Drug Solubility Prediction: A Comparative Analysis of GNN, MLP, and Traditional Machine Learning Algorithms
Прогнозирование растворимости лекарственных веществ: сравнительный анализ графовых нейронных сетей, многослойного перцептрона и традиционных алгоритмов машинного обучения
2024-03-05
SCID: 54.1/2capvvnp
Discuss with AI
Graph Neural Networks (GNN)Multilayer Perceptron (MLP)Random Forest (RF)drug solubility predictionpharmaceutical design
Figures from the paper
Abstract (AI)
The effective development and design of pharmaceuticals hold fundamental importance in the fields of medicine and the pharmaceutical industry. In this process, the accurate prediction of drug molecule solubility is a critical factor influencing the bioavailability, pharmacokinetics, and toxicity of drugs. Traditionally, mathematical equations based on chemical and physical properties have been used for drug solubility prediction. However, in recent years, with the advancement of artificial intelligence and machine learning techniques, new approaches have been developed in this field. This study evaluated different modeling approaches consisting of Graph Neural Networks (GNN), Multilayer Perceptron (MLP), and traditional Machine Learning (ML) algorithms. The Random Forest (RF) model stands out as the optimal performer, manifesting superior efficacy through the attainment of minimal error rates. It attains a Root Mean Square Error (RMSE) value of 1.2145, a Mean Absolute Error (MAE) value of 0.9221, and an R-squared (R2) value of 0.6575. In contrast, GNN model displays comparatively suboptimal performance, as evidenced by an RMSE value of 1.8389, an MAE value of 1.4684, and an R2 value of 0.2147. These values suggest that the predictions of this model contain higher errors compared to other models, and its explanatory power is lower. These findings highlight the performance differences among different modeling approaches in drug solubility prediction. The RF model is shown to be more effective than other methods, while the GNN model performs less effectively. This information provides valuable insights into which model should be preferred in pharmaceutical design and development processes.
Key Findings
1
Random Forest achieved the best performance, with RMSE 1.2145, MAE 0.9221, and R² 0.6575.
2
The GNN model performed comparatively poorly, obtaining RMSE 1.8389, MAE 1.4684, and R² 0.2147.
3
The findings provide model-selection guidance for pharmaceutical design and development applications involving drug solubility prediction.
4
The results indicate that Random Forest is more effective than the evaluated neural-network approaches for this drug solubility prediction task.
5
The study compares Graph Neural Networks, Multilayer Perceptrons, and traditional machine-learning algorithms for drug solubility prediction.
Research Object
drug molecules
Research Subject
aqueous solubility prediction and comparative modeling performance of GNN, MLP, and traditional machine-learning algorithms
Publication Details
Publication Date
2024-03-05
Journal
Publisher
ISSN
Cited by
6
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest