Abstract
Data fusion is the name given to a range of methods for combining multiple sources of evidence. This mini-review summarizes the use of one such class of methods for combining the rankings obtained when similarity searching is used for ligand-based virtual screening. Two main approaches are described: similarity fusion involves combining rankings from single searches based on multiple similarity measures; and group fusion involves combining rankings from multiple searches based on a single similarity measure. The review then focuses on the rules that are available for combining similarity rankings, and on the evidence that exists for the superiority of fusion-based methods over conventional similarity searching.
Highlights
Virtual screening involves ranking a database of previously of atoms and bonds; and representations that encode 3D atom untested molecules in order of decreasing probability of biological coordinate or shape information
Data fusion is the name given to a range of methods for combining multiple sources of evidence. This mini-review summarizes the use of one such class of methods for combining the rankings obtained when similarity searching is used for ligandbased virtual screening
Two main approaches are described: similarity fusion involves combining rankings from single searches based on multiple similarity measures; and group fusion involves combining rankings from multiple searches based on a single similarity measure
Summary
Virtual screening involves ranking a database of previously of atoms and bonds; and representations that encode 3D atom untested molecules in order of decreasing probability of biological coordinate or shape information. Which is arguably the simplest, and similarity searching [8, 18-20] It has become widely probably the most widely, used approach currently available for recognised that no single measure can be expected to provide the best ligand-based virtual screening [5-9]. In its simplest form, similarity searching assumes the existence of the result that researchers have looked for ways of combining the at least one active (or potentially active) molecule, which is normally results obtained from use of multiple similarity searches This is referred to as the or structure, and a database of normally effected using the technique known as [24]; an molecules that have not, far, been tested in the assay of interest. The availability of multiple sources of information means that combining several different similarity rankings to give a single fused ranking is expected to provide a superior level of screening effectiveness than will the ranking obtained from any single similarity measure
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have