LatMixSol augments solubility training data by clustering molecules, interpolating their autoencoder latent codes, and decoding the results, yielding small RMSE gains on three of four boosting models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.QM 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Enhancing Drug Discovery: Autoencoder-Based Latent Space Augmentation for Improved Molecular Solubility Prediction using LatMixSol
LatMixSol augments solubility training data by clustering molecules, interpolating their autoencoder latent codes, and decoding the results, yielding small RMSE gains on three of four boosting models.