Towards machine learning discovery of dual antibacterial drug–nanoparticle systems

Diéguez-Santana, Karel; González-Dı́az, Humberto

doi:10.1039/d1nr04178a

Cited by 17 publications

(19 citation statements)

References 122 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result of this search, we can conclude that the IFPTML models reported in this work are the only one considering the three subsystems at time AD, NP, and MD. On the other hand, Ortega-Tenezaca et al 86 and Diéguez-Santana et al 87 also published IFPTML approaches to the present problem. Nevertheless, both models fail to account for one of the parts of the system.…”

Section: Resultsmentioning

confidence: 84%

Section: Resultsmentioning

confidence: 99%

“…In any case, the DADNP complexes discovered contained a wide set of ADs, including PEN (ampicillin, meropenem, and imipenem), TETRA (tetracycline), MACRO (gentamicin, vancomycin, and rifampicin), QUIN (ofloxacin and ciprofloxacin), aminoglycoside (tobramycin, kanamycin, and streptomycin), amphenicols (chloramphenicol), lipopeptide (daptomycin), and polypeptide (polymyxin B). 34,[78][79][80][81][82][83][84][85][86][87][88][89][90][91][92][93][94][95][96][97] We may infer that this experimental collection of DADNP complex preclinical experiments contains a significant degree of structural and biological variety. Our initial collection of AD and NP assays vs. MN used to assemble putative DADNP complexes was sampled intentinally with significant structural The study of the interaction of the physical properties of conjugated nanoparticles with antibacterial drugs vs. the various metabolic networks of microorganisms could have an impact on the reduction of costs and environmental impacts.…”

Section: Discussionmentioning

confidence: 99%

“…As a result of this search, we can conclude that the IFPTML models reported in this work are the only one considering the three subsystems at time AD, NP, and MD. On the other hand, Ortega-Tenezaca et al 86 and Diéguez-Santana et al 87 In this last case, the NP introduced on both models have to be the same. However, all these combinations involve the use of two equations with different kinds of parameters, errors, etc.…”

Section: Comparison Of Ifptml With Previous Modelsmentioning

confidence: 99%

See 3 more Smart Citations

Towards rational nanomaterial design by predicting drug–nanoparticle system interaction vs. bacterial metabolic networks

Gonzalez-Diaz

Rasulev

Dieugez-Santana

2022

Environ. Sci.: Nano

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 84%

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

“…As a result of this search, we can conclude that the IFPTML models reported in this work are the only one considering the three subsystems at time AD, NP, and MD. On the other hand, Ortega-Tenezaca et al 86 and Diéguez-Santana et al 87 In this last case, the NP introduced on both models have to be the same. However, all these combinations involve the use of two equations with different kinds of parameters, errors, etc.…”

Section: Comparison Of Ifptml With Previous Modelsmentioning

confidence: 99%

See 2 more Smart Citations

Towards rational nanomaterial design by predicting drug–nanoparticle system interaction vs. bacterial metabolic networks

Gonzalez-Diaz

Rasulev

Dieugez-Santana

2022

Environ. Sci.: Nano

Self Cite

View full text Add to dashboard Cite

show abstract

“…The scoring function f ( s ij ) calc is produced by the IFPTML model. IFPTML has been applied to complicated data analysis in molecular sciences, , infectious disease, nanotechnology, , etc . Drugs, drug cocktails, proteins, genes, vaccines, MNs, and complex networks have all been implicated in these issues. ,,− …”

Section: Introductionmentioning

confidence: 99%

Machine Learning Study of Metabolic NetworksvsChEMBL Data of Antibacterial Compounds

et al. 2022

Self Cite

View full text Add to dashboard Cite

Antibacterial drugs (AD) change the metabolic status of bacteria, contributing to bacterial death. However, antibiotic resistance and the emergence of multidrug-resistant bacteria increase interest in understanding metabolic network (MN) mutations and the interaction of AD vs MN. In this study, we employed the IFPTML = Information Fusion (IF) + Perturbation Theory (PT) + Machine Learning (ML) algorithm on a huge dataset from the ChEMBL database, which contains >155,000 AD assays vs >40 MNs of multiple bacteria species. We built a linear discriminant analysis (LDA) and 17 ML models centered on the linear index and based on atoms to predict antibacterial compounds. The IFPTML-LDA model presented the following results for the training subset: specificity (Sp) = 76% out of 70,000 cases, sensitivity (Sn) = 70%, and Accuracy (Acc) = 73%. The same model also presented the following results for the validation subsets: Sp = 76%, Sn = 70%, and Acc = 73.1%. Among the IFPTML nonlinear models, the k nearest neighbors (KNN) showed the best results with Sn = 99.2%, Sp = 95.5%, Acc = 97.4%, and Area Under Receiver Operating Characteristic (AUROC) = 0.998 in training sets. In the validation series, the Random Forest had the best results: Sn = 93.96% and Sp = 87.02% (AUROC = 0.945). The IFPTML linear and nonlinear models regarding the ADs vs MNs have good statistical parameters, and they could contribute toward finding new metabolic mutations in antibiotic resistance and reducing time/costs in antibacterial drug research.

show abstract

Interdisciplinary‐Inspired Smart Antibacterial Materials and Their Biomedical Applications

Liu

Mehrjou

et al. 2023

Advanced Materials

View full text Add to dashboard Cite

The discovery of antibiotics has saved millions of lives, but the emergence of antibiotic‐resistant bacteria has become another problem in modern medicine. To avoid or reduce the overuse of antibiotics in antibacterial treatments, stimuli‐responsive materials, pathogen‐targeting nanoparticles, immunogenic nano‐toxoids, and biomimetic materials are being developed to make sterilization better and smarter than conventional therapies. The common goal of smart antibacterial materials (SAMs) is to increase the antibiotic efficacy or function via an antibacterial mechanism different from that of antibiotics in order to increase the antibacterial and biological properties while reducing the risk of drug resistance. The research and development of SAMs are increasingly interdisciplinary because new designs require the knowledge of different fields and input/collaboration from scientists in different fields. A good understanding of energy conversion in materials, physiological characteristics in cells and bacteria, and bactericidal structures and components in nature are expected to promote the development of SAMs. In this review, the importance of multidisciplinary insights for SAMs is emphasized, and the latest advances in SAMs are categorized and discussed according to the pertinent disciplines including materials science, physiology, and biomimicry.This article is protected by copyright. All rights reserved

show abstract

Towards machine learning discovery of dual antibacterial drug–nanoparticle systems

Abstract: Artificial Intelligence/Machine Learning (AI/ML) algorithms may speed up the design of DADNP systems formed by Antibacterial Drugs (AD) and Nanoparticles (NP). In this work, we used IFPTML = Information Fusion...

Cited by 17 publications

References 122 publications

Towards rational nanomaterial design by predicting drug–nanoparticle system interaction vs. bacterial metabolic networks

Towards rational nanomaterial design by predicting drug–nanoparticle system interaction vs. bacterial metabolic networks

Machine Learning Study of Metabolic NetworksvsChEMBL Data of Antibacterial Compounds

Interdisciplinary‐Inspired Smart Antibacterial Materials and Their Biomedical Applications

Contact Info

Product

Resources

About