DAESTB: inferring associations of small molecule–miRNA via a scalable tree boosting model based on deep autoencoder

Yuan, Tao; Huang, Li; Yang, Li; Fu, Xiquan; Chen, Xiang

doi:10.1093/bib/bbac478

Cited by 31 publications

(20 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The challenges associated with experimental validation and the high-dimensional nature of the interactions makes the use of computational methods vital. Bounded Nuclear Norm Regularization 112 and the Deep Autoencoder and Scalable Tree Boosting Model (DAESTB) 113 are two useful methods that already exist for the prediction of drug–target interactions with microRNAs. Our belief is that HyperPCM, with its capacity for accurate prediction of drug–target interactions even in low-data settings, could effectively enhance the prediction of interactions between drug compounds and microRNAs.…”

Section: Discussionmentioning

confidence: 99%

HyperPCM: Robust Task-Conditioned Modeling of Drug–Target Interactions

Svensson,

Hoedt,

Hochreiter

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

A central problem in drug discovery is to identify the interactions between drug-like compounds and protein targets. Over the past few decades, various quantitative structure−activity relationship (QSAR) and proteo-chemometric (PCM) approaches have been developed to model and predict these interactions. While QSAR approaches solely utilize representations of the drug compound, PCM methods incorporate both representations of the protein target and the drug compound, enabling them to achieve above-chance predictive accuracy on previously unseen protein targets. Both QSAR and PCM approaches have recently been improved by machine learning and deep neural networks, that allow the development of drug−target interaction prediction models from measurement data. However, deep neural networks typically require large amounts of training data and cannot robustly adapt to new tasks, such as predicting interaction for unseen protein targets at inference time. In this work, we propose to use HyperNetworks to efficiently transfer information between tasks during inference and thus to accurately predict drug−target interactions on unseen protein targets. Our HyperPCM method reaches state-of-the-art performance compared to previous methods on multiple well-known benchmarks, including Davis, DUD-E, and a ChEMBL derived data set, and particularly excels at zero-shot inference involving unseen protein targets. Our method, as well as reproducible data preparation, is available at https://github.com/ml-jku/hyper-dti.

show abstract

Section: Discussionmentioning

confidence: 99%

HyperPCM: Robust Task-Conditioned Modeling of Drug–Target Interactions

Svensson,

Hoedt,

Hochreiter

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…As another ensemble technique, boosting [ 30 , 31 ] has been used as a powerful tool for classification, especially in high-dimensional settings. As weak learners, random rank trees are ensembled according to a LogitBoost cost function [ 32 ] with , where and .…”

Section: Methodsmentioning

confidence: 99%

Ensemble methods of rank-based trees for single sample classification with gene expression profiles

Lu,

Yin,

Chen

2024

J Transl Med

View full text Add to dashboard Cite

Building Single Sample Predictors (SSPs) from gene expression profiles presents challenges, notably due to the lack of calibration across diverse gene expression measurement technologies. However, recent research indicates the viability of classifying phenotypes based on the order of expression of multiple genes. Existing SSP methods often rely on Top Scoring Pairs (TSP), which are platform-independent and easy to interpret through the concept of “relative expression reversals”. Nevertheless, TSP methods face limitations in classifying complex patterns involving comparisons of more than two gene expressions. To overcome these constraints, we introduce a novel approach that extends TSP rules by constructing rank-based trees capable of encompassing extensive gene-gene comparisons. This method is bolstered by incorporating two ensemble strategies, boosting and random forest, to mitigate the risk of overfitting. Our implementation of ensemble rank-based trees employs boosting with LogitBoost cost and random forests, addressing both binary and multi-class classification problems. In a comparative analysis across 12 cancer gene expression datasets, our proposed methods demonstrate superior performance over both the k-TSP classifier and nearest template prediction methods. We have further refined our approach to facilitate variable selection and the generation of clear, precise decision rules from rank-based trees, enhancing interpretability. The cumulative evidence from our research underscores the significant potential of ensemble rank-based trees in advancing disease classification via gene expression data, offering a robust, interpretable, and scalable solution. Our software is available at https://CRAN.R-project.org/package=ranktreeEnsemble.

show abstract

“…In addition, Peng et al created a prediction model named GATCL2CD by assessing similarities between circRNAs and diseases, in which a heterogeneous network was built first, and then, based on the heterogeneous network, a graph attention network for feature convolution learning was proposed to predict circRNA disease connections ( Peng et al, 2023 ). Additionally, Peng et al employed a scalable tree-enhanced model to predict potential correlations between each pair of small-molecule miRNAs, in which a deep autoencoder was adopted to produce probable feature representations of each pair ( Peng et al, 2022 ).…”

Section: Introductionmentioning

confidence: 99%

MDSVDNV: predicting microbe–drug associations by singular value decomposition and Node2vec

Tan,

Zhang,

Liu

et al. 2024

Front. Microbiol.

View full text Add to dashboard Cite

IntroductionRecent researches have demonstrated that microbes are crucial for the growth and development of the human body, the movement of nutrients, and human health. Diseases may arise as a result of disruptions and imbalances in the microbiome. The pathological investigation of associated diseases and the advancement of clinical medicine can both benefit from the identification of drug-associated microbes.MethodsIn this article, we proposed a new prediction model called MDSVDNV to infer potential microbe-drug associations, in which the Node2vec network embedding approach and the singular value decomposition (SVD) matrix decomposition method were first adopted to produce linear and non-linear representations of microbe interactions.Results and discussionCompared with state-of-the-art competitive methods, intensive experimental results demonstrated that MDSVDNV could achieve the best AUC value of 98.51% under a 5-fold CV, which indicated that MDSVDNV outperformed existing competing models and may be an effective method for discovering latent microbe–drug associations in the future.

show abstract

DAESTB: inferring associations of small molecule–miRNA via a scalable tree boosting model based on deep autoencoder

Cited by 31 publications

References 56 publications

HyperPCM: Robust Task-Conditioned Modeling of Drug–Target Interactions

HyperPCM: Robust Task-Conditioned Modeling of Drug–Target Interactions

Ensemble methods of rank-based trees for single sample classification with gene expression profiles

MDSVDNV: predicting microbe–drug associations by singular value decomposition and Node2vec

Contact Info

Product

Resources

About