MOTIVATION: Aberrant DNA methylation is a fundamental epigenetic hallmark of cancer. However, existing resources often lack technological diversity and comprehensive cancer coverage. Furthermore, most platforms fail to achieve deep multi-omics integration and tend to ignore cancer-type-specific methylation features, limiting their utility in precision oncology and drug discovery. RESULTS: We developed Cancer Methylation Atlas (CMAtlas), a comprehensive platform integrating 13 753 samples across 34 cancer types. By applying technology-tailored pipelines to data from various profiling technologies, we identified 830 725 tumor-specific differentially methylated elements (DMEs) and 1 480 098 differentially methylated regions (DMRs), alongside 1 154 256 cancer-type-specific DMEs and 329 154 DMRs. The platform demonstrates high cross-platform consistency and strong concordance between tumor tissues and cell lines, ensuring the robustness of our findings. All DMEs and DMRs are annotated with multi-omics data (RNA expression, somatic mutations, and chromatin accessibility) and clinical relevance (survival associations and cell-free DNA profiling). We further demonstrate the utility of CMAtlas by identifying prognostic aberrant methylation in colorectal cancer driver genes. AVAILABILITY AND IMPLEMENTATION: CMAtlas is freely accessible at {{https://cmatlas.renlab.cn/}}. The platform offers an intuitive web interface supporting gene-centric and cancer-centric queries, alongside customizable analysis modules designed to facilitate user-specific research needs.

Many students enjoy listening to background music (BGM) when they read, but it is challenging to measure their meta-cognitive states (e.g., understanding of the passage, engagement in reading). Eye movements, as an approach in multimodal learning analytics (MmLA), can offer continuous fine-grained data that reflect learners’ cognitive processes. This study explored the potential of utilizing eye movement measures to predict learners’ meta-cognition during reading with BGM. Results showed that learners’ eye movement measures integrated with the characteristics of the BGM, learner traits, and text complexity could predict their meta-cognitive states in reading. Findings can advance our understanding of human meta-cognition in multi-channel learning settings and provide insights for personalized BGM recommendations to enhance reading experiences.

Model explanations are generated by XAI (explainable AI) methods to help people understand and interpret machine learning models. To study XAI methods from the human perspective, we propose a human-based benchmark dataset, i.e., human saliency benchmark (HSB), for evaluating saliency-based XAI methods. Different from existing human saliency annotations where class-related features are manually and subjectively labeled, this benchmark collects more objective human attention on vision information with a precise eye-tracking device and a novel crowdsourcing experiment. Taking the labor cost of human experiment into consideration, we further explore the potential of utilizing a prediction model trained on HSB to mimic saliency annotating by humans. Hence, a dense prediction problem is formulated, and we propose an encoder-decoder architecture which combines multi-modal and multi-scale features to produce the human saliency maps. Accordingly, a pretraining-finetuning method is designed to address the model training problem. Finally, we arrive at a model trained on HSB named human saliency imitator (HSI). We show, through an extensive evaluation, that HSI can successfully predict human saliency on our HSB dataset, and the HSI-generated human saliency dataset on ImageNet showcases the ability of benchmarking XAI methods both qualitatively and quantitatively.

Reading is an essential medium for learning, but it is challenging to measure learners’ cognitive processes during reading. Eye-tracking, as an approach in multimodal learning analytics (MmLA), can provide fine-grained data that reflect cognitive processes during reading. In this study, we investigated whether eye movements could predict passage reading performance in addition to language proficiency and cognitive abilities. In particular, we assessed learners’ eye movement pattern and consistency through a novel method, Eye Movement analysis with Hidden Markov Models (EMHMM), in addition to traditional eye movement measures. We found that longer saccade length predicted faster reading speed Also, higher English proficiency predicted faster reading speed through the mediation of longer saccade length. In contrast, reading comprehension accuracy was best predicted by a more consistent eye fixation at the beginning of reading engagement, which may result from a better developed visual routine due to higher reading expertise. These findings have important implications for ways to assess and facilitate learners’ reading through eye movement measures and to examine factors influencing reading performance. The methods adopted could further the development of MmLA and serve as an empirical example of understanding learners’ cognitive processes through collecting and modeling critical learner-centered metrics in novel modalities.

Perturbation-based techniques are promising for explaining black-box machine learning models due to their effectiveness and ease of implementation. However, prior works have faced the problem of Out-of-Distribution (OoD) — an artifact of randomly perturbed data becoming inconsistent with the original dataset, degrading the reliability of generated explanations, which is still under-explored according to our best knowledge. This work addresses the OoD issue by designing a simple yet effective module that can quantify the affinity between the perturbed data and the original dataset distribution. Specifically, we penalize the influences of unreliable OoD data for the perturbed samples by integrating the inlier scores and prediction results of the target models, thereby making the final explanations more robust. Our solution is shown to be compatible with the most popular perturbation-based XAI algorithms: RISE, OCCLUSION, and LIME. Extensive experiments confirmed that our methods exhibit superior performance in most cases with computational and cognitive metrics. In particular, we point out the degradation problem of RISE algorithm for the first time. With our design, the performance of RISE can be boosted significantly. Besides, our solution also resolves a fundamental problem with a faithfulness indicator, a commonly used evaluation metric of XAI algorithms that appears sensitive to the OoD issue.

UNLABELLED: Biological sequence diagrams are fundamental for visualizing various functional elements in protein or nucleotide sequences that enable a summarization and presentation of existing information as well as means of intuitive new discoveries. Here, we present a software package called illustrator of biological sequences (IBS) that can be used for representing the organization of either protein or nucleotide sequences in a convenient, efficient and precise manner. Multiple options are provided in IBS, and biological sequences can be manipulated, recolored or rescaled in a user-defined mode. Also, the final representational artwork can be directly exported into a publication-quality figure. AVAILABILITY AND IMPLEMENTATION: The standalone package of IBS was implemented in JAVA, while the online service was implemented in HTML5 and JavaScript. Both the standalone package and online service are freely available at http://ibs.biocuckoo.org. CONTACT: [email protected] or [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.