OBPred: feature-fusion-based deep neural network classifier for odorant-binding protein prediction

Odorant-binding proteins (OBPs) are small, water-soluble, globular, and ligand-specific proteins found in the sensillar lymph in insects and mucus layer in vertebrates. They function as a carrier for transferring odorants to their respective olfactory receptors. However, the functionality and expression of OBPs are not limited to olfaction mechanism and olfactory organs. OBPs are involved in various other functions like measuring odorant concentration and deactivating odorants. They are found in insect taste organs, venom glands, and sex hormone glands. To gain more insight into the functioning and expression pattern of OBPs, it has become essential to identify OBP sequences. The available OBP prediction methods are primarily based on sequence similarity, which seems inefficient since OBPs share low interspecies and intraspecies sequence similarities. Effective representation of protein sequence-based features is essential for the development of predictive models. Single feature representation like physicochemical properties and secondary structure content (PCSS), amino acid composition (AAC), and sequence graph transform may be insufficient. Therefore, we propose two feature combination schemes: feature fusion and feature concatenation, for OBP prediction. The role of conventional machine learning algorithms and deep learning algorithms have not been explored much for identifying OBP sequences. The performance metrics suggest the feature fusion scheme enhances the overall performance of the OBP prediction classifiers. Deep networks yield better accuracy as compared to traditional Machine learning algorithms. The performance of the deep neural network and one-dimensional convolution neural network was found to be comparative. Among all feature representation schemes, the feature fusion scheme with AAC + PCSS gave the best performance. The accuracy of deep neural network and convolutional neural network-1D for AAC + PCSS representation was found to be 98.6% and 96.5%, respectively. We propose OBPred, a deep neural network model with the fused ACC + PCSS feature set, for OBP identification. The current study is the first attempt, to our knowledge, to predict OBPs using deep neural networks.

[1]  Zhiliang Li,et al.  Factor Analysis Scale of Generalized Amino Acid Information as the Source of a New Set of Descriptors for Elucidating the Structure and Activity Relationships of Cationic Antimicrobial Peptides , 2007 .

[2]  P. Pelosi,et al.  Odorant-binding proteins. , 1994, Critical reviews in biochemistry and molecular biology.

[3]  Quoc V. Le,et al.  Searching for Activation Functions , 2018, arXiv.

[4]  P. Xu,et al.  Drosophila OBP LUSH Is Required for Activity of Pheromone-Sensitive Neurons , 2005, Neuron.

[5]  Rahul Semwal,et al.  DeepOlf: Deep Neural Network Based Architecture for Predicting Odorants and Their Interacting Olfactory Receptors , 2020, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[6]  L. Riddiford,et al.  Pheromone binding and inactivation by moth antennae , 1981, Nature.

[7]  M. Tanouye,et al.  Genome-wide analysis of the odorant-binding protein gene family in Drosophila melanogaster. , 2002, Genome research.

[8]  C. Masson,et al.  Separation, characterization and sexual heterogeneity of multiple putative odorant-binding proteins in the honeybee Apis mellifera L. (Hymenoptera: Apidea). , 1998, Chemical senses.

[9]  Shuai Zhang,et al.  Two Minus-C odorant binding proteins from Helicoverpa armigera display higher ligand binding affinity at acidic pH than neutral pH. , 2013, Journal of insect physiology.

[10]  Andrea Zaliani,et al.  MS-WHIM Scores for Amino Acids: A New 3D-Description for Peptide QSAR and QSPR Studies , 1999, J. Chem. Inf. Comput. Sci..

[11]  Yuehui Chen,et al.  Predicting the Subcellular Localization of Proteins with Multiple Sites Based on Multiple Features Fusion , 2014, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[12]  Rodrigo Torres,et al.  Peptides: A Package for Data Mining of Antimicrobial Peptides , 2015, R J..

[13]  P. Varadwaj,et al.  Sense of Smell: Structural, Functional, Mechanistic Advancements and Challenges in Human Olfactory Research , 2019, Current neuropharmacology.

[14]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[15]  Yan Liu,et al.  A new method of feature fusion and its application in image recognition , 2005, Pattern Recognit..

[16]  Xia Sun,et al.  Deep Convolution Neural Networks for Drug-Drug Interaction Extraction , 2018, 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[17]  Daisuke Haba,et al.  Behavioral analyses of mutants for two odorant-binding protein genes, Obp57d and Obp57e, in Drosophila melanogaster. , 2008, Genes & genetic systems.

[18]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[19]  Dong-Sheng Cao,et al.  protr/ProtrWeb: R package and web server for generating various numerical representation schemes of protein sequences , 2015, Bioinform..

