Next Article in Journal
Learning Optimal Dynamic Treatment Regime from Observational Clinical Data through Reinforcement Learning
Next Article in Special Issue
Tertiary Review on Explainable Artificial Intelligence: Where Do We Stand?
Previous Article in Journal
Diverse Machine Learning for Forecasting Goal-Scoring Likelihood in Elite Football Leagues
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Insights from Augmented Data Integration and Strong Regularization in Drug Synergy Prediction with SynerGNet

by
Mengmeng Liu
1,
Gopal Srivastava
2,
J. Ramanujam
1,3 and
Michal Brylinski
2,3,*
1
Division of Electrical and Computer Engineering, Louisiana State University, Baton Rouge, LA 70803, USA
2
Department of Biological Sciences, Louisiana State University, Baton Rouge, LA 70803, USA
3
Center for Computation and Technology, Louisiana State University, Baton Rouge, LA 70803, USA
*
Author to whom correspondence should be addressed.
Mach. Learn. Knowl. Extr. 2024, 6(3), 1782-1797; https://doi.org/10.3390/make6030087
Submission received: 24 May 2024 / Revised: 17 July 2024 / Accepted: 25 July 2024 / Published: 29 July 2024
(This article belongs to the Special Issue Machine Learning in Data Science)

Abstract

SynerGNet is a novel approach to predicting drug synergy against cancer cell lines. In this study, we discuss in detail the construction process of SynerGNet, emphasizing its comprehensive design tailored to handle complex data patterns. Additionally, we investigate a counterintuitive phenomenon when integrating more augmented data into the training set results in an increase in testing loss alongside improved predictive accuracy. This sheds light on the nuanced dynamics of model learning. Further, we demonstrate the effectiveness of strong regularization techniques in mitigating overfitting, ensuring the robustness and generalization ability of SynerGNet. Finally, the continuous performance enhancements achieved through the integration of augmented data are highlighted. By gradually increasing the amount of augmented data in the training set, we observe substantial improvements in model performance. For instance, compared to models trained exclusively on the original data, the integration of the augmented data can lead to a 5.5% increase in the balanced accuracy and a 7.8% decrease in the false positive rate. Through rigorous benchmarks and analyses, our study contributes valuable insights into the development and optimization of predictive models in biomedical research.
Keywords: drug synergy prediction; graph neural networks; computational biology; regularization in deep learning; data augmentation; model evaluation drug synergy prediction; graph neural networks; computational biology; regularization in deep learning; data augmentation; model evaluation

Share and Cite

MDPI and ACS Style

Liu, M.; Srivastava, G.; Ramanujam, J.; Brylinski, M. Insights from Augmented Data Integration and Strong Regularization in Drug Synergy Prediction with SynerGNet. Mach. Learn. Knowl. Extr. 2024, 6, 1782-1797. https://doi.org/10.3390/make6030087

AMA Style

Liu M, Srivastava G, Ramanujam J, Brylinski M. Insights from Augmented Data Integration and Strong Regularization in Drug Synergy Prediction with SynerGNet. Machine Learning and Knowledge Extraction. 2024; 6(3):1782-1797. https://doi.org/10.3390/make6030087

Chicago/Turabian Style

Liu, Mengmeng, Gopal Srivastava, J. Ramanujam, and Michal Brylinski. 2024. "Insights from Augmented Data Integration and Strong Regularization in Drug Synergy Prediction with SynerGNet" Machine Learning and Knowledge Extraction 6, no. 3: 1782-1797. https://doi.org/10.3390/make6030087

APA Style

Liu, M., Srivastava, G., Ramanujam, J., & Brylinski, M. (2024). Insights from Augmented Data Integration and Strong Regularization in Drug Synergy Prediction with SynerGNet. Machine Learning and Knowledge Extraction, 6(3), 1782-1797. https://doi.org/10.3390/make6030087

Article Metrics

Back to TopTop