AMPGAN v2: Machine Learning Guided Discovery of Anti-Microbial Peptides

Antibiotic resistance is a critical public health problem. Each year ~2.8 million resistant infections lead to more than 35,000 deaths in the U.S. alone. Anti-microbial peptides (AMPs) show promise in treating resistant infections. But, applications of known AMPs have encountered issues in development, production, and shelf-life. To drive the development of AMPbased treatments it is necessary to create design approaches with higher precision and selectivity towards resistant targets. In this paper we present AMPGAN v2, a generative adversarial network (GAN) based approach for rational AMP design. Like AMP-GAN,1 AMPGAN v2 combines data driven priors and controlled generation. These elements allow for the generation of AMP candidates tailored for specific applications. AMPGAN v2 is able to generate AMP candidates that are novel and diverse, making it an efficient AMP design tool.

[1]  Jürgen Schmidhuber,et al.  A possibility for implementing curiosity and boredom in model-building neural controllers , 1991 .

[2]  Gregory Stephanopoulos,et al.  A linguistic model for the rational design of antimicrobial peptides , 2006, Nature.

[3]  J. Zico Kolter,et al.  Gradient descent GAN optimization is locally stable , 2017, NIPS.

[4]  The UniProt Consortium,et al.  UniProt: a worldwide hub of protein knowledge , 2018, Nucleic Acids Res..

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

[6]  C. Pál,et al.  Integrated evolutionary analysis reveals antimicrobial peptides with limited resistance , 2019, Nature Communications.

[7]  Bolei Zhou,et al.  Interpreting the Latent Space of GANs for Semantic Face Editing , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  P. Agrawal,et al.  In silico approaches for predicting the half-life of natural and modified peptides in blood , 2018, PloS one.

[9]  V. Brendel,et al.  Genome structure described by formal languages. , 1984, Nucleic acids research.

[10]  Jacob Witten,et al.  Deep learning regression model for antimicrobial peptide design , 2019, bioRxiv.

[11]  John Canny,et al.  Evaluating Protein Transfer Learning with TAPE , 2019, bioRxiv.

[12]  A. Hollmann,et al.  Antimicrobial Peptides: Interaction With Model and Biological Membranes and Synergism With Chemical Antibiotics , 2018, Front. Chem..

[13]  David Lopez-Paz,et al.  Optimizing the Latent Space of Generative Networks , 2017, ICML.

[14]  Axel Hollmann,et al.  Designing improved active peptides for therapeutic approaches against infectious diseases. , 2018, Biotechnology advances.

[15]  Jinyin Chen,et al.  Customizable text generation via conditional text generative adversarial network , 2020, Neurocomputing.

[16]  Sebastian Nowozin,et al.  Which Training Methods for GANs do actually Converge? , 2018, ICML.

[17]  M. Lefranc,et al.  DBAASP: database of antimicrobial activity and structure of peptides. , 2014, FEMS microbiology letters.

[18]  Xiao Li,et al.  A High Efficient Biological Language Model for Predicting Protein–Protein Interactions , 2019, Cells.

[19]  Thomas Blaschke,et al.  Application of Generative Autoencoder in De Novo Molecular Design , 2017, Molecular informatics.

[20]  Roland R. Regoes,et al.  Combination Effects of Antimicrobial Peptides , 2016, Antimicrobial Agents and Chemotherapy.

[21]  Gianluca Pollastri,et al.  SCLpred: protein subcellular localization prediction by N-to-1 neural networks , 2011, Bioinform..

[22]  C. Pál,et al.  Antibiotic-resistant bacteria show widespread collateral sensitivity to antimicrobial peptides , 2018, Nature Microbiology.

[23]  Sebastian Gehrmann,et al.  Interactive Visual Exploration of Latent Space (IVELS) for peptide auto-encoder model selection , 2019, DGS@ICLR.

[25]  R. Hancock,et al.  Antibacterial peptides for therapeutic use: obstacles and realistic outlook. , 2006, Current opinion in pharmacology.

[26]  Artem Cherkasov,et al.  BIOINFORMATICS ORIGINAL PAPER doi:10.1093/bioinformatics/btm068 Databases and ontologies AMPer: a database and an automated discovery tool for antimicrobial peptides , 2022 .

[27]  O. Gotoh.  An improved algorithm for matching biological sequences. , 1982, Journal of molecular biology.

[28]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[29]  J. Bradshaw,et al.  Cationic Antimicrobial Peptides , 2012, BioDrugs.

[30]  Gianluca Pollastri,et al.  PeptideLocator: prediction of bioactive peptides in protein sequences , 2013, Bioinform..

[31]  Charles A. Sutton,et al.  VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning , 2017, NIPS.

[32]  Kai Hilpert,et al.  High-throughput generation of small antibacterial peptides with improved activity , 2005, Nature Biotechnology.

