- Title：MAIB-Class-016 Diffusion Model for Molecular Docking
- Date：10:00pm US East time, 05/27/2023
- Date：10:00am Beijing time, 05/28/2023
- Zoom ID：933 1613 9423
- Zoom PWD：416262
- Zoom: https://uwmadison.zoom.us/meeting/register/tJcudu-prTIuGNda1MsF8PKyRQlnGn06TP2E
Presentation Record(Previous Presentation will be showed here if the video is not released for this talk)
-
Momiao Xiong, Ph. D, Professor in Department of Biostatistics snd Data Science , University of Texas, School of Public Health. Dr. Xiong graduated from the Department of Statistics at the University of Georgia in 1993. From 1993 to 1995, Dr. Xiong was postdoctoral fellow at the University of Southern California working with Michael Waterman.
-
Research Interest： Causal Inference, Artificial Intelligence , Manifold Learning, Statistic Genetics and Bioinformatics .
Background
The diffusion model is a computational approach used in molecular docking, which is a method for predicting the binding affinity and orientation of a small molecule (ligand) with a target protein or receptor. The diffusion model aims to simulate the movement of ligand molecules within the binding site of the protein and explore the conformational space to find the most energetically favorable binding pose.
The diffusion model typically involves the following steps:
Initial Placement: The ligand molecule is placed in the vicinity of the binding site of the protein using random or systematic methods.
Sampling: Multiple conformations or poses of the ligand are generated by applying various translations, rotations, and torsional changes to explore the binding site space.
Scoring: Each generated pose is evaluated using a scoring function that assesses the binding affinity between the ligand and the protein. The scoring function typically considers factors such as van der Waals interactions, electrostatic interactions, hydrogen bonding, and solvation effects.
Acceptance/Rejection: The generated poses are accepted or rejected based on the scoring function. Poses with better scores (indicating higher affinity) are more likely to be accepted, while poses with poorer scores are rejected.
Refinement: The accepted poses may undergo further refinement steps to optimize the ligand-protein interactions and improve the binding affinity. This can involve techniques such as energy minimization or molecular dynamics simulations.
Selection of Final Pose: After the sampling, scoring, acceptance/rejection, and refinement steps, the ligand pose with the highest predicted binding affinity is selected as the most probable binding conformation.
The diffusion model aims to explore a diverse range of ligand conformations and orientations within the binding site, allowing for a more comprehensive search of the ligand-protein interaction space. This approach increases the likelihood of finding the optimal binding pose and predicting accurate binding affinities.
