Liking score

Fig. 17.6 Distribution of predicted drug-like scores for the test sets of ACD (dashed line) and WDI (continuous line) compounds.

Ertl P, Roggo S, Schuffenhauer A. (2008) Natural product-likeness score and its application for prioritization of compound hbraries. J Chem Inf Model 48 68-74. 

Figure 13.2 Multiple property-based library shaping. Property distributions are shown for the raw collection (gray bars) and for the selected library members (black bars). The drug-likeness score corresponds to the output value of an artificial neural network, where a value of 1 indicates maximal drug-likeness (for details, see the text). The rule-of-5 violations are counted per molecule.

Drug-like scores are frequently the result of binary classification models, vhich evaluate the potential biological behavior of a molecule on the basis of a number of contemporarily occurring structural features and molecular property values. 

The drug-like score s of a compound is finally calculated by adding the weights for each substructural feature present in the considered compound as... 

This is a drug-like score derived by a substructural analysis approach used to calculate biological activity profiles, which contain weights that describe the differential occurrences of selected molecular properties in active and inactive molecules [Gillet, Willett et al, 1998]. 

A similar scoring function calculated by PLS-DA applied to the Daylight jingerprints was called Daylight-FingerPrint drug-like Score (DFPS) [Oprea, 2000]. 

Table S4 MAMMA drug-like and lead-like scores, x is the value of the considered property.

Considering these observations, we decided not to implicate directly the interface value in the scoring functions. On the contrary, we preferred to use this parameter in the form of a penalty-like score, when the interface value is less than 1200 A. When completing our knowledge-based recognition score with the interface contribution, we thus obtained the final expression of the PP geometric score ... 

Research in this area continues, with recent approaches using a fragmentation based method that looks at the co-occurrence of structural fragments present in known drugs to yield a drug like score for a novel molecule. ... 

Progressive drug-like score Progressive lead-like score Using Autodock Vina... 

Table 12.1 shows a fictional example of how a table of raw data might look (taken from Piqueras-Fiszman et al. s 2011 data). In this case, it represents data from a free word elicitation (or word association task), where liking scores for each yoghurt product were collected as well (note that, as mentioned previously, several other measures could be included in the table, but this is a simplified example). 

Respondents Perceived intensity Liking scores Ideal Profiles Deviation (perceived- ideal)... 

In IPM, the liking score is considered as a weighted linear combination of the distances between the attributes levels and their corresponding ideals (Equation [14.2] van Trijp et al, 2007 Worch et al, 2010b). 

A second limitation that it is important to point out is that in these procedures, only the linear relationship between attributes level and liking scores are considered. Although in some cases quadratic effects would be a better fit, in our experience linear relationships are often sufficient to evaluate the consistency of the ideal products. 

---