Visualization of Molecular Selectivity and Structure Generation for Selective Dopamine Inhibitors

Abstract

Activity landscapes were used in combination with atom colourings for the visualization of molecular selectivity. Multiple inhibitory activities in the dopamine family were selected in order to derive its molecular selectivity. All molecular structures were mapped in 2D chemical space by preserving the relative distance between any pair of molecules using multidimensional scaling. The values for the inhibitory activity against each dopamine isoenzyme (D2, D3, and D4) were added independently to the data points in 2D chemical space. Three activity landscapes were generated after carrying out colour-graded interpolation between the data points. The activity landscapes facilitated the detection of three specific active regions and the corresponding specific inhibitors for D2, D3, and D4 isoenzymes. Three support vector regression models were separately constructed using extended connectivity fingerprint descriptors and each inhibitory data set. By applying the atom scores along with the graded-colours to the specific inhibitors, the molecular selectivity differentiating each dopamine isoenzyme could be understood visually. Furthermore, the landscape technique was combined with structure generation to produce chemical structures that stay within the D3 specific active region.

e-Bitter: Bitterant Prediction by the Consensus Voting From the Machine-Learning Methods

“…In this work, feature importance of each ECFP bit is derived from the random forest (RF) after the five-fold cross-validation as mentioned above, and feature importance will be automatically linked to the corresponding fingerprint bit “1” and structural feature in our e-Bitter program. However, the feature importance from RF can only tell us whether these features are vital to the bitter/bitterless classification, but cannot inform us whether each ECFP bit “1” in a compound positively or negatively influences the bitterness, which can be described by the concept “feature partial derivative.” (Hasegawa et al, 2010 ; Marcou et al, 2012 ; Polishchuk, 2017 ).…”

“…The feature partial derivative, exactly defined by Equation (8) and Hasegawa et al ( 2010 ) is firstly proposed in the work of Byvatov and Schneider ( 2004 ) and is systematically reviewed in the work of Polishchuk ( 2017 ). To derive the feature partial derivative of each ECFP bit, the backward finite difference approach is adopted and briefly described as follows (Hasegawa et al, 2010 ).…”

“…The feature partial derivative, exactly defined by Equation (8) and Hasegawa et al ( 2010 ) is firstly proposed in the work of Byvatov and Schneider ( 2004 ) and is systematically reviewed in the work of Polishchuk ( 2017 ). To derive the feature partial derivative of each ECFP bit, the backward finite difference approach is adopted and briefly described as follows (Hasegawa et al, 2010 ). Firstly, the fingerprint bit nullification is simply done by the replacement of the bit “1” with zero, and then the difference between the predicted probabilities, from the original prediction and the new prediction after the bit nullification, is defined as the feature partial derivative for this fingerprint bit.…”

CompoundProtein Interaction Prediction Within Chemogenomics: Theoretical Concepts, Practical Usage, and Future Directions

“…Marcou et al [78] as well as Hasegawa et al [79] have both recently reported methodologies to accomplish this task (also see references therein). In both methods, the idea is to perturbate an atomic feature systematically and evaluate the extent to which the perturbation causes a change in predicted endpoint value.…”

Mining basic active structures from a large-scale database

“…While some research has focused on predicting biological activity based on these data, the results have not provided insight on characteristic structures [4,5]. Rough set and activity landscape methods have provided useful suggestions as to the active substructure, but the number of molecules in the datasets was limited [6,7]. …”