Structural interaction fingerprints and machine learning for predicting and explaining binding of small molecule ligands to RNA

Szulc, Natalia A; Mackiewicz, Zuzanna; Bujnicki, Janusz; Stefaniak, Filip

doi:10.1093/bib/bbad187

Cited by 7 publications

(6 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have compared the performance of our method with other existing methods in the literature [ 30 , 35 ]. Oliver et al.…”

Section: Resultsmentioning

confidence: 99%

“…10-fold CV and jack-knife tests were implemented with the in-built functions available in the scikit-learn python package [ 60 ]. Further, the generalizability and performance of the predictive models was tested with five blind test datasets collected for four of the six RNA subtypes [ 23 , 30 , 34 , 35 ]. These datasets have no overlap of small molecules with that of the training datasets considered ( Figure S3 ), and provide a measure of model performance in a real-world scenario ( Table S8 ).…”

Section: Methodsmentioning

confidence: 99%

“…Five external blind test datasets of both classification and regression type, have been used to validate the models along with jack-knife test and stratified 10-fold cross validation (CV). Upon validation, the models were found to outperform existing QSAR models [ 23 , 35 ] and classification models [ 30 , 34 ]. Interestingly, the selected set of features are distinct for each RNA subtype.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Reliable method for predicting the binding affinity of RNA-small molecule interactions using machine learning

Krishnan,

Roy,

Gromiha

2024

Briefings in Bioinformatics

View full text Add to dashboard Cite

Ribonucleic acids (RNAs) play important roles in cellular regulation. Consequently, dysregulation of both coding and non-coding RNAs has been implicated in several disease conditions in the human body. In this regard, a growing interest has been observed to probe into the potential of RNAs to act as drug targets in disease conditions. To accelerate this search for disease-associated novel RNA targets and their small molecular inhibitors, machine learning models for binding affinity prediction were developed specific to six RNA subtypes namely, aptamers, miRNAs, repeats, ribosomal RNAs, riboswitches and viral RNAs. We found that differences in RNA sequence composition, flexibility and polar nature of RNA-binding ligands are important for predicting the binding affinity. Our method showed an average Pearson correlation (r) of 0.83 and a mean absolute error of 0.66 upon evaluation using the jack-knife test, indicating their reliability despite the low amount of data available for several RNA subtypes. Further, the models were validated with external blind test datasets, which outperform other existing quantitative structure-activity relationship (QSAR) models. We have developed a web server to host the models, RNA-Small molecule binding Affinity Predictor, which is freely available at: https://web.iitm.ac.in/bioinfo2/RSAPred/.

show abstract

“…We have compared the performance of our method with other existing methods in the literature [ 30 , 35 ]. Oliver et al.…”

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reliable method for predicting the binding affinity of RNA-small molecule interactions using machine learning

Krishnan,

Roy,

Gromiha

2024

Briefings in Bioinformatics

View full text Add to dashboard Cite

show abstract

“…They were originally designed to convert static 3D coordinates, such as those obtained from molecular modelling techniques or experimental studies, into a 1D bit vector [ 4 , 5 ]. Several methods have been developed to derive IFPs of protein-ligand interactions, and most have been used as post-processing methods for virtual screening approaches (i.e., large-scale docking approaches) and conformational space analysis [ 4 , 19 – 28 ] and have also been used for machine learning approaches [ 3 , 29 – 31 ]. Unlike static structures, IFPs derived from MD simulations are more challenging to analyse because MD simulations allow studying the temporal motion and dynamics (e.g., conformation, interaction) of a system [ 1 ].…”

Section: Introductionmentioning

confidence: 99%

Systematic analysis, aggregation and visualisation of interaction fingerprints for molecular dynamics simulation data

