Application of belief theory to similarity data fusion for use in analog searching and lead hopping
- PMID: 18416545
- DOI: 10.1021/ci7004498
Application of belief theory to similarity data fusion for use in analog searching and lead hopping
Abstract
A wide variety of computational algorithms have been developed that strive to capture the chemical similarity between two compounds for use in virtual screening and lead discovery. One limitation of such approaches is that, while a returned similarity value reflects the perceived degree of relatedness between any two compounds, there is no direct correlation between this value and the expectation or confidence that any two molecules will in fact be equally active. A lack of a common framework for interpretation of similarity measures also confounds the reliable fusion of information from different algorithms. Here, we present a probabilistic framework for interpreting similarity measures that directly correlates the similarity value to a quantitative expectation that two molecules will in fact be equipotent. The approach is based on extensive benchmarking of 10 different similarity methods (MACCS keys, Daylight fingerprints, maximum common subgraphs, rapid overlay of chemical structures (ROCS) shape similarity, and six connectivity-based fingerprints) against a database of more than 150,000 compounds with activity data against 23 protein targets. Given this unified and probabilistic framework for interpreting chemical similarity, principles derived from decision theory can then be applied to combine the evidence from different similarity measures in such a way that both capitalizes on the strengths of the individual approaches and maintains a quantitative estimate of the likelihood that any two molecules will exhibit similar biological activity.
Similar articles
-
Similarity searching using 2D structural fingerprints.Methods Mol Biol. 2011;672:133-58. doi: 10.1007/978-1-60761-839-3_5. Methods Mol Biol. 2011. PMID: 20838967 Review.
-
Unconventional 2D shape similarity method affords comparable enrichment as a 3D shape method in virtual screening experiments.J Chem Inf Model. 2009 Jun;49(6):1313-20. doi: 10.1021/ci900015b. J Chem Inf Model. 2009. PMID: 19480404
-
New methods for ligand-based virtual screening: use of data fusion and machine learning to enhance the effectiveness of similarity searching.J Chem Inf Model. 2006 Mar-Apr;46(2):462-70. doi: 10.1021/ci050348j. J Chem Inf Model. 2006. PMID: 16562973
-
Complex molecules: do they add value?Curr Opin Chem Biol. 2005 Jun;9(3):310-6. doi: 10.1016/j.cbpa.2005.04.001. Curr Opin Chem Biol. 2005. PMID: 15939334 Review.
-
Comparison of topological descriptors for similarity-based virtual screening using multiple bioactive reference structures.Org Biomol Chem. 2004 Nov 21;2(22):3256-66. doi: 10.1039/B409865J. Epub 2004 Sep 29. Org Biomol Chem. 2004. PMID: 15534703
Cited by
-
Using Generative Modeling to Endow with Potency Initially Inert Compounds with Good Bioavailability and Low Toxicity.J Chem Inf Model. 2024 Feb 12;64(3):590-596. doi: 10.1021/acs.jcim.3c01777. Epub 2024 Jan 23. J Chem Inf Model. 2024. PMID: 38261763 Free PMC article.
-
Exploring chemical space for lead identification by propagating on chemical similarity network.Comput Struct Biotechnol J. 2023 Aug 25;21:4187-4195. doi: 10.1016/j.csbj.2023.08.016. eCollection 2023. Comput Struct Biotechnol J. 2023. PMID: 37680266 Free PMC article.
-
Building Block-Based Binding Predictions for DNA-Encoded Libraries.J Chem Inf Model. 2023 Aug 28;63(16):5120-5132. doi: 10.1021/acs.jcim.3c00588. Epub 2023 Aug 14. J Chem Inf Model. 2023. PMID: 37578123 Free PMC article.
-
CACHE (Critical Assessment of Computational Hit-finding Experiments): A public-private partnership benchmarking initiative to enable the development of computational methods for hit-finding.Nat Rev Chem. 2022 Apr;6(4):287-295. doi: 10.1038/s41570-022-00363-z. Epub 2022 Feb 15. Nat Rev Chem. 2022. PMID: 35783295 Free PMC article.
-
Retro Drug Design: From Target Properties to Molecular Structures.J Chem Inf Model. 2022 Jun 13;62(11):2659-2669. doi: 10.1021/acs.jcim.2c00123. Epub 2022 Jun 2. J Chem Inf Model. 2022. PMID: 35653613 Free PMC article. Review.
MeSH terms
Substances
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical