Editing Quantitative structure–activity relationship (section)

===Matched molecular pair analysis===
{{main|Matched molecular pair analysis}}

Typically QSAR models derived from non linear [[machine learning]] is seen as a "black box", which fails to guide medicinal chemists. Recently there is a relatively new concept of [[matched molecular pair analysis]]<ref name="Dossetter_2013">{{cite journal | vauthors = Dossetter AG, Griffen EJ, Leach AG | title = Matched molecular pair analysis in drug discovery | journal = Drug Discovery Today | volume = 18 | issue = 15–16 | pages = 724–31 | year = 2013 | pmid = 23557664 | doi = 10.1016/j.drudis.2013.03.003 }}</ref> or prediction driven MMPA which is coupled with QSAR model in order to identify activity cliffs.<ref name="Sushko_2014">{{cite journal | vauthors = Sushko Y, Novotarskyi S, Körner R, Vogt J, Abdelaziz A, Tetko IV | title = Prediction-driven matched molecular pairs to interpret QSARs and aid the molecular optimization process | journal = Journal of Cheminformatics | volume = 6 | issue = 1 | pages = 48 | year = 2014 | pmid = 25544551 | pmc = 4272757 | doi = 10.1186/s13321-014-0048-0 | doi-access = free }}</ref>