Combination of a Naive Bayes Classifier with Consensus Scoring Improves Enrichment of High-Throughput Docking Results

Klon, Anthony E.; Glick, Meir; Davies, John W.

doi:10.1021/jm049970d

Cited by 64 publications

(61 citation statements)

References 11 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been reported that the median rank is more suitable than the average rank in consensus-scoring because the former is less sensitive to outliers [40].…”

Section: Consensus Scoringmentioning

confidence: 99%

Discovery of Plasmepsin Inhibitors by Fragment‐Based Docking and Consensus Scoring

Friedman

Caflisch

2009

ChemMedChem

View full text Add to dashboard Cite

Plasmepsins (PMs) are essential proteases of the plasmodia parasites and are therefore promising targets for developing drugs against malaria. We have discovered six inhibitors of PM II by high‐throughput fragment‐based docking of a diversity set of ∼40 000 molecules, and consensus scoring with force field energy functions. Using the common scaffold of the three most active inhibitors (IC50=2–5 μM), another seven inhibitors were identified by substructure search. Furthermore, these 13 inhibitors belong to at least three different classes of compounds. The in silico approach was very effective since a total of 13 active compounds were discovered by testing only 59 molecules in an enzymatic assay. This hit rate is about one to two orders of magnitude higher than those reported for medium‐ and high‐throughput screening techniques in vitro. Interestingly, one of the inhibitors identified by docking was halofantrine, an antimalarial drug of unknown mechanism. Explicit water molecular dynamics simulations were used to discriminate between two putative binding modes of halofantrine in PM II.

show abstract

“…It has been reported that the median rank is more suitable than the average rank in consensus-scoring because the former is less sensitive to outliers [40].…”

Section: Consensus Scoringmentioning

confidence: 99%

Discovery of Plasmepsin Inhibitors by Fragment‐Based Docking and Consensus Scoring

Friedman

Caflisch

2009

ChemMedChem

View full text Add to dashboard Cite

show abstract

“…Substructural analysis was studied in considerable detail by workers at the National Institutes of Health in an extended programme to develop novel anti-cancer agents [47][48][49], and also by workers at Lederle [29] and Sheffield [50][51][52]. However, it is only in the last few years that this general approach has become widely used [53][54][55][56][57][58][59][60][61][62].…”

Section: Substructural Analysis Naive Bayesian Classifiers and Groupmentioning

confidence: 99%

Evaluation of machine-learning methods for ligand-based virtual screening

Chen

Harrison

Papadatos

et al. 2007

J Comput Aided Mol Des

113

View full text Add to dashboard Cite

Abstract. Machine-learning methods can be used for virtual screening by analysing the structural characteristics of molecules of known (in)activity, and we here discuss the use of kernel discrimination and naive Bayesian classifier methods for this purpose. We report a kernel method that allows the processing of molecules represented by binary, integer and real-valued descriptors, and show that it is little different in screening performance from a previously described kernel that had been developed specifically for the analysis of binary fingerprint representations of molecular structure. We then evaluate the performance of a naive Bayesian classifier when the training-set contains only a very few active molecules. In such cases, a simpler approach based on group fusion would appear to provide superior screening performance, especially when structurally heterogeneous datasets are to be processed.

show abstract

“…66 Furthermore, the median rank is more suitable than the average rank in consensus-scoring because the former is less sensitive to outliers. 67 Rank by median consensus scoring was used in the in silico screening against plasmepsin and cathepsin B (Table 1). For plasmepsin, consensus scoring was preferred to ranking by LIECE because visual inspection of the best LIECE poses revealed several unlikely binding modes.…”

Section: Consensus Scoringmentioning

confidence: 99%

Library screening by fragment‐based docking

Huang

Caflisch

2009

J of Molecular Recognition

View full text Add to dashboard Cite

We review our computational tools for high-throughput screening by fragment-based docking of large collections of small molecules. Applications to six different enzymes, four proteases, and two protein kinases, are presented. Remarkably, several low-micromolar inhibitors were discovered in each of the high-throughput docking campaigns. Probable reasons for the lack of submicromolar inhibitors are the tiny fraction of chemical space covered by the libraries of available compounds, as well as the approximations in the methods employed for scoring, and the use of a rigid conformation of the target protein.

show abstract

Combination of a Naive Bayes Classifier with Consensus Scoring Improves Enrichment of High-Throughput Docking Results

Cited by 64 publications

References 11 publications

Discovery of Plasmepsin Inhibitors by Fragment‐Based Docking and Consensus Scoring

Discovery of Plasmepsin Inhibitors by Fragment‐Based Docking and Consensus Scoring

Evaluation of machine-learning methods for ligand-based virtual screening

Library screening by fragment‐based docking

Contact Info

Product

Resources

About