Deffini: A family-specific deep neural network model for structure-based virtual screening

Zhou, Dixin; Liu, Fei; Y, Zheng; Hu, Liangjian; Huang, Tao; Huang, Yu S.

doi:10.1016/j.compbiomed.2022.106323

Cited by 3 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The methods we compare include the traditional machine learning methods NNscore and RFscore, the virtual docking method Autodock Vina, methods using 3D information such as 3D-CNN, AtomNet, PocketGCN, and Deffini, and methods using 2D graph information such as DrugVQA and AttentionSiteDTI. 18 , 22 , 38 , 39 , 40 , 41 , 42 , 43 In this experiment, FOTF-CPI uses the same training and test sets as the other methods, and its AUC and RE are calculated at 0.5%, 1.0%, 2.0%, and 5.0%. The specific experimental results are shown in the following table.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

FOTF-CPI: A compound-protein interaction prediction transformer based on the fusion of optimal transport fragments

Yin,

Chen,

Hao

et al. 2024

iScience

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

“… 41 https://pubs.acs.org/doi/abs/10.1021/acs.jcim.9b00628 Deffini Zhou et al. 42 https://github.com/jooewood/Deffini DrugVQA Zheng et al. 22 https://github.com/prokia/drugVQA AttentionSiteDTI Yazdani-Jahromi et al.…”

Section: Methodsmentioning

confidence: 99%

FOTF-CPI: A compound-protein interaction prediction transformer based on the fusion of optimal transport fragments

Yin,

Chen,

Hao

et al. 2024

iScience

View full text Add to dashboard Cite

“…This procedure allowed us to neglect the methodological differences associated with various parameters expressing the activity of compounds and use a binary binding class to compare ligands indirectly. A similar procedure was successfully applied earlier to protein targets (e.g., [50][51][52]) as well as in our previous work [23]. Afterward, to remove structurally similar compounds, binders and non-binders were clustered using the k-medoids algorithm, and for each cluster, a representative ligand was selected (Fig 5A).…”

Section: Database Of Rna-targeting Ligandsmentioning

confidence: 99%

Structural Interaction Fingerprints and Machine Learning for predicting and explaining binding of small molecule ligands to RNA

Szulc

Mackiewicz

Bujnicki

et al. 2023

Preprint

View full text Add to dashboard Cite

Ribonucleic acids (RNA) play crucial roles in living organisms as they are involved in key processes necessary for proper cell functioning. Some RNA molecules, such as bacterial ribosomes and precursor messenger RNA, are targets of small molecule drugs, while others, e.g., bacterial riboswitches or viral RNA motifs are considered as potential therapeutic targets. Thus, the continuous discovery of new functional RNA increases the demand for developing compounds targeting them and for methods for analyzing RNA-small molecule interactions. We recently developed fingeRNAt - a software for detecting non-covalent bonds formed within complexes of nucleic acids with different types of ligands. The program detects several non-covalent interactions, such as hydrogen and halogen bonds, ionic, Pi, inorganic ion- and water-mediated, lipophilic interactions, and encodes them as computational-friendly Structural Interaction Fingerprint (SIFt). Here we present the application of SIFts accompanied by machine learning methods for binding prediction of small molecules to RNA targets. We show that SIFt-based models outperform the classic, general-purpose scoring functions in virtual screening. We discuss the aid offered by Explainable Artificial Intelligence in the analysis of the binding prediction models, elucidating the decision-making process, and deciphering molecular recognition processes.

show abstract

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

Szulc

Mackiewicz

Bujnicki

et al. 2023

Briefings in Bioinformatics

View full text Add to dashboard Cite

Ribonucleic acids (RNAs) play crucial roles in living organisms and some of them, such as bacterial ribosomes and precursor messenger RNA, are targets of small molecule drugs, whereas others, e.g. bacterial riboswitches or viral RNA motifs are considered as potential therapeutic targets. Thus, the continuous discovery of new functional RNA increases the demand for developing compounds targeting them and for methods for analyzing RNA—small molecule interactions. We recently developed fingeRNAt—a software for detecting non-covalent bonds formed within complexes of nucleic acids with different types of ligands. The program detects several non-covalent interactions and encodes them as structural interaction fingerprint (SIFt). Here, we present the application of SIFts accompanied by machine learning methods for binding prediction of small molecules to RNA. We show that SIFt-based models outperform the classic, general-purpose scoring functions in virtual screening. We also employed Explainable Artificial Intelligence (XAI)—the SHapley Additive exPlanations, Local Interpretable Model-agnostic Explanations and other methods to help understand the decision-making process behind the predictive models. We conducted a case study in which we applied XAI on a predictive model of ligand binding to human immunodeficiency virus type 1 trans-activation response element RNA to distinguish between residues and interaction types important for binding. We also used XAI to indicate whether an interaction has a positive or negative effect on binding prediction and to quantify its impact. Our results obtained using all XAI methods were consistent with the literature data, demonstrating the utility and importance of XAI in medicinal chemistry and bioinformatics.

show abstract

Deffini: A family-specific deep neural network model for structure-based virtual screening

Cited by 3 publications

References 27 publications

FOTF-CPI: A compound-protein interaction prediction transformer based on the fusion of optimal transport fragments

FOTF-CPI: A compound-protein interaction prediction transformer based on the fusion of optimal transport fragments

Structural Interaction Fingerprints and Machine Learning for predicting and explaining binding of small molecule ligands to RNA

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

Contact Info

Product

Resources

About