A Machine Learning Bioinformatics Method to Predict Biological Activity from Biosynthetic Gene Clusters

Overview

Journal J Chem Inf Model

Publisher American Chemical Society

Specialties Chemistry
Medical Informatics

Date 2021 May 27

PMID 34042443

Citations 33

Authors

Allison S Walker

Jon Clardy

Affiliations

Soon will be listed here.

Abstract

Research in natural products, the genetically encoded small molecules produced by organisms in an idiosyncratic fashion, deals with molecular structure, biosynthesis, and biological activity. Bioinformatics analyses of microbial genomes can successfully reveal the genetic instructions, biosynthetic gene clusters, that produce many natural products. Genes to molecule predictions made on biosynthetic gene clusters have revealed many important new structures. There is no comparable method for genes to biological activity predictions. To address this missing pathway, we developed a machine learning bioinformatics method for predicting a natural product's antibiotic activity directly from the sequence of its biosynthetic gene cluster. We trained commonly used machine learning classifiers to predict antibacterial or antifungal activity based on features of known natural product biosynthetic gene clusters. We have identified classifiers that can attain accuracies as high as 80% and that have enabled the identification of biosynthetic enzymes and their corresponding molecular features that are associated with antibiotic activity.

Citing Articles

Amphibian skin bacteria contain a wide repertoire of genes linked to their antifungal capacities.

Gonzalez-Serrano F, Romero-Contreras Y, Orta A, Basanta M, Morales H, Sandoval Garcia G World J Microbiol Biotechnol. 2025; 41(3):78.

PMID: 40011297 PMC: 11865118. DOI: 10.1007/s11274-025-04292-z.

Artificial Intelligence in Natural Product Drug Discovery: Current Applications and Future Perspectives.

Gangwal A, Lavecchia A J Med Chem. 2025; 68(4):3948-3969.

PMID: 39916476 PMC: 11874025. DOI: 10.1021/acs.jmedchem.4c01257.

Interpretable adenylation domain specificity prediction using protein language models.

Adduri A, McNutt A, Ellington C, Suraparaju K, Fang N, Yan D bioRxiv. 2025; .

PMID: 39868251 PMC: 11761653. DOI: 10.1101/2025.01.13.632878.

Exploring the Promoter Generation and Prediction of spp. Based on GAN and Multi-Model Fusion Methods.

Zhao C, Guan Y, Yan S, Li J Int J Mol Sci. 2024; 25(23).

PMID: 39684846 PMC: 11642183. DOI: 10.3390/ijms252313137.

TPGPred: A Mixed-Feature-Driven Approach for Identifying Thermophilic Proteins Based on GradientBoosting.

Zhao C, Yan S, Li J Int J Mol Sci. 2024; 25(22).

PMID: 39595936 PMC: 11594102. DOI: 10.3390/ijms252211866.

References

Khaldi N, Seifuddin F, Turner G, Haft D, Nierman W, Wolfe K . SMURF: Genomic mapping of fungal secondary metabolite clusters. Fungal Genet Biol. 2010; 47(9):736-41. PMC: 2916752. DOI: 10.1016/j.fgb.2010.06.003. View

Kautsar S, Blin K, Shaw S, Navarro-Munoz J, Terlouw B, van der Hooft J . MIBiG 2.0: a repository for biosynthetic gene clusters of known function. Nucleic Acids Res. 2019; 48(D1):D454-D458. PMC: 7145714. DOI: 10.1093/nar/gkz882. View

Hanchen A, Rausch S, Landmann B, Toti L, Nusser A, Sussmuth R . Alanine scan of the peptide antibiotic feglymycin: assessment of amino acid side chains contributing to antimicrobial activity. Chembiochem. 2013; 14(5):625-32. DOI: 10.1002/cbic.201300032. View

Umezawa K, Nakazawa K, Ikeda Y, Naganawa H, Kondo S . Polyoxypeptins A and B Produced by Streptomyces: Apoptosis-Inducing Cyclic Depsipeptides Containing the Novel Amino Acid (2S,3R)-3-Hydroxy-3-methylproline. J Org Chem. 2001; 64(9):3034-3038. DOI: 10.1021/jo981512n. View

Butcher R, Schroeder F, Fischbach M, Straight P, Kolter R, Walsh C . The identification of bacillaene, the product of the PksX megacomplex in Bacillus subtilis. Proc Natl Acad Sci U S A. 2007; 104(5):1506-9. PMC: 1785240. DOI: 10.1073/pnas.0610503104. View

