The increasing volume of high-throughput molecular data has presented substantial computational challenges in the identification of cancer driver genes. We introduce ATTAG, a framework based on topology-adaptive graph neural networks with an attention mechanism, aimed at predicting cancer driver genes by integrating multi-omics data with biomolecular networks. ATTAG creates three distinct gene networks derived from protein interactions, gene semantic similarities, and co-occurrence within signaling pathways. Graph convolutional networks (GCNs) are employed to generate low-dimensional embeddings from these networks and multi-omics data. These embeddings are then refined through topology-adaptive graph neural networks for the prediction of cancer driver genes in BLCA. When compared to state-of-the-art methods, ATTAG demonstrates exceptional performance in identifying cancer driver genes. The experimental results underscore its ability to accurately identify both well-known driver genes and novel candidate cancer genes.

MOTIVATION: Predicting protein-protein interaction (PPI) sites is essential for advancing our understanding of protein interactions, as accurate predictions can significantly reduce experimental costs and time. While considerable progress has been made in identifying binding sites at the level of individual amino acid residues, the prediction accuracy for residue subsequences at transitional boundaries-such as those represented by patterns like singular structures (mutation characteristics of contiguous interacting-residue segments) or edge structures (boundary transitions between interacting/non-interacting residue segments) still requires improvement. RESULTS: we propose a novel PPI site prediction method named MVSO-PPIS. This method integrates two complementary feature extraction modules, a subgraph-based module and an enhanced graph attention module. The extracted features are fused using an attention-based fusion mechanism, producing a composite representation that captures both local protein substructures and global contextual dependencies. MVSO-PPIS is trained to jointly optimize three objectives: overall PPI site prediction accuracy, edge structural consistency, and recognition of unique structural patterns in PPI site sequences. Experimental results on benchmark datasets demonstrate that MVSO-PPIS outperforms existing baseline models in both accuracy and structural interpretability. AVAILABILITY AND IMPLEMENTATION: The datasets, source codes, and models of MVSO-PPIS are all available at https://github.com/Edwardblue282/MVSO-PPIS.

MicroRNAs (miRNAs) play a crucial role in the regulation of gene expression and have been implicated in the pathogenesis of various cancers. Predicting miRNA-cancer associations is essential for understanding cancer mechanisms and developing therapeutic strategies. In this work, we introduce a computational method named PERGAT (Pretrained Embeddings based on the Residual Graph Attention Network) for predicting miRNA-cancer associations. Extensive experimental results demonstrate the superior performance of PERGAT compared to other state-of-the-art methods. We achieved the AUC as high as 0.9641 in terms of the area under the Receiver Operating Characteristic (ROC) curves, and the area under the precision-recall curves as 0.9377. Our approach leverages the structure of miRNA-disease networks to capture complex relationships efficiently and improves prediction accuracy. Additionally, PERGAT exhibits exceptional performance in three cancer case studies, underscoring its reliability for studying miRNA-disease associations. The data and source codes are available at https://github.com/ericsaliway/PERGAT.

In healthcare, AI techniques are widely used for tasks like risk assessment and anomaly detection. Despite AI’s potential as a valuable assistant, its role in complex medical data analysis often over-simplifies human-AI collaboration dynamics. To address this, we collaborated with a local hospital, engaging six physicians and one data scientist in a formative study. From this collaboration, we propose a framework integrating two-phase interactive visualization systems: one for Human-Led, AI-Assisted Retrospective Analysis and another for AI-Mediated, Human-Reviewed Iterative Modeling. This framework aims to enhance understanding and discussion around effective human-AI collaboration in healthcare.

While deep learning has achieved great success in computer vision and many other fields, currently it does not work very well on patient genomic data with the “big p, small N” problem (i.e., a relatively small number of samples with highdimensional features). In order to make deep learning work with a small amount of training data, we have to design new models that facilitate few-shot learning. Here we present the Affinity Network Model (AffinityNet), a data efficient deep learning model that can learn from a limited number of training examples and generalize well. The backbone of the AffinityNet model consists of stacked k-Nearest-Neighbor (kNN) attention pooling layers. The kNN attention pooling layer is a generalization of the Graph Attention Model (GAM), and can be applied to not only graphs but also any set of objects regardless of whether a graph is given or not. As a new deep learning module, kNN attention pooling layers can be plugged into any neural network model just like convolutional layers. As a simple special case of kNN attention pooling layer, feature attention layer can directly select important features that are useful for classification tasks. Experiments on both synthetic data and cancer genomic data from TCGA projects show that our AffinityNet model has better generalization power than conventional neural network models with little training data.

