TY - JOUR
T1 - Improved Prediction of Blood–Brain Barrier Permeability Through Machine Learning with Combined Use of Molecular Property-Based Descriptors and Fingerprints
AU - Yuan, Yaxia
AU - Zheng, Fang
AU - Zhan, Chang Guo
N1 - Publisher Copyright:
© 2018, American Association of Pharmaceutical Scientists.
PY - 2018/5/1
Y1 - 2018/5/1
N2 - Blood–brain barrier (BBB) permeability of a compound determines whether the compound can effectively enter the brain. It is an essential property which must be accounted for in drug discovery with a target in the brain. Several computational methods have been used to predict the BBB permeability. In particular, support vector machine (SVM), which is a kernel-based machine learning method, has been used popularly in this field. For SVM training and prediction, the compounds are characterized by molecular descriptors. Some SVM models were based on the use of molecular property-based descriptors (including 1D, 2D, and 3D descriptors) or fragment-based descriptors (known as the fingerprints of a molecule). The selection of descriptors is critical for the performance of a SVM model. In this study, we aimed to develop a generally applicable new SVM model by combining all of the features of the molecular property-based descriptors and fingerprints to improve the accuracy for the BBB permeability prediction. The results indicate that our SVM model has improved accuracy compared to the currently available models of the BBB permeability prediction.
AB - Blood–brain barrier (BBB) permeability of a compound determines whether the compound can effectively enter the brain. It is an essential property which must be accounted for in drug discovery with a target in the brain. Several computational methods have been used to predict the BBB permeability. In particular, support vector machine (SVM), which is a kernel-based machine learning method, has been used popularly in this field. For SVM training and prediction, the compounds are characterized by molecular descriptors. Some SVM models were based on the use of molecular property-based descriptors (including 1D, 2D, and 3D descriptors) or fragment-based descriptors (known as the fingerprints of a molecule). The selection of descriptors is critical for the performance of a SVM model. In this study, we aimed to develop a generally applicable new SVM model by combining all of the features of the molecular property-based descriptors and fingerprints to improve the accuracy for the BBB permeability prediction. The results indicate that our SVM model has improved accuracy compared to the currently available models of the BBB permeability prediction.
KW - blood–brain barrier permeability
KW - fingerprint
KW - modeling
KW - molecular descriptor
KW - physical property
UR - http://www.scopus.com/inward/record.url?scp=85044193486&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85044193486&partnerID=8YFLogxK
U2 - 10.1208/s12248-018-0215-8
DO - 10.1208/s12248-018-0215-8
M3 - Article
C2 - 29564576
AN - SCOPUS:85044193486
SN - 1550-7416
VL - 20
JO - AAPS Journal
JF - AAPS Journal
IS - 3
M1 - 54
ER -