Multi-label classification using deep belief networks for virtual screening of multi-target drug

Fitriawan, Aries; Wasito, Ito; Syafiandini, Arida Ferti; Amien, Mukhlis; Yanuar, Arry

doi:10.1109/ic3ina.2016.7863032

Cited by 5 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This distinct feature of the data-driven approach has encouraged the active development of deep learning-based drug–target interaction (DTI) models that accomplish both high accuracy and low cost. 22–30…”

Section: Introductionmentioning

confidence: 99%

PIGNet: a physics-informed deep learning model toward generalized drug–target interaction predictions

et al. 2022

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

PIGNet: a physics-informed deep learning model toward generalized drug–target interaction predictions

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Several studies used deep learning to predict this DTI ( Fitriawan et al, 2016 ; Lee et al, 2019 ; Mei and Zhang, 2019 ; Sulistiawan et al, 2020 ; Sajadi et al, 2021 ). Lee et al (2019) proposed a deep learning-based prediction model capturing local residue patterns of proteins participating in DTIs.…”

Section: Introductionmentioning

confidence: 99%

Bipartite graph search optimization for type II diabetes mellitus Jamu formulation using branch and bound algorithm

et al. 2022

View full text Add to dashboard Cite

Jamu is an Indonesian traditional herbal medicine that has been practiced for generations. Jamu is made from various medicinal plants. Each plant has several compounds directly related to the target protein that are directly associated with a disease. A pharmacological graph can form relationships between plants, compounds, and target proteins. Research related to the prediction of Jamu formulas for some diseases has been carried out, but there are problems in finding combinations or compositions of Jamu formulas because of the increase in search space size. Some studies adopted the drug–target interaction (DTI) implemented using machine learning or deep learning to predict the DTI for discovering the Jamu formula. However, this approach raises important issues, such as imbalanced and high-dimensional dataset, overfitting, and the need for more procedures to trace compounds to their plants. This study proposes an alternative approach by implementing bipartite graph search optimization using the branch and bound algorithm to discover the combination or composition of Jamu formulas by optimizing the search on a plant–protein bipartite graph. The branch and bound technique is implemented using the search strategy of breadth first search (BrFS), Depth First Search, and Best First Search. To show the performance of the proposed method, we compared our method with a complete search algorithm, searching all nodes in the tree without pruning. In this study, we specialize in applying the proposed method to search for the Jamu formula for type II diabetes mellitus (T2DM). The result shows that the bipartite graph search with the branch and bound algorithm reduces computation time up to 40 times faster than the complete search strategy to search for a composition of plants. The binary branching strategy is the best choice, whereas the BrFS strategy is the best option in this research. In addition, the the proposed method can suggest the composition of one to four plants for the T2DM Jamu formula. For a combination of four plants, we obtain Angelica Sinensis, Citrus aurantium, Glycyrrhiza uralensis, and Mangifera indica. This approach is expected to be an alternative way to discover the Jamu formula more accurately.

show abstract

“…Coronavirus infectious disease 2019 (COVID- 19) is an infectious disease that causes its victim's fever, cough, respiratory problems, pneumonia, and even death [1]. COVID-19 is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) [2].…”

Section: Introductionmentioning

confidence: 99%

“…Several studies related to the multilabel classification of DTI have been conducted before. Research [19] conducted a multilabel DTI search using a deep belief network (DBN) model with a binary relevance data transformation approach on protease and kinase data taken from the DUD-E site. Feature extraction on compounds was carried out using the PubChem fingerprint and Klekota-Roth fingerprint descriptors.…”

Section: Introductionmentioning

confidence: 99%

Screening of Potential Indonesia Herbal Compounds Based on Multi-Label Classification for 2019 Coronavirus Disease

Fadli

Kusuma

Annisa

et al. 2021

BDCC

View full text Add to dashboard Cite

Coronavirus disease 2019 pandemic spreads rapidly and requires an acceleration in the process of drug discovery. Drug repurposing can help accelerate the drug discovery process by identifying new efficacy for approved drugs, and it is considered an efficient and economical approach. Research in drug repurposing can be done by observing the interactions of drug compounds with protein related to a disease (DTI), then predicting the new drug-target interactions. This study conducted multilabel DTI prediction using the stack autoencoder-deep neural network (SAE-DNN) algorithm. Compound features were extracted using PubChem fingerprint, daylight fingerprint, MACCS fingerprint, and circular fingerprint. The results showed that the SAE-DNN model was able to predict DTI in COVID-19 cases with good performance. The SAE-DNN model with a circular fingerprint dataset produced the best average metrics with an accuracy of 0.831, recall of 0.918, precision of 0.888, and F-measure of 0.89. Herbal compounds prediction results using the SAE-DNN model with the circular, daylight, and PubChem fingerprint dataset resulted in 92, 65, and 79 herbal compounds contained in herbal plants in Indonesia respectively.

show abstract

Multi-label classification using deep belief networks for virtual screening of multi-target drug

Cited by 5 publications

References 11 publications

PIGNet: a physics-informed deep learning model toward generalized drug–target interaction predictions

PIGNet: a physics-informed deep learning model toward generalized drug–target interaction predictions

Bipartite graph search optimization for type II diabetes mellitus Jamu formulation using branch and bound algorithm

Screening of Potential Indonesia Herbal Compounds Based on Multi-Label Classification for 2019 Coronavirus Disease

Contact Info

Product

Resources

About