Solubility Prediction

Predicting the solubility of molecules, crucial for drug development and other chemical applications, is actively being advanced through machine learning. Current research focuses on improving the accuracy and efficiency of predictive models, employing architectures like graph convolutional networks, recurrent neural networks (including LSTMs and BiLSTMs), and transformer networks, often combined for enhanced performance. A key challenge is mitigating overfitting during model training and improving interpretability to understand the underlying chemical factors influencing solubility. These advancements promise to accelerate drug discovery and materials science by streamlining experimental processes and improving the selection of candidate compounds.

Papers

July 30, 2024

Be aware of overfitting by hyperparameter optimization!
Igor V. Tetko, Ruud van Deursen, Guillaume Godin
Machine Learning Hyperparameter Optimization Hyper Parameter Solubility Prediction

July 8, 2024

Accelerating Drug Safety Assessment using Bidirectional-LSTM for SMILES Data
K. Venkateswara Rao, Dr. Kunjam Nageswara Rao, Dr. G. Sita Ratnam
Sequence to Sequence Drug Discovery Biological Sequence Bidirectional LSTM Molecular Input Line Entry System Drug Safety Solubility Prediction

June 27, 2024

YZS-model: A Predictive Model for Organic Drug Solubility Based on Graph Convolutional Networks and Transformer-Attention
Chenxu Wang, Haowei Ming, Jian He, Yao Lu, Junhong Chen
Predictive Model Drug Like Transformer Attention Solubility Prediction

August 23, 2023

Predicting Drug Solubility Using Different Machine Learning Methods -- Linear Regression Model with Extracted Chemical Features vs Graph Convolutional Neural Network
John Ho, Zhao-Heng Yin, Colin Zhang, Nicole Guo, Yang Ha
Machine Learning Known Molecule Regression Model Graph Convolutional Neural Network Chemical Structure Solubility Prediction

July 11, 2023

Predicting small molecules solubilities on endpoint devices using deep ensemble neural networks
Mayk Caldas Ramos, Andrew D. White
Molecular Property Prediction First Principle Deep Neural Network Ensemble Endpoint Detection Solubility Prediction

April 7, 2023

Automated Solubility Analysis System and Method Using Computer Vision and Machine Learning
Gahee Kim, Minwoo Jeon, Hyun Do Choi, Jun Ki Cho, Youn-Suk Choi, Hyoseok Hwang
Machine Learning Computer Vision Practical Method Separation Performance Solubility Prediction Dissolution Profile

September 29, 2022

Accurate, reliable and interpretable solubility prediction of druglike molecules with attention pooling and Bayesian learning
Seongok Ryu, Sumin Lee
Bayesian Learning Drug Like Chemical Data Attention Based Pooling Pharmacokinetic Parameter Solubility Prediction

March 18, 2022

SOLIS: Autonomous Solubility Screening using Deep Neural Networks
Gabriella Pizzuto, Jacopo de Berardinis, Louis Longley, Hatem Fakhruldeen, Andrew I. Cooper
Deep Neural Network Material Discovery Solubility Prediction

Solubility Prediction

Papers

Be aware of overfitting by hyperparameter optimization!

Accelerating Drug Safety Assessment using Bidirectional-LSTM for SMILES Data

YZS-model: A Predictive Model for Organic Drug Solubility Based on Graph Convolutional Networks and Transformer-Attention

Predicting Drug Solubility Using Different Machine Learning Methods -- Linear Regression Model with Extracted Chemical Features vs Graph Convolutional Neural Network

Predicting small molecules solubilities on endpoint devices using deep ensemble neural networks

Automated Solubility Analysis System and Method Using Computer Vision and Machine Learning

Accurate, reliable and interpretable solubility prediction of druglike molecules with attention pooling and Bayesian learning

SOLIS: Autonomous Solubility Screening using Deep Neural Networks