Neural network analysis in pharmacogenetics of mood disorders

Alessandro Serretti, Enrico Smeraldi

Research output: Contribution to journalArticle

38 Citations (Scopus)

Abstract

Background: The increasing number of available genotypes for genetic studies in humans requires more advanced techniques of analysis. We previously reported significant univariate associations between gene polymorphisms and antidepressant response in mood disorders. However the combined analysis of multiple gene polymorphisms and clinical variables requires the use of non linear methods. Methods: In the present study we tested a neural network strategy for a combined analysis of two gene polymorphisms. A Multi Layer Perceptron model showed the best performance and was therefore selected over the other networks. One hundred and twenty one depressed inpatients treated with fluvoxamine in the context of previously reported pharmacogenetic studies were included. The polymorphism in the transcriptional control region upstream of the 5HTT coding sequence (SERTPR) and in the Tryptophan Hydroxylase (TPH) gene were analysed simultaneously. Results: A multi layer perceptron network composed by 1 hidden layer with 7 nodes was chosen. 77.5 % of responders and 51.2% of non responders were correctly classified (ROC area = 0.731 - empirical p value = 0.0082). Finally, we performed a comparison with traditional techniques. A discriminant function analysis correctly classified 34.1 % of responders and 68.1 % of non responders (F = 8.16 p = 0.0005). Conclusions: Overall, our findings suggest that neural networks may be a valid technique for the analysis of gene polymorphisms in pharmacogenetic studies. The complex interactions modelled through NN may be eventually applied at the clinical level for the individualized therapy.

Original languageEnglish
Article number27
JournalBMC Medical Genetics
Volume5
DOIs
Publication statusPublished - Dec 9 2004

Fingerprint

Mood Disorders
Neural Networks (Computer)
Genes
Fluvoxamine
Tryptophan Hydroxylase
Discriminant Analysis
Antidepressive Agents
Inpatients
Genotype
Pharmacogenomic Testing
Therapeutics

ASJC Scopus subject areas

  • Medicine(all)
  • Genetics(clinical)
  • Genetics

Cite this

Neural network analysis in pharmacogenetics of mood disorders. / Serretti, Alessandro; Smeraldi, Enrico.

In: BMC Medical Genetics, Vol. 5, 27, 09.12.2004.

Research output: Contribution to journalArticle

Serretti, Alessandro ; Smeraldi, Enrico. / Neural network analysis in pharmacogenetics of mood disorders. In: BMC Medical Genetics. 2004 ; Vol. 5.
@article{1351fca5e1ab44839d6819f35d3df32b,
title = "Neural network analysis in pharmacogenetics of mood disorders",
abstract = "Background: The increasing number of available genotypes for genetic studies in humans requires more advanced techniques of analysis. We previously reported significant univariate associations between gene polymorphisms and antidepressant response in mood disorders. However the combined analysis of multiple gene polymorphisms and clinical variables requires the use of non linear methods. Methods: In the present study we tested a neural network strategy for a combined analysis of two gene polymorphisms. A Multi Layer Perceptron model showed the best performance and was therefore selected over the other networks. One hundred and twenty one depressed inpatients treated with fluvoxamine in the context of previously reported pharmacogenetic studies were included. The polymorphism in the transcriptional control region upstream of the 5HTT coding sequence (SERTPR) and in the Tryptophan Hydroxylase (TPH) gene were analysed simultaneously. Results: A multi layer perceptron network composed by 1 hidden layer with 7 nodes was chosen. 77.5 {\%} of responders and 51.2{\%} of non responders were correctly classified (ROC area = 0.731 - empirical p value = 0.0082). Finally, we performed a comparison with traditional techniques. A discriminant function analysis correctly classified 34.1 {\%} of responders and 68.1 {\%} of non responders (F = 8.16 p = 0.0005). Conclusions: Overall, our findings suggest that neural networks may be a valid technique for the analysis of gene polymorphisms in pharmacogenetic studies. The complex interactions modelled through NN may be eventually applied at the clinical level for the individualized therapy.",
author = "Alessandro Serretti and Enrico Smeraldi",
year = "2004",
month = "12",
day = "9",
doi = "10.1186/1471-2350-5-27",
language = "English",
volume = "5",
journal = "BMC Medical Genetics",
issn = "1471-2350",
publisher = "BioMed Central",

}

TY - JOUR

T1 - Neural network analysis in pharmacogenetics of mood disorders

AU - Serretti, Alessandro

AU - Smeraldi, Enrico

PY - 2004/12/9

Y1 - 2004/12/9

N2 - Background: The increasing number of available genotypes for genetic studies in humans requires more advanced techniques of analysis. We previously reported significant univariate associations between gene polymorphisms and antidepressant response in mood disorders. However the combined analysis of multiple gene polymorphisms and clinical variables requires the use of non linear methods. Methods: In the present study we tested a neural network strategy for a combined analysis of two gene polymorphisms. A Multi Layer Perceptron model showed the best performance and was therefore selected over the other networks. One hundred and twenty one depressed inpatients treated with fluvoxamine in the context of previously reported pharmacogenetic studies were included. The polymorphism in the transcriptional control region upstream of the 5HTT coding sequence (SERTPR) and in the Tryptophan Hydroxylase (TPH) gene were analysed simultaneously. Results: A multi layer perceptron network composed by 1 hidden layer with 7 nodes was chosen. 77.5 % of responders and 51.2% of non responders were correctly classified (ROC area = 0.731 - empirical p value = 0.0082). Finally, we performed a comparison with traditional techniques. A discriminant function analysis correctly classified 34.1 % of responders and 68.1 % of non responders (F = 8.16 p = 0.0005). Conclusions: Overall, our findings suggest that neural networks may be a valid technique for the analysis of gene polymorphisms in pharmacogenetic studies. The complex interactions modelled through NN may be eventually applied at the clinical level for the individualized therapy.

AB - Background: The increasing number of available genotypes for genetic studies in humans requires more advanced techniques of analysis. We previously reported significant univariate associations between gene polymorphisms and antidepressant response in mood disorders. However the combined analysis of multiple gene polymorphisms and clinical variables requires the use of non linear methods. Methods: In the present study we tested a neural network strategy for a combined analysis of two gene polymorphisms. A Multi Layer Perceptron model showed the best performance and was therefore selected over the other networks. One hundred and twenty one depressed inpatients treated with fluvoxamine in the context of previously reported pharmacogenetic studies were included. The polymorphism in the transcriptional control region upstream of the 5HTT coding sequence (SERTPR) and in the Tryptophan Hydroxylase (TPH) gene were analysed simultaneously. Results: A multi layer perceptron network composed by 1 hidden layer with 7 nodes was chosen. 77.5 % of responders and 51.2% of non responders were correctly classified (ROC area = 0.731 - empirical p value = 0.0082). Finally, we performed a comparison with traditional techniques. A discriminant function analysis correctly classified 34.1 % of responders and 68.1 % of non responders (F = 8.16 p = 0.0005). Conclusions: Overall, our findings suggest that neural networks may be a valid technique for the analysis of gene polymorphisms in pharmacogenetic studies. The complex interactions modelled through NN may be eventually applied at the clinical level for the individualized therapy.

UR - http://www.scopus.com/inward/record.url?scp=26444561943&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=26444561943&partnerID=8YFLogxK

U2 - 10.1186/1471-2350-5-27

DO - 10.1186/1471-2350-5-27

M3 - Article

VL - 5

JO - BMC Medical Genetics

JF - BMC Medical Genetics

SN - 1471-2350

M1 - 27

ER -