Prob-cGAN: A Probabilistic Conditional Generative Adversarial Network for LSD1 Inhibitor Activity Prediction

TL;DR

This paper presents Prob-cGAN, a novel probabilistic conditional GAN that predicts LSD1 inhibitor activity with higher accuracy than existing models, aiding drug discovery in cancer treatment.

Contribution

Introduction of Prob-cGAN, a new probabilistic conditional GAN model that outperforms state-of-the-art methods in predicting LSD1 inhibitor activity.

Findings

Prob-cGAN achieved a top-1 R^2 of 0.739, outperforming previous models.

Prob-cGAN recorded a lower RMSE of 0.562, indicating better prediction accuracy.

The model demonstrates potential for improving drug design and understanding biological systems.

Abstract

The inhibition of Lysine-Specific Histone Demethylase 1 (LSD1) is a promising strategy for cancer treatment and targeting epigenetic mechanisms. This paper introduces a Probabilistic Conditional Generative Adversarial Network (Prob-cGAN), designed to predict the activity of LSD1 inhibitors. The Prob-cGAN was evaluated against state-of-the-art models using the ChEMBL database, demonstrating superior performance. Specifically, it achieved a top-1 $R^2$ of 0.739, significantly outperforming the Smiles-Transformer model at 0.591 and the baseline cGAN at 0.488. Furthermore, it recorded a lower $RMSE$ of 0.562, compared to 0.708 and 0.791 for the Smiles-Transformer and cGAN models respectively. These results highlight the potential of Prob-cGAN to enhance drug design and advance our understanding of complex biological systems through machine learning and bioinformatics.