MetIDB: a publicly accessible database of predicted and experimental 1H NMR spectra of flavonoids.

Identification of natural compounds, especially secondary metabolites, has been hampered by the lack of easy to use and accessible reference databases. Nuclear magnetic resonance (NMR) spectroscopy is the most selective technique for identification of unknown metabolites. High quality (1)H NMR (proton nuclear magnetic resonance) spectra combined with elemental composition obtained from mass spectrometry (MS) are essential for the identification process. Here, we present MetIDB, a reference database of experimental and predicted (1)H NMR spectra of 6000 flavonoids. By incorporating the stereochemistry, intramolecular interactions, and solvent effects into the prediction model, chemical shifts and couplings were predicted with great accuracy. A user-friendly web-based interface for MetIDB has been established providing various interfaces to the data and data-mining possibilities. For each compound, additional information is available comprising compound annotation, a (1)H NMR spectrum, 2D and 3D structure with correct stereochemistry, and monoisotopic mass as well as links to other web resources. The combination of chemical formula and (1)H NMR chemical shifts proved to be very efficient in metabolite identification, especially for isobaric compounds. Using this database, the process of flavonoid identification can then be significantly shortened by avoiding repetitive elucidation of already described compounds.

Performance of multicomponent self-organizing regression (MCSOR) in QSAR, QSPR, and multivariate calibration: comparison with partial least-squares (PLS) and validation with large external data sets.

A novel method for underdetermined regression problems, multicomponent self-organizing regression (MCSOR), has been recently introduced. Here, its performance is compared with partial least-squares (PLS), which is perhaps the most widely adopted multivariate method in chemometrics. A potpourri of models is presented, and MCSOR appears to provide highly predictive models that are comparable with or better than the corresponding PLS models in large internal (leave-one-out, LOO) and pseudo-external (leave-many-out, LMO) validation tests. The "blind" external predictive ability of MCSOR and PLS is demonstrated employing large melting point, factor Xa, log P and log S data sets. In a nutshell, MCSOR is fast, conceptually simple (employing multiple linear regression, MLR, as a statistical tool), and applicable to all kinds of multivariate problems with single Y-variable.

Improving the performance of SOMFA by use of standard multivariate methods.

Self-Organizing Molecular Field Analysis (SOMFA) comes with a built-in regression methodology, the Self-Organizing Regression (SOR), instead of relying on external methods such as PLS. In this article we present a proof of the equivalence between SOR and SIMPLS with one principal component. Thus, the modest performance of SOMFA on complex datasets can be primarily attributed to the low performance of the SOMFA regression methodology. A multi-component extension of the original SOR methodology (MCSOR) is introduced, and the performances of SOR, MCSOR and SIMPLS are compared using several datasets. The results indicate that in general the performance of SOMFA models is greatly improved if SOR is replaced with a more sophisticated regression method. The results obtained for the Cramer (CBG) dataset further underline the fact that it is a very poor benchmark dataset and should not be used to evaluate the performance of QSAR techniques.