Moon, T Chi, MW Choi, MJ Yoon, CN 2024-01-21T06:41:10Z 2024-01-21T06:41:10Z 2021-09-05 2004-07-05 0960-894X https://pubs.kist.re.kr/handle/201004/137414 The multiple linear regression (MLR) analysis and back propagation neural networks (NN) were performed to examine the quantitative structure-polarization relationships (QSPR) for the formation of antibody-BTEX-EDF complex. Five descriptors out of 18 ones were selected for both MLR and NN, respectively, and the selected descriptors in MLR were the same as those in NN. These descriptors were the number of atoms, which can form hydrogen bonds (HA), connolly surface area (Area), the highest occupied molecular orbital energy (HOMO), partial charge of C-3 carbon atom (C-3) and HOMO pi coefficient of C-2 carbon atom (P-2). The fact that the descriptors in MLR are identical to those in NN suggests that these descriptors have good linear relationships and play a significant role in the formation of antibody-tracer complex. (C) 2004 Elsevier Ltd. All rights reserved. English PERGAMON-ELSEVIER SCIENCE LTD MICROFLUIDIC DEVICE NEURAL-NETWORK AIRBORNE BTEX BENZENE TOLUENE WATER Quantitative structure-polarization relationships (QSPR) study of BTEX tracers for the formation of antibody-BTEX-EDF complex Article 10.1016/j.bmcl.2004.04.063 1 BIOORGANIC & MEDICINAL CHEMISTRY LETTERS, v.14, no.13, pp.3461 - 3466 BIOORGANIC & MEDICINAL CHEMISTRY LETTERS 14 13 3461 3466 scie scopus 000221998100017 2-s2.0-2942620822 Chemistry, Medicinal Chemistry, Organic Pharmacology & Pharmacy Chemistry Article MICROFLUIDIC DEVICE NEURAL-NETWORK AIRBORNE BTEX BENZENE TOLUENE WATER BTEX tracer QSPR multiple linear regression neural network