Joint deep autoencoder and subgraph augmentation for inferring microbial responses to drugs

Abstract

Exploring microbial stress responses to drugs is crucial for the advancement of new therapeutic methods. While current artificial intelligence methodologies have expedited our understanding of potential microbial responses to drugs, the models are constrained by the imprecise representation of microbes and drugs. To this end, we combine deep autoencoder and subgraph augmentation technology for the first time to propose a model called JDASA-MRD, which can identify the potential indistinguishable responses of microbes to drugs. In the JDASA-MRD model, we begin by feeding the established similarity matrices of microbe and drug into the deep autoencoder, enabling to extract robust initial features of both microbes and drugs. Subsequently, we employ the MinHash and HyperLogLog algorithms to account intersections and cardinality data between microbe and drug subgraphs, thus deeply extracting the multi-hop neighborhood information of nodes. Finally, by integrating the initial node features with subgraph topological information, we leverage graph neural network technology to predict the microbes’ responses to drugs, offering a more effective solution to the ’over-smoothing’ challenge. Comparative analyses on multiple public datasets confirm that the JDASA-MRD model’s performance surpasses that of current state-of-the-art models. This research aims to offer a more profound insight into the adaptability of microbes to drugs and to furnish pivotal guidance for drug treatment strategies. Our data and code are publicly available at: https://github.com/ZZCrazy00/JDASA-MRD.

Finding potential lncRNA–disease associations using a boosting-based ensemble learning model

“…Consequently, machine learning algorithms have been broadly applied in LDA prediction, for example, collaborative filtering (Yu et al, 2019), graph regularization (Liu et al, 2020;, matrix factorization (Fu et al, 2018;Wang et al, 2020;Xi et al, 2022), heterogeneous graph learning framework, (Cao et al, 2023), and ensemble learning models (Peng et al, 2022a). Notably, deep learning has been broadly applied due to its powerful classification performance (Sun et al, 2022;Wang et al, 2023b;Hu et al, 2023;Jiang et al, 2023;Zhou et al, 2024a), such as in the graph convolution network (Wang W. et al, 2022), node2vec (Li et al, 2021), collaborative deep learning (Lan et al, 2020), deep neural network (Wei et al, 2020), deep multi-network embedding (Ma, 2022), graph autoencoder (Liang et al, 2023;Zhou et al, 2024b), and a capsule network with the attention mechanism . In particular, to identify new LDAs, a few models first extracted LDA features and classified unknown lncRNA-disease pairs (LDPs) by combining machine leaning models.…”

HPTRMF: Collaborative Matrix Factorization-Based Prediction Method for LncRNA-Disease Associations Using High-Order Perturbation and Flexible Trifactor Regularization

“…LncRNA-disease Noncoding RNAs (ncRNAs) are primarily classified into small RNAs, medium RNAs, and long noncoding RNAs (LncRNAs) based on nucleotide length, with LncRNAs playing a pivotal role in the regulation of disease expression in both animals and plants. − Biological studies indicate that the long noncoding RNA HAGLR inhibits tumor growth and acts as a tumor suppressor factor in lung adenocarcinoma (LUAD) . In esophageal cancer (EC), the long noncoding RNA ADAMTS9-AS2 effectively suppresses cancer cell proliferation, invasion, and migration processes .…”