A summary of the number of pathways, genes and gene pairs from different databases after normalization is given in Table 2. To tackle inconsistent molecular relationship representations, we also normalized the relationships of different databases into the IntPath unified relationship types as shown in Table 1.
We begin by describing molecular representations and different metrics used to quantify the similarity between pairs of molecules.
To do so, in Section 2, we first define the molecular representations and similarity scores to be used in the study.
We achieve compatible data formats, consistent molecular representations, consistent relationship representations, consistent referrals to pathway names and comprehensive data in our IntPath database for several organisms--viz., H. sapiens, S. cerevisiae, M. musculus and M. tuberculosis H37Rv.
To test the hypothesis whether a landscape and its activity cliffs are valid, we used several data sets and different molecular representations previously used to generate activity landscapes.
Results: We develop a new detailed theory of molecular similarity scores that can be applied to a variety of molecular representations and similarity measures.
CDPs portray the diversity calculated with three major molecular representations: molecular scaffolds, fingerprints, and physicochemical properties.
According to the different molecular representations, the molecular descriptors are divided into 20 logical blocks.
representations we are interested in.
Testing the statistical significance of molecular representations is a rational approach to select molecular representations to generate robust activity landscape models and identify statistically significant activity cliffs.
