DFpin: Deep learning–based protein-binding site prediction with feature-based non-redundancy from RNA level

Identification of protein binding sites is critical for studying the function of the proteins. In this paper, we proposed a method for protein binding site prediction, which combined the order profile propensities and hidden Markov support vector machine (HM-SVM). This method employed the sequential labeling technique to the field of protein binding site prediction. The input features of HM-SVM include the profile-based propensities, the Position-Specific Score Matrix (PSSM), and Accessible Surface Area (ASA). When tested on different data sets, the proposed method showed promising results, and outperformed some closely relative methods by more than 10% in terms of AUC.

Download Full-text

Division of Protein Surface Patches and Its Application in Protein Binding Site Prediction

Acta Physico-Chimica Sinica ◽

10.3866/pku.whxb201208162 ◽

2012 ◽

Vol 28 (11) ◽

pp. 2729-2734

Author(s):

WANG Pan-Wen ◽

◽

GONG Xin-Qi ◽

LI Chun-Hua ◽

CHEN Wei-Zu ◽

...

Keyword(s):

Protein Binding ◽

Binding Site ◽

Protein Binding Site ◽

Protein Surface ◽

Site Prediction ◽

Binding Site Prediction ◽

Surface Patches

Download Full-text

Protein−Protein Binding Site Prediction by Local Structural Alignment

Journal of Chemical Information and Modeling ◽

10.1021/ci100265x ◽

2010 ◽

Vol 50 (10) ◽

pp. 1906-1913 ◽

Cited By ~ 9

Author(s):

Nejc Carl ◽

Janez Konc ◽

Blaž Vehar ◽

Dušanka Janežič

Keyword(s):

Protein Binding ◽

Binding Site ◽

Structural Alignment ◽

Protein Binding Site ◽

Site Prediction ◽

Binding Site Prediction

Download Full-text

Interpretable attention model in transcription factor binding site prediction with deep neural networks

10.1101/648691 ◽

2019 ◽

Cited By ~ 5

Author(s):

Chen Chen ◽

Jie Hou ◽

Xiaowen Shi ◽

Hua Yang ◽

James A. Birchler ◽

...

Keyword(s):

Neural Networks ◽

Transcription Factor ◽

Deep Learning ◽

Binding Site ◽

Transcription Factor Binding Site ◽

Attention Mechanism ◽

Factor Binding Site ◽

Site Prediction ◽

Factor Binding ◽

Binding Site Prediction

AbstractDue to the complexity of the biological factors that may influence the binding of transcription factors to DNA sequences, prediction of the potential binding sites remains a difficult task in computational biology. The attention mechanism in deep learning has shown its capability to learn from input features with long-range dependencies. Until now, no study has applied this mechanism in deep neural network models with input data from massively parallel sequencing. In this study, we aim to build a model for binding site prediction with the combination of attention mechanism and traditional deep learning techniques, including convolutional neural networks and recurrent neural networks. The performance of our methods is evaluated on the ENCODE-DREAM in vivo Transcription Factor Binding Site Prediction Challenge datasets.The benchmark shows that our implementation with attention mechanism (called DeepGRN) improves the performance of the deep learning models. Our model achieves better performance in at least 9 of 13 targets than any of the methods participated in the DREAM challenge. Visualization of the attention weights extracted from the trained models reveals how those weights shift when binding signal peaks move along the genomic sequence, which can interpret how the predictions are made. Case studies show that the attention mechanism helps to extract useful features by focusing on regions that are critical to successful prediction while ignoring the irrelevant signals from the input.

Download Full-text

The ribosomal protein binding site in Saccharomyces cerevisiae ribosomal 5 S RNA. A conserved protein binding site in 5 S RNA.

Journal of Biological Chemistry ◽

10.1016/s0021-9258(18)36006-x ◽

1979 ◽

Vol 254 (16) ◽

pp. 7724-7729 ◽

Cited By ~ 3

Author(s):

R.N. Nazar

Keyword(s):

Saccharomyces Cerevisiae ◽

Protein Binding ◽

Ribosomal Protein ◽

Binding Site ◽

Protein Binding Site

Download Full-text

Functional homology between the yeast regulatory proteins GAL4 and LAC9: LAC9-mediated transcriptional activation in Kluyveromyces lactis involves protein binding to a regulatory sequence homologous to the GAL4 protein-binding site.

Molecular and Cellular Biology ◽

10.1128/mcb.7.12.4400 ◽

1987 ◽

Vol 7 (12) ◽

pp. 4400-4406 ◽

Cited By ~ 50

Author(s):

K D Breunig ◽

P Kuger

Keyword(s):

Protein Binding ◽

Binding Site ◽

Transcriptional Activation ◽

Kluyveromyces Lactis ◽

Regulatory Protein ◽

Binding Activity ◽

Protein Binding Site ◽

Regulatory Sequence ◽

Functional Homology ◽

Beta Galactosidase

As shown previously, the beta-galactosidase gene of Kluyveromyces lactis is transcriptionally regulated via an upstream activation site (UASL) which contains a sequence homologous to the GAL4 protein-binding site in Saccharomyces cerevisiae (M. Ruzzi, K.D. Breunig, A.G. Ficca, and C.P. Hollenberg, Mol. Cell. Biol. 7:991-997, 1987). Here we demonstrate that the region of homology specifically binds a K. lactis regulatory protein. The binding activity was detectable in protein extracts from wild-type cells enriched for DNA-binding proteins by heparin affinity chromatography. These extracts could be used directly for DNase I and exonuclease III protection experiments. A lac9 deletion strain, which fails to induce the beta-galactosidase gene, did not contain the binding factor. The homology of LAC9 protein with GAL4 (J.M. Salmeron and S. A. Johnston, Nucleic Acids Res. 14:7767-7781, 1986) strongly suggests that LAC9 protein binds directly to UASL and plays a role similar to that of GAL4 in regulating transcription.

Download Full-text