PandoraRL: DQN and Graph Convolution based ligand pose learning for SARS-COV1 Mprotease

Jose, Justin; Alam, Ujjaini; Singh, Divye; Jatana, Nidhi; Arora, Pooja

doi:10.1109/bibm55620.2022.9994854

Cited by 3 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The protein-ligand docking problem is different from any other RL problem where either the path or the final destination is known. The differences between each complex, as highlighted in [30] makes it difficult for the RL agent to learn and generate a reusable model due to the diversity in the protein-ligand complexes, especially for unseen ones.…”

Section: Training Strategymentioning

confidence: 99%

See 1 more Smart Citation

PandoraRLO: DQN and Graph convolution based method for optimized ligand pose

Jose

Alam

Singh

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Predicting how proteins interact with small molecules is a complex and challenging task in the field of drug discovery. Two important aspects in this are shape complementarity and inter molecular interactions which are highly driven by the binding site and the ultimate pose of the ligand in which it interacts with the protein. Various state of the art methods exist which provide a range of ligand poses that are potentially a good fit for a given specific receptor, these are usually compute intensive and expensive. In this study, we have designed a method that provides a single optimized ligand pose for a specific receptor. The method is based on reinforcement learning where when exposed to a diverse protein ligand data set the agent is able to learn the underlying complex biochemistry of the protein ligand pair and provide an optimized pair. As a first study on usage of reinforcement learning for optimized ligand pose, the PandoraRLO model is able to predict pose within a range of 0.5A to 4A for a large number of test complexes. This indicates the potential of reinforcement learning in uncovering the inherent patterns of protein-ligand pair in 3D space.

show abstract

Section: Training Strategymentioning

confidence: 99%

“…In [29] the authors have explored the used voxelbased representation, with a single-atom ligand (copper ion). Recently, [30] used graph representation for protein and ligand with a Graph Neural Network (GNN) to obtain a learned model for addressing the protein-ligand docking problem using RL.…”

Section: Introductionmentioning

confidence: 99%