Machine learning approaches for phenotype-genotype mapping: predicting heterozygous mutations in the CYP21B gene from steroid profiles

Prank K, Schulze E, Eckert O, Nattkemper TW, Bettendorf M, Maser-Gluth C, Sejnowski TJ, Grote A, Penner E, von zur Muhlen A, Brabant G (2005)
EUROPEAN JOURNAL OF ENDOCRINOLOGY 153(2): 301-305.

Journal Article | Published | English

No fulltext has been uploaded

Author
; ; ; ; ; ; ; ; ; ;
Abstract
Objective: Non-linear relations between multiple biochemical parameters are the basis for the diagnosis of many diseases. Traditional linear analytical methods are not reliable predictors. Novel nonlinear techniques are increasingly used to improve the diagnostic accuracy of automated data interpretation. This has been exemplified in particular for the classification and diagnostic prediction of cancers based on expression profiling data. Our objective was to predict the genotype from complex biochemical data by comparing the performance of experienced clinicians to traditional linear analysis, and to novel non-linear analytical methods. Design and methods: As a model, we used a well-defined set of interconnected data consisting of unstimulated serum levels of steroid intermediates assessed in 54 subjects heterozygous for a mutation of the 21-hydroxylase gene (CYP21B) and in 43 healthy controls. Results: The genetic alteration was predicted from the pattern of steroid levels with an accuracy of 39% by clinicians and of 64% by linear analysis. In contrast, non-linear analysis, such as self-organizing artificial neural networks, support vector machines, and nearest neighbour classifiers, allowed for higher accuracy up to 83%. Conclusions: The successful application of these non-linear adaptive methods to capture specific biochemical problems may have generalized implications for biochemical testing in many areas. Nonlinear analytical techniques such as neural networks, support vector machines, and nearest neighbour classifiers may serve as an important adjunct to the decision process of a human investigator not ' trained ' in a specific complex clinical or laboratory setting and may aid them to classify the problem more directly.
Publishing Year
ISSN
eISSN
PUB-ID

Cite this

Prank K, Schulze E, Eckert O, et al. Machine learning approaches for phenotype-genotype mapping: predicting heterozygous mutations in the CYP21B gene from steroid profiles. EUROPEAN JOURNAL OF ENDOCRINOLOGY. 2005;153(2):301-305.
Prank, K., Schulze, E., Eckert, O., Nattkemper, T. W., Bettendorf, M., Maser-Gluth, C., Sejnowski, T. J., et al. (2005). Machine learning approaches for phenotype-genotype mapping: predicting heterozygous mutations in the CYP21B gene from steroid profiles. EUROPEAN JOURNAL OF ENDOCRINOLOGY, 153(2), 301-305.
Prank, K., Schulze, E., Eckert, O., Nattkemper, T. W., Bettendorf, M., Maser-Gluth, C., Sejnowski, T. J., Grote, A., Penner, E., von zur Muhlen, A., et al. (2005). Machine learning approaches for phenotype-genotype mapping: predicting heterozygous mutations in the CYP21B gene from steroid profiles. EUROPEAN JOURNAL OF ENDOCRINOLOGY 153, 301-305.
Prank, K., et al., 2005. Machine learning approaches for phenotype-genotype mapping: predicting heterozygous mutations in the CYP21B gene from steroid profiles. EUROPEAN JOURNAL OF ENDOCRINOLOGY, 153(2), p 301-305.
K. Prank, et al., “Machine learning approaches for phenotype-genotype mapping: predicting heterozygous mutations in the CYP21B gene from steroid profiles”, EUROPEAN JOURNAL OF ENDOCRINOLOGY, vol. 153, 2005, pp. 301-305.
Prank, K., Schulze, E., Eckert, O., Nattkemper, T.W., Bettendorf, M., Maser-Gluth, C., Sejnowski, T.J., Grote, A., Penner, E., von zur Muhlen, A., Brabant, G.: Machine learning approaches for phenotype-genotype mapping: predicting heterozygous mutations in the CYP21B gene from steroid profiles. EUROPEAN JOURNAL OF ENDOCRINOLOGY. 153, 301-305 (2005).
Prank, K, Schulze, E, Eckert, O, Nattkemper, Tim Wilhelm, Bettendorf, M, Maser-Gluth, C, Sejnowski, TJ, Grote, A, Penner, E, von zur Muhlen, A, and Brabant, G. “Machine learning approaches for phenotype-genotype mapping: predicting heterozygous mutations in the CYP21B gene from steroid profiles”. EUROPEAN JOURNAL OF ENDOCRINOLOGY 153.2 (2005): 301-305.
This data publication is cited in the following publications:
This publication cites the following data publications:

2 Citations in Europe PMC

Data provided by Europe PubMed Central.

Improving enzyme regulatory protein classification by means of SVM-RFE feature selection.
Fernandez-Lozano C, Fernandez-Blanco E, Dave K, Pedreira N, Gestal M, Dorado J, Munteanu CR., Mol Biosyst 10(5), 2014
PMID: 24556806
Markov mean properties for cell death-related protein classification.
Fernandez-Lozano C, Gestal M, Gonzalez-Diaz H, Dorado J, Pazos A, Munteanu CR., J. Theor. Biol. 349(), 2014
PMID: 24491256

30 References

Data provided by Europe PubMed Central.

Epileptic seizures can be anticipated by non-linear analysis.
Martinerie J, Adam C, Le Van Quyen M, Baulac M, Clemenceau S, Renault B, Varela FJ., Nat. Med. 4(10), 1998
PMID: 9771751
Steroid 21-hydroxylase deficiency: genotype may not predict phenotype.
Wilson RC, Mercado AB, Cheng KC, New MI., J. Clin. Endocrinol. Metab. 80(8), 1995
PMID: 7629224
Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks.
Khan J, Wei JS, Ringner M, Saal LH, Ladanyi M, Westermann F, Berthold F, Schwab M, Antonescu CR, Peterson C, Meltzer PS., Nat. Med. 7(6), 2001
PMID: 11385503
Delineation of prognostic biomarkers in prostate cancer.
Dhanasekaran SM, Barrette TR, Ghosh D, Shah R, Varambally S, Kurachi K, Pienta KJ, Rubin MA, Chinnaiyan AM., Nature 412(6849), 2001
PMID: 11518967

Export

0 Marked Publications

Open Data PUB

Web of Science

View record in Web of Science®

Sources

PMID: 16061837
PubMed | Europe PMC

Search this title in

Google Scholar