Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

BE-DTI': Ensemble framework for drug target interaction prediction using dimensionality reduction and active

Aman Sharma¹, Rinkle Rani¹

¹Computer Science and Engineering Department, Thapar Institute of Engineering & Technology, Punjab, Patiala, India.

Computer Methods and Programs in Biomedicine

|October 20, 2018

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Giant cell arteritis can occur in people of colour.

The Lancet. Rheumatology·2024

Same author

Should race be considered in diagnosing giant cell arteritis? - Authors' reply.

The Lancet. Rheumatology·2024

Same author

Cannonball opacities in a pregnant woman.

The Lancet. Rheumatology·2024

Same author

Antibody response to mycobacterial Rpf B protein and its immunodominant peptides in HIV-TB co-infected individuals.

Tuberculosis (Edinburgh, Scotland)·2023

Same author

Cutaneous manifestations of VEXAS syndrome: multiple changing faces in the same patient.

International journal of dermatology·2023

Same author

Discovery of triazole tethered thymol/carvacrol-coumarin hybrids as new class of α-glucosidase inhibitors with potent in vivo antihyperglycemic activities.

European journal of medicinal chemistry·2023

Same journal

MMFVS-Net: A triple-symmetric cross-attention network for multimodal optical image fusion and high-accuracy virtual staining of breast cancer tissues.

Computer methods and programs in biomedicine·2026

Same journal

A novel Milstein-stochastic epidemiologically-informed neural network for approaching epidemic dynamics: Application to Mpox disease.

Computer methods and programs in biomedicine·2026

Same journal

Accounting for approximation errors using surrogate-based parameter estimation of cardiac mechanics digital twins.

Computer methods and programs in biomedicine·2026

Same journal

Facial iPPG heatmap patterns based on period-aware autoencoder show association with carotid atherosclerosis towards non-contact hemodynamic assessment.

Computer methods and programs in biomedicine·2026

Same journal

Explainable machine learning models predict liver fibrosis risk and outcome in the general population: Development and multi-cohort external validation.

Computer methods and programs in biomedicine·2026

Same journal

Evaluation of surrogate endpoints for survival outcomes using the surrogate package in R.

Computer methods and programs in biomedicine·2026

See all related articles

This study introduces BE-DTI, a machine learning framework for predicting drug-target interactions (DTI). The model effectively addresses class imbalance and high-dimensional data, outperforming existing methods.

Area of Science:

Bioinformatics
Computational Chemistry
Machine Learning in Drug Discovery

Background:

Drug-target interaction (DTI) prediction is crucial for drug discovery and repositioning.
Accurate DTI prediction aids in identifying novel drugs and therapies for diseases.
Challenges in DTI prediction include class imbalance and high-dimensional data.

Purpose of the Study:

To develop a machine learning framework for predicting drug-target interactions.
To address challenges of class imbalance and high dimensionality in DTI prediction.
To improve the accuracy and efficiency of identifying potential drug-target pairs.

Main Methods:

Proposed a bagging-based ensemble framework named BE-DTI.
Utilized dimensionality reduction to handle high-dimensional data.

Keywords:

Active learning Bagging Dimensionality reduction Drug-Target interaction prediction Ensemble learning Gene expression

Related Experiment Videos

Employed active learning to improve under-sampling in bagging ensembles for class-imbalanced data.

Main Results:

The BE-DTI framework achieved high performance in 10-fold cross-validation.
Achieved AUC=0.927, Sensitivity=0.886, Specificity=0.864, and G-mean=0.874.
Outperformed five other competing methods.

Conclusions:

BE-DTI successfully predicts missing and novel drug-target interactions.
The framework demonstrates accuracy through recalculation of removed known interactions.
External dataset validation confirms the approach, highlighting that similar drugs interact with similar targets.