Aristos Aristodimou1, Athos Antoniades2, Efthimios Dardiotis3, Eleni Loizidou4,5, George Spyrou6, Christina Votsi7, Christodoulou Kyproula7, Marios Pantzaris8, Nikolaos Grigoriadis9, Georgios Hadjigeorgiou10, Theodoros Kyriakides11, Constantinos Pattichi1,12. 1. Department of Computer ScienceUniversity of Cyprus Nicosia 1678 Cyprus. 2. Stremble Ventures Ltd. Limassol 59 4042 Cyprus. 3. Department of Neurology, Faculty of MedicineUniversity of Thessaly Volos 38221 Greece. 4. Department of Hygiene and EpidemiologyUniversity of Ioannina Ioannina 451 10 Greece. 5. Institute for BioinnovationBiomedical Sciences Research Center Alexander Fleming, Athens, 16672 Greece. 6. Bioinformatics Department and Cyprus School of Molecular MedicineCyprus Institute of Neurology and Genetics Nicosia 2371 Cyprus. 7. Neurogenetics Department and Cyprus School of Molecular MedicineCyprus Institute of Neurology and Genetics Nicosia 2371 Cyprus. 8. Department of Neurology and Cyprus School of Molecular MedicineCyprus Institute of Neurology and Genetics Nicosia 2371 Cyprus. 9. Department of Neurology IIAristotle University of Thessaloniki Thessaloniki 541 24 Greece. 10. Medical SchoolUniversity of Cyprus Nicosia 1678 Cyprus. 11. Department of Basic and Clinical SciencesMedical School University of Nicosia Nicosia 1678 Cyprus. 12. Biomedical Engineering Research CentreUniversity of Cyprus Nicosia 1678 Cyprus.
Abstract
Goal: Most common diseases are influenced by multiple gene interactions and interactions with the environment. Performing an exhaustive search to identify such interactions is computationally expensive and needs to address the multiple testing problem. A four-step framework is proposed for the efficient identification of n-Way interactions. Methods: The framework was applied on a Multiple Sclerosis dataset with 725 subjects and 147 tagging SNPs. The first two steps of the framework are quality control and feature selection. The next step uses clustering and binary encodes the features. The final step performs the n-Way interaction testing. Results: The feature space was reduced to 7 SNPs and using the proposed binary encoding, more 2-SNP and 3-SNP interactions were identified compared to using the initial encoding. Conclusions: The framework selects informative features and with the proposed binary encoding it is able to identify more n-way interactions by increasing the power of the statistical analysis.
Goal: Most common diseases are influenced by multiple gene interactions and interactions with the environment. Performing an exhaustive search to identify such interactions is computationally expensive and needs to address the multiple testing problem. A four-step framework is proposed for the efficient identification of n-Way interactions. Methods: The framework was applied on a Multiple Sclerosis dataset with 725 subjects and 147 tagging SNPs. The first two steps of the framework are quality control and feature selection. The next step uses clustering and binary encodes the features. The final step performs the n-Way interaction testing. Results: The feature space was reduced to 7 SNPs and using the proposed binary encoding, more 2-SNP and 3-SNP interactions were identified compared to using the initial encoding. Conclusions: The framework selects informative features and with the proposed binary encoding it is able to identify more n-way interactions by increasing the power of the statistical analysis.
Authors: Angeline S Andrew; Margaret R Karagas; Heather H Nelson; Simonetta Guarrera; Silvia Polidoro; Sara Gamberini; Carlotta Sacerdote; Jason H Moore; Karl T Kelsey; Eugene Demidenko; Paolo Vineis; Giuseppe Matullo Journal: Hum Hered Date: 2007-09-26 Impact factor: 0.444
Authors: Katherine M Kocan; Zorica Zivkovic; Edmour F Blouin; Victoria Naranjo; Consuelo Almazán; Ruchira Mitra; José de la Fuente Journal: BMC Dev Biol Date: 2009-07-16 Impact factor: 1.978
Authors: Ting Hu; Yuanzhu Chen; Jeff W Kiralis; Ryan L Collins; Christian Wejse; Giorgio Sirugo; Scott M Williams; Jason H Moore Journal: J Am Med Inform Assoc Date: 2013-02-08 Impact factor: 4.497