Recent progress on the prospective application of machine learning to structure-based virtual screening

Ghislat, Ghita; Rahman, Taufiq; Ballester, Pedro J.

doi:10.1016/j.cbpa.2021.04.009

Cited by 48 publications

(30 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike the broad antibiofilm effects of D20 on S. mutans , S. gordonii and S. sanguinis , which would function by means of bactericidal effects or in other pathways without destroying bacterial cells, the selectivity of D25 would be an advantage for its future application, as D25 did not affect the growth and biofilm formation of S. gordonii and S. sanguinis , and this may account for the specific and unique sequence of C3 domain used in screening. Virtual screening, which is an effective computational methodology aided in the discovery of new drugs, were utilized in this study (Baig et al 2016 ; Ghislat et al 2021 ; Kimber et al 2021 ; Zorn et al 2021 ). Generally, structural information of protein is the core of computational virtual screening that variations in crystal structures would result in different binding pockets and binding affinity (Baig et al 2016 ; Ochoa et al 2017 ; Rivera-Pérez et al 2019 ).…”

Section: Discussionmentioning

confidence: 99%

Small molecule targeting amyloid fibrils inhibits Streptococcus mutans biofilm formation

Chen¹,

Cui²,

Cui³

et al. 2021

AMB Expr

View full text Add to dashboard Cite

Amyloid fibrils are important scaffold in bacterial biofilms. Streptococcus mutans is an established cariogenic bacteria dwelling within biofilms, and C123 segment of P1 protein is known to form amyloid fibrils in S. mutans biofilms, among which C3 segment could serve as a promising anti-amyloid target due to its critical role in C123-P1 interactions. Recently, small molecules have been found to successfully inhibit biofilms by targeting amyloid fibrils. Thus, our study aimed to screen small molecules targeting C3 segment with the capacity to influence amyloid fibrils and S. mutans biofilms. In silico screening was utilized to discover promising small molecules, which were evaluated for their effects on bacterial cells and amyloid fibrils. We selected 99 small molecules and enrolled 55 small molecules named D1–D55 for crystal violet staining. Notably, D25 selectively inhibit S. mutans biofilms but had no significant influence on biofilms formed by Streptococcus gordonii and Streptococcus sanguinis, and D25 showed no bactericidal effects and low cytotoxicity. In addition, amyloid fibrils in free-floating bacteria, biofilms and purified C123 were quantified with ThT assays, and the differences were not statistically significant in the presence or absence of D25. Morphological changes of amyloid fibrils were visualized with TEM images, where amorphous aggregates were obvious coupled with long and atypical amyloid fibrils. Moreover, amyloid-related genes were upregulated in response to D25. In conclusion, D25 is a promising antimicrobial agent with the capacity to influence amyloid fibrils and inhibit S. mutans biofilms.

show abstract

Section: Discussionmentioning

confidence: 99%

Small molecule targeting amyloid fibrils inhibits Streptococcus mutans biofilm formation

Chen¹,

Cui²,

Cui³

et al. 2021

AMB Expr

View full text Add to dashboard Cite

show abstract

“…Molecular interactions between drug candidates and protein binding sites can be virtually simulated using docking techniques. Specifically, in SBVS, a vast number of ligands from chemical libraries are ranked according to their binding affinity, which is predicted by a regression model, known as scoring function (SF) [ 64 ].…”

Section: Recent Applications Of Big Data and Ai-driven Technologies I...mentioning

confidence: 99%

Big data and artificial intelligence (AI) methodologies for computer-aided drug design (CADD)

Lee

Maria-Solano

et al. 2022

Biochemical Society Transactions

View full text Add to dashboard Cite

There have been numerous advances in the development of computational and statistical methods and applications of big data and artificial intelligence (AI) techniques for computer-aided drug design (CADD). Drug design is a costly and laborious process considering the biological complexity of diseases. To effectively and efficiently design and develop a new drug, CADD can be used to apply cutting-edge techniques to various limitations in the drug design field. Data pre-processing approaches, which clean the raw data for consistent and reproducible applications of big data and AI methods are introduced. We include the current status of the applicability of big data and AI methods to drug design areas such as the identification of binding sites in target proteins, structure-based virtual screening (SBVS), and absorption, distribution, metabolism, excretion and toxicity (ADMET) property prediction. Data pre-processing and applications of big data and AI methods enable the accurate and comprehensive analysis of massive biomedical data and the development of predictive models in the field of drug design. Understanding and analyzing biological, chemical, or pharmaceutical architectures of biomedical entities related to drug design will provide beneficial information in the biomedical big data era.

show abstract

“…Thus, building different MLSFs for specific tasks (i.e., binding pose prediction, binding affinity prediction or virtual screening) with the involvement of decoy poses and/or inactive compounds in the training set is a mainstream strategy rather than building a single generalized MLSF. Recently, the scoring power and screening power of a number of MLSFs have been systematically assessed [ 20 – 22 , 27 – 35 ], and in this study we tend to investigate the capability of MLSFs in binding pose prediction.…”

Section: Introductionmentioning

confidence: 99%

The impact of cross-docked poses on performance of machine learning classifier for protein–ligand binding pose prediction

Shen

Gao

et al. 2021

J Cheminform

View full text Add to dashboard Cite

Structure-based drug design depends on the detailed knowledge of the three-dimensional (3D) structures of protein–ligand binding complexes, but accurate prediction of ligand-binding poses is still a major challenge for molecular docking due to deficiency of scoring functions (SFs) and ignorance of protein flexibility upon ligand binding. In this study, based on a cross-docking dataset dedicatedly constructed from the PDBbind database, we developed several XGBoost-trained classifiers to discriminate the near-native binding poses from decoys, and systematically assessed their performance with/without the involvement of the cross-docked poses in the training/test sets. The calculation results illustrate that using Extended Connectivity Interaction Features (ECIF), Vina energy terms and docking pose ranks as the features can achieve the best performance, according to the validation through the random splitting or refined-core splitting and the testing on the re-docked or cross-docked poses. Besides, it is found that, despite the significant decrease of the performance for the threefold clustered cross-validation, the inclusion of the Vina energy terms can effectively ensure the lower limit of the performance of the models and thus improve their generalization capability. Furthermore, our calculation results also highlight the importance of the incorporation of the cross-docked poses into the training of the SFs with wide application domain and high robustness for binding pose prediction. The source code and the newly-developed cross-docking datasets can be freely available at https://github.com/sc8668/ml_pose_prediction and https://zenodo.org/record/5525936, respectively, under an open-source license. We believe that our study may provide valuable guidance for the development and assessment of new machine learning-based SFs (MLSFs) for the predictions of protein–ligand binding poses.

show abstract

Recent progress on the prospective application of machine learning to structure-based virtual screening

Cited by 48 publications

References 47 publications

Small molecule targeting amyloid fibrils inhibits Streptococcus mutans biofilm formation

Small molecule targeting amyloid fibrils inhibits Streptococcus mutans biofilm formation

Big data and artificial intelligence (AI) methodologies for computer-aided drug design (CADD)

The impact of cross-docked poses on performance of machine learning classifier for protein–ligand binding pose prediction

Contact Info

Product

Resources

About