Abstract
BackgroundCheminformaticians are equipped with a very rich toolbox when carrying out molecular similarity calculations. A large number of molecular representations exist, and there are several methods (similarity and distance metrics) to quantify the similarity of molecular representations. In this work, eight well-known similarity/distance metrics are compared on a large dataset of molecular fingerprints with sum of ranking differences (SRD) and ANOVA analysis. The effects of molecular size, selection methods and data pretreatment methods on the outcome of the comparison are also assessed.ResultsA supplier database (https://mcule.com/) was used as the source of compounds for the similarity calculations in this study. A large number of datasets, each consisting of one hundred compounds, were compiled, molecular fingerprints were generated and similarity values between a randomly chosen reference compound and the rest were calculated for each dataset. Similarity metrics were compared based on their ranking of the compounds within one experiment (one dataset) using sum of ranking differences (SRD), while the results of the entire set of experiments were summarized on box and whisker plots. Finally, the effects of various factors (data pretreatment, molecule size, selection method) were evaluated with analysis of variance (ANOVA).ConclusionsThis study complements previous efforts to examine and rank various metrics for molecular similarity calculations. Here, however, an entirely general approach was taken to neglect any a priori knowledge on the compounds involved, as well as any bias introduced by examining only one or a few specific scenarios. The Tanimoto index, Dice index, Cosine coefficient and Soergel distance were identified to be the best (and in some sense equivalent) metrics for similarity calculations, i.e. these metrics could produce the rankings closest to the composite (average) ranking of the eight metrics. The similarity metrics derived from Euclidean and Manhattan distances are not recommended on their own, although their variability and diversity from other similarity metrics might be advantageous in certain cases (e.g. for data fusion). Conclusions are also drawn regarding the effects of molecule size, selection method and data pretreatment on the ranking behavior of the studied metrics.Graphical A visual summary of the comparison of similarity metrics with sum of ranking differences (SRD).Electronic supplementary materialThe online version of this article (doi:10.1186/s13321-015-0069-3) contains supplementary material, which is available to authorized users.
Highlights
Cheminformaticians are equipped with a very rich toolbox when carrying out molecular similarity calculations
In this paper we present a large-scale comparison of eight commonly available similarity metrics (Tanimoto, Dice, Cosine, Substructure [24] and Superstructure [25] similarities, and similarity definitions derived from the Manhattan, Euclidean and Soergel distances, see Equation 1) based on their rankings of the same datasets, using analysis of variance (ANOVA) and sum of ranking differences (SRD) [26,27]
Input data generation Our general objective in this study was to compare similarity metrics on a dataset as large as possible
Summary
Cheminformaticians are equipped with a very rich toolbox when carrying out molecular similarity calculations. Previous work aiming to compare and assess such methods includes a 2009 article by Bender and coworkers, Bajusz et al Journal of Cheminformatics (2015) 7:20 in which 37 molecular fingerprints were compared and their similarities were quantified (based on their rankorderings of the same dataset) by means of statistical methods, such as principal component analysis (PCA) [5]. They were able to estimate the extent to which the information captured by these descriptors overlap, and to visualize them in a three-dimensional space. Based on their evaluation with the calculation of retrieval rates of active molecules, extended connectivity fingerprints performed best ( only slightly better from the runner-up SEFP4, LCFP4 and FCFP4/6 fingerprints), regardless of diameter (i.e. ECFP4 and ECFP6 performed well, the notations are explained in the corresponding reference) [6]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.