Computational Prediction of Drug-Target Interactions via Ensemble Learning

Ezzat, Ali; Wu, Min; Li, Xiaoli; Kwoh, Chee-Keong

doi:10.1007/978-1-4939-8955-3_14

Cited by 29 publications

(21 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both RF and the aforementioned technique from the Kaggle competition used ensemble learning, a technique which builds a set of learning models and combines multiple models to produce final predictions. Theoretically and empirically, it has been shown that the predictive power of ensemble learning surpasses that of a single individual learner if the individual algorithms are accurate and diverse [11][12][13][14]. Ensemble learning manages the strengths and weaknesses of individual learners, similar to how people consider diverse opinions when faced with critical issues.…”

Section: Introductionmentioning

confidence: 99%

Comprehensive ensemble in QSAR prediction for drug discovery

et al. 2019

View full text Add to dashboard Cite

Background: Quantitative structure-activity relationship (QSAR) is a computational modeling method for revealing relationships between structural properties of chemical compounds and biological activities. QSAR modeling is essential for drug discovery, but it has many constraints. Ensemble-based machine learning approaches have been used to overcome constraints and obtain reliable predictions. Ensemble learning builds a set of diversified models and combines them. However, the most prevalent approach random forest and other ensemble approaches in QSAR prediction limit their model diversity to a single subject. Results: The proposed ensemble method consistently outperformed thirteen individual models on 19 bioassay datasets and demonstrated superiority over other ensemble approaches that are limited to a single subject. The comprehensive ensemble method is publicly available at http://data.snu.ac.kr/QSAR/. Conclusions: We propose a comprehensive ensemble method that builds multi-subject diversified models and combines them through second-level meta-learning. In addition, we propose an end-to-end neural network-based individual classifier that can automatically extract sequential features from a simplified molecular-input line-entry system (SMILES). The proposed individual models did not show impressive results as a single model, but it was considered the most important predictor when combined, according to the interpretation of the meta-learning.

show abstract

Section: Introductionmentioning

confidence: 99%

Comprehensive ensemble in QSAR prediction for drug discovery

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Drug repurposing involves various computational methods [1,3]. Of these techniques, DTI inference is one of the most important foundations [68,69]. In this paper, we summarized data sources and related representation involved in DTI prediction.…”

Section: Discussionmentioning

confidence: 99%

Revealing Drug-Target Interactions with Computational Models and Algorithms

Zhou

Yang

et al. 2019

Molecules

View full text Add to dashboard Cite

Background: Identifying possible drug-target interactions (DTIs) has become an important task in drug research and development. Although high-throughput screening is becoming available, experimental methods narrow down the validation space because of extremely high cost, low success rate, and time consumption. Therefore, various computational models have been exploited to infer DTI candidates. Methods: We introduced relevant databases and packages, mainly provided a comprehensive review of computational models for DTI identification, including network-based algorithms and machine learning-based methods. Specially, machine learning-based methods mainly include bipartite local model, matrix factorization, regularized least squares, and deep learning. Results: Although computational methods have obtained significant improvement in the process of DTI prediction, these models have their limitations. We discussed potential avenues for boosting DTI prediction accuracy as well as further directions.

show abstract

“…Ensemble method-based researches: these approaches combine various techniques in several different ways [34], with the result that an efficient tool for predicting and discovering the hidden benefits of drugs can be generated [35]. For example, some of the related works have mixed different aspects of the computational methods and have obtained a suitable predictive model [36,37].…”

Section: V)mentioning

confidence: 99%

Synthetic Repurposing of Drugs in Hypertension: a Datamining Method Based on Association Rules and a Novel Discrete Algorithm

Masoudi-Sobhanzadeh

Masoudi‐Nejad²

2020

Preprint

View full text Add to dashboard Cite

Background Drug repurposing aims to detect the new benefits of the existing drugs and to reduce the spent time and cost of the drug development projects. Although synthetic repurposing of drugs may be more useful than single repurposing in terms of reducing toxicity and enhancing efficacy, the researchers have not taken it into account. To address the issue, a novel datamining method is introduced and applied to the repositioning of drugs in hypertension (HT), which is a serious medical condition and therefore needs to be dealt with effectively through making some improved treatment plans to help cure it. Results a novel two-step data mining method, which is based on the If-Then association rules and a novel discrete optimization algorithm, is proposed and applied to the synthetic repurposing of drugs in HT. The required data are extracted from DruhBank, KEGG, and DrugR+ databases. The outcomes presented that the proposed method outperforms the other state-of-the-art approaches in terms of different statistical criteria. In contrast to the previously proposed methods which failed to discover a list for some datasets, our method managed to suggest a combination of drugs for all the datasets. Conclusion The proposed synthetic method may revive some failed drug development projects and be a suitable plan for curing orphan and rare diseases due to using a low dosage of medicines. It is also essential to use some efficient computational methods to produce better results.

show abstract

Computational Prediction of Drug-Target Interactions via Ensemble Learning

Cited by 29 publications

References 59 publications

Comprehensive ensemble in QSAR prediction for drug discovery

Comprehensive ensemble in QSAR prediction for drug discovery

Revealing Drug-Target Interactions with Computational Models and Algorithms

Synthetic Repurposing of Drugs in Hypertension: a Datamining Method Based on Association Rules and a Novel Discrete Algorithm

Contact Info

Product

Resources

About