Corpus ID: 236469353

Toward Drug-Target Interaction Prediction via Ensemble Modeling and Transfer Learning

@inproceedings{Kao2021TowardDI,
  title={Toward Drug-Target Interaction Prediction via Ensemble Modeling and Transfer Learning},
  author={Po-Yu Kao and Shu-min Kao and Nan-Lan Huang and Yen-Chu Lin},
  year={2021}
}
  • Po-Yu Kao, S. Kao, +1 author Yen-Chu Lin
  • Published 2021
  • Biology, Computer Science
Drug-target interaction (DTI) prediction plays a crucial role in drug discovery, and deep learning approaches have achieved state-of-the-art performance in this field. We introduce an ensemble of deep learning models (EnsembleDLM) for DTI prediction. EnsembleDLM only uses the sequence information of chemical compounds and proteins, and it aggregates the predictions from multiple deep neural networks. This approach not only achieves state-of-the-art performance in Davis and KIBA datasets but… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 40 REFERENCES
Pearson correlation coefficient
THE AMINO ACID COMPOSITION OF PROTEINS.
DeepCDA: deep cross-domain compound-protein affinity prediction through LSTM and convolutional neural networks
TLDR
The results show that the proposed method learns a more reliable model for the test domain in more challenging situations. Expand
DeepDTA: deep drug–target binding affinity prediction
TLDR
A deep learning based model that uses only sequence information of both targets and drugs to predict DT interaction binding affinities is proposed, outperforming the KronRLS algorithm and SimBoost, a state‐of‐the‐art method for DT binding affinity prediction. Expand
Daylight
  • online; accessed 06 April 2021. [Online]. Available: https://www.daylight.com/
  • 2021
DeepPurpose: a deep learning library for drug–target interaction prediction
TLDR
DeepPurpose is presented, a comprehensive and easy-to-use DL library for DTI prediction, which supports training of customizedDTI prediction models by implementing 15 compound and protein encoders and over 50 neural architectures, along with providing many other useful features. Expand
A comprehensive review of hybrid models for solar radiation forecasting
TLDR
A comparative study between different hybrid models, explore their application, and identify promising and potential models for solar radiation application assessment is presented to provide preliminary guidelines for a complete view of the hybrid models and tools that can be used in order to improve solar radiation assessment. Expand
An ensemble approach for supporting the respiratory isolation of presumed tuberculosis inpatients
TLDR
This paper proposes a novel technique for developing a committee of classifiers aiming at supporting the decision making relative to inpatient respiratory isolation, and confirms that the resulting committees have outperformed several recently proposed single-models and ensemble solutions, including deep learning techniques. Expand
AttentionDTA: prediction of drug–target binding affinity using attention model
TLDR
An end-to-end model, named AttentionDTA, which associates attention mechanism to predict the binding affinity of DTI, and shows that the attention-based model can effectively extract effective representations by calculating the weight of the representation between the drug and the protein. Expand
Improving Patch-Based Convolutional Neural Networks for MRI Brain Tumor Segmentation by Leveraging Location Information
TLDR
A novel method to integrate location information with the state-of-the-art patch-based neural networks for brain tumor segmentation is introduced, which improves the segmentation performance of state- of- the-art networks including 3D U-Net and DeepMedic. Expand
...
1
2
3
4
...