Drug-Drug Interaction (DDI) prediction has attracted considerable attention in designing multi-drug combination strategies and avoiding adverse reactions. Notably, Artificial Intelligence (AI)-driven DDI prediction methods have emerged as a pivotal research paradigm. However, most AI-driven DDI prediction methods fall short in exploring intra-molecular motifs, and heavily rely on the overly idealized assumption of the complete inter-molecular topology, limiting their expressive capacities. To this end, we propose a Motif-Oriented representation learning with TOpology Refinement for DDI prediction, namely MOTOR, to exploit both the multi-granularity motif information and the topological structure of DDI networks. Specifically, MOTOR effectively captures motif internal structures, motif local contexts, and motif global semantics. Furthermore, MOTOR employs an iterative learning strategy to continuously refine the DDI topology and optimize the corresponding drug representations. Extensive experimental results demonstrate that MOTOR exhibits superior performance with interpretable insights in DDI prediction tasks across three real-world datasets, thereby opening up new avenues in AI-driven DDI prediction.

Foundation models, which exploit self-supervised learning on vast amounts of data, have demonstrated superior performance in various biomedical domains. However, the differences in existing foundation models, such as pre-training data sources, model architectures, and pre-training tasks, lead to noticeable variations in their performance across diverse biomedical tasks. Therefore, it remains unclear how to select the most appropriate foundation model for a new task. Here, we propose an alternative solution scMoE to integrate multiple foundation models within the same domain through a mixture-of-expert framework. The key idea of scMoE is to selectively activate certain foundation models according to the specific task and input using a multi-head sparse router. scMoE can be further extended to integrate foundation models across modalities, such as integrating multiple single-cell foundation models and multiple molecular foundation models. Our experiments across three biomedical tasks, including cancer drug response prediction, drug combination perturbation prediction, and synergistic drug combination prediction, demonstrate that scMoE significantly outperforms individual foundation models, highlighting its effectiveness and robustness in complex biomedical applications. Overall, scMoE provides a novel integrative framework for utilizing heterogeneous foundation models, paving the path for applying multiple diverse foundation models to new tasks.

Zero-shot hashing (ZSH) has shown excellent success owing to its efficiency and generalization in large-scale retrieval scenarios. However, existing works ignore the locality relationships of representations and attributes, which have effective transferability between seeable classes and unseeable classes. Also, the continuous value attributes are not fully harnessed. In response, we conduct a COMprehensive Attribute Exploration for ZSH, named COMAE, which depicts the relationships from seen classes to unseen ones through three meticulously designed explorations, i.e., point-wise, pair-wise and class-wise consistency constraints. By regressing attributes from the proposed attribute prototype network, COMAE learns the local features that are relevant to the visual attributes. Then COMAE utilizes contrastive learning to comprehensively depict the context of attributes, rather than instance-independent optimization. Finally, the class-wise constraint is designed to cohesively learn the hash code, image representation, and visual attributes more effectively. Furthermore, theoretical analysis is provided to show the effectiveness of COMAE. Experimental results demonstrate that COMAE outperforms state-of-the-art hashing models, especially in scenarios with a larger number of unseen label classes.

BACKGROUND: With the accumulation of phylogenomic data and the growing demand for bioinformatics analyses, it has become increasingly important and complex to construct evolutionary relationships for different research purposes. Therefore, the ability to support multiple scenarios has become an essential need for phylogenetic visualization. RESULTS: In this study, we present PhyloScape, a web-based application for interactive visualization of phylogenetic trees that can be used stand-alone or as a toolkit deployed on the users' website. The platform supports customizable multiple visualization features and is equipped with a flexible metadata annotation system, providing researchers with publishable, interactive views of trees. PhyloScape extensions include views of amino acid identity, geometry, and protein structure, which are applicable to various areas such as microbial taxonomy, pathogen phylogeny, and plant conservation. Trees published on the website can be efficiently shared and integrated into the users' own system via a unique address. CONCLUSIONS: As a scalable platform, PhyloScape provides a variety of online plug-ins that users can easily combine for specific scenarios. PhyloScape is freely available at http://darwintree.cn/PhyloScape .

Gene regulatory networks (GRNs) are crucial for understanding gene regulation and cellular processes. Inferring GRNs helps uncover regulatory pathways, shedding light on the regulation and development of cellular processes. With the rise of high-throughput sequencing and advancements in computational technology, computational models have emerged as cost-effective alternatives to traditional experimental studies. Moreover, the surge in ChIP-seq data for TF-DNA binding has catalyzed the development of graph neural network (GNN)-based methods, greatly advancing GRN inference capabilities. However, most existing GNN-based methods suffer from the inability to capture long-distance structural semantic correlations due to transitive interactions. In this paper, we introduce a novel GNN-based model named Hierarchical Graph Transformer with Contrastive Learning for GRN (HGTCGRN) inference. HGTCGRN excels at capturing structural semantics using a hierarchical graph Transformer, which introduces a series of gene family nodes representing gene functions as virtual nodes to interact with nodes in the GRNS. These semantic-aware virtual-node embeddings are aggregated to produce node representations with varying emphasis. Additionally, we leverage gene ontology information to construct gene interaction networks for contrastive learning optimization of GRNs. Experimental results demonstrate that HGTCGRN achieves superior performance in GRN inference.

