Parapred: antibody paratope prediction using convolutional and recurrent neural networks

Motivation Antibodies play essential roles in the immune system of vertebrates and are powerful tools in research and diagnostics. While hypervariable regions of antibodies, which are responsible for binding, can be readily identified from their amino acid sequence, it remains challenging to accurately pinpoint which amino acids will be in contact with the antigen (the paratope). Results In this work, we present a sequence-based probabilistic machine learning algorithm for paratope prediction, named Parapred. Parapred uses a deep-learning architecture to leverage features from both local residue neighbourhoods and across the entire sequence. The method significantly improves on the current state-of-the-art methodology, and only requires a stretch of amino acid sequence corresponding to a hypervariable region as an input, without any information about the antigen. We further show that our predictions can be used to improve both speed and accuracy of a rigid docking algorithm. Availability and implementation The Parapred method is freely available as a webserver at http://www-mvsoftware.ch.cam.ac.uk/and for download at https://github.com/eliberis/parapred. Supplementary information Supplementary information is available at Bioinformatics online.

[1]  Michele Vendruscolo,et al.  Rapid and accurate in silico solubility screening of a monoclonal antibody library , 2017, Scientific Reports.

[2]  W. Youden,et al.  Index for rating diagnostic tests , 1950, Cancer.

[3]  Yanay Ofran,et al.  Structural Consensus among Antibodies Defines the Antigen Binding Site , 2012, PLoS Comput. Biol..

[4]  Jens Meiler,et al.  Generation and evaluation of dimension-reduced amino acid parameter representations by artificial neural networks , 2001 .

[5]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[6]  Janice M. Reichert,et al.  Antibodies to watch in 2017 , 2016, mAbs.

[7]  Xuhua Xia,et al.  Protein structure, neighbor effect, and a new index of amino acid dissimilarities. , 2002, Molecular biology and evolution.

[8]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[9]  Jean-Christophe Nebel,et al.  Progress and challenges in predicting protein interfaces , 2015, Briefings Bioinform..

[10]  Rasiah Loganantharaj,et al.  Towards recognition of protein function based on its structure using deep convolutional networks , 2016, 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[11]  A. Lesk,et al.  Standard conformations for the canonical structures of immunoglobulins. , 1997, Journal of molecular biology.

[12]  C. Deane,et al.  Antibody i-Patch prediction of the antibody binding site improves rigid local antibody-antigen docking. , 2013, Protein engineering, design & selection : PEDS.

[13]  Pietro Liò,et al.  X-CNN: Cross-modal convolutional neural networks for sparse datasets , 2016, 2016 IEEE Symposium Series on Computational Intelligence (SSCI).

[14]  B. Frey,et al.  Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning , 2015, Nature Biotechnology.

[15]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[17]  Jiye Shi,et al.  SAbDab: the structural antibody database , 2013, Nucleic Acids Res..

[18]  Paolo Marcatili,et al.  Prediction of site-specific interactions in antibody-antigen complexes: the proABC method and server , 2013, Bioinform..

[19]  He Jing,et al.  Deep convolutional neural networks for detecting secondary structures in protein density maps from cryo-electron microscopy , 2016 .

[20]  D. Ecker,et al.  The therapeutic monoclonal antibody market , 2015, mAbs.

[21]  Charlotte M. Deane,et al.  ANARCI: antigen receptor numbering and receptor classification , 2015, Bioinform..

[22]  Ruth Nussinov,et al.  Efficient Unbound Docking of Rigid Molecules , 2002, WABI.

[23]  G. Gilliland,et al.  Engineering antibody therapeutics. , 2016, Current opinion in structural biology.

[24]  Kenji Mizuguchi,et al.  The diversity of H3 loops determines the antigen‐binding tendencies of antibody CDR loops , 2016, Protein science : a publication of the Protein Society.

[25]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[26]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[27]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[28]  O. Leavy Therapeutic antibodies: past, present and future , 2010, Nature Reviews Immunology.

[29]  A. Yang,et al.  Origins of specificity and affinity in antibody–protein interactions , 2014, Proceedings of the National Academy of Sciences.