Download presentation
Presentation is loading. Please wait.
Published byScott Tyler Modified over 9 years ago
1
PharmaMiner: Geometric Mining of Pharmacophores 1
2
PharmaMiner Analysis of 3D arrangements of pharmacophoric features in compound collections Flexible definition of features of interest (donor, acceptor, hydrophobic core, etc.) Classification and clustering of arrangements 2
3
Applications of PharmaMiner What makes compounds active against a target? – Develop pharmacophore models based on results – What features impart specific biological activity (e.g., BBB permeability)? Screen compounds for specific arrangements – Query for combination of properties and arrangements Diversity analysis in 3D space Scaffold hopping 3
4
Key Benefits Only automatic tool that analyzes the 3D space of pharmacophores Identification of activity against a target based on a set of actives and inactives (clustering) Unique exploration of the pharmacophore space through biological activity (classification) Unique querying for proximity and distance from clusters – Specification of toxicity, absorption, side-effects 4
5
Validation Studies Activity prediction of cancer datasets 5
6
Pharmacophoric Features: Cancer Datasets Cations Anions Hydrogen Bond Donors Hydrogen Bond Acceptors Hydrophobic Centers Aromatic Rings
7
Results: Cancer Datasets Many clusters show significant behavior – Examples of some positive clusters DatasetTriangle TypeExpected Ratio Observed Ratio LeukemiaAcceptor Acceptor-Donor3.5%22.6% OvarianCation-Cation-Acceptor3.7%24.6% ColonCation-Acceptor-Anion4.3%34% CNSCation-Acceptor-Anion3.6%30% ProstateCation-Cation-Acceptor4.1%31.6%
8
Results: Cancer Datasets Clusters involving anions show strong negative significance: However, typically Acceptor-Acceptor-Anion clusters also contained a positive cluster indicating a certain structure that occurs frequently in active molecules DatasetTriangle TypeExpected Ratio Observed Ratio LeukemiaAcceptor-Acceptor-Anion3.5%0.8% OvarianAcceptor-Acceptor-Anion3.7%0.6% ColonAcceptor-Acceptor-Anion4.3%0.6% CNSAcceptor-Acceptor-Anion3.6%0.4%
9
Prediction Pipeline Molecular DB Extract all pharmacophoric triangles K-medoid clustering Significant cluster centers Triangles Classification Model Vector representation of molecules SVM with MinMax kernel Feature Vector Result
10
Complementary to GraphSig Pharmacophoric atoms vs. atom types – E.g., N-O-N and N-O-O get clustered together due to similar pharmacophoric type Graph based approach allows more flexibility and computational efficiency 3D analysis has better accuracy Possible to combine the two techniques
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.