Emerging topics in biomedical research are continuously expanding, providing a wealth of information about genes and their function. This rapid proliferation of knowledge presents unprecedented opportunities for scientific discovery and formidable challenges for researchers striving to keep abreast of the latest advancements. One significant challenge is navigating the vast corpus of literature to extract vital gene-related information, a time-consuming and cumbersome task. To enhance the efficiency of this process, it is crucial to address several key challenges: (1) the overwhelming volume of literature, (2) the complexity of gene functions, and (3) the automated integration and generation. In response, we propose GeneSum, a two-stage automated gene summary extractor utilizing a large language model (LLM). Our approach retrieves and eliminates redundancy of target gene literature and then fine-tunes the LLM to refine and streamline the summarization process. We conducted extensive experiments to validate the efficacy of our proposed framework. The results demonstrate that LLM significantly enhances the integration of gene-specific information, allowing more efficient decision-making in ongoing research.

Accurately predicting Drug-Drug Interactions (DDIs) is critical to designing effective drug combination therapies. Recently, Artificial Intelligence (AI)-powered DDI prediction approaches have emerged as a new paradigm. However, most existing methods oversimplify the complex hierarchical structure within molecules and overlook the multi-source heterogeneous information external to molecules, limiting their modeling and predictive capabilities. To address this, we propose a H ierarchical H eterogeneous graph learning framework for D DI prediction, namely H2D. H2D employs an internal-to-external, local-to-global hierarchical perspective, exploiting intra-molecular multi-granularity structures and inter-molecular biomedical interactions to mutually enhance across hierarchical levels. Extensive experimental results demonstrate H2D's effectiveness on three real-world DDI prediction tasks (binary-class, multi-class, and multi-label). In sum, H2D achieves state-of-the-art performance in DDI prediction by leveraging the multi-scale graph structures, opening up new avenues in AI-powered DDI prediction.

Molecular property prediction stands as a cornerstone task in AI-driven drug design and discovery, wherein the atoms within a molecule serve as nodes, collectively forming a graph with bonds acting as edges. Given the crucial role of geometric structures in molecular property prediction, the integration of 3D information with various graph learning methods has been explored to enhance prediction performance. Despite the increasing adoption of the "Graph pre-training and fine-tuning" paradigm to refine molecular representations, a significant challenge persists due to the misalignment between pre-training objectives and downstream tasks. Drawing inspiration from prompt tuning techniques in Natural Language Processing (NLP), several graph prompt-based methods have emerged. However, existing approaches tend to overlook the unique properties inherent in molecular graphs. To address this gap, our paper introduces a novel approach named 3D MO lecul A rpromp T (MOAT) designed specifically for geometric molecules. Specifically, we propose atom-level prompts to capture atom distribution, geometry-level prompts tailored for molecular conformers, where different conformations have distinct chemical properties, and task-level prompts to leverage functional group properties. Results on both 3D and 2D downstream tasks demonstrate its ability to successfully bridge the data gap across diverse settings. To the best of our knowledge, this paper is the first attempt to introduce geometric graph-prompting learning for molecules.

Constructing accurate gene regulatory network s (GRNs), which reflect the dynamic governing process between genes, is critical to understanding the diverse cellular process and unveiling the complexities in biological systems. With the development of computer sciences, computational-based approaches have been applied to the GRNs inference task. However, current methodologies face challenges in effectively utilizing existing topological information and prior knowledge of gene regulatory relationships, hindering the comprehensive understanding and accurate reconstruction of GRNs. In response, we propose a novel graph neural network (GNN)-based Multi-Task Learning framework for GRN reconstruction, namely MTLGRN. Specifically, we first encode the gene promoter sequences and the gene biological features and concatenate the corresponding feature representations. Then, we construct a multi-task learning framework including GRN reconstruction, Gene knockout predict, and Gene expression matrix reconstruction. With joint training, MTLGRN can optimize the gene latent representations by integrating gene knockout information, promoter characteristics, and other biological attributes. Extensive experimental results demonstrate superior performance compared with state-of-the-art baselines on the GRN reconstruction task, efficiently leveraging biological knowledge and comprehensively understanding the gene regulatory relationships. MTLGRN also pioneered attempts to simulate gene knockouts on bulk data by incorporating gene knockout information.

