Integration of Computational Docking into Anti-Cancer Drug Response Prediction Models

Narykov, Oleksandr; Zhu, Yitan; Brettin, Thomas; Evrard, Yvonne A.; Partin, Alexander; Shukla, Maulik; Xia, Fangfang; Clyde, Austin; Vasanthakumari, Priyanka; Doroshow, James H.; Stevens, Rick L.

doi:10.3390/cancers16010050

Cited by 3 publications

(2 citation statements)

References 86 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After completing these tasks, Spruce created a docking-ready receptor. The generated grid box upon the active site had a dimension of 37.884282, − 3.588333, and 20.849103 in XYZ dimensions from the obtained design units for the target UDP_GlcNAc-MurG complex 63 . Following this prerequisite step, validation of docking method was performed by redocking of co-crystalized substrate, UDP_GlcNAc and found to have an RMSD value lower than 2 Å.…”

Section: Methodsmentioning

confidence: 99%

A comprehensive computational study to explore promising natural bioactive compounds targeting glycosyltransferase MurG in Escherichia coli for potential drug development

Shtaiwi,

Khan,

Khedraoui

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Peptidoglycan is a carbohydrate with a cross-linked structure that protects the cytoplasmic membrane of bacterial cells from damage. The mechanism of peptidoglycan biosynthesis involves the main synthesizing enzyme glycosyltransferase MurG, which is known as a potential target for antibiotic therapy. Many MurG inhibitors have been recognized as MurG targets, but high toxicity and drug-resistant Escherichia coli strains remain the most important problems for further development. In addition, the discovery of selective MurG inhibitors has been limited to the synthesis of peptidoglycan-mimicking compounds. The present study employed drug discovery, such as virtual screening using molecular docking, drug likeness ADMET proprieties predictions, and molecular dynamics (MD) simulation, to identify potential natural products (NPs) for Escherichia coli. We conducted a screening of 30,926 NPs from the NPASS database. Subsequently, 20 of these compounds successfully passed the potency, pharmacokinetic, ADMET screening assays, and their validation was further confirmed through molecular docking. The best three hits and the standard were chosen for further MD simulations up to 400 ns and energy calculations to investigate the stability of the NPs-MurG complexes. The analyses of MD simulations and total binding energies suggested the higher stability of NPC272174. The potential compounds can be further explored in vivo and in vitro for promising novel antibacterial drug discovery.

show abstract

Section: Methodsmentioning

confidence: 99%

A comprehensive computational study to explore promising natural bioactive compounds targeting glycosyltransferase MurG in Escherichia coli for potential drug development

Shtaiwi,

Khan,

Khedraoui

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Examples of conventional machine learning algorithms employed for anti-cancer drug response prediction include linear regression [8], support vector machine (SVM) [9,10], random forests (RF) [3,11,12], and boosting-based methods [13,14]. MOLI [15], DrugOrchestra [16], PathDSP [17], and several other models [18] use fully connected neural networks to predict drug responses of cancer cell lines represented by their genomic signatures. GraphDRP [19], tCNNs [20], and DeepCDR [21] are representative drug response prediction models utilizing convolutional neural networks (CNN) in their model architectures.…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Investigation of Active Learning Strategies for Conducting Anti-Cancer Drug Screening

Vasanthakumari,

Zhu,

Brettin

et al. 2024

Cancers

Self Cite

View full text Add to dashboard Cite

It is well-known that cancers of the same histology type can respond differently to a treatment. Thus, computational drug response prediction is of paramount importance for both preclinical drug screening studies and clinical treatment design. To build drug response prediction models, treatment response data need to be generated through screening experiments and used as input to train the prediction models. In this study, we investigate various active learning strategies of selecting experiments to generate response data for the purposes of (1) improving the performance of drug response prediction models built on the data and (2) identifying effective treatments. Here, we focus on constructing drug-specific response prediction models for cancer cell lines. Various approaches have been designed and applied to select cell lines for screening, including a random, greedy, uncertainty, diversity, combination of greedy and uncertainty, sampling-based hybrid, and iteration-based hybrid approach. All of these approaches are evaluated and compared using two criteria: (1) the number of identified hits that are selected experiments validated to be responsive, and (2) the performance of the response prediction model trained on the data of selected experiments. The analysis was conducted for 57 drugs and the results show a significant improvement on identifying hits using active learning approaches compared with the random and greedy sampling method. Active learning approaches also show an improvement on response prediction performance for some of the drugs and analysis runs compared with the greedy sampling method.

show abstract

Enhancing Drug Solubility, Bioavailability, and Targeted Therapeutic Applications through Magnetic Nanoparticles

Zhuo,

Zhao,

Zhang

2024

Molecules

View full text Add to dashboard Cite

Biological variability poses significant challenges in the development of effective therapeutics, particularly when it comes to drug solubility and bioavailability. Poor solubility across varying physiological conditions often leads to reduced absorption and inconsistent therapeutic outcomes. This review examines how nanotechnology, especially through the use of nanomaterials and magnetic nanoparticles, offers innovative solutions to enhance drug solubility and bioavailability. This comprehensive review focuses on recent advancements and approaches in nanotechnology. We highlight both the successes and remaining challenges in this field, emphasizing the role of continued innovation. Future research should prioritize developing universal therapeutic solutions, conducting interdisciplinary research, and leveraging personalized nanomedicine to address biological variability.

show abstract

Integration of Computational Docking into Anti-Cancer Drug Response Prediction Models

Cited by 3 publications

References 86 publications

A comprehensive computational study to explore promising natural bioactive compounds targeting glycosyltransferase MurG in Escherichia coli for potential drug development

A comprehensive computational study to explore promising natural bioactive compounds targeting glycosyltransferase MurG in Escherichia coli for potential drug development

A Comprehensive Investigation of Active Learning Strategies for Conducting Anti-Cancer Drug Screening

Enhancing Drug Solubility, Bioavailability, and Targeted Therapeutic Applications through Magnetic Nanoparticles

Contact Info

Product

Resources

About