solubility-prediction

fastsolv python package, website, and paper code

GNN, GCN, Molecular Solubility, RDKit, Cheminformatics

📈 Fusion of sequence, structure and feature information to improve protein solubility prediction (IEEE BIBM 2024).

Hansen Solubility Parameters in Python.

Template with code & dataset for the "Structural basis for solubility in protein expression systems" challenge at the Copenhagen Bioinformatics Hackathon 2021.

Online solubility prediction tool (streamlit) that runs the top-performing ML model (AqSolPred).

Modeling solubility of organic molecules with multivariate linear regression and machine learning

A comprehensive toolkit for predicting drug-polymer and drug-solvent system behavior using the COSMO-SAC model, aimed at enhancing the development of pharmaceutical amorphous solid dispersions and miscibility studies.

Classification of HER2(human epidermal growth factor receptor 2) molecules using deep neural network.

MEng research project, assessing the performance of various co-solvent solubility models. MATLAB tool to run solubility predictions/import data and perform analysis on results.

End-to-end Chemoinformatics QSAR pipeline predicting aqueous solubility using Machine Learning, featuring Scaffold Splitting and a Streamlit dashboard.

Molecular Solubility Prediction Web App

Fiedler Topology Molecular & Water Network Simulator

Welcome to the Solubility Prediction project! This project aims to understand the relationship between molecular descriptors and solubility in chemical compounds, crucial for medication design and environmental research.

Solubility Prediction from SMILE by Random Forest Algorithm Using RDKit 2D and 3D Descriptors

Rapid E. coli protein solubility prescreening across His/GST/MBP/SUMO tags. NetSolP engine + zero-dependency eSOL-calibrated heuristic. Benchmarked on 2,665 proteins (eSOL/cbh21/yeast). GUI + CLI + Windows exe.

Silva workflow for organic solubility prediction using MIT fastsolv — ranks solvents by log(S) across temperatures, helping experimentalists shortlist candidates for purification.

RDKit molecular descriptors, scaffold-aware solubility modeling, and FastAPI model serving for public small molecules.

OLMo-7B QLoRA fine-tuned on ESOL solubility regression. RDKit-Augmented Prompts + Regression Head on 4096-dim hidden states. Best RMSE: 0.8582. DeepChem GSoC 2026.

Dual-graph interaction GNN for predicting molecular solubility (logS) from solute-solvent SMILES using cross-attention and BigSolDB 2.0