Machine learning for antimicrobial peptide identification and design

Nature Reviews Bioengineering, Год журнала: 2024, Номер 2(5), С. 392 - 407

Опубликована: Фев. 26, 2024

Язык: Английский

---

Designing antimicrobial peptides using deep learning and molecular dynamic simulations

Briefings in Bioinformatics, Год журнала: 2023, Номер 24(2)

Опубликована: Март 1, 2023

Abstract With the emergence of multidrug-resistant bacteria, antimicrobial peptides (AMPs) offer promising options for replacing traditional antibiotics to treat bacterial infections, but discovering and designing AMPs using methods is a time-consuming costly process. Deep learning has been applied de novo design address AMP classification with high efficiency. In this study, several natural language processing models were combined identify AMPs, i.e. sequence generative adversarial nets, bidirectional encoder representations from transformers multilayer perceptron. Then, six candidate screened by AlphaFold2 structure prediction molecular dynamic simulations. These show low homology known belong novel class AMPs. After initial bioactivity testing, one peptides, A-222, showed inhibition against gram-positive gram-negative bacteria. The structural analysis peptide A-222 obtained nuclear magnetic resonance confirmed presence an alpha-helix, which was consistent results predicted AlphaFold2. We then performed structure–activity relationship study new series analogs found that activities these could be increased 4–8-fold Stenotrophomonas maltophilia WH 006 Pseudomonas aeruginosa PAO1. Overall, deep shows great potential in accelerating discovery holds promise as important tool developing

Язык: Английский

---

ToxinPred 3.0: An improved method for predicting the toxicity of peptides

Computers in Biology and Medicine, Год журнала: 2024, Номер 179, С. 108926 - 108926

Опубликована: Июль 21, 2024

Язык: Английский

---

Diff-AMP: tailored designed antimicrobial peptide framework with all-in-one generation, identification, prediction and optimization

Briefings in Bioinformatics, Год журнала: 2024, Номер 25(2)

Опубликована: Янв. 22, 2024

Abstract Antimicrobial peptides (AMPs), short with diverse functions, effectively target and combat various organisms. The widespread misuse of chemical antibiotics has led to increasing microbial resistance. Due their low drug resistance toxicity, AMPs are considered promising substitutes for traditional antibiotics. While existing deep learning technology enhances AMP generation, it also presents certain challenges. Firstly, generation overlooks the complex interdependencies among amino acids. Secondly, current models fail integrate crucial tasks like screening, attribute prediction iterative optimization. Consequently, we develop a integrated framework, Diff-AMP, that automates identification, We innovatively kinetic diffusion attention mechanisms into reinforcement framework efficient generation. Additionally, our module incorporates pre-training transfer strategies precise identification screening. employ convolutional neural network multi-attribute learning-based optimization strategy produce AMPs. This molecule optimization, thereby advancing research. have deployed Diff-AMP on web server, code, data server details available in Data Availability section.

Язык: Английский

---

AIPs-DeepEnC-GA: Predicting Anti-inflammatory Peptides using Embedded Evolutionary and Sequential Feature Integration with Genetic Algorithm based Deep Ensemble Model

Chemometrics and Intelligent Laboratory Systems, Год журнала: 2024, Номер unknown, С. 105239 - 105239

Опубликована: Сен. 1, 2024

Язык: Английский

---

AI Methods for Antimicrobial Peptides: Progress and Challenges

Microbial Biotechnology, Год журнала: 2025, Номер 18(1)

Опубликована: Янв. 1, 2025

ABSTRACT Antimicrobial peptides (AMPs) are promising candidates to combat multidrug‐resistant pathogens. However, the high cost of extensive wet‐lab screening has made AI methods for identifying and designing AMPs increasingly important, with machine learning (ML) techniques playing a crucial role. approaches have recently revolutionised this field by accelerating discovery new anti‐infective activity, particularly in preclinical mouse models. Initially, classical ML dominated field, but there been shift towards deep (DL) Despite significant contributions, existing reviews not thoroughly explored potential large language models (LLMs), graph neural networks (GNNs) structure‐guided AMP design. This review aims fill that gap providing comprehensive overview latest advancements, challenges opportunities using methods, particular emphasis on LLMs, GNNs We discuss limitations current highlight most relevant topics address coming years

Язык: Английский

---

Deep learning tools to accelerate antibiotic discovery

Expert Opinion on Drug Discovery, Год журнала: 2023, Номер 18(11), С. 1245 - 1257

