On the information content of 2D and 3D descriptors for QSAR

Abstract

Com o objetivo de melhor entender as informações paramétricas contidas em descritores bidimensionais (2D) e tridimensionais (3D), os escores de 87 descritores 2D e 798 variáveis 3D (ALMOND) obtidos de uma série de 5998 compostos de interesse em química medicinal, foram analisados através de análise de componentes principais. A fração de variância explicada (r 2 ) e a validação cruzada (q 2 ) para sete grupos, em duas componentes PLS, foram de 40%. Uma análise individual dos componentes, mostra que as duas primeiras PCs obtidas a partir dos descritores 2D estão relacionadas com a primeira e terceira PCs dos descritores 3D. A primeira componente 3D é explicada (61%) por descritores relacionados ao tamanho, enquanto que o conteúdo da terceira é essencialmente hidrofóbico, mas com pequena variância (25%). Surpreendentemente, descritores relacionados a ligações hidrogênio não contribuíram de forma significativa para a análise final. Estes resultados não permitem, a priori, a escolha de um método em detrimento de outro, quando da realização de estudos em QSAR.To gain better understanding on the information content of two-dimensional (2D) vs. threedimensional (3D) descriptor systems, we analyzed principal component analysis scores derived from 87 2D descriptors and 798 3D (ALMOND) variables on a set of 5998 compounds of medicinal chemistry interest. The information overlap between ALMOND and 2D-based descriptors, as modeled by the fraction of explained variance (r 2 ) and by seven-groups cross-validation (q 2 ) in a two PLS components model was 40%. Individual component analysis indicates that the first and second principal components from the 2D-descriptors are related to the first and third dimensions from the ALMOND PCA model. The first ALMOND component is explained (61%) by size-related descriptors, whereas the third component is marginally explained (25%) by hydrophobicity-related descriptors. Surprisingly, 2D-based hydrogen-bonding descriptors did not contribute significantly in this analysis. These results do not a priori justify the choice of one methodology over the other, when performing QSAR studies. Keywords: ALMOND, cheminformatics, chemometrics, QSAR IntroductionThere are currently over 3000 molecular descriptors 1 that can be used in QSAR (Quantitative Structure Activity Relationship) studies.2 Their application to QSAR has been recently surveyed.3 Significant information about a QSAR dataset can be extracted using 2D-(two-dimensional) descriptors, i.e., descriptors that do not use information related to the three-dimensional characteristics of model compounds. Most of these descriptors can be classified as: i) Size-related: molecular weight -MW; calculated 4 molecular refractivity -CMR; molecular volume and molecular surface area, pre-computed from tabulated values (e.g., using Van The above types of descriptors have been successfully used to derive QSAR models for the past four decades. However, for the past 15 years, our ability to investigate the third dimension in a meaningful way, e.g., by analyz...

An automated PLS search for biologically relevant QSAR descriptors

“…The top 20 2Dprop descriptors, ranked according to the VIP sum and at two cumulative thresholds, is given in Table 2. Between 8 and 9 of these top 20 descriptors are size-related; this is not unexpected, since size covers 60% of the first latent variable in chemistry-and-property independent spaces [59,60]. Between 8 and 10 topological indices are also present in the top 20 list, whereas hydrophobicity is related to a maximum of three descriptors.…”

Optimization of CAMD techniques 3. Virtual screening enrichment studies: a help or hindrance in tool selection?

“…It can be seen that not all 3D methods outperform the 2D technique, highlighting potential analogue bias in the data as much as any shortcomings in screening technique. This is not a reflection on the relative merits of 2D versus 3D methods, both of which have significant utility and only limited information overlap [45]. Rather, the results highlight potential issues in interpreting said merits in the context of these target data.…”

Surrogate data – a secure way to share corporate data

“…However, in practice, one would like to use different sets of described in the method section. The 3D descriptors represent a very different method to describe the property of molecules, compared to topological indices; the overlap in information content between 2D and 3D descriptors has been estimated as 40% [25]. Surprisingly, the performance of the surrogate model for the prediction of the PHYS-PROP set was even better than the one based on the original molecules.…”