Drug-target interaction (DTI) prediction can identify novel ligands for specific protein targets, and facilitate the rapid screening of effective new drug candidates to speed up the drug discovery process. However, the current methods are not sensitive enough to complex topological structures, and complicated relations between multiple node types are not fully captured yet. To address the above challenges, we construct a metapath-based heterogeneous bioinformatics network, and then propose a DTI prediction method with metapath-based hierarchical transformer and attention network for drug-target interaction prediction (MHTAN-DTI), applying metapath instance-level transformer, single-semantic attention and multi-semantic attention to generate low-dimensional vector representations of drugs and proteins. Metapath instance-level transformer performs internal aggregation on the metapath instances, and models global context information to capture long-range dependencies. Single-semantic attention learns the semantics of a certain metapath type, introduces the central node weight and assigns different weights to different metapath instances to obtain the semantic-specific node embedding. Multi-semantic attention captures the importance of different metapath types and performs weighted fusion to attain the final node embedding. The hierarchical transformer and attention network weakens the influence of noise data on the DTI prediction results, and enhances the robustness and generalization ability of MHTAN-DTI. Compared with the state-of-the-art DTI prediction methods, MHTAN-DTI achieves significant performance improvements. In addition, we also conduct sufficient ablation studies and visualize the experimental results. All the results demonstrate that MHTAN-DTI can offer a powerful and interpretable tool for integrating heterogeneous information to predict DTIs and provide new insights into drug discovery.

Drug-drug interaction (DDI) prediction can discover potential risks of drug combinations in advance by detecting drug pairs that are likely to interact with each other, sparking an increasing demand for computational methods of DDI prediction. However, existing computational DDI methods mostly rely on the single-view paradigm, failing to handle the complex features and intricate patterns of DDIs due to the limited expressiveness of the single view. To this end, we propose a Hierarchical Triple-view Contrastive Learning framework for Drug-Drug Interaction prediction (HTCL-DDI), leveraging the molecular, structural and semantic views to model the complicated information involved in DDI prediction. To aggregate the intra-molecular compositional and structural information, we present a dual attention-aware network in the molecular view. Based on the molecular view, to further capture inter-molecular information, we utilize the one-hop neighboring information and high-order semantic relations in the structural view and semantic view, respectively. Then, we introduce contrastive learning to enhance drug representation learning from multifaceted aspects and improve the robustness of HTCL-DDI. Finally, we conduct extensive experiments on three real-world datasets. All the experimental results show the significant improvement of HTCL-DDI over the state-of-the-art methods, which also demonstrates that HTCL-DDI opens new avenues for ensuring medication safety and identifying synergistic drug combinations.

Abstract Satellite image processing has been widely used in recent years in a number of applications such as land classification, Identification transfer, resource exploration, super‐resolution image, etc. Due to the orbital location, revision time, quick view angle limitations, and weather impact, the satellite images are challenging to manage. There are many types of resolution, such as spatial, spectral, and temporal. Still, in our case, we concentrated on spatial image resolution to super resolve the images from low‐resolution images. For remote sensing image super‐resolution fast wavelet‐based super‐resolution (FWSR), we propose a novel, fast wavelet‐based plexus framework that performs super‐resolution convolutional neural network (SRCNN)‐like extraction of features based on three hidden layers. First, wavelet sub‐band images are combined into a pre‐defined full‐scale data training factor, including approximation and interchangeable stand‐alone units (frequency sub‐bands). Second, to speed up image recovery, mapping the sub‐band image of the wavelet is then measured using its approximate image. Third, the added sub‐pixel layer at the end of the network model is intended to reproduce image quality using a plexus framework. The approximation sub‐band images obtained after discrete wavelet transform wavelet decomposition are used as input rather than the original image because of their high‐frequency data and preserved characteristics. Five current super‐resolution neural network approaches are compared with the proposed technique and tested on three pubic satellite image datasets and two benchmark datasets. The experimental findings are well compared qualitatively and quantitatively.

Abstract The object identification within an image captured during rough weather conditions (such as haze, fog) poses difficulty due to the reduction of an image. The rough weather conditions lead not only to the variation of the image's visual effect but also to the disadvantage of post‐processing of an image. Furthermore, it causes inconvenience of all types of instruments that rely on optical imaging, such as satellite remote‐sensing systems, aerial photo systems, outdoor monitoring systems, and object identification systems, respectively. Hence, the improvement and restorement of the visual effects and enhanced post‐processing are needed. This research introduces a new image enhancement approach for image dehazing based on dark channel prior and piecewise linear transformation; also, the histogram equalisation technique, i.e. contrast limited adaptive histogram equalisation is applied. A dark channel prior is well known for its simplicity and productivity. In this work, the dark channel prior to a new angle is analysed in the first step, where average patch sizes are estimated for the computation of haze densities. Furthermore, the sky is approximated up to 5–10% of the hazy images, which has a good effect in removing the haze from the image. Using the dark channel, the proposed algorithm significantly boosted the effects of the dark images as well as reduced the influence of haze and noise. Eventually, for colour correction, the piecewise linear transformation technique is applied, which enhances the colour close to the original image. Experimental results demonstrate that the proposed method significantly improves the visibility of the algorithm on dark remote‐sensing images as well as on hazy natural images.

