Lumbanraja, Favorisen R and Mahesworo, Bharuno and Cenggoro, Tjeng Wawan and Budiarto, Arif and Pardanean, Bens (2019) An Evaluation of Deep Neural Network Performance on Limited Protein Phosphorylation Site Prediction Data. Procedia Computer Science, 157. pp. 25-30. ISSN 1877-0509

1-s2.0-S1877050919310555-main.pdf - Published Version

Download (312kB) | Preview
Official URL:


One of the common and important post-translational modification (PTM) types is phosphorylation. Protein phosphorylation is used to regulate various enzyme and receptor activations which include signal pathways. There have been many significant studies conducted to predict phosphorylation sites using various machine learning methods. Recently, several researchers claimed deep learning based methods as the best methods for phosphorylation sited prediction. However, the performance of these methods were backed up with the massive training data used in the researches. In this paper, we study the performance of simple deep neural network on the limited data generally used prior to deep learning employment. The result shows that a deep neural network can still achieve comparable performance in the limited data settings.

Item Type: Article
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Fakultas Matematika dan Ilmu Pengetahuan Alam (FMIPA) > Prodi Ilmu Komputer
Depositing User: Favorisen R Lumbanraja
Date Deposited: 04 Nov 2019 02:56
Last Modified: 04 Nov 2019 02:56

Actions (login required)

View Item View Item