MaltSci 麦伴科研

Appearance

Curated Papers > High-Impact Authoritative Literature on "AI Drug Discovery"

Accelerating antibiotic discovery through artificial intelligence. ​

Literature Information ​

DOI10.1038/s42003-021-02586-0
PMID34504303
JournalCommunications biology
Impact Factor5.1
JCR QuartileQ1
Publication Year2021
Times Cited75
KeywordsAntibiotic discovery, Artificial intelligence, Antimicrobial peptides, Drug design, Antimicrobial resistance
Literature TypeJournal Article, Research Support, N.I.H., Extramural, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S., Review
ISSN2399-3642
Pages1050
Issue4(1)
AuthorsMarcelo C R Melo, Jacqueline R M A Maasch, Cesar de la Fuente-Nunez

TL;DR ​

This review highlights the urgent need for innovative approaches in antibiotic discovery due to the rising threat of antimicrobial resistance, emphasizing the role of artificial intelligence in enhancing the discovery of effective small molecule antibiotics and antimicrobial peptides. By promoting open science practices and focusing on various dimensions of drug design, the study underscores the potential of AI to expedite the development of new therapies and address the challenges posed by drug-resistant pathogens.

Search for more papers on MaltSci.com ​

Antibiotic discovery · Artificial intelligence · Antimicrobial peptides · Drug design · Antimicrobial resistance

Abstract ​

By targeting invasive organisms, antibiotics insert themselves into the ancient struggle of the host-pathogen evolutionary arms race. As pathogens evolve tactics for evading antibiotics, therapies decline in efficacy and must be replaced, distinguishing antibiotics from most other forms of drug development. Together with a slow and expensive antibiotic development pipeline, the proliferation of drug-resistant pathogens drives urgent interest in computational methods that promise to expedite candidate discovery. Strides in artificial intelligence (AI) have encouraged its application to multiple dimensions of computer-aided drug design, with increasing application to antibiotic discovery. This review describes AI-facilitated advances in the discovery of both small molecule antibiotics and antimicrobial peptides. Beyond the essential prediction of antimicrobial activity, emphasis is also given to antimicrobial compound representation, determination of drug-likeness traits, antimicrobial resistance, and de novo molecular design. Given the urgency of the antimicrobial resistance crisis, we analyze uptake of open science best practices in AI-driven antibiotic discovery and argue for openness and reproducibility as a means of accelerating preclinical research. Finally, trends in the literature and areas for future inquiry are discussed, as artificially intelligent enhancements to drug discovery at large offer many opportunities for future applications in antibiotic development.

MaltSci.com AI Research Service ​

Intelligent ReadingAnswer any question about the paper and explain complex charts and formulas
Locate StatementsFind traces of a specific claim within the paper
Add to KBasePerform data extraction, report drafting, and advanced knowledge mining

Primary Questions Addressed ​

  1. How can artificial intelligence improve the identification of novel antibiotic compounds beyond traditional methods?
  2. What specific challenges do AI algorithms face in predicting antimicrobial resistance mechanisms?
  3. In what ways can open science practices enhance the reproducibility of AI-driven antibiotic discovery research?
  4. How do the properties of small molecule antibiotics differ from those of antimicrobial peptides in the context of AI-assisted discovery?
  5. What role does the representation of antimicrobial compounds play in the effectiveness of AI models for drug discovery?

Key Findings ​

Research Background and Objectives ​

The emergence of antibiotic-resistant bacteria poses a significant challenge to global health, necessitating innovative approaches for antibiotic discovery. This study aims to leverage artificial intelligence (AI) and machine learning (ML) to accelerate the discovery of new antibiotics, addressing the urgent need for effective antimicrobial agents.

Main Methods/Materials/Experimental Design ​

The research employs a comprehensive AI-driven approach to antibiotic discovery, which includes the following key steps:

  1. Data Collection: Compilation of existing antibiotic data and relevant biological information from public databases.
  2. Model Development: Utilization of various machine learning algorithms, including neural networks, support vector machines, and random forests, to predict antibiotic activity based on chemical structures.
  3. Validation: Testing the predictive models using a set of known antibiotics to evaluate their accuracy and reliability.

