ABSTRACT
In this research, the learning based solely on amino acid sequences were conducted using ANN. By considering various conditions such as window size, dropout, optimizer, etc., it was shown that the highest accuracy of predicting whether the amino acid is part of α-helix or not was about 74%, and whether the amino acid is part of α-helix, β-sheet or the other structures was about 50%. Our model has a limitation that highest accuracy is bound to a certain value. However, it has a significance of embodying the protein secondary structure prediction model that learns only from amino acid sequences; it is simpler than multiple sequence alignment, the widely used method in protein secondary structure prediction.
- Choi, H. 2004. Protein Secondary Structure Prediction using SVDD. Master's thesis. Ewha Womans University, Seoul, Korea.Google Scholar
- Glorot, X. and Bengio, Y. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (Sardinia, Italy, May 13-15, 2010). AISTATS '10. PMLR, 249--256.Google Scholar
- He, K., Zhang, X., Ren, S., and Sun, J. 2015. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. arXiv:1502.01852. Retrieved from https://arxiv.org/abs/1502.01852.Google Scholar
- Kabsch, W. and Sander, C. 1983. Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features. Biopolymers 22, 12 (Dec. 1983), 2557--637Google ScholarCross Ref
- LeCun, Y., Boser, B.E., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W.E. and Jackel, L.D. 1990. Handwritten digit recognition with a back-propagation network. Adv. Neur. In. (1990), 396--404 Google ScholarDigital Library
- Rost, B. and Sander, C. 1993. Prediction of Protein Secondary Structure at Better than 70% Accuracy. J. Mol. Biol. 232, 2 (Jul. 1993), 584--599.Google ScholarCross Ref
- Saito, K. 2017. Deep Learning from Scratch. Hanbit Media, Inc., Seoul.Google Scholar
- Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. 2014. Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research 15, 1 (Jan. 2014), 1929--58 Google ScholarDigital Library
Index Terms
- Protein Secondary Structure Prediction from Amino Acid Sequence Using Artificial Neural Network
Recommendations
Reliable prediction of protein thermostability change upon double mutation from amino acid sequence
Summary: The accurate prediction of protein stability change upon mutation is one of the important issues for protein design. In this work, we have focused on the stability change of double mutations and systematically analyzed the wild-type and ...
Identification of β-barrel membrane proteins based on amino acid composition properties and predicted secondary structure
Unlike all-helices membrane proteins, @b-barrel membrane proteins can not be successfully discriminated from other proteins, especially from all-@b soluble proteins. This paper performs an analysis on the amino acid composition in membrane parts of 12 @...
Weave amino acid sequences for protein secondary structure prediction
DMKD '03: Proceedings of the 8th ACM SIGMOD workshop on Research issues in data mining and knowledge discoveryGiven a known protein sequence, predicting its secondary structure can help understand its three-dimensional (tertiary) structure, i.e., the folding. In this paper, we present an approach for predicting protein secondary structures. Different from the ...
Comments