Please use this identifier to cite or link to this item: http://repository.ipb.ac.id/handle/123456789/112860
Full metadata record
DC FieldValueLanguage
dc.contributor.advisorKusuma, Wisnu Ananta-
dc.contributor.authorRomdendine, Muhammad Fahrury-
dc.date.accessioned2022-07-27T00:18:20Z-
dc.date.available2022-07-27T00:18:20Z-
dc.date.issued2022-
dc.identifier.urihttp://repository.ipb.ac.id/handle/123456789/112860-
dc.description.abstractPrecision Medicine bertujuan untuk mendesain strategi pengobatan maupun pencegahan paling tepat terhadap suatu individu berdasarkan profil genetiknya. Profil genetik bisa didapatkan melalui penanda genetik yang bisa diidentifikasi menggunakan metode machine learning. Data penanda genetik seperti data Single Nucleotide Polymorphism (SNP) memiliki permasalahan high dimensionality data yang tidak bisa diatasi oleh metode regresi linear biasa. Pada penelitian ini digunakan metode regularisasi yaitu Elastic Net untuk membangun model prediktif untuk memprediksi nilai insulin tolerance yang merupakan fenotipe Type 2 Diabetes Mellitus (T2DM) sekaligus menyeleksi SNP yang signifikan. Hasil yang didapat menunjukkan Elastic Net mampu menyeleksi 201 SNP signifikan dari 690 SNP dengan galat yang rendah (MAE = 0,619) dan koefisien determinasi yang baik (R2 = 0,99). Sebanyak 201 SNP yang terseleksi merepresentasikan 36 gen yang paling berasosiasi dari 68 gen yang ada pada data. Sebanyak 77,8% gen yang didapatkan berhasil divalidasi menggunakan studi literatur sehingga dapat dikatakan Elastic Net memiliki kemampuan yang baik dalam mengasosiasikan SNP-Fenotipe T2DM. Hasil penelitian ini bermanfaat untuk membantu mengurangi ruang pencarian kandidat penanda genetik T2DM.id
dc.description.abstractPrecision medicine aimed to design the most precise strategy to medicate or prevent someone from a disease based on an individual genetic profile. Genetic profile could be obtained through machine learning identification of genetic marker. Genetic data such as single nucleotide polymorphism (SNP) has a high dimensionality problem that traditional linear regression could not overcome. Regularized method named Elastic Net were utilized in this research to build predictive model of insulin tolerance value which is a type 2 diabetes mellitus’s (T2DM) phenotype marker and selects most significant SNPs simultaneously. The results shown that Elastic Net selected 201 SNPs out of 690 SNPs with low error (MAE = 0.619) and good coefficient of determination (R2 = 0,99). 201 selected SNPs represented 36 most associated genes out of 68 genes. 77.8% genes were successfully validated using literature research thus proofing the performance of Elastic Net. The results are useful to narrow the search space of T2DM’s genetic marker candidates thus wet lab experiment would become more efficient.id
dc.description.sponsorshipTropical Biopharmaca Research Centerid
dc.language.isoidid
dc.publisherIPB Universityid
dc.titleAsosiasi Single Nucleotide Polymorphism dan Fenotipe pada Penyakit Diabetes Mellitus Tipe 2 Menggunakan Metode Elastic Netid
dc.title.alternativeAssociation of Single Nucleotide Polymorphism and Phenotype in Type 2 Diabetes Mellitus Using Elastic Net Methodid
dc.typeUndergraduate Thesisid
dc.subject.keywordassociationid
dc.subject.keywordT2DMid
dc.subject.keywordphenotypeid
dc.subject.keywordSNPid
dc.subject.keywordprecision medicineid
Appears in Collections:UT - Computer Science

Files in This Item:
File Description SizeFormat 
cover_fahrury.pdf
  Restricted Access
Cover800.33 kBAdobe PDFView/Open
G64180069_M.F.Romdendine.pdf
  Restricted Access
Fullteks1.67 MBAdobe PDFView/Open
lampiran_fahrury.pdf
  Restricted Access
Lampiran443.95 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.