Characterizing biomarkers based on microbiome profiles has great potential for translational medicine and precision medicine. Here, we present microbiomeMarker, an R/Bioconductor package implementing commonly used normalization and differential analysis (DA) methods, and three supervised learning models to identify microbiome markers. microbiomeMarker also allows comparison of different methods of DA and confounder analysis. It uses standardized input and output formats, which renders it highly scalable and extensible, and allows it to seamlessly interface with other microbiome packages and tools. In addition, the package provides a set of functions to visualize and interpret the identified microbiome markers. microbiomeMarker is freely available from Bioconductor (https://www.bioconductor.org/packages/microbiomeMarker). Source code is available and maintained at GitHub (https://github.com/yiluheihei/microbiomeMarker). Supplementary data are available at Bioinformatics online.

Unexpected toxicity has become a significant obstacle to drug candidate development, accounting for 30% of drug discovery failures. Traditional toxicity assessment through animal testing is costly and time‐consuming. Big data and artificial intelligence (AI), especially machine learning (ML), are robustly contributing to innovation and progress in toxicology research. However, the optimal AI model for different types of toxicity usually varies, making it essential to conduct comparative analyses of AI methods across toxicity domains. The diverse data sources also pose challenges for researchers focusing on specific toxicity studies. In this review, 10 categories of drug‐induced toxicity is examined, summarizing the characteristics and applicable ML models, including both predictive and interpretable algorithms, striking a balance between breadth and depth. Key databases and tools used in toxicity prediction are also highlighted, including toxicology, chemical, multi‐omics, and benchmark databases, organized by their focus and function to clarify their roles in drug‐induced toxicity prediction. Finally, strategies to turn challenges into opportunities are analyzed and discussed. This review may provide researchers with a valuable reference for understanding and utilizing the available resources to bridge prediction and mechanistic insights, and further advance the application of ML in drugs‐induced toxicity prediction.

Summary: Heat acclimation (HA) is the best strategy to improve heat stress tolerance by inducing positive physiological adaptations. Evidence indicates that the gut microbiome plays a fundamental role in the development of HA, and modulation of gut microbiota can improve tolerance to heat exposure and decrease the risks of heat illness. In this study, for the first time, we applied 16S rRNA gene sequencing and untargeted liquid chromatography–mass spectrometry (LC‐MS) metabolomics to explore variations in the gut microbiome and faecal metabolic profiles in rats after HA. The gut microbiota of HA subjects exhibited higher diversity and richer microbes. HA altered the gut microbiota composition with significant increases in the genera Lactobacillus (a major probiotic) and Oscillospira alongside significant decreases in the genera Blautia and Allobaculum . The faecal metabolome was also significantly changed after HA, and among the 13 perturbed metabolites, (S)‐AL 8810 and celastrol were increased. Moreover, the two increased genera were positively correlated with the two upregulated metabolites and negatively correlated with the other 11 downregulated metabolites, while the correlations between the two decreased genera and the upregulated/downregulated metabolites were completely contrary. In summary, both the structure of the gut microbiome community and the faecal metabolome were improved after 28 days of HA. These findings provide novel insights regarding the improvement of the gut microbiome and its functions as a potential mechanism by which HA confers protection against heat stress.

Predicting protein–ligand binding sites is an integral part of structural biology and drug design. A comprehensive understanding of these binding sites is essential for advancing drug innovation, elucidating mechanisms of biological function, and exploring the nature of disease. However, accurately identifying protein–ligand binding sites remains a challenging task. To address this, we propose PGpocket, a geometric deep learning-based framework to improve protein–ligand binding site prediction. Initially, the protein surface is converted into a point cloud, and then the geometric and chemical properties of each point are calculated. Subsequently, the point cloud graph is constructed based on the inter-point distances, and the point cloud graph neural network (GNN) is applied to extract and analyze the protein surface information to predict potential binding sites. PGpocket is trained on the scPDB dataset, and its performance is verified on two independent test sets, Coach420 and HOLO4K. The results show that PGpocket achieves a 58% success rate on the Coach420 dataset and a 56% success rate on the HOLO4K dataset. These results surpass competing algorithms, demonstrating PGpocket’s advancement and practicality for protein–ligand binding site prediction.

Trained immunity is a newly emerging concept that defines the ability of the innate immune system to form immune memory and provide long-lasting protection against previously encountered antigens. Accumulating evidence reveals that trained immunity not only has broad benefits to host defense but is also harmful to the host in chronic inflammatory diseases. However, all trained immunity-related information is scattered in the literature and thus is difficult to access. Here, we describe Trained Immunity DataBase (TIDB), a comprehensive database that provides well-studied trained immunity-related genes from human, rat and mouse as well as the related literature evidence. Moreover, TIDB also provides three modules to analyze the function of the trained-immunity-related genes of interest, including Reactome pathway over-representation analysis, Gene Ontology enrichment analysis and protein–protein interaction subnetwork reconstruction. We believe TIDB will help developing valuable strategies for vaccine design and immune-mediated disease therapy. Database URL:http://www.ieom-tm.com/tidb