Comparing Neural-Network Scoring Functions and the State of the Art: Applications to Common Library Screening
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
We compare established docking programs, AutoDock Vina and Schrödinger's Glide, to the recently published NNScore scoring functions. As expected, the best protocol to use in a virtual-screening project is highly dependent on the target receptor being studied. However, the mean screening performance obtained when candidate ligands are docked with Vina and rescored with NNScore 1.0 is not statistically different than the mean performance obtained when docking and scoring with Glide. We further demonstrate that the Vina and NNScore docking scores both correlate with chemical properties like small-molecule size and polarizability. Compensating for these potential biases leads to improvements in virtual screen performance. Composite NNScore-based scoring functions suited to a specific receptor further improve performance. We are hopeful that the current study will prove useful for those interested in computer-aided drug design.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Benchmarking sets for molecular docking.
Huang, N., Shoichet, B. K., & Irwin, J. J. (2006) · Journal of Medicinal Chemistry · doi:10.1021/jm0608356 · Cited by 1,318 · cited 6×
“28 Additionally, Vina-and Glide-docked poses are reevaluated using NNScore 1.0 and 2.0.”
InfluentialSimilarity-based virtual screening using 2D fingerprints
Willett, P. (2006) · Drug Discovery Today · doi:10.1016/j.drudis.2006.10.005 · Cited by 849
Implications of protein flexibility for drug discovery
Teague, S. J. (2003) · Nature Reviews Drug Discovery · doi:10.1038/nrd1129 · Cited by 755 · cited 2×
“For example, most docking programs do not account for full receptor fl exibility, despite the fact that fl exibility plays a critical role in modern theories of small-molecule binding (e.g., induced-fi t 7,8 and population-shift 9 − 12 models).”
Bissantz, C., Folkers, G., & Rognan, D. (2000) · Journal of Medicinal Chemistry · doi:10.1021/jm001044l · Cited by 740
Folding funnels, binding funnels, and protein function
Tsai, C., Kumar, S., Ma, B., & Nussinov, R. (1999) · Protein Science · doi:10.1110/ps.8.6.1181 · Cited by 648
Folding funnels and binding mechanisms
Ma, B., Kumar, S., Tsai, C.-J., & Nussinov, R. (1999) · Protein Engineering, Design and Selection · doi:10.1093/protein/12.9.713 · Cited by 594
Moitessier, N., Englebienne, P., Lee, D., Lawandi, J., & Corbeil, C. R. (2008) · British Journal of Pharmacology · doi:10.1038/sj.bjp.0707515 · Cited by 514 · cited 1×
“16, 17 Some of our own recent efforts have focused on training neural networks to rapidly predict the binding energies of protein−ligand complexes leading to the creation of two neural-networkbased scoring functions, NNScore 1.0 18 and NNScore 2.0.”
InfluentialHuang, S.-Y., Grinter, S. Z., & Zou, X. (2010) · Physical Chemistry Chemical Physics · doi:10.1039/c0cp00151a · Cited by 508 · cited 1×
“16,17 Some of our own recent e ff orts have focused on training neural networks to rapidly predict the binding energies of protein − ligand complexes leading to the creation of two neural-network-based scoring functions, NNScore 1.0 18 and NNScore 2.0.”
InfluentialMultiple diverse ligands binding at a single protein site: A matter of pre‐existing populations
Ma, B., Shatsky, M., Wolfson, H. J., & Nussinov, R. (2002) · Protein Science · doi:10.1110/ps.21302 · Cited by 420
Binding MOAD (Mother Of All Databases)
Hu, L., Benson, M. L., Smith, R. D., Lerner, M. G., & Carlson, H. A. (2005) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.20512 · Cited by 328 · cited 1×
“59 In total, 2081 entries representing 1598 unique compounds had both known structures and precise or approximate K i measurements (i.e., measurements described as "=" or "≈").”
Cited by
An Overview of Scoring Functions Used for Protein–Ligand Interactions in Molecular Docking
Li, J., Fu, A., & Zhang, L. (2019) · Interdisciplinary Sciences: Computational Life Sciences · doi:10.1007/s12539-019-00327-w · Cited by 434
Boosting docking-based virtual screening with deep learning.
Pereira, J. C., Caffarena, E. R., & dos Santos, C. N. (2016) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6b00355 · Cited by 395
Machine-learning methods for ligand–protein molecular docking
Crampon, K., Giorkallos, A., Deldossi, M., Baud, S., & Steffenel, L. A. (2022) · Drug Discovery Today · doi:10.1016/j.drudis.2021.09.007 · Cited by 388
Ain, Q. U., Aleksandrova, A., Roessler, F. D., & Ballester, P. J. (2015) · WIREs Computational Molecular Science · doi:10.1002/wcms.1225 · Cited by 357
Benchmarking AlphaFold‐enabled molecular docking predictions for antibiotic discovery
Wong, F., Krishnan, A., Zheng, E. J., Stärk, H., Manson, A. L., Earl, A. M., Jaakkola, T., & Collins, J. J. (2022) · Molecular Systems Biology · doi:10.15252/msb.202211081 · Cited by 284
“…AutoDock Vina, DOCK6, Schro¨dinger’s Glide, Surflex, and internal coordinate mechanics (ICM) have shown that performance is similar on the directory of useful decoys (DUD) dataset (Durrant et al , 2013; Pereira et al , 2016), suggesting that our findings do not depend on the docking software used.”
BackgroundMethod
Metadata
- Authors
- Durrant, J. D., Friedman, A. J., Rogers, K. E., & McCammon, J. A.
- Venue
- Journal of Chemical Information and Modeling
- Publisher
- American Chemical Society (ACS)
- Published
- 2013-07-11
- Volume
- 53
- Issue
- 7
- Pages
- 1726-1735
- ISSN
- 1549-9596 (ISSN-L)
- 1549-960X
- OpenAlex
- W2009841182
- Cited by
- 54
- References
- 11
- FWCI
- 4.25
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Comparing Neural-Network Scoring Functions and the State of the Art: Applications to Common Library Screening. https://app.cochat.ai/papers/10.1021/ci400042y
- The paper
- Durrant, J. D., Friedman, A. J., Rogers, K. E., & McCammon, J. A. (2013). Comparing Neural-Network Scoring Functions and the State of the Art: Applications to Common Library Screening. Journal of Chemical Information and Modeling. https://doi.org/10.1021/ci400042y
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.