Single Image Super-resolution (SISR) produces high-resolution images with fine spatial resolutions from a remotely sensed image with low spatial resolution. Recently, deep learning and generative adversarial networks (GANs) have made breakthroughs for the challenging task of single image super-resolution (SISR) . However, the generated image still suffers from undesirable artifacts such as the absence of texture-feature representation and high-frequency information. We propose a frequency domain-based spatio-temporal remote sensing single image super-resolution technique to reconstruct the HR image combined with generative adversarial networks (GANs) on various frequency bands (TWIST-GAN). We have introduced a new method incorporating Wavelet Transform (WT) characteristics and transferred generative adversarial network. The LR image has been split into various frequency bands by using the WT, whereas the transfer generative adversarial network predicts high-frequency components via a proposed architecture. Finally, the inverse transfer of wavelets produces a reconstructed image with super-resolution. The model is first trained on an external DIV2 K dataset and validated with the UC Merced Landsat remote sensing dataset and Set14 with each image size of 256 × 256. Following that, transferred GANs are used to process spatio-temporal remote sensing images in order to minimize computation cost differences and improve texture information. The findings are compared qualitatively and qualitatively with the current state-of-art approaches. In addition, we saved about 43% of the GPU memory during training and accelerated the execution of our simplified version by eliminating batch normalization layers.

This paper presents results of the ongoing development of a crowdsourcing platform for labelling remote sensing images. In order to perform fast spatial and temporal retrieval and read data efficiently, this paper proposes an adaptive grid design method to enable the remote sensing images being segmented into tiles, which supports parallel reading and writing, and uses Ceph cluster for storage. To guarantee crowdsourcing results' quality, a quality control mechanism combining expertsourcing and crowdsourcing is proposed. The online labelling system is designed and a prototype has been developed. Users neither have to install any software, nor download large remote sensing images. They can directly label the images by just selecting tags and drawing polygons. By providing such a platform, a large volume of training dataset for remote sensing classification can be obtained.

Diverse storage formats, archive dispersal, and inconsistent naming make it difficult for researchers and the general public to find and access remote sensing data. To facilitate the use of remote sensing data, this paper provides an integrated framework for direct reading remote sensing data in a widely compatible and analysis-ready format, NumPy ndarray. The framework is composed of two main components. One is the raster data processing and storage model. All the operational gridded remote sensing data are split into tiles, and reorganized in n-dimensional array. Then the N-Dimensional data array is serialized into netCDF and stored into distributed file system. The other is the spatiotemporal filter to achieve parallel query, and it has been encapsulated into Internet-accessible application programming interfaces (APIs). The scenario of calculating NDVI of a specified spatiotemporal range given at last illustrate the efficiency and convenience of our platform provided for remote sensing data analysis.

The massive data is constantly and rapidly growing in remote sensing field. How to achieve efficient storage and rapid retrieval of massive remote sensing image metadata is a difficult problem. Big Data technologies provide convenient and fast tools for the storage, retrieval and analysis of remote sensing image metadata. According to the feature of remote sensing image metadata, we first give new concepts of fat grid and thin grid and propose a grid indexing method called Spark-Fat-Thin-Grid-Index (SFTGridIndex). In SFTGridIndex, the index file and partitions files are stored in HDFS. We then design an optimized retrieval method based on SFTGrid-Index. The method can avoid the intersection computing of a large number of polygons. This research can ensure efficient storage and fast query of massive remote sensing image metadata and has good scalability.

Species distribution modeling is an important ecological research task that has received a great deal of interest. There are several single model packages and applications available for species distribution analysis. This paper introduces Bird-SDPS, a Prediction System for Migratory Birds' Spatial Distribution, which is an extensible system for birds' spatial distribution prediction. The Bird-SDPS uses birds' GPS tracking data and remote sensing data as input to build multiple distribution models, which are implemented by different programming languages. And the system provides online access and visualization functions. In order to store large dataset of remote sensing data, we design a hybrid storage structure based on HBase. We extensively evaluate our system using a real-world GPS dataset collected from 90 wild birds over 3 years. We show that the system can conduct birds' distribution prediction based on multiple models, and our hybrid data storage modes can outperform the traditional storage modes of files.