Summary In order to study bionic walking machinery, the uphill walking processes on different slopes (0°, 10°, 20°, and 30°) were recorded by a high speed video system (VRI Phantom M110). The kinematics parameters of goat slope are analyzed using PCC and ORIGIN software. Goat's average speed decreases with the increase in gradient. The average speed of goats on the 0° slope, 10° slope, 20° slope, and 30° slope are 1.72 m/s, 1.352 m/s, 0.742 m/s, and 0.609 m/s. In the Y axis direction, the variation ranges from 0.1 m to 0.37 m. The left hind legs are basically the same as the feet of the right hind legs. In the Y axis direction, the variation ranges from 0.1 m to 0.195 m. The length of the change in the X axis is greater than the posterior foot. The range of hip joint angle changes is from 46.10 to 135.50. The knee joint angle changes is from 87.90 to 179.80. The hip joint angle of hind leg changes from 115.30 to 1700. The knee joint angle of hind leg changes from 80.50 to 172.80. The present research can provide theoretical basis for the design of a biomimetic agricultural walking mechanism.

Clustering cancer patients into subgroups and identifying cancer subtypes is an important task in cancer genomics. Clustering based on comprehensive multi-omic molecular profiling can often achieve better results than those using a single data type, since each omic data type may contain complementary information. However, it is challenging to integrate heterogeneous omic data directly. Based on one popular method - Similarity Network Fusion (SNF), we presented Affinity Network Fusion (ANF), an “upgrade” of SNF with several advantages. Similar to SNF, ANF treats each omic data type as one view of patients and learns a fused affinity matrix for clustering. We applied ANF to a harmonized TCGA dataset consisting of 2193 patients, and generated promising results on clustering patients into correct disease types. Our experimental results also demonstrated the power of feature selection and transformation combined with using ANF in patient clustering. Moreover, eigengap analysis suggests that the learned affinity matrices of four cancer types using our proposed framework may have successfully captured patient group structure and can be used for discovering unknown cancer subtypes.

Omic data analyses pose great informatics challenges. As an emerging subfield of bioinformatics, omics informatics focuses on analyzing multi-omic data efficiently and effectively, and is gaining momentum. There are two underlying trends in the expansion of omics informatics landscape: the explosion of scattered individual omics informatics tools with each of which focuses on a specific task in both single- and multi- omic settings, and the fast-evolving integrated software platforms such as workflow management systems that can assemble multiple tools into pipelines and streamline integrative analysis for complicated tasks. In this survey, we give a holistic view of omics informatics, from scattered individual informatics tools to integrated workflow management systems. We not only outline the landscape and challenges of omics informatics, but also sample a number of widely used and cutting-edge algorithms in omics data analysis to give readers a fine-grained view. We survey various workflow management systems (WMSs), classify them into three levels of WMSs from simple software toolkits to integrated multi-omic analytical platforms, and point out the emerging needs for developing intelligent workflow management systems. We also discuss the challenges, strategies and some existing work in systematic evaluation of omics informatics tools. We conclude by providing future perspectives of emerging fields and new frontiers in omics informatics.

Functional gene network analysis, such as gene co-expression network analysis, is useful for detecting disease-associated gene modules. Compared with many gene interaction networks in pathway databases, co-expression networks constructed directly from RNA-seq experiment are context-specific and thus more helpful for detecting differential gene modules under defined conditions. However, existing co-expression network inference approaches for RNA-seq data suffer from high noise and biases due to small sample sizes and many confounding factors. In this paper we proposed a framework for constructing robust, context-specific differential gene co-expression networks consisting of only high confidence edges. To detect disease-associated submodules, we devised a new metric to measure module significance scores. Based on this metric, we developed a gene ontology(GO)-driven module discovery algorithm for identifying disease-associated differential modular structures. Experiments on real RNA-seq data shows this framework works well in detecting biologically meaningful signals.