Опубликована: Окт. 4, 2023

ABSTRACTIntroduction As machine learning (ML) and artificial intelligence (AI) expand to many segments of our society, they are increasingly being used for drug discovery. Recent deep models offer an efficient way explore high-dimensional data design compounds with desired properties, including those antibacterial activity.Areas covered This review covers key frameworks in antibiotic discovery, highlighting physicochemical features addressing dataset limitations. The approaches here described include discriminative such as convolutional neural networks, recurrent graph generative like language models, variational autoencoders, adversarial normalizing flow, diffusion models. the integration these discovery continues evolve, this aims provide insights into promising prospects challenges that lie ahead harnessing technologies development antibiotics.Expert opinion Accurate antimicrobial prediction using faces imbalanced data, limited datasets, experimental validation, target strains, structure. bioinformatics, molecular dynamics, augmentation holds potential overcome challenges, enhance model performance, utlimately accelerate discovery.KEYWORDS: Drug discoverydrug designantimicrobialsDeep-learning modelsinfectious diseases Article highlights AI ML innovative ways expedite by optimizing design.The successful use is directly impacted algorithm influences model´s ability represent diverse structures.Discriminative computational predicting activity, leveraging their specific architectures approaches.Generative applied utilizing composition molecules generate potent candidates.Deep yet face due quality availability limitations.AcknowledgmentsThe authors thank Dr. Karen Pepper editing manuscript de la Fuente Lab members insightful discussions. All figures were prepared BioRender.com. Molecules shown paper rendered PyMOL Molecular Graphics System, Version 2.5.2 Schrödinger, LLC.Declaration interestC Fuente-Nunez provides consulting services Invaio Sciences a member Scientific Advisory Boards Nowture S.L. Phare Bio. have no other relevant affiliations or financial involvement any organization entity interest conflict subject matter materials discussed apart from disclosed.Reviewer disclosuresPeer reviewers on relationships disclose.Additional informationFundingCesar Presidential Professorship at University Pennsylvania, recipient Langer Prize AIChE Foundation, acknowledges funding IADR Innovation Oral Care Award, Procter & Gamble Company, United Therapeutics, BBRF Young Investigator Grant, Nemirovsky Prize, Penn Health-Tech Accelerator Dean's Fund Perelman School Medicine National Institute General Medical Institutes Health under award number R35GM138201, Defense Threat Reduction Agency (DTRA; HDTRA11810041, HDTRA1-21-1-0014, HDTRA1-23-1-0001).

Язык: Английский

---

Geometric deep learning as a potential tool for antimicrobial peptide prediction

Frontiers in Bioinformatics, Год журнала: 2023, Номер 3

Опубликована: Июль 13, 2023

Antimicrobial peptides (AMPs) are components of natural immunity against invading pathogens. They polymers that fold into a variety three-dimensional structures, enabling their function, with an underlying sequence is best represented in non-flat space. The structural data AMPs exhibits non-Euclidean characteristics, which means certain properties, e.g., differential manifolds, common system coordinates, vector space structure, or translation-equivariance, along basic operations like convolution, not distinctly established. Geometric deep learning (GDL) refers to category machine methods utilize neural models process and analyze settings, such as graphs manifolds. This emerging field seeks expand the use structured these domains. review provides detailed summary latest developments designing predicting utilizing GDL techniques also discusses both current research gaps future directions field.

Язык: Английский

---

Predicting Antimicrobial Peptides Using ESMFold-Predicted Structures and ESM-2-Based Amino Acid Features with Graph Deep Learning

Journal of Chemical Information and Modeling, Год журнала: 2024, Номер 64(10), С. 4310 - 4321

Опубликована: Май 13, 2024

Currently, antimicrobial resistance constitutes a serious threat to human health. Drugs based on peptides (AMPs) constitute one of the alternatives address it. Shallow and deep learning (DL)-based models have mainly been built from amino acid sequences predict AMPs. Recent advances in tertiary (3D) structure prediction opened new opportunities this field. In sense, graphs derived predicted peptide structures recently proposed. However, these are not correspondence with state-of-the-art approaches codify evolutionary information, and, addition, they memory- time-consuming because depend multiple sequence alignment. Herein, we presented framework create alignment-free graph representations generated ESMFold-predicted structures, whose nodes characterized acid-level information Evolutionary Scale Modeling (ESM-2) models. A attention network (GAT) was implemented assess usefulness AMP classification. To end, set comprised 67,058 used. It demonstrated that proposed methodology allowed build GAT generalization abilities consistently better than 20 non-DL-based DL-based The best were developed using 36- 33-layer ESM-2 Similarity studies showed best-built codified different chemical spaces, thus fused significantly improve general, results suggest esm-AxP-GDL is promissory tool develop good, structure-dependent, can be successfully applied screening large data sets. This should only useful classify AMPs but also for modeling other protein activities.

Язык: Английский

---

A computational model of circRNA-associated diseases based on a graph neural network: prediction and case studies for follow-up experimental validation

BMC Biology, Год журнала: 2024, Номер 22(1)

Опубликована: Янв. 29, 2024

Abstract Background Circular RNAs (circRNAs) have been confirmed to play a vital role in the occurrence and development of diseases. Exploring relationship between circRNAs diseases is far-reaching significance for studying etiopathogenesis treating To this end, based on graph Markov neural network algorithm (GMNN) constructed our previous work GMNN2CD, we further considered multisource biological data that affects association circRNA disease developed an updated web server CircDA human hepatocellular carcinoma (HCC) tissue verify prediction results CircDA. Results built Tumarkov-based deep learning framework. The regards biomolecules as nodes interactions molecules edges, reasonably abstracts multiomics data, models them heterogeneous biomolecular network, which can reflect complex different biomolecules. Case studies using literature from HCC, cervical, gastric cancers demonstrate predictor identify missing associations known diseases, quantitative real-time PCR (RT-qPCR) experiment HCC samples, it was found five were significantly differentially expressed, proved predict related new circRNAs. Conclusions This efficient computational case analysis with sufficient feedback allows us circRNA-associated disease-associated Our provides method provide guidance certain For ease use, online ( http://server.malab.cn/CircDA ) provided, code open-sourced https://github.com/nmt315320/CircDA.git convenience improvement.

Язык: Английский

---