Author:
von Korff Modest,Sander Thomas
Abstract
In drug discovery, molecules are optimized towards desired properties. In this context, machine learning is used for extrapolation in drug discovery projects. The limits of extrapolation for regression models are known. However, a systematic analysis of the effectiveness of extrapolation in drug discovery has not yet been performed. In response, this study examined the capabilities of six machine learning algorithms to extrapolate from 243 datasets. The response values calculated from the molecules in the datasets were molecular weight, cLogP, and the number of sp3-atoms. Three experimental set ups were chosen for response values. Shuffled data were used for interpolation, whereas data for extrapolation were sorted from high to low values, and the reverse. Extrapolation with sorted data resulted in much larger prediction errors than extrapolation with shuffled data. Additionally, this study demonstrated that linear machine learning methods are preferable for extrapolation.
Subject
Pharmacology (medical),Pharmacology
Reference28 articles.
1. LIBSVM: A Library for Support Vector Machines;Chang;ACM Trans. Intell. Syst. Technol. (Tist).,2011
2. ChemAxon Chemical Hashed Fingerprint1998
3. QSAR Modeling: where Have You Been? Where Are You Going to?;Cherkasov;J. Med. Chem.,2014
4. Discovering Highly Potent Molecules from an Initial Set of Inactives Using Iterative Screening;Cortés-Ciriano;J. Chem. Inf. Model.,2018
5. Daylight Fingerprints1998
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献