1 / 15

Particle Swarm Optimization applied to Automated Docking

Particle Swarm Optimization applied to Automated Docking. Automated docking of a ligand to a macromolecule Particle Swarm Optimization Multi-objective PSO + Clustering Docking experiments Conclusion. Automated Docking. Predict binding of a ligand molecule to a receptor macromolecule

faris
Télécharger la présentation

Particle Swarm Optimization applied to Automated Docking

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Particle Swarm Optimization applied to Automated Docking • Automated docking of a ligand to a macromolecule • Particle Swarm Optimization • Multi-objective PSO + Clustering • Docking experiments • Conclusion

  2. Automated Docking • Predict binding of a ligand molecule to a receptor macromolecule • Minimize resulting binding energy

  3. Energy Evaluation [Morris et al.]

  4. Autodock 3.05 • Determine energies using trilinear interpolation on precalculated grid maps • Minimize docking energy with various optimization techniques • Simulated Annealing • Genetic Algorithm with Local Search • Sum of energies is minimized

  5. Particle Swarm Optimization • Multi-dimensional, numerical optimization by a swarm of particles • Each particle has current position ,best position and velocity • Attracted by personal best positionand neighbourhood best position

  6. PSO Algorithm

  7. Clustering • Particles are clustered into K separate swarm • K-means Clustering • m data-vectors are clustered into k clusters • Iteratively calculate centroids of each cluster

  8. Multiple Objectives • Optimize , simultaneously • Find dominating solutions • Non-Dominated Front

  9. Clust-MPSO • Update personal best position • Each swarm has non-dominated front • is dominated if no particle is in • Dominated swarms are relocated • Neighbourhood best particle • Picked for several iterations

  10. 1hvr Docking

  11. 4cha Docking

  12. Convergence – 1hvr

  13. Convergence – 4cha

  14. Conclusions • Application of PSO to Automated Docking • Optimization of two objectives • Clustering to divide the search space

More Related