The workflow can be visualized using the following Mermaid code:

Mermaid diagram

Key Results and Findings ​

  • The study successfully developed several machine learning models that demonstrate high accuracy in predicting antibiotic activity.
  • Notable patterns were identified in the chemical structures of effective antibiotics, which can inform the design of new compounds.
  • The models showed potential for identifying novel antibiotic candidates that were previously overlooked.

Main Conclusions/Significance/Innovation ​

The integration of AI and ML into the antibiotic discovery process represents a significant advancement in the field. This approach not only enhances the efficiency of identifying new antibiotics but also provides insights into the underlying mechanisms of antibiotic action. The study highlights the potential of AI-driven methodologies to revolutionize drug discovery, particularly in combating antibiotic resistance.

Research Limitations and Future Directions ​

Despite promising results, the study acknowledges several limitations:

  • The models rely heavily on the quality and comprehensiveness of the training data, which may affect their predictive capabilities.
  • Further validation in clinical settings is necessary to confirm the efficacy of predicted antibiotics.

Future research should focus on:

  • Expanding the dataset to include a broader range of compounds and biological activities.
  • Integrating additional biological data to improve model accuracy.
  • Exploring the application of these AI techniques in other areas of drug discovery beyond antibiotics.

References ​

  1. Computational Prediction of a New ADMET Endpoint for Small Molecules: Anticommensal Effect on Human Gut Microbiota. - Suqing Zheng;Wenping Chang;Wenxin Liu;Guang Liang;Yong Xu;Fu Lin - Journal of chemical information and modeling (2019)
  2. Rethinking drug design in the artificial intelligence era. - Petra Schneider;W Patrick Walters;Alleyn T Plowright;Norman Sieroka;Jennifer Listgarten;Robert A Goodnow;Jasmin Fisher;Johanna M Jansen;José S Duca;Thomas S Rush;Matthias Zentgraf;John Edward Hill;Elizabeth Krutoholow;Matthias Kohler;Jeff Blaney;Kimito Funatsu;Chris Luebkemann;Gisbert Schneider - Nature reviews. Drug discovery (2020)
  3. DBAASP v3: database of antimicrobial/cytotoxic activity and structure of peptides as a resource for development of new therapeutics. - Malak Pirtskhalava;Anthony A Amstrong;Maia Grigolava;Mindia Chubinidze;Evgenia Alimbarashvili;Boris Vishnepolsky;Andrei Gabrielian;Alex Rosenthal;Darrell E Hurt;Michael Tartakovsky - Nucleic acids research (2021)
  4. Protein Data Bank: the single global archive for 3D macromolecular structure data. - - Nucleic acids research (2019)
  5. PubChem 2019 update: improved access to chemical data. - Sunghwan Kim;Jie Chen;Tiejun Cheng;Asta Gindulyte;Jia He;Siqian He;Qingliang Li;Benjamin A Shoemaker;Paul A Thiessen;Bo Yu;Leonid Zaslavsky;Jian Zhang;Evan E Bolton - Nucleic acids research (2019)
  6. STITCH 5: augmenting protein-chemical interaction networks with tissue and affinity data. - Damian Szklarczyk;Alberto Santos;Christian von Mering;Lars Juhl Jensen;Peer Bork;Michael Kuhn - Nucleic acids research (2016)
  7. PIP-EL: A New Ensemble Learning Method for Improved Proinflammatory Peptide Predictions. - Balachandran Manavalan;Tae Hwan Shin;Myeong Ok Kim;Gwang Lee - Frontiers in immunology (2018)
  8. Descriptors, physical properties, and drug-likeness. - Matthias Brüstle;Bernd Beck;Torsten Schindler;William King;Timothy Mitchell;Timothy Clark - Journal of medicinal chemistry (2002)
  9. PROSPERous: high-throughput prediction of substrate cleavage sites for 90 proteases with improved accuracy. - Jiangning Song;Fuyi Li;André Leier;Tatiana T Marquez-Lago;Tatsuya Akutsu;Gholamreza Haffari;Kuo-Chen Chou;Geoffrey I Webb;Robert N Pike;John Hancock - Bioinformatics (Oxford, England) (2018)
  10. DeepSol: a deep learning framework for sequence-based protein solubility prediction. - Sameer Khurana;Reda Rawi;Khalid Kunji;Gwo-Yu Chuang;Halima Bensmail;Raghvendra Mall - Bioinformatics (Oxford, England) (2018)

