A Biclustering Method for Rationalizing Chemical Biology Mechanisms of Action
1 like1,328 views
This document discusses using a chemical interaction matrix and biclustering approach to analyze multi-dimensional biochemical and chemical biology data to better understand mechanisms of action. The procedure involves assembling a matrix of compounds versus activity and descriptive features, normalizing the data, folding activity measurements into the features, and then using biclustering to identify contiguous regions within the matrix that may indicate groups of compounds sharing a mechanism of action or features correlated with activity. An example application to a dataset of 773 molecules and 298 molecular descriptors relating to oral bioavailability achieves promising results, with biclustering condensing the data into 18 high-quality clusters that cover most of the training space and should provide a strong basis for target identification when compared
A Biclustering Method for Rationalizing Chemical Biology Mechanisms of Action
- 1. Chemical Interaction Matrix: Gerald Lushington / LiS Consulting http://geraldlushington.com / [email protected]
- 2. Personalized Medicine Comprehensive Biochemical & Chemical Biology Understanding Big data: NGS, medical outcomes, etc.
- 3. Personalized Medicine Comprehensive Biochemical & Chemical Biology Understanding Informatics & Creativity HTS & Chemical Proteomics Big data: NGS, medical outcomes, etc.
- 4. Example Challenges: ●Toxicology: single toxin may modulate several different biochemical processes ●Cancer: malignant cells have multiple biochemical sensitivities that may be targeted ●Spectral disorders (e.g., Autism, Alzheimers, etc.): distinct phenotypes produce similar symptoms Discovery Paradigm: Chemical screening prospective hits Chemical proteomics prospective targets How to attain comprehensive understanding?
- 9. How to make sense of diffuse multimode data? Mechanism of Action (MOA) discovery: find compound subsets that conserve common mechanism Excellent (but imperfect) example: TEST (Toxicology Estimation Software Tool) http://www.epa.gov/nrmrl/std/qsar/qsar.html
- 10. TEST Multiple data sets covering toxicity outcomes for numerous compounds Predict toxicity of query compounds via on-the-fly training to similar pre-characterized analogs
- 11. TEST Multiple data sets covering toxicity outcomes for numerous compounds Predict toxicity of query compounds via on-the-fly training to similar pre-characterized analogs Use Tanimoto distances over molecular fingerprints: no validated relevance specific outcomes
- 12. Procedure: 1. Assemble Matrix of compounds vs. activity & features MOA method: feature / compound selection
- 13. Procedure: 1. Assemble Matrix of compounds vs. activity & features 2. Normalize MOA method: feature / compound selection
- 14. Procedure: 1. Assemble Matrix of compounds vs. activity & features 2. Normalize 3. Fold activity into features as per: Ci = |Act* - Xi*| X values: 0 = perfect correlation 1 = perfect anticorrelation MOA method: feature / compound selection
- 15. Procedure: 1. Assemble Matrix of compounds vs. activity & features 2. Normalize 3. Fold activity into features as per: Ci = |Act* - Xi*| 4. Bicluster MOA method: feature / compound selection
- 16. Procedure: 1. Assemble Matrix of compounds vs. activity & features 2. Normalize 3. Fold activity into features as per: Ci = |Act* - Xi*| 4. Bicluster Clusters Contiguous correlative or anticorrelative regions or matrix Within clusters: molecules may share MOA; features may correlate with activity Confidence: correlative & predictive quality of model derived from cluster MOA method: feature / compound selection
- 17. Example: Oral Bioavailability Oral update depends on: ● Polar solubility ● Membrane permeability ● Interaction with various transporters Data (from Tingjun Hou): 773 molecules http://modem.ucsd.edu/adme/databases/databases_bioavailability.htm Descriptors (from VolSurf and DVS): 298 features passing information content and linear independence (R < 0.90) filters
- 18. Example: Oral Bioavailability Oral update depends on: ● Polar solubility ● Membrane permeability ● Interaction with various transporters Data (from Tingjun Hou): 773 molecules http://modem.ucsd.edu/adme/databases/databases_bioavailability.htm Descriptors (from VolSurf and DVS): 298 features passing information content and linear independence (R < 0.90) filters Preliminary Model (Weka: Bootstrap Aggregating / RepTree): Q2 (5-fold) = 0.4712
- 19. Example: Oral Bioavailability Oral update depends on: ● Polar solubility ● Membrane permeability ● Interaction with various transporters Data (from Tingjun Hou): 773 molecules http://modem.ucsd.edu/adme/databases/databases_bioavailability.htm Descriptors (from VolSurf and DVS): 298 features passing information content and linear independence (R < 0.90) filters Preliminary Model (Weka: Bootstrap Aggregating / RepTree): Q2 (5-fold) = 0.4712 CFS & RF: reduced to 27 features Q2 (5-fold) = 0.4739
- 20. Biclustering: Before and After
- 21. Clusters as local training sets:
- 22. Clusters as local training sets: Condense to 18 high quality clusters that cover almost entire training space (omit only 10 of 768 cpds)
- 23. Conclusions Correlative & predictive performance of subset models gives strong confidence in MOA conservation in clusters Head-to-head comparison with chemical proteomics data should provide strong basis for target identification Questions / Suggestions? [email protected]