[20]  Daniel Berrar,et al.  Bayes' Theorem and Naive Bayes Classifier , 2019, Encyclopedia of Bioinformatics and Computational Biology.

[21]  K. Galindo,et al.  A large family of divergent Drosophila odorant-binding proteins expressed in gustatory and olfactory sensilla. , 2001, Genetics.

[22]  Murray B. Isman,et al.  Analysis of the Insect OS-D-Like Gene Family , 2004, Journal of Chemical Ecology.

[23]  Kamran Paynabar,et al.  Sequence Graph Transform (SGT): A Feature Extraction Function for Sequence Data Mining , 2016, ArXiv.

[24]  F. Davis,et al.  Odorant binding protein 69a connects social interaction to modulation of social responsiveness in Drosophila , 2018, PLoS genetics.

[25]  M. W. Pandit,et al.  Correlation between stability of a protein and its dipeptide composition: a novel approach for predicting in vivo stability of a protein from its primary sequence. , 1990, Protein engineering.

[26]  Sarah Jane Delany.  k-Nearest Neighbour Classifiers , 2007 .

[27]  R. Anholt,et al.  Functional dissection of Odorant binding protein genes in Drosophila melanogaster , 2011, Genes, brain, and behavior.

[28]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[29]  P. Pelosi,et al.  Soluble proteins in insect chemical communication , 2006, Cellular and Molecular Life Sciences CMLS.

[30]  B. Redl,et al.  Molecular Cloning of a Novel Lipocalin-1 Interacting Human Cell Membrane Receptor Using Phage Display* , 2001, The Journal of Biological Chemistry.

[31]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[32]  Pritish Kumar Varadwaj,et al.  A prediction model for oral bioavailability of drugs using physicochemical properties by support vector machine , 2011, Journal of natural science, biology, and medicine.

[33]  H. Biessmann,et al.  The Anopheles gambiae Odorant Binding Protein 1 (AgamOBP1) Mediates Indole Recognition in the Antennae of Female Mosquitoes , 2010, PloS one.

[34]  Junxiang Wu,et al.  Binding Properties of General Odorant Binding Proteins from the Oriental Fruit Moth, Grapholita molesta (Busck) (Lepidoptera: Tortricidae) , 2016, PloS one.

[35]  R. Vogt,et al.  Functional and expression pattern analysis of chemosensory proteins expressed in antennae and pheromonal gland of Mamestra brassicae. , 2001, Chemical senses.

[36]  Cathy H. Wu,et al.  UniProt: the Universal Protein knowledgebase , 2004, Nucleic Acids Res..

[37]  Mohammad Yusuf Mulla,et al.  Capacitance-modulated transistor detects odorant binding protein chiral interactions , 2015, Nature Communications.

[38]  C. Montell,et al.  An Odorant-Binding Protein Required for Suppression of Sweet Taste by Bitter Chemicals , 2013, Neuron.

[39]  Nichole A. Broderick,et al.  Symbiont-induced odorant binding proteins mediate insect host hematopoiesis , 2017, eLife.

[40]  Alexander G. Georgiev,et al.  Interpretable Numerical Descriptors of Amino Acid Space , 2009, J. Comput. Biol..

[41]  Gunnar Rätsch,et al.  Support Vector Machines and Kernels for Computational Biology , 2008, PLoS Comput. Biol..

[42]  C. Cambillau,et al.  Complexes of porcine odorant binding protein with odorant molecules belonging to different chemical classes. , 2000, Journal of molecular biology.

[43]  Rajesh Kumar Tiwari,et al.  Prediction of Human Intestinal Absorption of Compounds Using Artificial Intelligence Techniques. , 2017, Current drug discovery technologies.

[44]  Rajesh Kumar Tiwari,et al.  Promises of Machine Learning Approaches in Prediction of Absorption of Compounds. , 2018, Mini reviews in medicinal chemistry.

[45]  Fei Gu,et al.  Improved Chou-Fasman method for protein secondary structure prediction , 2006, BMC Bioinformatics.

[46]  R. Franklin,et al.  Structure and synthesis of a lipid-containing bacteriophage. I. Growth of bacteriophage PM2 and alterations in nucleic acid metabolism in the infected cell. , 1969, Virology.

[47]  F. Tian,et al.  T-scale as a novel vector of topological descriptors for amino acids and its application in QSARs of peptides , 2007 .

[48]  Gabriele Cruciani,et al.  Peptide studies by means of principal properties of amino acids derived from MIF descriptors , 2004 .

