دانلود رایگان مقاله انگلیسی پیش بینی محلی سازی زیرسلولی های پروتئین انسانی با استفاده از یادگیری عمیق - الزویر 2018

Abstract

Protein subcellular localization (PSL), as one of the most critical characteristics of human cells, plays an important role for understanding specific functions and biological processes in cells. Accurate prediction of protein subcellular localization is a fundamental and challenging problem, for which machine learning algorithms have been widely used. Traditionally, the performance of PSL prediction highly depends on handcrafted feature descriptors to represent proteins. In recent years, deep learning has emerged as a hot research topic in the field of machine learning, achieving outstanding success in learning high-level latent features within data samples. In this paper, to accurately predict protein subcellular locations, we propose a deep learning based predictor called DeepPSL by using Stacked Auto-Encoder (SAE) networks. In this predictor, we automatically learn high-level and abstract feature representations of proteins by exploring non-linear relations among diverse subcellular locations, addressing the problem of the need of handcrafted feature representations. Experimental results evaluated with 3-fold cross validation show that the proposed DeepPSL outperforms traditional machine learning based methods. It is expected that DeepPSL, as the first predictor in the field of PSL prediction, has great potential to be a powerful computational method complementary to existing tools.

Conclusion

In this paper, we have proposed a deep architecture, namely DeepPSL, for the classification of protein subcellular localizations. Unlike existing machine learning based methods that consider only handcrafted features extracted directly from protein primary sequences, the proposed predictor can automatically learn and extract meaningful feature representations such as non-linear correlations among features that enable to improve the prediction accuracy. We evaluated and compared the performance of the proposed method with traditional machine learning algorithms. The experimental results show that the proposed DeepPSL has better prediction performance, indicating that deep learning has great potential for the performance improvement in Bioinformatics. In future work, we expect that as more protein subcellular location data becomes available, this model will further improve in performance and reveal more useful and meaningful feature patterns. Deep learning based methods require large-scale data sets.