This means that the highest information content lies in 'least informative' descriptors, and that overall expression levels ('sparseness' of expression) are important factors in functional prediction of genes based on their spatial expression.
As a first step, multiple linear regression (MLR) was employed to find informative descriptors that can predict the RRFs of these compounds.
The proposed method, denoted as H-ELM-E, effectively combines multiple complementary descriptors by a two-level ELM-E based architecture, which ensures that a more informative descriptors will gain more impact on the final decision.
Subsequent features from the top ten informative descriptors were also primarily hydrophobic in nature.
Notably, the top informative descriptors was the tripeptide RMY, which is comprised of the positively-charged Arg, the hydrophobic Met as well as the aromatic/hydrophobic Tyr.
Despite the numerous statistical approaches for feature or descriptor selection, real users that want to extract the most informative descriptors to understand or predict a property/activity still face an important challenge.
Recently, these charges have become popular in chemoinformatics, as they are informative descriptors that can be utilised in pharmacophore design, virtual screening, similarity searches etc. Especially conformationally-dependent charges perform very successfully.
Recently, partial atomic charges also became popular in chemoinformatics, as they proved to be informative descriptors for QSAR and QSPR modelling [1 9] and for other applications [10 12]; they can be utilised in pharmacophore design [13 15], virtual screening [16 18], similarity searches [19 21], molecular structure comparison [22 24] etc.
The correlations helped to recognize informative descriptors and to detect redundancies.
