Warszycki Dawid, Śmieja Marek, Kafel Rafał
Institute of Pharmacology, Polish Academy of Sciences, Smetna street 12, 31-343, Kraków, Poland.
Faculty of Mathematics and Computer Science, Jagiellonian University, 6 Lojasiewicza Street, 30-348, Kraków, Poland.
Mol Divers. 2017 May;21(2):407-412. doi: 10.1007/s11030-017-9729-8. Epub 2017 Feb 9.
The Average Information Content Maximization algorithm (AIC-MAX) based on mutual information maximization was recently introduced to select the most discriminatory features. Here, this methodology was applied to select the most significant bits from the Klekota-Roth fingerprint for serotonin receptors ligands as well as to select the most important features for distinguishing ligands with activity for one receptor versus another. The interpretation of selected bits and machine-learning experiments performed using the reduced interpretations outperformed the raw fingerprints and indicated the most important structural features of the analyzed ligands in terms of activity and selectivity. Moreover, the AIC-MAX methodology applied here for serotonin receptor ligands can also be applied to other target classes.
基于互信息最大化的平均信息内容最大化算法（AIC-MAX）最近被引入以选择最具区分性的特征。在此，该方法被应用于从Klekota-Roth指纹中为血清素受体配体选择最重要的位，以及选择用于区分对一种受体有活性与对另一种受体有活性的配体的最重要特征。对所选位的解释以及使用简化解释进行的机器学习实验优于原始指纹，并指出了所分析配体在活性和选择性方面最重要的结构特征。此外，这里应用于血清素受体配体的AIC-MAX方法也可应用于其他目标类别。
