**5. Conclusion**

*3.3.3. Support Vector Machine*

350 Recent Advances in Autism Spectrum Disorders - Volume I

mizing the margin and minimizing the number of errors.

segments and the *y*-axis represents the percentage average LOOCV accuracy.

ments and the *y*-axis shows the average LOOCV accuracy.

**4. Validation of the predicted variant segments**

method [62].

The Support Vector Machine (SVM) belongs to a new generation of learning system based on recent advances in statistical learning theory [65]. A linear SVM, which is used in our sys‐ tem, aims to find the separating hyper-plane with the largest margin, defined as the sum of the distances from a hyper-plane (implied by a linear classifier) to the closest positive and negative exemplars. The expectation is that the larger the margin, the better the generaliza‐ tion of the classifier. In a non-separable case, a linear SVM seeks a trade-off between maxi‐

**Figure 6.** Comparison study of the performance of the three tested classifiers. The *x*-axis represents the number of

Figure 6 illustrates the LOOCV classification accuracies using the tested classifiers, *k*-NN, NN, and SVM. The *x*-axis is associated with the number of selected top-ranked variant seg‐

To evaluate our predictive power of our method in detecting and identifying patients with ASD, we use molecular test, quantitative Polymerase Chain Reaction (qPCR). It is a very sensitive and precise tool used for the quantification of nucleic acids. It can detect and quantify very small amounts of specific nucleic acid sequence. It is based on the method of PCR, developed by Kary Mullis in the 1980s. It allows the amplification of specific nucleic acid sequence (DNA) more than a billion-fold. Using qPCR allows scientists to quantify the starting amount of a specific DNA sequence in the sample before the amplification by PCR

The etiology of Autism spectrum disorders involves genetic and environmental risk factors. In this chapter, we have discussed the genetics basis of the complex disorder, autism. With the recent advances in the new screening technologies to investigate the entire genome such as array comparative genomic hybridization (aCGH) and whole genome sequencing, pro‐ vide the opportunities insight into the pattern of the genetic variations and reveal their roles in the genetic diseases. In this study, we have demonstrated an overview for the analysis of genetic variations in the form of DNA copy number changes and their association with au‐ tism susceptibility.

[5] Marshall, C. R., Noor, A., Vincent, J. B., Lionel, A. C., Feuk, L., Skaug, J., Shago, M., Moessner, R., Pinto, D., & Ren, Y. (2008). Structural variation of chromosomes in au‐

Discovering the Genetics of Autism http://dx.doi.org/10.5772/ 53797 353

[6] Sebat, J., Lakshmi, B., Malhotra, D., Troge, J., Lese-Martin, C., Walsh, T., Yamrom, B., Yoon, S., Krasnitz, A., & Kendall, J. (2007). Strong association of de novo copy num‐

[7] Kirov, G., Gumus, D., Chen, W., Norton, N., Georgieva, L., Sari, M., O'Donovan, M. C., Erdogan, F., Owen, , & Ropers, H. H. (2008). Comparative genome hybridization suggests a role for NRXN1 and APBA2 in schizophrenia. *Human Molecular Genetics*,

[8] Sharp, A. J., Hansen, S., Selzer, R. R., Cheng, Z., Regan, R., Hurst, J. A., Stewart, H., Price, S. M., Blair, E., & Hennekam, R. C. (2006). Discovery of previously unidentified genomic disorders from the duplication architecture of the human genome. *Nature*

[9] Sharp, A. J., Mefford, H. C., Li, K., Baker, C., Skinner, C., Stevenson, R. E., Schroer, R. J., Novara, F., De Gregori, M., & Ciccone, R. (2008). A recurrent 15q13.3 microdele‐ tion syndrome associated with mental retardation and seizures. *Nature Genetics*,

[10] Cantor, R. M., & Geschwind, D. H. (2008). Schizophrenia: genome, interrupted. *Neu‐*

[11] Stefansson, H., Rujescu, D., Cichon, S., Pietilainen, O. P., Ingason, A., Steinberg, S., Fossdal, R., Sigurdsson, E., Sigmundsson, T., & Buizer-Voskamp, J. E. (2008). Large recurrent microdeletions associated with schizophrenia. *Nature,*, 455(7210), 232-236. [12] Stone, J. L., O'Donovan, M. C., Gurling, H., Kirov, G. K., Blackwood, D. H., Corvin, A., Craddock, N. J., Gill, M., Hultman, C. M., & Lichtenstein, P. (2008). Rare chromo‐ somal deletions and duplications increase risk of schizophrenia. *Nature,*, 455(7210),

[13] Walsh, T., Mc Clellan, J. M., Mc Carthy, S. E., Addington, A. M., Pierce, S. B., Cooper, G. M., Nord, , Kusenda, M., Malhotra, D., & Bhandari, A. (2008). Rare structural var‐ iants disrupt multiple genes in neurodevelopmental pathways in schizophrenia. *Sci‐*

[14] Estivill, X., & Armengol, L. (2007). Copy number variants and common disorders: filling the gaps and exploring complexity in genome-wide association studies. *PLoS*

[15] Greer, M. K., Brown, F. R., Pai, G. S., Choudry, S. H., & Klein, A. J. (1997). Cognitive, adaptive, and behavioral characteristics of Williams syndrome. *American Journal of*

[16] Somerville, M. J., Mervis, C. B., Young, E. J., Seo, E. J., del Campo, M., Bamforth, S., Peregrine, E., Loo, W., Lilley, M., & Perez-Jurado, L. A. (2005). Severe expressive-lan‐

tism spectrum disorder. *American Journal of Human Genetics,*, 82(2), 477-488.

ber mutations with autism. *Science,*, 316(5823), 445-449.

17(3), 458-465.

40(3), 322-328.

237-241.

*ron,*, 58(2), 165-167.

*ence*, 320(5875), 539-543.

*Genetics*, 3(10), 1787-1799.

*Human Genetics,*, 74(5), 521-525.

*Genetics*, 38(9), 1038-1042.

Through mathematical-based models and computational-based approaches, we analyze the genetic data trying to discover and identify the relationship between the structural chromoso‐ mal rearrangements along the genome and the targeted disorder, ASD. In conclusion, the results show strong evidence that the genetic variations contribute in the complex disorder, autism.
