In contrast to wild species, drought-tolerance in crops requires a fully functional metabolism during drought (particularly photosynthetic processes). However, the link between drought-tolerance, photosynthetic regulation during drought, and the associated transcript and metabolic foundation, remains largely unknown. For this study, we used two rice cultivars with contrasting drought-tolerance (the drought-intolerant cultivar IRAT109 and the drought-tolerant cultivar IAC1246) to explore transcript and metabolic responses to long-term drought. The drought-tolerant cultivar represented higher osmotic adjustment and antioxidant capacity, as well as higher relative photosynthesis rate under a progressive drought stress occurred in a modified field with shallow soil-layers. A total of 4059 and 2677 differentially expressed genes (DEGs) were identified in IRAT109 and IAC1246 between the drought and well-watered conditions, respectively. A total of 69 and 47 differential metabolites (DMs) were identified between the two treatments in IRAT109 and IAC1246, respectively. Compared to IRAT109, the DEGs of IAC1246 displayed enhanced regulatory amplitude during drought. We found significant correlations between DEGs and the osmolality and total antioxidant capacity (AOC) of both cultivars. During the early stages of drought, we detected up-regulation of DEGs in IAC1246 related to photosynthesis, in accordance with its higher relative photosynthesis rate. The contents of six differential metabolites were correlated with the osmotic potential and AOC. Moreover, they were differently regulated between the two cultivars. Particularly, up-regulations of 4-hydroxycinnamic acid and ferulic acid were consistent with the performance of photosynthesis-related DEGs at the early stages of drought in IAC1246. Therefore, 4-hydroxycinnamic acid and ferulic acid were considered as key metabolites for rice drought-tolerance. DEGs involved in pathways of these metabolites are expected to be good candidate genes to improve drought-tolerance. In conclusion, well-maintained photosynthesis under drought should contribute to improved drought-tolerance in rice. Metabolites play vital roles in protecting photosynthesis under dehydration via osmotic adjustments and/or antioxidant mechanisms. A metabolite-based method was thus an effective way to explore drought candidate genes. Metabolic accompanied by transcript responses to drought stress should be further studied to find more useful metabolites, pathways, and genes.

Predicting the response of a cancer cell line to a therapeutic drug is an important topic in modern oncology that can help personalized treatment for cancers. Although numerous machine learning methods have been developed for cancer drug response (CDR) prediction, integrating diverse information about cancer cell lines, drugs and their known responses still remains a great challenge. In this paper, we propose a graph neural network method with contrastive learning for CDR prediction. GraphCDR constructs a graph neural network based on multi-omics profiles of cancer cell lines, the chemical structure of drugs and known cancer cell line-drug responses for CDR prediction, while a contrastive learning task is presented as a regularizer within a multi-task learning paradigm to enhance the generalization ability. In the computational experiments, GraphCDR outperforms state-of-the-art methods under different experimental configurations, and the ablation study reveals the key components of GraphCDR: biological features, known cancer cell line-drug responses and contrastive learning are important for the high-accuracy CDR prediction. The experimental analyses imply the predictive power of GraphCDR and its potential value in guiding anti-cancer drug selection.

Motivation Drug combinations have exhibited promise in treating cancers with less toxicity and fewer adverse reactions. However, in vitro screening of synergistic drug combinations is time-consuming and labour-intensive because of the combinatorial explosion. Although a number of computational methods have been developed for predicting synergistic drug combinations, the multi-way relations between drug combinations and cell lines existing in drug synergy data have not been well exploited. Results We propose a multi-way relation-enhanced hypergraph representation learning method to predict anti-cancer drug synergy, named HypergraphSynergy. HypergraphSynergy formulates synergistic drug combinations over cancer cell lines as a hypergraph, in which drugs and cell lines are represented by nodes and synergistic drug-drug-cell line triplets are represented by hyperedges, and leverages the biochemical features of drugs and cell lines as node attributes. Then, a hypergraph neural network is designed to learn the embeddings of drugs and cell lines from the hypergraph and predict drug synergy. Moreover, the auxiliary task of reconstructing the similarity networks of drugs and cell lines is considered to enhance the generalization ability of the model. In the computational experiments, HypergraphSynergy outperforms other state-of-the-art synergy prediction methods on two benchmark datasets for both classification and regression tasks, and is applicable to unseen drug combinations or cell lines. The studies revealed that the hypergraph formulation allows us to capture and explain complex multi-way relations of drug combinations and cell lines, and also provides a flexible framework to make the best use of diverse information. Availability and implementation The source data and codes of HypergraphSynergy can be freely downloaded from https://github.com/liuxuan666/HypergraphSynergy. Supplementary information Supplementary data are available at Bioinformatics online.

MiRNAs can regulate genes encoding specific proteins which are related to the efficacy of drugs, and predicting miRNA-drug resistance associations is of great importance. In this work, we propose an attentive multimodal graph convolution network method (AMMGC) to predict miRNA-drug resistance associations. AMMGC learns the latent representations of drugs and miRNAs from four graph convolution sub-networks with distinctive combinations of features. Then, an attention neural network is employed to obtain attentive representations of drugs and miRNAs, and miRNA-drug resistance associations are predicted by the inner product of learned attentive representations. The computational experiments show that AMMGC outperforms other state-of-the-art methods and baseline methods, achieving the AUPR score of 0.2399 and the AUC score of 0.9467. The analysis demonstrates that leveraging multiple features of drugs and miRNAs can make a contribution to the miRNA-drug resistance association prediction. The usefulness of AMMGC is further validated by case studies.

Identifying the potential associations among drugs, microbes and diseases is of great significance in exploring the pathogenesis and improving precision medicine. There are plenty of computational methods for pair-wise association prediction, such as drug-microbe and microbe-disease associations, but few methods focus on the higher-order triple-wise drug-microbe-disease (DMD) associations. Driven by the advancement of hypergraph neural networks (HGNNs), we expect them to fully capture high-order interaction patterns behind the hypergraph formulated by DMD associations and realize sound prediction performance. However, the confirmed DMD associations are insufficient due to the high cost of in vitro screening, which forms a sparse DMD hypergraph and thus brings in suboptimal generalization ability. To mitigate the limitation, we propose a Multi-view Contrastive Learning Hypergraph Neural Network, named MCHNN, for DMD association prediction. We design a novel multi-view contrastive learning on the DMD hypergraph as an auxiliary task, which guides the HGNN to learn more discriminative representations and enhances the generalization ability. Extensive computational experiments show that MCHNN achieves satisfactory performance in DMD association prediction and, more importantly, demonstrate the effectiveness of our devised multi-view contrastive learning on the sparse DMD hypergraph.