Comparison of Fingerprint-Based Methods for Virtual Screening Using Multiple Bioactive Reference Structures

Hert, Jérôme; Willett, Peter; Wilton, David J.; Acklin, Pierre; Azzaoui, Kamal; Jacoby, Edgar; Schuffenhauer, Ansgar

doi:10.1021/ci034231b

Cited by 309 publications

(456 citation statements)

References 31 publications

Supporting

Mentioning

441

Contrasting

Unclassified

Order By: Relevance

“…[34] The results were unequivocal in highlighting the effectiveness of group fusion, and this finding was confirmed in other studies that compared it with similarity fusion and with conventional similarity searching across a range of types of bioactivity data. [35][36] The advantages of group fusion were greatest when searching for structurally diverse sets of bioactive molecules, suggesting its use in the scaffoldhopping and bioisostere studies that are of particular importance in the lead-discovery stage of drug research.…”

Section: Data Fusionsupporting

confidence: 66%

Chemoinformatics at the University of Sheffield 2002–2014

Gillet

Holliday

Willett

2015

Molecular Informatics

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Data Fusionsupporting

confidence: 66%

Chemoinformatics at the University of Sheffield 2002–2014

Gillet

Holliday

Willett

2015

Molecular Informatics

Self Cite

View full text Add to dashboard Cite

show abstract

“…11 More recently, the same phenomena has been reported in information retrieval (IR) and molecular similarity measurements. [12][13][14][15][16][17] Charifson et al 11 presented a computational study in which they used an intersection-based consensus approach to combine scoring functions. They showed an enrichment in the ability to discriminate between active and inactive enzyme inhibitors for three different enzymes (p38 MAP kinase, inosine monophosphate dehydrogenase, and HIV protease) using two different docking methods (DOCK 18 and GAMBLER) and 13 scoring functions.…”

Section: Introductionmentioning

confidence: 99%

Consensus Scoring Criteria for Improving Enrichment in Virtual Screening

Yang

Chen

Shen

et al. 2005

J. Chem. Inf. Model.

222

240

View full text Add to dashboard Cite

Motivation: Virtual screening of molecular compound libraries is a potentially powerful and inexpensive method for the discovery of novel lead compounds for drug development. The major weakness of virtual screeningsthe inability to consistently identify true positives (leads)sis likely due to our incomplete understanding of the chemistry involved in ligand binding and the subsequently imprecise scoring algorithms. It has been demonstrated that combining multiple scoring functions (consensus scoring) improves the enrichment of true positives. Previous efforts at consensus scoring have largely focused on empirical results, but they have yet to provide a theoretical analysis that gives insight into real features of combinations and data fusion for virtual screening. Results: We demonstrate that combining multiple scoring functions improves the enrichment of true positives only if (a) each of the individual scoring functions has relatively high performance and (b) the individual scoring functions are distinctive. Notably, these two prediction variables are previously established criteria for the performance of data fusion approaches using either rank or score combinations. This work, thus, establishes a potential theoretical basis for the probable success of data fusion approaches to improve yields in in silico screening experiments. Furthermore, it is similarly established that the second criterion (b) can, in at least some cases, be functionally defined as the area between the rank versus score plots generated by the two (or more) algorithms. Because rank-score plots are independent of the performance of the individual scoring function, this establishes a second theoretically defined approach to determining the likely success of combining data from different predictive algorithms. This approach is, thus, useful in practical settings in the virtual screening process when the performance of at least two individual scoring functions (such as in criterion a) can be estimated as having a high likelihood of having high performance, even if no training sets are available. We provide initial validation of this theoretical approach using data from five scoring systems with two evolutionary docking algorithms on four targets, thymidine kinase, human dihydrofolate reductase, and estrogen receptors of antagonists and agonists. Our procedure is computationally efficient, able to adapt to different situations, and scalable to a large number of compounds as well as to a greater number of combinations. Results of the experiment show a fairly significant improvement (vs single algorithms) in several measures of scoring quality, specifically "goodness-of-hit" scores, false positive rates, and "enrichment". This approach (available online at http://gemdock.life. nctu.edu.tw/dock/download.php) has practical utility for cases where the basic tools are known or believed to be generally applicable, but where specific training sets are absent.

show abstract

“…9,10 It is evident, that the RTR fulfills both goals of VS validation as stated above: comparability of methods and estimation of the expected hit number. Often so-called "enrichment factors" (EF) 11 are calculated from the RTR, that are meant to normalize to the null hypothesis of uniformly distributed active molecules in the final ranking list.…”

Section: Introductionmentioning

confidence: 85%

“…9,10 The similarity of each molecule in the screened database (here the validation set) with each molecule in the query is calculated, and the maximum of these values of similaritysi.e. the nearest neighbor similaritysis used to rank-order the molecules in the search output.…”

Section: Compilation and Preparation Of Benchmark Datamentioning

confidence: 99%

Impact of Benchmark Data Set Topology on the Validation of Virtual Screening Methods: Exploration and Quantification by Spatial Statistics

Rohrer

Baumann

2008

J. Chem. Inf. Model.

View full text Add to dashboard Cite

A common finding of many reports evaluating ligand-based virtual screening methods is that validation results vary considerably with changing benchmark data sets. It is widely assumed that these data set specific effects are caused by the redundancy, self-similarity, and cluster structure inherent to those data sets. These phenomena manifest themselves in the data sets' representation in descriptor space, which is termed the data set topology. A methodology for the characterization of data set topology based on spatial statistics is introduced. The method is nonparametric and can deal with arbitrary distributions of descriptor values. With this methodology it is possible to associate differences in virtual screening performance on different data sets with differences in data set topology. Moreover, the better virtual screening performance of certain descriptors can be explained by their ability of representing the benchmark data sets by a more favorable topology. Finally it is shown, that the composition of some benchmark data sets causes topologies that lead to overoptimistic validation results even in very "simple" descriptor spaces. Spatial statistics analysis as proposed here facilitates the detection of such biased data sets and may provide a tool for the future design of unbiased benchmark data sets.

show abstract

Comparison of Fingerprint-Based Methods for Virtual Screening Using Multiple Bioactive Reference Structures

Cited by 309 publications

References 31 publications

Chemoinformatics at the University of Sheffield 2002–2014

Chemoinformatics at the University of Sheffield 2002–2014

Consensus Scoring Criteria for Improving Enrichment in Virtual Screening

Impact of Benchmark Data Set Topology on the Validation of Virtual Screening Methods: Exploration and Quantification by Spatial Statistics

Contact Info

Product

Resources

About