A Hybrid Deep Learning Model for Predicting Protein Hydroxylation Sites

Protein hydroxylation is one type of post-translational modifications (PTMs) playing critical roles in human diseases. It is known that protein sequence contains many uncharacterized residues of proline and lysine. The question that needs to be answered is: which residue can be hydroxylated, and which one cannot. The answer will not only help understand the mechanism of hydroxylation but can also benefit the development of new drugs. In this paper, we proposed a novel approach for predicting hydroxylation using a hybrid deep learning model integrating the convolutional neural network (CNN) and long short-term memory network (LSTM). We employed a pseudo amino acid composition (PseAAC) method to construct valid benchmark datasets based on a sliding window strategy and used the position-specific scoring matrix (PSSM) to represent samples as inputs to the deep learning model. In addition, we compared our method with popular predictors including CNN, iHyd-PseAAC, and iHyd-PseCp. The results for 5-fold cross-validations all demonstrated that our method significantly outperforms the other methods in prediction accuracy.

[1]  Balachandran Manavalan,et al.  MLACP: machine-learning-based prediction of anticancer peptides , 2017, Oncotarget.

[2]  Wei Chen,et al.  Recent Advances in Conotoxin Classification by Using Machine Learning Methods , 2017, Molecules.

[3]  T. Guszczyn,et al.  Deregulation of Collagen Metabolism in Human Stomach Cancer , 2004, Pathobiology.

[4]  K. Chou,et al.  Predicting human immunodeficiency virus protease cleavage sites in proteins by a discriminant function method , 1996, Proteins.

[5]  Jiangning Song,et al.  ACPred-FL: a sequence-based predictor using effective feature representation to improve the prediction of anti-cancer peptides , 2018, Bioinform..

[6]  Balachandran Manavalan,et al.  DHSpred: support-vector-machine-based human DNase I hypersensitive sites prediction using the optimal features selected by random forest , 2017, bioRxiv.

[7]  K. Chou,et al.  iHyd-PseAAC: Predicting Hydroxyproline and Hydroxylysine in Proteins by Incorporating Dipeptide Position-Specific Propensity into Pseudo Amino Acid Composition , 2014, International journal of molecular sciences.

[8]  Kenji Satou,et al.  DNA Sequence Classification by Convolutional Neural Network , 2016 .

[9]  Kuo-Chen Chou,et al.  iHyd-PseCp: Identify hydroxyproline and hydroxylysine in proteins by incorporating sequence-coupled effects into general PseAAC , 2016, Oncotarget.

[10]  Myeong Ok Kim,et al.  PIP-EL: A New Ensemble Learning Method for Improved Proinflammatory Peptide Predictions , 2018, Front. Immunol..

[11]  Zheng Rong Yang,et al.  Predict Collagen Hydroxyproline Sites Using Support Vector Machines , 2009, J. Comput. Biol..

[12]  G. Kuttan,et al.  Anti-metastatic effect of Biophytum sensitivum is exerted through its cytokine and immunomodulatory activity and its regulatory effect on the activation and nuclear translocation of transcription factors in B16F-10 melanoma cells. , 2008, Journal of experimental therapeutics & oncology.

[13]  Yu-Dong Cai,et al.  Prediction of carbamylated lysine sites based on the one-class k-nearest neighbor method. , 2013, Molecular bioSystems.

[14]  K. Chou.  Prediction of human immunodeficiency virus protease cleavage sites in proteins. , 1996, Analytical biochemistry.

[15]  Gwang Lee,et al.  PVP-SVM: Sequence-Based Prediction of Phage Virion Proteins Using a Support Vector Machine , 2018, Front. Microbiol..

[16]  Marcus Rohrbach,et al.  Translating Videos to Natural Language Using Deep Recurrent Neural Networks , 2014, NAACL.

[17]  S. Krane,et al.  The importance of proline residues in the structure, stability and susceptibility to proteolytic degradation of collagens , 2008, Amino Acids.

[18]  Ran Su,et al.  M6APred-EL: A Sequence-Based Predictor for Identifying N6-methyladenosine Sites Using Ensemble Learning , 2018, Molecular therapy. Nucleic acids.

[19]  K. Chou.  Some remarks on protein attribute prediction and pseudo amino acid composition , 2010, Journal of Theoretical Biology.

[20]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[21]  M. Yamauchi,et al.  Lysine hydroxylation and crosslinking of collagen. , 2002, Methods in molecular biology.

[22]  Balachandran Manavalan,et al.  Machine-Learning-Based Prediction of Cell-Penetrating Peptides and Their Uptake Efficiency with Improved Accuracy. , 2018, Journal of proteome research.

[23]  Myeong Ok Kim,et al.  iBCE-EL: A New Ensemble Learning Framework for Improved Linear B-Cell Epitope Prediction , 2018, Front. Immunol..

[24]  Gwang Lee,et al.  AIPpred: Sequence-Based Prediction of Anti-inflammatory Peptides Using Random Forest , 2018, Front. Pharmacol..

[25]  J. Whitehead,et al.  Adiponectin multimerization is dependent on conserved lysines in the collagenous domain: evidence for regulation of multimerization by alterations in posttranslational modifications. , 2006, Molecular endocrinology.

[26]  Rong Chen,et al.  HBPred: a tool to identify growth hormone-binding proteins , 2018, International journal of biological sciences.

[27]  Thomas L. Madden,et al.  Improving the accuracy of PSI-BLAST protein database searches with composition-based statistics and other refinements. , 2001, Nucleic acids research.

[28]  Yu-Dong Cai,et al.  Prediction and Analysis of Protein Hydroxyproline and Hydroxylysine , 2010, PloS one.

[29]  Min Chen,et al.  Deep Learning for Imbalanced Multimedia Data Classification , 2015, 2015 IEEE International Symposium on Multimedia (ISM).

[30]  P. Ratcliffe,et al.  Proteomics-based Identification of Novel Factor Inhibiting Hypoxia-inducible Factor (FIH) Substrates Indicates Widespread Asparaginyl Hydroxylation of Ankyrin Repeat Domain-containing Proteins*S⃞ , 2009, Molecular & Cellular Proteomics.

[31]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.