[49]  Mohamed Abdel-Mottaleb,et al.  Fully automatic face normalization and single sample face recognition in unconstrained environments , 2016, Expert Syst. Appl..

[50]  M. Shu,et al.  ST-scale as a novel amino acid descriptor and its application in QSAM of peptides and analogues , 2010, Amino Acids.

[51]  G. Archunan.  Odorant Binding Proteins: a key player in the sense of smell , 2018, Bioinformation.

[52]  P. Pelosi,et al.  Odorant-binding proteins of the mouse. , 1995, Comparative biochemistry and physiology. Part B, Biochemistry & molecular biology.

[53]  A Ikai,et al.  Thermostability and aliphatic index of globular proteins. , 1980, Journal of biochemistry.

[54]  Rajesh Kumar Tiwari,et al.  Prediction of Drug-Plasma Protein Binding Using Artificial Intelligence Based Algorithms. , 2017, Combinatorial chemistry & high throughput screening.

[55]  P. Davies,et al.  The odorant-binding proteins of Drosophila melanogaster: annotation and characterization of a divergent gene family. , 2002, Gene.

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

[57]  Pritish Kumar Varadwaj,et al.  A comparative study of support vector machine, artificial neural network and Bayesian classifier for mutagenicity prediction , 2011, Interdisciplinary Sciences: Computational Life Sciences.

[58]  M. Koganezawa,et al.  Novel odorant-binding proteins expressed in the taste tissue of the fly. , 2002, Chemical senses.

[59]  H. Scheraga,et al.  Statistical analysis of the physical properties of the 20 naturally occurring amino acids , 1985 .

[60]  H. G. Boman,et al.  Antibacterial peptides: basic facts and emerging concepts , 2003, Journal of internal medicine.

[61]  H. Bull,et al.  Surface tension of amino acid solutions: a hydrophobicity scale of the amino acid residues. , 1974, Archives of biochemistry and biophysics.

[62]  Y. Fuyama,et al.  Odorant-Binding Proteins OBP57d and OBP57e Affect Taste Perception and Host-Plant Preference in Drosophila sechellia , 2007, PLoS biology.

[63]  Sean R. Eddy,et al.  Profile hidden Markov models , 1998, Bioinform..

[64]  H. Breer,et al.  Olfactory receptors: molecular basis for recognition and discrimination of odors , 2003, Analytical and bioanalytical chemistry.

[65]  R D Appel,et al.  Protein identification and analysis tools in the ExPASy server. , 1999, Methods in molecular biology.

[66]  A. Cornel,et al.  Knockdown of a Mosquito Odorant-binding Protein Involved in the Sensitive Detection of Oviposition Attractants , 2010, Journal of Chemical Ecology.

[67]  Zhengwei Zhu,et al.  CD-HIT: accelerated for clustering the next-generation sequencing data , 2012, Bioinform..

[68]  Y. Liou,et al.  Characterization and cloning of a Tenebrio molitor hemolymph protein with sequence similarity to insect odorant-binding proteins. , 2001, Insect biochemistry and molecular biology.

[69]  S. Snyder,et al.  Isolation and characterization of an olfactory receptor protein for odorant pyrazines. , 1985, Proceedings of the National Academy of Sciences of the United States of America.

[70]  Md. Al Mehedi Hasan,et al.  Feature Fusion Based SVM Classifier for Protein Subcellular Localization Prediction. , 2016, Journal of integrative bioinformatics.

[71]  Bartek Wilczynski,et al.  Biopython: freely available Python tools for computational molecular biology and bioinformatics , 2009, Bioinform..

[72]  K C Persaud,et al.  Purification and characterisation of an odorant-binding protein from cow nasal tissue. , 1985, European journal of biochemistry.

[73]  J. Carlson,et al.  The diverse small proteins called odorant-binding proteins , 2018, Royal Society Open Biology.

[74]  J. Carlson,et al.  Organization and function of Drosophila odorant binding proteins , 2016, eLife.

[75]  C. Cambillau,et al.  Domain swapping creates a third putative combining site in bovine odorant binding protein dimer , 1996, Nature Structural Biology.

[76]  J. S. Chahda,et al.  Humidity response depends on the small soluble protein Obp59a in Drosophila , 2018, eLife.

[77]  H. Breer,et al.  Identification of a third rat odorant-binding protein (OBP3). , 2001, Chemical senses.

[78]  S. Snyder,et al.  Odorant-binding protein: odorant transport function in the vertebrate nasal epithelium , 1990 .

[79]  P. Pelosi,et al.  Subtypes of odorant-binding proteins--heterologous expression and ligand binding. , 1998, European journal of biochemistry.