Abstract
BackgroundBayesian inference networks enable the computation of the probability that an event will occur. They have been used previously to rank textual documents in order of decreasing relevance to a user-defined query. Here, we modify the approach to enable a Bayesian inference network to be used for chemical similarity searching, where a database is ranked in order of decreasing probability of bioactivity.ResultsBayesian inference networks were implemented using two different types of network and four different types of belief function. Experiments with the MDDR and WOMBAT databases show that a Bayesian inference network can be used to provide effective ligand-based screening, especially when the active molecules being sought have a high degree of structural homogeneity; in such cases, the network substantially out-performs a conventional, Tanimoto-based similarity searching system. However, the effectiveness of the network is much less when structurally heterogeneous sets of actives are being sought.ConclusionA Bayesian inference network provides an interesting alternative to existing tools for ligand-based virtual screening.
Highlights
Bayesian inference networks enable the computation of the probability that an event will occur
A Bayesian inference network provides an interesting alternative to existing tools for ligand-based virtual screening
The algorithm A Bayesian inference network is a tool that permits the computation of the probability that an event will occur, allowing for the fact that this chosen event can be dependent on other events occurring
Summary
Bayesian inference networks enable the computation of the probability that an event will occur They have been used previously to rank textual documents in order of decreasing relevance to a user-defined query. We modify the approach to enable a Bayesian inference network to be used for chemical similarity searching, where a database is ranked in order of decreasing probability of bioactivity. Virtual screening is the name given to a range of computational techniques for searching a chemical database to assess the probability that each molecule will exhibit activity against a specified biological target [1]. If it is not possible to identify a common pharmacophore, as often occurs with heterogeneous sets of actives, and if significant numbers of both active and inactive molecules are available, (page number not for citation purposes)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have