Recent Advances in the Machine Learning-Based Drug-Target Interaction Prediction

Zhang, Wen; Lin, Weiran; Zhang, Ding; Wang, Siman; Shi, Jingwen; Niu, Yanqing

doi:10.2174/1389200219666180821094047

Cited by 52 publications

(20 citation statements)

References 86 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, machine learningebased approaches are helping scientists to target their efforts to those areas most likely to meet with success as opposed to squandering time on experiments that are less likely to be fruitful. For example, machine learning has helped scientists predict chemical properties of drugs and proteins [9], predict vaccine immunogenicity [10], identify promising drug targets [11], and even identify existing drugs that have the potential to be repurposed for use against other pathogens [12]. It remains to be seen if these advancements will be successfully applied to the discovery of treatments and a vaccine for SARS-CoV-2, the virus that causes COVID-19.…”

Section: Data Sciencementioning

confidence: 99%

Digital Orthopaedics: A Glimpse Into the Future in the Midst of a Pandemic

Bini

Schilling

Patel

et al. 2020

The Journal of Arthroplasty

View full text Add to dashboard Cite

Background:The response to COVID-19 catalyzed the adoption and integration of digital health tools into the health care delivery model for musculoskeletal patients. The change, suspension, or relaxation of Medicare and federal guidelines enabled the rapid implementation of these technologies. The expansion of payment models for virtual care facilitated its rapid adoption. The authors aim to provide several examples of digital health solutions utilized to manage orthopedic patients during the pandemic and discuss what features of these technologies are likely to continue to provide value to patients and clinicians following its resolution. Conclusion:The widespread adoption of new technologies enabling providers to care for patients remotely has the potential to permanently change the expectations of all stakeholders about the way care is provided in orthopedics. The new era of Digital Orthopaedics will see a gradual and nondisruptive integration of technologies that support the patient's journey through the successful management of their musculoskeletal disease.

show abstract

Section: Data Sciencementioning

confidence: 99%

Digital Orthopaedics: A Glimpse Into the Future in the Midst of a Pandemic

Bini

Schilling

Patel

et al. 2020

The Journal of Arthroplasty

View full text Add to dashboard Cite

show abstract

“…Recently, great interest has been witnessed in developing machine learning models for DTI prediction [34]. Kernel learning was employed for DTI prediction in [35], where the authors constructed kernels for drugs, target proteins and the interaction matrix.…”

Section: Related Workmentioning

confidence: 99%

Drug-target interaction prediction with tree-ensemble learning and output space reconstruction

Pliakos

Vens

2020

BMC Bioinformatics

View full text Add to dashboard Cite

Background: Computational prediction of drug-target interactions (DTI) is vital for drug discovery. The experimental identification of interactions between drugs and target proteins is very onerous. Modern technologies have mitigated the problem, leveraging the development of new drugs. However, drug development remains extremely expensive and time consuming. Therefore, in silico DTI predictions based on machine learning can alleviate the burdensome task of drug development. Many machine learning approaches have been proposed over the years for DTI prediction. Nevertheless, prediction accuracy and efficiency are persisting problems that still need to be tackled. Here, we propose a new learning method which addresses DTI prediction as a multi-output prediction task by learning ensembles of multi-output bi-clustering trees (eBICT) on reconstructed networks. In our setting, the nodes of a DTI network (drugs and proteins) are represented by features (background information). The interactions between the nodes of a DTI network are modeled as an interaction matrix and compose the output space in our problem. The proposed approach integrates background information from both drug and target protein spaces into the same global network framework. Results: We performed an empirical evaluation, comparing the proposed approach to state of the art DTI prediction methods and demonstrated the effectiveness of the proposed approach in different prediction settings. For evaluation purposes, we used several benchmark datasets that represent drug-protein networks. We show that output space reconstruction can boost the predictive performance of tree-ensemble learning methods, yielding more accurate DTI predictions. Conclusions: We proposed a new DTI prediction method where bi-clustering trees are built on reconstructed networks. Building tree-ensemble learning models with output space reconstruction leads to superior prediction results, while preserving the advantages of tree-ensembles, such as scalability, interpretability and inductive setting.

show abstract

“…Although these methods enhance the separability power of a drug-target predictor, they increase the error rate and suffer from the disadvantages of the combined methods.Review-based approaches: Large numbers of drug-target prediction literature studies are considered just to review articles which have investigated the problem from various viewpoints such as applied tools 27 , methods 28 , databases, software applications 29 , etc. These articles usually include a discussion of the advantages and disadvantages of proposed methods and give some directions to be followed in the future 30 .…”

Section: Related Workmentioning

confidence: 99%

Trader as a new optimization algorithm predicts drug-target interactions efficiently

Masoudi-Sobhanzadeh

Omidi

Amanlou

et al. 2019

Sci Rep

View full text Add to dashboard Cite

Several machine learning approaches have been proposed for predicting new benefits of the existing drugs. Although these methods have introduced new usage(s) of some medications, efficient methods can lead to more accurate predictions. To this end, we proposed a novel machine learning method which is based on a new optimization algorithm, named Trader . To show the capabilities of the proposed algorithm which can be applied to the different scope of science, it was compared with ten other state-of-the-art optimization algorithms based on the standard and advanced benchmark functions. Next, a multi-layer artificial neural network was designed and trained by Trader to predict drug-target interactions (DTIs). Finally, the functionality of the proposed method was investigated on some DTIs datasets and compared with other methods. The data obtained by Trader showed that it eliminates the disadvantages of different optimization algorithms, resulting in a better outcome. Further, the proposed machine learning method was found to achieve a significant level of performance compared to the other popular and efficient approaches in predicting unknown DTIs. All the implemented source codes are freely available at https://github.com/LBBSoft/Trader .

show abstract

Recent Advances in the Machine Learning-Based Drug-Target Interaction Prediction

Cited by 52 publications

References 86 publications

Digital Orthopaedics: A Glimpse Into the Future in the Midst of a Pandemic

Digital Orthopaedics: A Glimpse Into the Future in the Midst of a Pandemic

Drug-target interaction prediction with tree-ensemble learning and output space reconstruction

Trader as a new optimization algorithm predicts drug-target interactions efficiently

Contact Info

Product

Resources

About