Pooja Arora

PandoraGAN generates novel antiviral peptides using a GAN model trained on curated data, producing sequences with properties similar to known active peptides.

PandoraRLO uses reinforcement learning to predict optimized ligand poses for protein-ligand interactions, achieving accuracy within 0.5 to 4 angstroms for many test complexes.

This paper introduces PandoraRL, a reinforcement learning model using DQN and graph convolution to predict optimal ligand poses for SARS-CoV1 Mprotease.

The paper predicts pIC50 values for antiviral peptides against Flaviviridae targets using proteochemometric modeling, achieving R2 of 0.85 and MAPE of 8.44%.

This study introduces a reinforcement learning method for predicting optimized ligand poses and identifying binding sites using graph CNNs.