A note on utilising binary features as ligand descriptors
Autor: | Mussa, Hamse Y., Mitchell, John B. O., Glen, Robert C. |
---|---|
Přispěvatelé: | BBSRC, University of St Andrews. School of Chemistry, University of St Andrews. Biomedical Sciences Research Complex, University of St Andrews. EaSTCHEM |
Jazyk: | angličtina |
Rok vydání: | 2015 |
Předmět: |
Technology
Binary descriptors Science & Technology Computer Science Information Systems Chemistry Multidisciplinary T-NDAS Bernoulli distribution MUTUAL INFORMATION Linear relationship Library and Information Sciences QD Chemistry Computer Graphics and Computer-Aided Design Computer Science Applications Chemistry Physical Sciences Computer Science Ligand chemical structure Commentary FEATURE-SELECTION QD Computer Science Interdisciplinary Applications Physical and Theoretical Chemistry |
Zdroj: | Journal of Cheminformatics |
ISSN: | 1758-2946 |
Popis: | Mussa and Mitchell thank the BBSRC for funding this research through grant BB/I00596X/1. Mitchell thanks the Scottish Universities Life Sciences Alliance (SULSA) for financial support. It is common in cheminformatics to represent the properties of a ligand as a string of 1’s and 0’s, with the intention of elucidating, inter alia, the relationship between the chemical structure of a ligand and its bioactivity. In this commentary we note that, where relevant but non-redundant features are binary, they inevitably lead to a classifier capable of capturing only a linear relationship between structural features and activity. If, instead, we were to use relevant but non-redundant real-valued features, the resulting predictive model would be capable of describing a non-linear structure-activity relationship. Hence, we suggest that real-valued features, where available, are to be preferred in this scenario. Publisher PDF |
Databáze: | OpenAIRE |
Externí odkaz: |