Accelerating Antimicrobial Peptide Discovery with Latent Structure

Antimicrobial peptides (AMPs) are promising therapeutic approaches against drug-resistant pathogens. Recently, deep generative models are used to discover new AMPs. However, previous studies mainly focus on peptide sequence attributes and do not consider crucial structure information. In this paper, we propose a latent sequence-structure model for designing AMPs (LSSAMP). LSSAMP exploits multi-scale vector quantization in the latent space to represent secondary structures (e.g. alpha helix and beta sheet). By sampling in the latent space, LSSAMP can simultaneously generate peptides with ideal sequence attributes and secondary structures. Experimental results show that the peptides generated by LSSAMP have a high probability of antimicrobial activity. Our wet laboratory experiments verified that two of the 21 candidates exhibit strong antimicrobial activity. The code is released at https://github.com/dqwang122/LSSAMP.

[1]  Jonathan W. Essex,et al.  Computational Methods and Tools in Antimicrobial Peptide Research , 2021, J. Chem. Inf. Model..

[2]  Safwan Wshah,et al.  AMPGAN v2: Machine Learning-Guided Design of Antimicrobial Peptides , 2021, J. Chem. Inf. Model..

[3]  Xinyu Dai,et al.  Non-Autoregressive Translation by Learning Target Categorical Codes , 2021, NAACL.

[4]  Weinan Zhang,et al.  MARS: Markov Molecular Sampling for Multi-objective Drug Discovery , 2021, ICLR.

[5]  Jean-Louis Reymond,et al.  Machine learning designs non-hemolytic antimicrobial peptides , 2021, Chemical science.

[6]  Yi Yan Yang,et al.  Accelerated antimicrobial discovery via deep generative models and molecular dynamics simulations , 2021, Nature Biomedical Engineering.

[7]  Dana L Carper,et al.  amPEPpy 1.0: A portable and accurate antimicrobial peptide prediction tool. , 2020, Bioinformatics.

[8]  Kaveh Kavousi,et al.  IAMPE: NMR-Assisted Computational Prediction of Antimicrobial Peptides , 2020, J. Chem. Inf. Model..

[9]  Scott A. Walper,et al.  Variational Autoencoder for Generation of Antimicrobial Peptides , 2020, ACS omega.

[10]  Yi Yan Yang,et al.  Accelerating Antimicrobial Discovery with Controllable Deep Generative Models and Molecular Dynamics , 2020, ArXiv.

[11]  Emma J. Chory,et al.  A Deep Learning Approach to Antibiotic Discovery , 2020, Cell.

[12]  S. Gronow,et al.  Influence of disulfide bonds in human beta defensin-3 on its strain specific activity against Gram-negative bacteria. , 2020, Biochimica et biophysica acta. Biomembranes.

[13]  R. L. Mancera,et al.  The unusual conformation of cross‐strand disulfide bonds is critical to the stability of β‐hairpin peptides , 2020, Proteins.

[14]  Michael I. Jordan,et al.  Decision-Making with Auto-Encoding Variational Bayes , 2020, NeurIPS.

[15]  Weinan Zhang,et al.  GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation , 2020, ICLR.

[16]  Marlon H. Cardoso,et al.  Computer-Aided Design of Antimicrobial Peptides: Are We Generating Effective Drug Candidates? , 2020, Frontiers in Microbiology.

[17]  David Wingate,et al.  ProSPr: Democratized Implementation of Alphafold Protein Distance Prediction Network , 2019, bioRxiv.

[18]  Mohammed AlQuraishi,et al.  AlphaFold at CASP13 , 2019, Bioinform..

[19]  C. de la Fuente-Nunez,et al.  Toward computer-made artificial antibiotics. , 2019, Current opinion in microbiology.

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

[21]  Rafael Gómez-Bombarelli,et al.  Generative Models for Automatic Chemical Design , 2019, Machine Learning Meets Quantum Physics.

[22]  Lei Li,et al.  Generating Sentences from Disentangled Syntactic and Semantic Spaces , 2019, ACL.

[23]  Ali Razavi,et al.  Generating Diverse High-Fidelity Images with VQ-VAE-2 , 2019, NeurIPS.

[24]  W. Wimley,et al.  Simulation-Guided Rational de Novo Design of a Small Pore-Forming Antimicrobial Peptide. , 2019, Journal of the American Chemical Society.

[25]  Karen G. N. Oshiro,et al.  Structure-function-guided exploration of the antimicrobial peptide polybia-CP identifies activity determinants and generates synthetic therapeutic candidates , 2018, Communications Biology.

[26]  C. D. Santos,et al.  PepCVAE: Semi-Supervised Targeted Design of Antimicrobial Peptide Sequences , 2018, ArXiv.

[27]  Jaswinder Singh,et al.  Single‐sequence‐based prediction of protein secondary structures and solvent accessibility by deep whole‐sequence learning , 2018, J. Comput. Chem..

[28]  Regina Barzilay,et al.  Learning Multimodal Graph-to-Graph Translation for Molecular Optimization , 2018, ICLR.

[29]  Suzana M. Ribeiro,et al.  Joker: An algorithm to insert patterns into sequences for designing antimicrobial peptides. , 2018, Biochimica et biophysica acta. General subjects.

[30]  Amarda Shehu,et al.  Deep learning improves antimicrobial peptide recognition , 2018, Bioinform..

[31]  Aurko Roy,et al.  Fast Decoding in Sequence Models using Discrete Latent Variables , 2018, ICML.

[32]  C. Wilke,et al.  Discovery of Next-Generation Antimicrobials through Bacterial Self-Screening of Surface-Displayed Peptide Libraries , 2018, Cell.

[33]  Oriol Vinyals,et al.  Neural Discrete Representation Learning , 2017, NIPS.

[34]  Ankush Gupta,et al.  A Deep Generative Framework for Paraphrase Generation , 2017, AAAI.

[35]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

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

[37]  Xia Li,et al.  APD3: the antimicrobial peptide database as a tool for research and education , 2015, Nucleic Acids Res..

[38]  Samy Bengio,et al.  Generating Sentences from a Continuous Space , 2015, CoNLL.

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

[40]  P. Derreumaux,et al.  Improved PEP-FOLD Approach for Peptide and Miniprotein Structure Prediction. , 2014, Journal of chemical theory and computation.

[41]  Angelo Bifone,et al.  Antimicrobial Peptides Design by Evolutionary Multiobjective Optimization , 2013, PLoS Comput. Biol..

[42]  Y. Kaznessis,et al.  Computational studies of protegrin antimicrobial peptides: A review , 2011, Peptides.

[43]  William C Wimley,et al.  Describing the mechanism of antimicrobial peptide action with the interfacial activity model. , 2010, ACS chemical biology.

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

[45]  Christian Kandt,et al.  Computer simulation of antimicrobial peptides. , 2007, Current medicinal chemistry.

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

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

[48]  Oleg Konovalov,et al.  Interaction of antimicrobial peptide protegrin with biomembranes , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[49]  Michael R. Yeaman,et al.  Mechanisms of Antimicrobial Peptide Action and Resistance , 2003, Pharmacological Reviews.

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

[51]  W. Delano.  The PyMOL Molecular Graphics System , 2002 .

[52]  Robert E W Hancock,et al.  Role of membranes in the activities of antimicrobial cationic peptides. , 2002, FEMS microbiology letters.

[53]  D. Eisenberg,et al.  The hydrophobic moment detects periodicity in protein hydrophobicity. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[54]  Vladimir I. Levenshtein,et al.  Binary codes capable of correcting deletions, insertions, and reversals , 1965 .