Next Article in Journal
Y-Box Binding Protein 1: Unraveling the Multifaceted Role in Cancer Development and Therapeutic Potential
Next Article in Special Issue
Generating Potential RET-Specific Inhibitors Using a Novel LSTM Encoder–Decoder Model
Previous Article in Journal
LIGHT/TNFSF14 Affects Adipose Tissue Phenotype
Previous Article in Special Issue
Literature-Based Discovery Predicts Antihistamines Are a Promising Repurposed Adjuvant Therapy for Parkinson’s Disease
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

SolPredictor: Predicting Solubility with Residual Gated Graph Neural Network

1
Department of Electronics and Information Engineering, Jeonbuk National University, Jeonju 54896, Republic of Korea
2
School of International Engineering and Science, Jeonbuk National University, Jeonju 54896, Republic of Korea
3
School of Pharmacy, Jeonbuk National University, Jeonju 54896, Republic of Korea
4
Advanced Electronics and Information Research Center, Jeonbuk National University, Jeonju 54896, Republic of Korea
*
Authors to whom correspondence should be addressed.
These authors contributed equally to this work.
Int. J. Mol. Sci. 2024, 25(2), 715; https://doi.org/10.3390/ijms25020715
Submission received: 6 December 2023 / Revised: 26 December 2023 / Accepted: 4 January 2024 / Published: 5 January 2024

Abstract

Computational methods play a pivotal role in the pursuit of efficient drug discovery, enabling the rapid assessment of compound properties before costly and time-consuming laboratory experiments. With the advent of technology and large data availability, machine and deep learning methods have proven efficient in predicting molecular solubility. High-precision in silico solubility prediction has revolutionized drug development by enhancing formulation design, guiding lead optimization, and predicting pharmacokinetic parameters. These benefits result in considerable cost and time savings, resulting in a more efficient and shortened drug development process. The proposed SolPredictor is designed with the aim of developing a computational model for solubility prediction. The model is based on residual graph neural network convolution (RGNN). The RGNNs were designed to capture long-range dependencies in graph-structured data. Residual connections enable information to be utilized over various layers, allowing the model to capture and preserve essential features and patterns scattered throughout the network. The two largest datasets available to date are compiled, and the model uses a simplified molecular-input line-entry system (SMILES) representation. SolPredictor uses the ten-fold split cross-validation Pearson correlation coefficient R2 0.79±0.02 and root mean square error (RMSE) 1.03±0.04. The proposed model was evaluated using five independent datasets. Error analysis, hyperparameter optimization analysis, and model explainability were used to determine the molecular features that were most valuable for prediction.
Keywords: molecular solubility; drug discovery; ADMET; artificial intelligence; regression; graph neural network; residual gated graph neural network; simplified molecular-input line-entry system molecular solubility; drug discovery; ADMET; artificial intelligence; regression; graph neural network; residual gated graph neural network; simplified molecular-input line-entry system

Share and Cite

MDPI and ACS Style

Ahmad, W.; Tayara, H.; Shim, H.; Chong, K.T. SolPredictor: Predicting Solubility with Residual Gated Graph Neural Network. Int. J. Mol. Sci. 2024, 25, 715. https://doi.org/10.3390/ijms25020715

AMA Style

Ahmad W, Tayara H, Shim H, Chong KT. SolPredictor: Predicting Solubility with Residual Gated Graph Neural Network. International Journal of Molecular Sciences. 2024; 25(2):715. https://doi.org/10.3390/ijms25020715

Chicago/Turabian Style

Ahmad, Waqar, Hilal Tayara, HyunJoo Shim, and Kil To Chong. 2024. "SolPredictor: Predicting Solubility with Residual Gated Graph Neural Network" International Journal of Molecular Sciences 25, no. 2: 715. https://doi.org/10.3390/ijms25020715

APA Style

Ahmad, W., Tayara, H., Shim, H., & Chong, K. T. (2024). SolPredictor: Predicting Solubility with Residual Gated Graph Neural Network. International Journal of Molecular Sciences, 25(2), 715. https://doi.org/10.3390/ijms25020715

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop