2022
DOI: 10.1016/j.compbiomed.2022.106323
|View full text |Cite
|
Sign up to set email alerts
|

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

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
2
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(3 citation statements)
references
References 27 publications
0
3
0
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
“…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%
“… 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%
“…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%