TMP-SSurface: A Deep Learning-Based Predictor for Surface Accessibility of Transmembrane Protein Residues

Transmembrane proteins (TMPs) play vital and diverse roles in many biological processes, such as molecular transportation and immune response. Like other proteins, many major interactions with other molecules happen in TMPs’ surface area, which is important for function annotation and drug discovery. Under the condition that the structure of TMP is hard to derive from experiment and prediction, it is a practical way to predict the TMP residues’ surface area, measured by the relative accessible surface area (rASA), based on computational methods. In this study, we presented a novel deep learning-based predictor TMP-SSurface for both alpha-helical and beta-barrel transmembrane proteins (α-TMP and β-TMP), where convolutional neural network (CNN), inception blocks, and CapsuleNet were combined to construct a network framework, simply accepting one-hot code and position-specific score matrix (PSSM) of protein fragment as inputs. TMP-SSurface was tested against an independent dataset achieving appreciable performance with 0.584 Pearson correlation coefficients (CC) value. As the first TMP’s rASA predictor utilizing the deep neural network, our method provided a referenceable sample for the community, as well as a practical step to discover the interaction sites of TMPs based on their sequence.

[1]  Chao Fang,et al.  Improving Protein Gamma-Turn Prediction Using Inception Capsule Networks , 2018, Scientific Reports.

[2]  Thomas L. Madden,et al.  Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. , 1997, Nucleic acids research.

[3]  G. Rose,et al.  Hydrophobicity of amino acid residues in globular proteins. , 1985, Science.

[4]  S. Rasmussen,et al.  The structure and function of G-protein-coupled receptors , 2009, Nature.

[5]  Hong-Bin Shen,et al.  MemBrain: An Easy-to-Use Online Webserver for Transmembrane Protein Structure Prediction , 2018, Nano-micro letters.

[6]  H. Ding,et al.  Identification of mitochondrial proteins of malaria parasite using analysis of variance , 2014, Amino Acids.

[7]  Zhibin Lv,et al.  Protein Function Prediction: From Traditional Classifier to Deep Learning , 2019, Proteomics.

[8]  Xing Gao,et al.  An Improved Protein Structural Classes Prediction Method by Incorporating Both Sequence and Structure Information , 2015, IEEE Transactions on NanoBioscience.

[9]  M. Butler,et al.  High Functioning Autism with Missense Mutations in Synaptotagmin-Like Protein 4 (SYTL4) and Transmembrane Protein 187 (TMEM187) Genes: SYTL4- Protein Modeling, Protein-Protein Interaction, Expression Profiling and MicroRNA Studies , 2019, International journal of molecular sciences.

[10]  W. Kabsch,et al.  Dictionary of protein secondary structure: Pattern recognition of hydrogen‐bonded and geometrical features , 1983, Biopolymers.

[11]  Huanxiang Liu,et al.  Accurate prediction of the burial status of transmembrane residues of α-helix membrane protein by incorporating the structural and physicochemical features , 2011, Amino Acids.

[12]  Xue-wen Chen,et al.  On Position-Specific Scoring Matrix for Protein Function Prediction , 2011, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[13]  D. Absher,et al.  Transmembrane Protein Aptamer Induces Cooperative Signaling by the EPO Receptor and the Cytokine Receptor β-Common Subunit , 2019, iScience.

[14]  Saeed Jalili,et al.  Protein secondary structure prediction using DWKF based on SVR-NSGAII , 2012, Neurocomputing.

[15]  Dmitrij Frishman,et al.  Residue co-evolution helps predict interaction sites in α-helical membrane proteins. , 2019, Journal of structural biology.

[16]  B. Lee,et al.  The interpretation of protein structures: estimation of static accessibility. , 1971, Journal of molecular biology.

[17]  Jijun Tang,et al.  Local-DPP: An improved DNA-binding protein prediction method by exploring local evolutionary information , 2017, Inf. Sci..

[18]  Zhiqiang Ma,et al.  MPLs-Pred: Predicting Membrane Protein-Ligand Binding Sites Using Hybrid Sequence-Based Features and Ligand-Specific Models , 2019, International journal of molecular sciences.

[19]  Wen-Lian Hsu,et al.  Lipid exposure prediction enhances the inference of rotational angles of transmembrane helices , 2013, BMC Bioinformatics.

[20]  M. Šikić,et al.  PSAIA – Protein Structure and Interaction Analyzer , 2008, BMC Structural Biology.

[21]  T. N. Bhat,et al.  The Protein Data Bank , 2000, Nucleic Acids Res..

[22]  P. He,et al.  In Vitro and In Vivo Study on the Effect of Lysosome-associated Protein Transmembrane 4 Beta on the Progression of Breast Cancer , 2019, Journal of breast cancer.

[23]  K. Chou,et al.  iCTX-Type: A Sequence-Based Predictor for Identifying the Types of Conotoxins in Targeting Ion Channels , 2014, BioMed research international.