Jaeger-Honz,

Klein,

Schreiber

2024

J Cheminform

View full text Add to dashboard Cite

Computational methods such as molecular docking or molecular dynamics (MD) simulations have been developed to simulate and explore the interactions between biomolecules. However, the interactions obtained using these methods are difficult to analyse and evaluate. Interaction fingerprints (IFPs) have been proposed to derive interactions from static 3D coordinates and transform them into 1D bit vectors. More recently, the concept has been applied to derive IFPs from MD simulations, which adds a layer of complexity by adding the temporal motion and dynamics of a system. As a result, many IFPs are obtained from one MD simulation, resulting in a large number of individual IFPs that are difficult to analyse compared to IFPs derived from static 3D structures. Scientific contribution: We introduce a new method to systematically aggregate IFPs derived from MD simulation data. In addition, we propose visualisations to effectively analyse and compare IFPs derived from MD simulation data to account for the temporal evolution of interactions and to compare IFPs across different MD simulations. This has been implemented as a freely available Python library and can therefore be easily adopted by other researchers and to different MD simulation datasets.

show abstract

“…Additionally, the supporting website for LigandRNA is currently invalid. On another note, the ML-based SFs, including AnnapuRNA, RNAPosers, and the work reported by Szulc et al, 27 are only specifically tailored for RNA targets. Additionally, assessing the performance of these ML-based SFs poses a challenge to the unified test set because different training sets were used by different ML-based SFs.…”

Section: ■ Introductionmentioning

confidence: 99%

How Good Are Current Docking Programs at Nucleic Acid–Ligand Docking? A Comprehensive Evaluation

Jiang

Zhao

et al. 2023

J. Chem. Theory Comput.

View full text Add to dashboard Cite

Nucleic acid (NA)–ligand interactions are of paramount importance in a variety of biological processes, including cellular reproduction and protein biosynthesis, and therefore, NAs have been broadly recognized as potential drug targets. Understanding NA–ligand interactions at the atomic scale is essential for investigating the molecular mechanism and further assisting in NA-targeted drug discovery. Molecular docking is one of the predominant computational approaches for predicting the interactions between NAs and small molecules. Despite the availability of versatile docking programs, their performance profiles for NA–ligand complexes have not been thoroughly characterized. In this study, we first compiled the largest structure-based NA–ligand binding data set to date, containing 800 noncovalent NA–ligand complexes with clearly identified ligands. Based on this extensive data set, eight frequently used docking programs, including six protein–ligand docking programs (LeDock, Surflex-Dock, UCSF Dock6, AutoDock, AutoDock Vina, and PLANTS) and two specific NA–ligand docking programs (rDock and RLDOCK), were systematically evaluated in terms of binding pose and binding affinity predictions. The results demonstrated that some protein–ligand docking programs, specifically PLANTS and LeDock, produced more promising or comparable results compared with the specialized NA–ligand docking programs. Among the programs evaluated, PLANTS, rDock, and LeDock showed the highest performance in binding pose prediction, and their top-1 and best root-mean-square deviation (rmsd) success rates were as follows: PLANTS (35.93 and 76.05%), rDock (27.25 and 72.16%), and LeDock (27.40 and 64.37%). Compared with the moderate level of binding pose prediction, few programs were successful in binding affinity prediction, and the best correlation (R p = −0.461) was observed with PLANTS. Finally, further comparison with the latest NA–ligand docking program (NLDock) on four well-established data sets revealed that PLANTS and LeDock outperformed NLDock in terms of binding pose prediction on all data sets, demonstrating their significant potential for NA–ligand docking. To the best of our knowledge, this study is the most comprehensive evaluation of popular molecular docking programs for NA–ligand systems.

show abstract

Structural interaction fingerprints and machine learning for predicting and explaining binding of small molecule ligands to RNA

Cited by 7 publications

References 63 publications

Reliable method for predicting the binding affinity of RNA-small molecule interactions using machine learning

Reliable method for predicting the binding affinity of RNA-small molecule interactions using machine learning

Systematic analysis, aggregation and visualisation of interaction fingerprints for molecular dynamics simulation data

How Good Are Current Docking Programs at Nucleic Acid–Ligand Docking? A Comprehensive Evaluation

Contact Info

Product

Resources

About