MOTIVATION: Multi-omics integration can improve cancer diagnosis and prognosis, but current models are limited by extreme dimensionality, redundant raw-feature similarities, missing assays, and incomplete pathway priors. We ask whether biologically meaningful patient manifolds can be learned directly from high-dimensional multi-omics data without heuristic graph construction or fixed knowledge-base constraints. RESULTS: We present OmicsTransformer, an end-to-end framework that projects each omics modality into latent patches, enforces masked semantic consistency through an Exponential Cosine Consistency Loss, models global patch dependencies with a Transformer encoder, and fuses modalities by sample-specific uncertainty. Across eight diagnostic and prognostic cohorts, OmicsTransformer achieved strong performance, including 89.4% accuracy for TCGA-BRCA subtyping and 90.6% area under the receiver operating characteristic curve (AUC) for TCGA-LGG grading. It improved recurrence prediction over the pathway-restricted DeepKEGG baseline by approximately 21.5 percentage points in accuracy (ACC) on TCGA-LIHC and 11.1 percentage points in ACC on TCGA-BLCA. Variance-weighted attribution with ensemble stability selection recovered reproducible cross-modal biomarker cores and non-canonical progression drivers. AVAILABILITY AND IMPLEMENTATION: Source code and datasets are freely available at https://github.com/FFJXX/OmicTransformer and https://doi.org/10.6084/m9.figshare.31523905. OmicsTransformer is implemented in PyTorch.

Since 2023, Vector Quantization (VQ)-based discrete generation methods have rapidly dominated human motion generation, primarily surpassing diffusion-based continuous generation methods in standard performance metrics. However, VQ-based methods have inherent limitations. Representing continuous motion data as limited discrete tokens leads to inevitable information loss, reduces the diversity of generated motions, and restricts their ability to function effectively as motion priors or generation guidance. In contrast, the continuous space generation nature of diffusion-based methods makes them well-suited to address these limitations and with even potential for model scalability. In this work, we systematically investigate why current VQ-based methods perform well and explore the limitations of existing diffusion-based methods from the perspective of motion data representation and distribution. Drawing on these insights, we preserve the inherent strengths of a diffusion-based human motion generation model and gradually optimize it with inspiration from VQ-based approaches. Our approach introduces a human motion diffusion model enabled to perform masked autoregression, optimized with a reformed data representation and distribution. Additionally, we propose a more robust evaluation method to assess different approaches. Extensive experiments on various datasets demonstrate our method outperforms previous methods and achieves state-of-the-art performances.

Metagenomic data plays a crucial role in analyzing the relationship between microbes and diseases. However, the limited number of samples, high dimensionality, and sparsity of metagenomic data pose significant challenges for the application of deep learning in data classification and prediction. Previous studies have shown that utilizing the phylogenetic tree structure to transform metagenomic abundance data into a 2D matrix input for convolutional neural networks (CNNs) improves classification performance. Inspired by the success of a Permutable MLP-like architecture in visual recognition, we propose Metagenomic Permutator (MetaP), which applied the Permutable MLP-like network structure to capture the phylogenetic information of microbes within the 2D matrix formed by phylogenetic tree. Our experiments demonstrate that our model achieved competitive performance compared to other deep neural networks and traditional machine learning, and has good prospects for multi-classification and large sample sizes. Furthermore, we utilize the SHAP (SHapley Additive exPlanations) method to interpret our model predictions, identifying the microbial features that are associated with diseases.

Multi-person pose forecasting remains a challenging problem, especially in modeling fine-grained human body interaction in complex crowd scenarios. Existing methods typically represent the whole pose sequence as a temporal series, yet overlook interactive influences among people based on skeletal body parts. In this paper, we propose a novel Trajectory-Aware Body Interaction Transformer (TBIFormer) for multi-person pose forecasting via effectively modeling body part interactions. Specifically, we construct a Temporal Body Partition Module that transforms all the pose sequences into a Multi-Person Body-Part sequence to retain spatial and temporal information based on body semantics. Then, we devise a Social Body Interaction Self-Attention (SBI-MSA) module, utilizing the transformed sequence to learn body part dynamics for inter- and intra-individual interactions. Furthermore, different from prior Euclidean distance-based spatial encodings, we present a novel and efficient Trajectory-Aware Relative Position Encoding for SBI-MSA to offer discriminative spatial information and additional interactive clues. On both short-and long-term horizons, we empirically evaluate our frame-work on CMU-Mocap, MuPoTS-3D as well as synthesized datasets (6 ~ 10 persons), and demonstrate that our method greatly outperforms the state-of-the-art methods.

Heterogeneous one-class collaborative filtering is an emerging and important problem in recommender systems, where two different types of one-class feedback, i.e., purchases and browses, are available as input data. The associated challenges include ambiguity of browses, scarcity of purchases, and heterogeneity arising from different feedback. In this article, we propose to model purchases and browses from a new perspective, i.e., users’ roles of mixer, browser and purchaser. Specifically, we design a novel transfer learning solution termed role-based transfer to rank (RoToR), which contains two variants, i.e., integrative RoToR and sequential RoToR. In integrative RoToR, we leverage browses into the preference learning task of purchases, in which we take each user as a sophisticated customer (i.e., mixer ) that is able to take different types of feedback into consideration. In sequential RoToR, we aim to simplify the integrative one by decomposing it into two dependent phases according to a typical shopping process. Furthermore, we instantiate both variants using different preference learning paradigms such as pointwise preference learning and pairwise preference learning. Finally, we conduct extensive empirical studies with various baseline methods on three large public datasets and find that our RoToR can perform significantly more accurate than the state-of-the-art methods.

Accurate node locations are critically demanded for various WSN applications. A widely adopted approach assumes a few nodes used as anchor nodes whose locations are known and the distances between nodes can be estimated. The accuracy of existing estimation can be improved due to the flip ambiguity (FA) phenomena. This paper presents an original anchor-based node location approach for better accuracy by using positioning priorities. We first comprehensively investigate the FA phenomena and study its effect factors, then introduce a new concept exploring the node positioning priority to avoid FA as much as possible. Finally an empirical simulation study has been carried out to evaluate our proposed approach against the simulated annealing based location (SAL), genetic algorithm based location (GAL) and collinearity-aware trilateration incorporated with the implicit collinearity method (TRI-ICD). The experimental results show that our proposed approach reduce location errors.

Automatic classification of web pages is an effective way to deal with the difficulty of retrieving information from the Internet. Although there are many automatic classification algorithms and systems that have been proposed, most of them ignore the conflict between the fixed number of categories and the growing number of web pages going into the system. They also require searching through all existing categories to make any classification. We propose a dynamic and hierarchical classification system that is capable of adding new categories as required, organizing the web pages into a tree structure, and classifying web pages by searching through only one path of the tree structure. Our test results show that our proposed single-path search technique reduces the search complexity and increases the accuracy by 6% comparing to related algorithms. Our dynamic-category expansion technique also achieves satisfying results on adding new categories into our system as required.