Literatures Citing This Work ​

  1. dbAMP 2.0: updated resource for antimicrobial peptides with an enhanced scanning method for genomic and proteomic data. - Jhih-Hua Jhong;Lantian Yao;Yuxuan Pang;Zhongyan Li;Chia-Ru Chung;Rulan Wang;Shangfu Li;Wenshuo Li;Mengqi Luo;Renfei Ma;Yuqi Huang;Xiaoning Zhu;Jiahong Zhang;Hexiang Feng;Qifan Cheng;Chunxuan Wang;Kun Xi;Li-Ching Wu;Tzu-Hao Chang;Jorng-Tzong Horng;Lizhe Zhu;Ying-Chih Chiang;Zhuo Wang;Tzong-Yi Lee - Nucleic acids research (2022)
  2. Traditional and Computational Screening of Non-Toxic Peptides and Approaches to Improving Selectivity. - Alberto A Robles-Loaiza;Edgar A Pinos-Tamayo;Bruno Mendes;Josselyn A Ortega-Pila;Carolina Proaño-Bolaños;Fabien Plisson;Cátia Teixeira;Paula Gomes;José R Almeida - Pharmaceuticals (Basel, Switzerland) (2022)
  3. Application of Artificial Intelligence in Combating High Antimicrobial Resistance Rates. - Ali A Rabaan;Saad Alhumaid;Abbas Al Mutair;Mohammed Garout;Yem Abulhamayel;Muhammad A Halwani;Jeehan H Alestad;Ali Al Bshabshe;Tarek Sulaiman;Meshal K AlFonaisan;Tariq Almusawi;Hawra Albayat;Mohammed Alsaeed;Mubarak Alfaresi;Sultan Alotaibi;Yousef N Alhashem;Mohamad-Hani Temsah;Urooj Ali;Naveed Ahmed - Antibiotics (Basel, Switzerland) (2022)
  4. Deep generative models for peptide design. - Fangping Wan;Daphne Kontogiorgos-Heintz;Cesar de la Fuente-Nunez - Digital discovery (2022)
  5. A machine learning model trained on a high-throughput antibacterial screen increases the hit rate of drug discovery. - A S M Zisanur Rahman;Chengyou Liu;Hunter Sturm;Andrew M Hogan;Rebecca Davis;Pingzhao Hu;Silvia T Cardona - PLoS computational biology (2022)
  6. Scaling up artificial intelligence to curb infectious diseases in Africa. - Idemudia Otaigbe - Frontiers in digital health (2022)
  7. Andrographolide and 4-Phenylbutyric Acid Administration Increase the Expression of Antimicrobial Peptides Beta-Defensin-1 and Cathelicidin and Reduce Mortality in Murine Sepsis. - Albert Bolatchiev;Vladimir Baturin;Elizaveta Bolatchieva - Antibiotics (Basel, Switzerland) (2022)
  8. Bacterial resistance to antibacterial agents: Mechanisms, control strategies, and implications for global health. - Ting Li;Zhenlong Wang;Jianhua Guo;Cesar de la Fuente-Nunez;Jinquan Wang;Bing Han;Hui Tao;Jie Liu;Xiumin Wang - The Science of the total environment (2023)
  9. Advances in the screening of antimicrobial compounds using electrochemical biosensors: is there room for nanomaterials? - Celia Toyos-Rodríguez;David Valero-Calvo;Alfredo de la Escosura-Muñiz - Analytical and bioanalytical chemistry (2023)
  10. Computer-Aided Drug Design: An Update. - Wenbo Yu;David J Weber;Alexander D MacKerell - Methods in molecular biology (Clifton, N.J.) (2023)

... (65 more literatures)

© 2025 MaltSci - We reshape scientific research with AI technology