Work

Enhancing generative molecular design via uncertainty-guided fine-tuning of variational autoencoders

Year: 2025

Type: article

Abstract: This study explores low-dimensional active subspace of pre-trained VAE-based generative molecular design models to perform uncertainty-guided fine-tuning of the VAE parameters to enhance downstream design task performance of the pre-trained models.

Source: Molecular Systems Design & Engineering

DOI: 10.1039/d5me00081e

Authors: A. N. M. Nafiz Abeer, Sanket Jantre, Nathan M. Urban, Byung-Jun Yoon

Institutions: Texas A&M University, Brookhaven National Laboratory

Language: English

Topic: Computational Drug Discovery Methods

Subfield: Computational Theory and Mathematics

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: U.S. Department of Energy, Office of Science, Advanced Scientific Computing Research

Awards: G394924661, G5829118104, G5900074199