Nam J, Shin D, Rew Y, Boger D . Alanine scan of [L-Dap(2)]ramoplanin A2 aglycon: assessment of the importance of each residue. J Am Chem Soc. 2007; 129(28):8747-55. PMC: 2593884. DOI: 10.1021/ja068573k. View

De Los Santos E . NeuRiPP: Neural network identification of RiPP precursor peptides. Sci Rep. 2019; 9(1):13406. PMC: 6746993. DOI: 10.1038/s41598-019-49764-z. View

Richter M, Drown B, Riley A, Garcia A, Shirai T, Svec R . Predictive compound accumulation rules yield a broad-spectrum antibiotic. Nature. 2017; 545(7654):299-304. PMC: 5737020. DOI: 10.1038/nature22308. View

Du Y, Wang Y, Huang T, Tao M, Deng Z, Lin S . Identification and characterization of the biosynthetic gene cluster of polyoxypeptin A, a potent apoptosis inducer. BMC Microbiol. 2014; 14:30. PMC: 3943440. DOI: 10.1186/1471-2180-14-30. View

10.

Kingston D . Modern natural products drug discovery and its relevance to biodiversity conservation. J Nat Prod. 2010; 74(3):496-511. PMC: 3061248. DOI: 10.1021/np100550t. View

11.

Hannigan G, Prihoda D, Palicka A, Soukup J, Klempir O, Rampula L . A deep learning genome-mining strategy for biosynthetic gene cluster prediction. Nucleic Acids Res. 2019; 47(18):e110. PMC: 6765103. DOI: 10.1093/nar/gkz654. View

12.

Blin K, Wolf T, Chevrette M, Lu X, Schwalen C, Kautsar S . antiSMASH 4.0-improvements in chemistry prediction and gene cluster boundary identification. Nucleic Acids Res. 2017; 45(W1):W36-W41. PMC: 5570095. DOI: 10.1093/nar/gkx319. View

13.

Jia B, Raphenya A, Alcock B, Waglechner N, Guo P, Tsang K . CARD 2017: expansion and model-centric curation of the comprehensive antibiotic resistance database. Nucleic Acids Res. 2016; 45(D1):D566-D573. PMC: 5210516. DOI: 10.1093/nar/gkw1004. View

14.

Sheldrick G, Jones P, KENNARD O, Williams D, Smith G . Structure of vancomycin and its complex with acetyl-D-alanyl-D-alanine. Nature. 1978; 271(5642):223-5. DOI: 10.1038/271223a0. View

15.

Tenson T, Lovmar M, Ehrenberg M . The mechanism of action of macrolides, lincosamides and streptogramin B reveals the nascent peptide exit path in the ribosome. J Mol Biol. 2003; 330(5):1005-14. DOI: 10.1016/s0022-2836(03)00662-4. View

16.

Bockus A, Schwochert J, Pye C, Townsend C, Sok V, Bednarek M . Going Out on a Limb: Delineating The Effects of β-Branching, N-Methylation, and Side Chain Size on the Passive Permeability, Solubility, and Flexibility of Sanguinamide A Analogues. J Med Chem. 2015; 58(18):7409-18. DOI: 10.1021/acs.jmedchem.5b00919. View

17.

Yang J, Zhu X, Cao M, Wang C, Zhang C, Lu Z . Genomics-Inspired Discovery of Three Antibacterial Active Metabolites, Aurantinins B, C, and D from Compost-Associated Bacillus subtilis fmb60. J Agric Food Chem. 2016; 64(46):8811-8820. DOI: 10.1021/acs.jafc.6b04455. View

18.

Al Toma R, Brieke C, Cryle M, Sussmuth R . Structural aspects of phenylglycines, their biosynthesis and occurrence in peptide natural products. Nat Prod Rep. 2015; 32(8):1207-35. DOI: 10.1039/c5np00025d. View

19.

Gerlt J, Bouvier J, Davidson D, Imker H, Sadkhin B, Slater D . Enzyme Function Initiative-Enzyme Similarity Tool (EFI-EST): A web tool for generating protein sequence similarity networks. Biochim Biophys Acta. 2015; 1854(8):1019-37. PMC: 4457552. DOI: 10.1016/j.bbapap.2015.04.015. View

20.

Palacios D, Dailey I, Siebert D, Wilcock B, Burke M . Synthesis-enabled functional group deletions reveal key underpinnings of amphotericin B ion channel and antifungal activities. Proc Natl Acad Sci U S A. 2011; 108(17):6733-8. PMC: 3084054. DOI: 10.1073/pnas.1015023108. View