.com/LWanzi/SIMMT

Test-time adaptation enables models to adapt to evolving domains. However, balancing the tradeoff between preserving knowledge and adapting to domain shifts remains challenging for model adaptation methods, since adapting to domain shifts can induce forgetting of task-relevant knowledge. To address this problem, we propose FOCUS, a novel frequency-based conditioning approach within a diffusion-driven input-adaptation framework. Utilising learned, spatially adaptive frequency priors, our approach conditions the reverse steps during diffusion-driven denoising to preserve task-relevant semantic information for dense prediction. FOCUS leverages a trained, lightweight, Y-shaped Frequency Prediction Network (Y-FPN) that disentangles high and low frequency information from noisy images. This minimizes the computational costs involved in implementing our approach in a diffusion-driven framework. We train Y-FPN with FrequencyMix, a novel data augmentation method that perturbs the images across diverse frequency bands, which improves the robustness of our approach to diverse corruptions. We demonstrate the effectiveness of FOCUS for semantic segmentation and monocular depth estimation across 15 corruption types and three datasets, achieving state-of-the-art averaged performance. In addition to improving standalone performance, FOCUS complements existing model adaptation methods since we can derive pseudo labels from FOCUS-denoised images for additional supervision. Even under limited, intermittent supervision with the pseudo labels derived from the FOCUS denoised images, we show that FOCUS mitigates catastrophic forgetting for recent model adaptation methods.

Accurate prediction of the Remaining Useful Life (RUL) in machinery can significantly diminish maintenance costs, enhance equipment up-time, and mitigate adverse outcomes. Data-driven RUL prediction techniques have demonstrated commendable performance. However, their efficacy often relies on the assumption that training and testing data are drawn from the same distribution or domain, which does not hold in real industrial settings. To mitigate this domain discrepancy issue, prior adversarial domain adaptation methods focused on deriving domain-invariant features. Nevertheless, they overlook target-specific information and inconsistency characteristics pertinent to the degradation stages, resulting in suboptimal performance. To tackle these issues, we propose a novel domain adaptation approach for cross-domain RUL prediction named TACDA. Specifically, we propose a target domain reconstruction strategy within the adversarial adaptation process, thereby retaining target-specific information while learning domain-invariant features. Furthermore, we develop a novel clustering and pairing strategy for consistent alignment between similar degradation stages. Through extensive experiments, our results demonstrate the remarkable performance of our proposed TACDA method, surpassing state-of-the-art approaches with regard to two different evaluation metrics. Our code is available at https://github.com/keyplay/TACDA.

Accurate Remaining Useful Life (RUL) prediction without labeled target domain data is a critical challenge, and domain adaptation (DA) has been widely adopted to address it by transferring knowledge from a labeled source domain to an unlabeled target domain. Despite its success, existing DA methods struggle significantly when faced with incomplete degradation trajectories in the target domain, particularly due to the absence of late degradation stages. This missing data introduces a key extrapolation challenge. When applied to such incomplete RUL prediction tasks, current DA methods encounter two primary limitations. First, most DA approaches primarily focus on global alignment, which can misaligns late degradation stage in the source domain with early degradation stage in the target domain. Second, due to varying operating conditions in RUL prediction, degradation patterns may differ even within the same degradation stage, resulting in different learned features. As a result, even if degradation stages are partially aligned, simple feature matching cannot fully align two domains. To overcome these limitations, we propose a novel evidential adaptation approach called EviAdapt, which leverages evidential learning to enhance domain adaptation. The method first segments the source and target domain data into distinct degradation stages based on degradation rate, enabling stage-wise alignment that ensures samples from corresponding stages are accurately matched. To address the second limitation, we introduce an evidential uncertainty alignment technique that estimates uncertainty using evidential learning and aligns the uncertainty across matched stages. The effectiveness of EviAdapt is validated through extensive experiments on the C-MAPSS, N-CMAPSS and PHM2010 datasets. Results show that our approach significantly outperforms state-of-the-art methods, demonstrating its potential for tackling incomplete degradation scenarios in RUL prediction. Our code is available via https://github.com/keyplay/EviAdapt.

Learning from noisy labels (LNL) aims to train high-performance deep models using noisy datasets. Meta learning based label correction methods have demonstrated remarkable performance in LNL by designing various meta label rectification tasks. However, extra clean validation set is a prerequisite for these methods to perform label correction, requiring extra labor and greatly limiting their practicality. To tackle this issue, we propose a novel noisy meta label correction framework STCT, which counterintuitively uses noisy data to correct label noise, borrowing the spirit in the saying ``Set a Thief to Catch a Thief''. The core idea of STCT is to leverage noisy data which is i.i.d. with the training data as a validation set to evaluate model performance and perform label correction in a meta learning framework, eliminating the need for extra clean data. By decoupling the complex bi-level optimization in meta learning into representation learning and label correction, STCT is solved through an alternating training strategy between noisy meta correction and semi-supervised representation learning. Extensive experiments on synthetic and real-world datasets demonstrate the outstanding performance of STCT, particularly in high noise rate scenarios. STCT achieves 96.9% label correction and 95.2% classification performance on CIFAR-10 with 80% symmetric noise, significantly surpassing the current state-of-the-art.

Motivation: Spatial transcriptomics (ST) technologies have revolutionized our ability to map gene expression patterns within native tissue context, providing unprecedented insights into tissue architecture and cellular heterogeneity. However, accurately deconvolving cell-type compositions from ST spots remains challenging due to the sparse and averaged nature of ST data, which is essential for accurately depicting tissue architecture. While numerous computational methods have been developed for cell-type deconvolution and spatial distribution reconstruction, most fail to capture tissue complexity at the single-cell level, thereby limiting their applicability in practical scenarios. Results: To this end, we propose a novel cycle-consistent generative adversarial network named STCGAN for cellular deconvolution in spatial transcriptomic. STCGAN first employs a cycle-consistent generative adversarial network (CGAN) to pre-train on ST data, ensuring that both the mapping from ST data to latent space and its reverse mapping are consistent, capturing complex spatial gene expression patterns and learning robust latent representations. Based on the learned representation, STCGAN then optimizes a trainable cell-to-spot mapping matrix to integrate scRNA-seq data with ST data, accurately estimating cellular composition within each capture spot and effectively reconstructing the spatial distribution of cells across the tissue. To further enhance deconvolution accuracy, we incorporate spatial-aware regularization that ensures accurate cellular distribution reconstruction within the spatial context. Benchmarking against seven state-of-the-art methods on five simulated and real datasets from various tissues, STCGAN consistently delivers superior cell-type deconvolution performance. Availability: The code of STCGAN can be downloaded from https://github.com/cs-wangbo/STCGAN and all the mentioned datasets are available on Zenodo at https://zenodo.org/doi/10.5281/zenodo.10799113.