Using Evolutionary Algorithms and Machine Learning to Explore Sequence Space for the Discovery of Antimicrobial Peptides

Yoshida, Mari; Hinkley, Trevor; Tsuda, Soichiro; Abul‐Haija, Yousef M.; McBurney, Roy T.; Куликов, В. Н.; Mathieson, Jennifer S.; Reyes, Sabrina Galiñanes; Castro, M. D. Luque de; Cronin, Leroy

doi:10.1016/j.chempr.2018.01.005

Cited by 113 publications

(107 citation statements)

References 43 publications

Supporting

Mentioning

105

Contrasting

Unclassified

Order By: Relevance

“…The concept of computer-aided de novo drug design was first introduced more than 25 years ago (Danziger and Dean, 1989). Fjell et al, 2011;Maccari et al, 2013;Porto et al, 2018b;Yoshida et al, 2018 In that study, an algorithm for knowledge acquisition about hydrogen-bonding regions on protein surfaces was generated, aiming at designing novel ligands that specifically bind to a target site. Ever since, diverse de novo algorithms have been reported and many feasible drug candidates have been generated, and vast libraries (from 10 4 to 10 6 compounds) are usually screened in biological assays (Dobson, 2004;Schneider and Fechner, 2005).…”

Section: De Novo Computational Designmentioning

confidence: 99%

Computer-Aided Design of Antimicrobial Peptides: Are We Generating Effective Drug Candidates?

et al. 2020

View full text Add to dashboard Cite

Computer-Aided Design of Antimicrobial Peptides http://crdd.osdd.net/raghava/antibp2/ ClassAMP Uses RF and SVM to predict the propensity of a protein sequence to have antibacterial, antifungal, or antiviral activity http://www.bicnirrh.res.in/classamp/ AMPA Web tool for assessing the antimicrobial domains of proteins, with a focus on the design on new antimicrobial drugs http://tcoffee.crg.cat/apps/ampa/do DBAASP Provides users with information on detailed structure (chemical, 3D) and activity for those peptides, for which antimicrobial activity against particular target species have been evaluated experimentally https://dbaasp.org/home Joker An algorithm to design antimicrobial peptides using their language https://github.com/williamfp7/Joker

show abstract

Section: De Novo Computational Designmentioning

confidence: 99%

Computer-Aided Design of Antimicrobial Peptides: Are We Generating Effective Drug Candidates?

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Other groups have 31 used regression approaches, based on peptide structure and biophysical properties, to quantitatively predict 32 antimicrobial activity. These approaches are often used for local sequence optimization around a specific known 33 AMP scaffold (Yoshida et al, 2018;Hilpert et al, 2006). 34…”

mentioning

confidence: 99%

Deep learning regression model for antimicrobial peptide design

Witten

2019

Preprint

View full text Add to dashboard Cite

7Antimicrobial peptides (AMPs) are naturally occurring or synthetic peptides that show promise for treating 8 antibiotic-resistant pathogens. Machine learning techniques are increasingly used to identify naturally occurring 9AMPs, but there is a dearth of purely computational methods to design novel effective AMPs, which would speed 10 AMP development. We collected a large database, Giant Repository of AMP Activities (GRAMPA), containing 11 AMP sequences and associated MICs. We designed a convolutional neural network to perform combined 12 classification and regression on peptide sequences to quantitatively predict AMP activity against Escherichia coli. 13Our predictions outperformed the state of the art at AMP classification and were also effective at regression, for 14 which there were no publicly available comparisons. We then used our model to design novel AMPs and 15 experimentally demonstrated activity of these AMPs against the pathogens E. coli, Pseudomonas aeruginosa, and 16Staphylococcus aureus. Data, code, and neural network architecture and parameters are available at

show abstract

“…Computation tools are now available to support the prediction of the outcome of chemical reactions, 52,53 and the design of follow-up molecules with desirable properties (including affinity, selectivity and physicochemical profiles). 2,43,54,55 However, the integration of all of these components remains an unmet challenge that is nonetheless needed to realise fully autonomous molecular discovery!…”

Section: Discussionmentioning

confidence: 99%

Streamlining bioactive molecular discovery through integration and automation

2018

View full text Add to dashboard Cite

Article:Chow, S orcid.org/0000-0002-3600-0497, Liver, S and Nelson, AS orcid.org/0000-0003-3886-363X (2018) Streamlining bioactive molecular discovery through integration and automation. Nature Reviews Chemistry, 2 (8). AbstractThe discovery of bioactive small molecules is generally driven via iterative design-make-purifytest cycles. Automation is routinely harnessed at individual stages in order to increase the productivity of drug discovery. We describe recent progress to automate and integrate two or more adjacent stages within discovery workflows. The value of these integrated technologies is illustrated in the context of specific discovery case studies. We note that, to maximise impact on the productivity of discovery, each of the integrated stages would need to have both high and matched throughput. We also consider the longer-term goal of realising the fully autonomous discovery of bioactive small molecules through integration and automation of all stages of discovery.

show abstract

Using Evolutionary Algorithms and Machine Learning to Explore Sequence Space for the Discovery of Antimicrobial Peptides

Abstract: Here, we use a closed-loop discovery and optimization approach for searching the peptide sequence space. Combining an evolutionary algorithm with machine learning and in vitro assay allowed for rapid development of new antimicrobial peptides.

Cited by 113 publications

References 43 publications

Computer-Aided Design of Antimicrobial Peptides: Are We Generating Effective Drug Candidates?

Computer-Aided Design of Antimicrobial Peptides: Are We Generating Effective Drug Candidates?

Deep learning regression model for antimicrobial peptide design

Streamlining bioactive molecular discovery through integration and automation

Contact Info

Product

Resources

About