[24]  Sumaiya Iqbal,et al.  RBSURFpred: Modeling protein accessible surface area in real and binary space using regularized and optimized regression. , 2018, Journal of theoretical biology.

[25]  Shuyan Li,et al.  A sequence‐based computational model for the prediction of the solvent accessible surface area for α‐helix and β‐barrel transmembrane residues , 2012, J. Comput. Chem..

[26]  Austin G. Meyer,et al.  Maximum Allowed Solvent Accessibilites of Residues in Proteins , 2012, PloS one.

[27]  Q. Zou,et al.  Gene2vec: gene subsequence embedding for prediction of mammalian N6-methyladenosine sites from mRNA , 2018, RNA.

[28]  Mikael Bodén,et al.  Predicting the solvent accessibility of transmembrane residues from protein sequence. , 2006, Journal of proteome research.

[29]  Jiu-Xin Tan,et al.  Identification of hormone binding proteins based on machine learning methods. , 2019, Mathematical biosciences and engineering : MBE.

[30]  Ying Gao,et al.  Bioinformatics Applications Note Sequence Analysis Cd-hit Suite: a Web Server for Clustering and Comparing Biological Sequences , 2022 .

[31]  A. Ikeda,et al.  [An adult female with proline-rich transmembrane protein 2 related paroxysmal disorders manifesting paroxysmal kinesigenic choreoathetosis and epileptic seizures]. , 2019, Rinsho shinkeigaku = Clinical neurology.

[32]  Haiting Chai,et al.  Recent In Silico Research in High-Throughput Drug Discovery and Molecular Biochemistry. , 2019, Current topics in medicinal chemistry.

[33]  Wei Chen,et al.  Predicting protein structural classes for low-similarity sequences by evaluating different features , 2019, Knowl. Based Syst..

[34]  Jian Huang,et al.  A Brief Survey of Machine Learning Methods in Protein Sub-Golgi Localization , 2019, Current Bioinformatics.

[35]  Yungki Park,et al.  Prediction of the burial status of transmembrane residues of helical membrane proteins , 2007, BMC Bioinformatics.

[36]  Thijs Beuming,et al.  A knowledge-based scale for the analysis and prediction of buried and exposed faces of transmembrane domain proteins , 2004, Bioinform..

[37]  C. Mierke,et al.  The transmembrane protein fibrocystin/polyductin regulates cell mechanics and cell motility , 2019, Physical biology.

[38]  S. Imaoka,et al.  Thioredoxin-related transmembrane protein 2 (TMX2) regulates the Ran protein gradient and importin-β-dependent nuclear cargo transport , 2019, Scientific Reports.

[39]  Geoffrey E. Hinton,et al.  Dynamic Routing Between Capsules , 2017, NIPS.

[40]  Dong Xu,et al.  Large-scale prediction of protein ubiquitination sites using a multimodal deep architecture , 2018, BMC Systems Biology.

[41]  A M Lesk,et al.  Interior and surface of monomeric proteins. , 1987, Journal of molecular biology.

[42]  Bryan L. Roth,et al.  Molecular control of δ-opioid receptor signalling , 2014, Nature.

[43]  Guohua Huang,et al.  The Advances and Challenges of Deep Learning Application in Biological Big Data Processing , 2017, Current Bioinformatics.

[44]  C. Bin,et al.  Transmembrane protein 126B protects against high fat diet (HFD)-induced renal injury by suppressing dyslipidemia via inhibition of ROS. , 2019, Biochemical and biophysical research communications.

[45]  Hong-Bin Shen,et al.  Prediction Enhancement of Residue Real-Value Relative Accessible Surface Area in Transmembrane Helical Proteins by Solving the Output Preference Problem of Machine Learning-Based Predictors , 2015, J. Chem. Inf. Model..

[46]  Dániel Kozma,et al.  PDBTM: Protein Data Bank of transmembrane proteins after 8 years , 2012, Nucleic Acids Res..

[47]  Jianfeng Lu,et al.  Inhibiting of Proliferation, Migration, and Invasion in Lung Cancer Induced by Silencing Interferon-Induced Transmembrane Protein 1 (IFITM1) , 2019, BioMed research international.

[48]  Arne Elofsson,et al.  MPRAP: An accessibility predictor for a-helical transmem-brane proteins that performs well inside and outside the membrane , 2010, BMC Bioinformatics.

[49]  Zhiqiang Ma,et al.  Bioinformatics Resources and Tools for Conformational B-Cell Epitope Prediction , 2013, Comput. Math. Methods Medicine.

[50]  Zhiqiang Ma,et al.  In silico Prediction of Human Secretory Proteins in Plasma Based on Discrete Firefly Optimization and Application to Cancer Biomarkers Identification , 2019, Front. Genet..

[51]  B. Jeong,et al.  Transmembrane protein 64 modulates prostate tumor progression by regulating Wnt3a secretion , 2019, Oncology letters.