JURNAL INTERNASIONAL

Journal of Theoritical and Apllied Information Technology

---

For several years, many studies attempt to discover biological processes of disesase mechanisms. Nevertheless, they are still far from completeness of understanding. This problem is caused by the complexity of complex disease. To solve this problem, many computational methods have been developed to predict uncovered disease genes. A lot of genetic information from protein interaction network, gene expression, and genetic sequences has ben integrated. With these approaches,a large number of candidate genes are produced increasingly. Therefore, a techenique than can select only relevant genes is needed. Ranking techniques have been developed to prioritize the candidate genes. Still, the results are inconsistent among different methods. Thes incompatibilities might be caused from different types of features. In this study, we performed a prioritization analysis for investigating network topology features for predicting disease-related genes. Four standart network topological features were calculated on a protein-protein interction network and examined with 46 groups of disease. The features were ranked independently according to their values for a disease. Then, the performance of disease gene classification with each feature was calculated. The closeness centrality showed a superior ability to classify disease genes in overall disease groups. Selecting relevant features can greatly improve the performance in disease gene classification.

---

Ketersediaan

JI03220003

004.0285 JATIT J JurnalInternasional

Perpus STMIK (Jurnal Internasional)

Tersedia

Informasi Detail

Judul Seri

-

No. Panggil

004.0285 JATIT J JurnalInternasional

Penerbit

USA : JATIT., 2014

Deskripsi Fisik

-

Bahasa

English

ISBN/ISSN

1992 8645

Klasifikasi

004.0285

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

Volume 69 Nomor 1 Tahun 2014

Subjek

-

Info Detail Spesifik

-

Pernyataan Tanggungjawab

-

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus login sebelum memberikan komentar