Next Article in Journal
3D-QSAR STUDY OF NEW ACETYL-COA:CHOLESTEROL O-ACYL TRANSFERASE (ACAT) INHIBITORS
Previous Article in Journal
Quantitative Structure-Property Study on Pyrazines with Bell Pepper Flavor
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Sci. Pharm.
Volume 68
Issue 1
10.3797/scipharm.aut-00-05
scipharm-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles thumb_up
...
Endorse textsms
...
Comment
Scientia Pharmaceutica is published by MDPI from Volume 84 Issue 3 (2016). Previous articles were published by another publisher in Open Access under a CC-BY (or CC-BY-NC-ND) licence, and they are hosted by MDPI on mdpi.com as a courtesy and upon agreement with Austrian Pharmaceutical Society (Österreichische Pharmazeutische Gesellschaft, ÖPhG).
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Artificial Neural Networks in Drug Design 11: Influence of Learning Rate and Momentum Factor on the Predictive Ability †

by
D. Kaiser
1,
C. Tmej
1,
P. Chiba
2,
K.-J. Schaper
3 and
G. Ecker
1,*
1
Institute of Pharmaceutical Chemistry, University of Vienna, Althanstraβe 14, A-1090 Vienna, Austria
2
Institute of Medical Chemistry, University of Vienna, Wiihringerstraβe 10, A-1090 Vienna, Austria
3
Medicinal and Pharmaceutical Chemistry, Research Center Borstel, Parkallee 1-40, D-23845 Borstel, Germany
*
Author to whom correspondence should be addressed.
†
Dedicated to Univ.-Prof. Dr. W. Kubelka on the occasion of his 65th birthday
Sci. Pharm. 2000, 68(1), 57-64; https://doi.org/10.3797/scipharm.aut-00-05
Submission received: 27 January 2000 / Revised: 3 March 2000 / Accepted: 3 March 2000 / Published: 6 March 2000
Versions Notes

Abstract

A data set of 48 propafenone-type modulators of multidrug resistance was used to investigate the influence of learning rate and momentum factor on the predictive power of artificial neural networks of different architecture. Generally, small learning rates and medium sized momentum factors are preferred. Some of the networks showed higher cross validated Q2 values than the corresponding linear model (0.87 vs. 0.83). Screening of a 158 compound virtual library identified several new lead compounds with activities in the nanomolar range.
Keywords: Modulators of multidrug resistance; propafenone; artificial neural network; P-glycoprotein Modulators of multidrug resistance; propafenone; artificial neural network; P-glycoprotein

Share and Cite

MDPI and ACS Style

Kaiser, D.; Tmej, C.; Chiba, P.; Schaper, K.-J.; Ecker, G. Artificial Neural Networks in Drug Design 11: Influence of Learning Rate and Momentum Factor on the Predictive Ability. Sci. Pharm. 2000, 68, 57-64. https://doi.org/10.3797/scipharm.aut-00-05

AMA Style

Kaiser D, Tmej C, Chiba P, Schaper K-J, Ecker G. Artificial Neural Networks in Drug Design 11: Influence of Learning Rate and Momentum Factor on the Predictive Ability. Scientia Pharmaceutica. 2000; 68(1):57-64. https://doi.org/10.3797/scipharm.aut-00-05

Chicago/Turabian Style

Kaiser, D., C. Tmej, P. Chiba, K.-J. Schaper, and G. Ecker. 2000. "Artificial Neural Networks in Drug Design 11: Influence of Learning Rate and Momentum Factor on the Predictive Ability" Scientia Pharmaceutica 68, no. 1: 57-64. https://doi.org/10.3797/scipharm.aut-00-05

Article Metrics

Back to TopTop