|
|
--- |
|
|
license: mit |
|
|
tags: |
|
|
- chemistry |
|
|
- molecular-property-prediction |
|
|
- drug-discovery |
|
|
datasets: |
|
|
- natelgrw/AMAX |
|
|
pipeline_tag: tabular-regression |
|
|
--- |
|
|
|
|
|
# AMAX Models: Molecular Absorption Wavelength Prediction |
|
|
|
|
|
A collection of machine learning models for predicting maximum absorption wavelength (λ<sub>max</sub>) of chemical compounds in various solvents. These models use molecular descriptors to predict spectroscopic properties, useful for drug discovery, materials science, and computational chemistry applications. |
|
|
|
|
|
Source code for the AMAX model collection is available at this [Github Repository](https://github.com/natelgrw/amax_models). |
|
|
|
|
|
The AMAX dataset is available at this [Hugging Face Repository](https://huggingface.co/datasets/natelgrw/AMAX). |
|
|
|
|
|
## 🤖 Available Models |
|
|
|
|
|
| Model | Architecture | Overall RMSE (nm) | Overall MAE (nm) | Overall R<sup>2</sup> | |
|
|
|-----|-----|-----|-----|-----| |
|
|
| **AMAX_XGB1** | XGBoost | 56.488 | 36.005 | 0.746 | |
|
|
| **AMAX_MLP1** | PyTorch Sequential MLP | 64.152 | 44.388 | 0.669 | |
|
|
|
|
|
All models were evaluated across rigorous scaffold, cluster, and method splits. |
|
|
|
|
|
## 📄 Citation |
|
|
|
|
|
If you use an AMAX prediction model in your research, please cite: |
|
|
|
|
|
```bibtex |
|
|
@modelcollection{amaxmodels, |
|
|
title={AMAX-Models: Machine Learning Models for Molecular Absorption Wavelength Prediction}, |
|
|
author={Leung, Nathan}, |
|
|
institution={Coley Research Group @ MIT} |
|
|
year={2025}, |
|
|
howpublished={\url{https://huggingface.co/natelgrw/AMAX-Models}}, |
|
|
} |
|
|
``` |
