Loading...

QSRR study of psychiatric drugs using classification and regression trees combined with adaptive neuro-fuzzy inference system

Jalali Heravi, M ; Sharif University of Technology | 2008

609 Viewed
  1. Type of Document: Article
  2. DOI: 10.1002/qsar.200710111
  3. Publisher: 2008
  4. Abstract:
  5. A new Quantitative Structure-Retention Relationship (QSRR) approach was carried out for prediction of gas-liquid retention times of 124 psychiatric drugs in whole blood on fused-silica capillary column coated with crosslinked methylsilicone with nitrogen-phosphorus detection. After screening the descriptors, a total of 699 topological, geometric, and electronic descriptors (zero-to three-dimensional) representing various structural characteristics were calculated for each molecule in the dataset. Combined method of Classification and Regression Tree (CART) as a feature selection method for the extraction of four relevant descriptors and Adaptive Neuro-Fuzzy Inference System (ANFIS) as a modeling technique was used for the prediction of retention times of diverse set of psychiatric drugs. The Root Mean Square Errors (RMSEs) for the calibration and prediction sets are 0.457 and 0.514, respectively. © 2008 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim
  6. Keywords:
  7. Aminophenazone ; Chlorpheniramine ; Clenbuterol ; Clomethiazole ; Diphenhydramine ; Ephedrine ; Fenfluramine ; Fenproporex ; Fluoxetine ; Fluvoxamine ; Lidocaine ; Methylphenidate ; Metoprolol ; Metronidazole ; Nitrogen ; Oxprenolol ; Paracetamol ; Pethidine ; Phenazone ; Phenobarbital ; Phosphorus ; Piracetam ; Pyrithyldione ; Silicon dioxide ; Theobromine ; Thiopental ; Tramadol ; Trimetazidine ; Unindexed drug ; Viloxazine ; Analytical error ; Drug retention ; Fuzzy system ; Mathematical analysis ; Prediction ; Priority journal ; Quantitative structure activity relation ; Structure analysis
  8. Source: QSAR and Combinatorial Science ; Volume 27, Issue 6 , 2008 , Pages 729-739 ; 1611020X (ISSN)
  9. URL: https://onlinelibrary.wiley.com/doi/10.1002/qsar.200710111