[33]  Andrew Brock,et al.  Neural Photo Editing with Introspective Adversarial Networks , 2016, ICLR.

[34]  Hyun Uk Kim,et al.  Designing Novel Functional Peptides by Manipulating a Temperature in the Softmax Function Coupled with Variational Autoencoder , 2019, 2019 IEEE International Conference on Big Data (Big Data).

[35]  Andrew M. Dai,et al.  MaskGAN: Better Text Generation via Filling in the ______ , 2018, ICLR.

[36]  Eric P. Xing,et al.  Toward Controlled Generation of Text , 2017, ICML.

[37]  Peter Sheridan Dodds,et al.  Generalized word shift graphs: a method for visualizing and explaining pairwise comparisons between texts , 2020, EPJ Data Science.

[38]  Niall J. Haslam,et al.  Towards the Improved Discovery and Design of Functional Peptides: Common Features of Diverse Classes Permit Generalized Prediction of Bioactivity , 2012, PloS one.

[39]  Gajendra P. S. Raghava,et al.  Prediction of Antimicrobial Potential of a Chemically Modified Peptide From Its Tertiary Structure , 2018, Front. Microbiol..

[40]  Trevor Darrell,et al.  Adversarial Feature Learning , 2016, ICLR.

[41]  T. G. Villa,et al.  Antimicrobial peptides (AMPs): Ancient compounds that represent novel weapons in the fight against bacteria. , 2017, Biochemical pharmacology.

[42]  K. Chou,et al.  iAMP-2L: a two-level multi-label classifier for identifying antimicrobial peptides and their functional types. , 2013, Analytical biochemistry.

[43]  Shreyas Karnik,et al.  CAMP: a useful resource for research on antimicrobial peptides , 2009, Nucleic Acids Res..

[44]  Gajendra P S Raghava,et al.  Prediction of Mitochondrial Proteins Using Support Vector Machine and Hidden Markov Model* , 2006, Journal of Biological Chemistry.

[45]  I. Eliseev,et al.  Application of Antimicrobial Peptides of the Innate Immune System in Combination With Conventional Antibiotics—A Novel Way to Combat Antibiotic Resistance? , 2019, Front. Cell. Infect. Microbiol..

[46]  Alán Aspuru-Guzik,et al.  Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules , 2016, ACS central science.

[47]  M. Mahlapuu,et al.  Antimicrobial Peptides: An Emerging Category of Therapeutic Agents , 2016, Front. Cell. Infect. Microbiol..

[48]  Jason Yosinski,et al.  An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution , 2018, NeurIPS.

[49]  Manoj Kumar,et al.  AVPdb: a database of experimentally validated antiviral peptides targeting medically important viruses , 2013, Nucleic Acids Res..

[50]  Karen Kafadar,et al.  Letter-Value Plots: Boxplots for Large Data , 2017 .

[51]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[52]  Alex Hawkins-Hooker,et al.  Generating functional protein variants with variational autoencoders , 2020, bioRxiv.

[53]  Mario Gimona,et al.  Protein linguistics — a grammar for modular protein assembly? , 2006, Nature Reviews Molecular Cell Biology.

[54]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[55]  Yoshua Bengio,et al.  Mode Regularized Generative Adversarial Networks , 2016, ICLR.

[56]  Sergey Nikolenko,et al.  druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico. , 2017, Molecular pharmaceutics.

[57]  Regina Barzilay,et al.  Junction Tree Variational Autoencoder for Molecular Graph Generation , 2018, ICML.

[58]  C. Aranha,et al.  Antimicrobial peptides: premises and promises. , 2004, International journal of antimicrobial agents.

[59]  S. Phinn,et al.  Australian vegetated coastal ecosystems as global hotspots for climate change mitigation , 2019, Nature Communications.

[60]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

[61]  Bogdan Raducanu,et al.  Invertible Conditional GANs for image editing , 2016, ArXiv.

[62]  Rainier Barrett,et al.  Classifying antimicrobial and multifunctional peptides with Bayesian network models , 2018, Peptide Science.

[63]  R. Hancock,et al.  Synergistic Interactions between Mammalian Antimicrobial Defense Peptides , 2001, Antimicrobial Agents and Chemotherapy.

[64]  Cícero Nogueira dos Santos,et al.  PepCVAE: Semi-Supervised Targeted Design of Antimicrobial Peptide Sequences , 2018, 1810.07743.

[65]  Aaron C. Courville,et al.  Adversarially Learned Inference , 2016, ICLR.

[66]  Sebastian Nowozin,et al.  Stabilizing Training of Generative Adversarial Networks through Regularization , 2017, NIPS.

[67]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[68]  Jeff Donahue,et al.  Large Scale GAN Training for High Fidelity Natural Image Synthesis , 2018, ICLR.

[69]  Alexei A. Efros,et al.  Generative Visual Manipulation on the Natural Image Manifold , 2016, ECCV.

[70]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[71]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.