An interpretable machine learning approach to identify the mechanism of action of antibiotics
World Health Organization et al. The lack of new antibiotics threatens global efforts to contain drug-resistant infections. (2020).
Neill, JO Antimicrobial resistance: tackling a crisis for the health and wealth of nations presided over by the antimicrobial resistance review. In Briefing Paper – Confronting a Crisis for the Health and Wealth of Nations1–20 (HM Government Wellcome Trust, 2014).
Pence, HE, & Williams A. Chemspider: An Online Chemical Information Resource (2010).
Kim, S. et al. Pubchem substance and compound databases. Nucl. Acids Res. 44(D1), D1202–D1213 (2016).
Irwin, JJ & Shoichet, BK Zinc—A free database of commercially available compounds for virtual screening. J. Chem. Inf. Model. 45(1), 177–182 (2005).
Ashby, J. The value and limitations of short-term genotoxicity testing and the inadequacy of current chemical screening criteria for cancer bioassays. Anna. NY Acad. Science. 534(1), 133-138 (1988).
King, RD, Muggleton, S., Lewis, RA, and Sternberg, M. Machine Learning Drug Design: Using Inductive Logic Programming to Model the Structure-Activity Relationships of Trimethoprim Analogs Binding to Dihydrofolate Reductase. proc. Natl. Acad. Science. 89(23), 11322–11326 (1992).
Hirst, JD, King, RD & Sternberg, MJ Quantitative structure-activity relationships using neural networks and inductive logic programming. I. Dihydrofolate reductase inhibition by pyrimidines. J. Comput.-Aided Mol. Of the. 8(4), 405–420 (1994).
Bronstein, MM, Bruna, J., LeCun, Y., Szlam, A. & Vandergheynst, P. Geometric Deep Learning: Going Beyond Euclidean Data. IEEE signal process. Mag. 34(4), 18–42 (2017).
Stokes, JM et al. A deep learning approach to antibiotic discovery. Cell 180(4), 688–702 (2020).
Dai, H., Dai, B., and Song, L. Discriminant Embeddings of Latent Variable Models for Structured Data. In International Conference on Machine Learning2702–2711 (PMLR, 2016).
Yang, K. et al. Analyze learned molecular representations for property prediction. J. Chem. Inf. Model. 59(8), 3370–3388 (2019).
Desk et al. Design, synthesis, and structure-activity relationship of competitive, selective, and in vivo active triazole and thiadiazole inhibitors on the n-terminal c-jun kinase substrate. J.Med. Chem. 52(7), 1943-1952 (2009).
Chen, X.-W., & Jeong, JC Improved recursive feature elimination. In Sixth International Conference on Machine Learning and its Applications (ICMLA 2007)429–435 (IEEE, 2007).
Kursa, MB & Rudnicki, WR Feature selection with the Boruta package. J. Stat. Software 361–13 (2010).
Tibshirani, R. Regression shrinkage and selection via lasso. JR statistics. Soc. Ser. B methodology. 58(1), 267–288 (1996).
Pope, PE, Kolouri, S., Rostami, M., Martin, CE, and Hoffmann, H. Explainability methods for graph convolutional neural networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition10772–10781 (2019).
Kojima, R. et al. kgcn: A graph-based deep learning framework for chemical structures. J. Cheminform. 12(1), 1–10 (2020).
Baldassarre, F., & Azizpour, H. Explainability techniques for convolutional networks of graphs. CoRR, flight. abs/1905.13686, (2019).
Montavon, G., Lapuschkin, S., Binder, A., Samek, W. & Müller, K.-R. Explain nonlinear classification decisions with a deep Taylor decomposition. Pattern recognition. 65211-222 (2017).
Ying, R., Bourgeois, D., You, J., Zitnik, M., & Leskovec, J. Gnn Explainer: A Tool for Post-Hoc Explanation of Graph Neural Networks. preprint arXiv arXiv:1903.03894, (2019).
Corsello, SM et al. The Medication Redirection Center: A library and information resource for next-generation medications. Nat. Med. 23(4), 405–408 (2017).
Zuegg, J., Hansford, KA, Elliott, AG, Cooper, MA, and Blaskovich, MA How to stimulate and facilitate early antibiotic discovery. ACS Infect. Say. 6(6), 1302-1304 (2020).
Blaskovich, MA, Zuegg, J., Elliott, AG & Cooper, MA Helping chemists discover new antibiotics. ACS Infect. Say. 1(7), 285–287 (2015).
Reeve, SM, Lombardo, MN & Anderson, AC Understanding the structural mechanisms of antibiotic resistance paves the way for new discoveries. Future Microbiol. ten(11), 1727-1733 (2015).
Cho, H., Uehara, T. & Bernhardt, TG Beta-lactam antibiotics induce lethal dysfunction of bacterial cell wall synthesis machinery. Cell 159(6), 1300–1311 (2014).
Pham, TD, Ziora, ZM, and Blaskovich, MA Quinolone antibiotics. MedChemComm ten(10), 1719-1739 (2019).
Person, G. et al. Mitogen-activated protein kinase (MAP) pathways: Regulation and physiological functions. Endocr. Round. 22(2), 153–183 (2001).
Fleman, R. et al. Combinatorial libraries as a tool for the discovery of novel broad-spectrum antibacterial agents targeting ESKAPE pathogens. J.Med. Chem. 58(8), 3340–3355 (2015).
Wang, B. et al. Antibacterial diamines targeting bacterial membranes. J.Med. Chem. 59(7), 3140–3151 (2016).
Qian, L., Guan, Y., He, B. & Xiao, H. Modified guanidine polymers: synthesis and antimicrobial mechanism revealed by AFM. Polymer 49(10), 2471-2475 (2008).
Olender, D., Żwawiak, J. & Zaprutko, L. Multidirectional efficacy of biologically active nitro compounds included in drugs. Medications 11(2), 54 (2018).
Whitt, J. et al. Synthesis of hydrazone derivatives of 4-[4-formyl-3-(2-oxochromen-3-yl) pyrazol-1-yl] benzoic acid as potent growth inhibitors of antibiotic resistant bacteria Staphylococcus aureus and Acinetobacter baumannii. Molecules 24(11), 2051 (2019).
Lv, Q.-Z. et al. A new antifungal agent (4-phenyl-1,3-thiazol-2-yl) hydrazine induces oxidative damage in Candida albicans. Front. Cell. Infect. Microbiol. ten557 (2020).
Landrum, G. et al.. Rdkit: Open-source chemistry. (2006).
Weininger, D. Smiles, a chemical language and an information system. 1. Introduction to methodology and encoding rules. J. Chem. Inf. Calculation. Science. 28(1), 31-36 (1988).
Him, H. & Ma, Y. Unbalanced learning: foundations, algorithms and applications (Wiley, 2013).