Recording Evolution Supervised by a Genetic Algorithm for Quantitative Structure-Activity Relationship Optimization

Journal Title: Applied Medical Informatics - Year 2010, Vol 26, Issue 2

Abstract

A genetic algorithm for structure-activity relationships optimization was developed and implemented. The genetic algorithm was designed to be feed with families of molecular descriptors, and was tested on Molecular Descriptors Family. The objective of the genetic algorithm was to optimize the multiple linear regressions with four descriptors for prediction of octanol-water partition coefficient (expressed in logarithmic scale) of a series of 206 polychlorinated biphenyls. Relevant factors for evolution were parameterized in the implementation of the evolutionary program. The configuration file allows running of the genetic algorithm under different settings of parameters. The defined parameters were parameters used to characterize the adaptation to the environment (three parameters), to characterize the breading sample (four), the reproduction (four), the evolution objective (two), the selection (ten), the survival (four), and the program execution (three).

Authors and Affiliations

Lorentz JÄNTSCHI, Sorana BOLBOACĂ, Radu SESTRAŞ

Keywords

Related Articles

Analysis of the Legal Aspects Concerning Data Protection in Electronic Medical Registry

The European and national legislation establish legal aspects regarding personal data protection in electronic records. The protection of medical personal data can be improved in relation with development of new modaliti...

Health Record in Occupational Medicine: Specific Aspects and Requirements of Data Structuring and Standardization

The service of occupational medicine of a specific economic agent, as integrated part of the System of Labor Health and Safety, requires efficient, well-organized information management through standardized and computeri...

Assessment of the Efficacy of Cardio-Metabolic Pathology Treatment and of the Medical Recommendations Adherence in a Military Population

[i][b]Aim[/b][/i]: To assess the efficacy of cardio-metabolic diseases treatment, the compliance to treatment, and to evaluate the obtained results compared to the previous published ones. [i][b]Methods[/b][/i][b][/b]:...

Risk Profile in a Sample of Patients with Breast Cancer from the Public Health Perspective

Cancer represents a major public health and economical burden in developed countries and has emerged as a major public health problem in developing countries, matching its effect in industrialized nations. Although there...

Risk Factors and Severity of Diabetic Retinopathy in Maramureş

Aims: We looked for the factors which can be adjust in order to reduce the frequency and severity of diabetic retinopathy in Maramureş County, Romania. Methods: We done a cross-sectional study of 1269 persons with dia...

Download PDF file
  • EP ID EP113326
  • DOI -
  • Views 70
  • Downloads 0

How To Cite

Lorentz JÄNTSCHI, Sorana BOLBOACĂ, Radu SESTRAŞ (2010). Recording Evolution Supervised by a Genetic Algorithm for Quantitative Structure-Activity Relationship Optimization. Applied Medical Informatics, 26(2), 89-100. https://europub.co.uk/articles/-A-113326