Applying Novel Molecular Electronegativity‐Interaction Vector (MEIV) to QSPR Study on Collision Cross Section of Singly Protonated Peptides
Peng Zhou, Hui Zeng, Feifei Tian, Bo Li, Zhiliang Li · QSAR & Combinatorial Science · 2006
Abstract A novel electrotopological descriptor, Molecular Electronegativity‐Interaction Vector (MEIV), has been developed in this paper to characterize molecular structures of 420 singly protonated peptides. Three different modeling methods, as Multiple Linear Regression (MLR), Partial Least Squares (PLS), and Computational Neural Network (CNN), are utilized to explore peptide structures in relation with the Collision Cross Section (CCS). The resulting correlative coefficients R of MLR, PLS, and CNN are 0.988, 0.986, and 0.993, respectively, indicating that the MEIV descriptor is in favorable relation with CCS value, the relatationship is mainly linear with some nonlinear factors‥