Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universität Bonn, Dahlmannstrasse 2, D-53113 Bonn, Germany.
J Chem Inf Model. 2011 Oct 24;51(10):2496-506. doi: 10.1021/ci2003472. Epub 2011 Sep 16.
A statistical approach named the conditional correlated Bernoulli model is introduced for modeling of similarity scores and predicting the potential of fingerprint search calculations to identify active compounds. Fingerprint features are rationalized as dependent Bernoulli variables and conditional distributions of Tanimoto similarity values of database compounds given a reference molecule are assessed. The conditional correlated Bernoulli model is utilized in the context of virtual screening to estimate the position of a compound obtaining a certain similarity value in a database ranking. Through the generation of receiver operating characteristic curves from cumulative distribution functions of conditional similarity values for known active and random database compounds, one can predict how successful a fingerprint search might be. The comparison of curves for different fingerprints makes it possible to identify fingerprints that are most likely to identify new active molecules in a database search given a set of known reference molecules.
引入了一种名为条件相关 Bernoulli 模型的统计方法，用于对相似度得分进行建模，并预测指纹搜索计算识别活性化合物的潜力。指纹特征被合理化作为依赖的 Bernoulli 变量，并且评估了数据库化合物的 Tanimoto 相似度值给定参考分子的条件分布。在虚拟筛选的背景下，条件相关 Bernoulli 模型用于估计在数据库排名中获得特定相似度值的化合物的位置。通过从已知活性和随机数据库化合物的条件相似度值累积分布函数生成接收者操作特征曲线，可以预测指纹搜索的成功率。不同指纹的曲线比较使得可以识别在给定一组已知参考分子的情况下，在数据库搜索中最有可能识别新的活性分子的指纹。
