The DOI matches its Crossref record; 70 of the 70 references it cites were found in a registry or an index; none of the 26 sources its claims cite is checked for support yet.
Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges
Open accessAbstract
Advanced mathematics, such as multiscale weighted colored subgraph and element specific persistent homology, and machine learning including deep neural networks were integrated to construct mathematical deep learning models for pose and binding affinity prediction and ranking in the last two D3R Grand Challenges in computer-aided drug design and discovery. D3R Grand Challenge 2 focused on the pose prediction, binding affinity ranking and free energy prediction for Farnesoid X receptor ligands. Our models obtained the top place in absolute free energy prediction for free energy set 1 in stage 2. The latest competition, D3R Grand Challenge 3 (GC3), is considered as the most difficult challenge so far. It has five subchallenges involving Cathepsin S and five other kinase targets, namely VEGFR2, JAK2, p38-α, TIE2, and ABL1. There is a total of 26 official competitive tasks for GC3. Our predictions were ranked 1st in 10 out of these 26 tasks.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
The paper reports mathematical deep learning models combining multiscale weighted colored subgraphs and element-specific persistent homology with machine learning for D3R Grand Challenge 2 and 3 pose, affinity ranking, and free energy tasks. In GC3, the authors’ submissions ranked 1st in 10 of 26 official competitive tasks, and in GC2 they achieved the top place in free energy prediction for free energy set 1 in stage 2.
Key findings
- In D3R GC3, the authors’ predictions were ranked 1st in 10 out of 26 official competitive tasks.
- For GC3 Subchallenge 1 (Cathepsin S), the best Kendall’s τ improved from 0.23 in stage 1 to 0.54 in stage 2 (receipt ID 6jekk); free energy RMSEc was 0.33 kcal/mol in stage 1 (receipt ID fomca) and 0.29 kcal/mol in stage 2 (receipt ID v4jv4).
- For GC3 Subchallenge 4 (TIE2), the model ranked first on all evaluated metrics: affinity ranking excluding Kds > 10 μM gave Kendall’s τ = 0.57 and Spearman = 0.76 (receipt ID uuihe); active/inactive classification gave MCC = 0.78; Set 1 absolute free energy gave MCC = 1.0 (receipt ID vwbp8); Set 2 gave RMSEc = 1.02 kcal/mol (receipt ID 5g8ed).
- In GC2, the submission with receipt ID 5bvwx ranked second in free energy set 1 of stage 1 with RMSEc = 0.68 kcal/mol, and in stage 2 the model obtained first place for free energy set 1 with Kendall’s τ = 0.41 (receipt ID 4rbjk).
Methods
- The models used multiscale weighted colored subgraph (MWCS) and element-specific persistent homology descriptors, combined with machine learning methods including random forest, gradient boosting trees, convolutional neural networks, and multi-task learning; training used PDBbind data.
- Ligands were prepared from SMILES using LIGPREP at pH 7.5, with Gasteiger charges added via MGLTools v1.5.6; docking used Autodock Vina, GOLD, GLIDE, induced fit docking, and several protocols named align-close, align-target, close-dock, cross-dock, constraint-IFD, and free-IFD.
- The paper evaluates submissions in D3R GC2 and GC3. GC2 involved FXR with 36 crystallographic ligands, 102 compounds for affinity ranking, and free energy subsets of 18 and 15 ligands. GC3 had five subchallenges involving Cathepsin S and kinases VEGFR2, JAK2, p38-α, TIE2, and ABL1, with 26 official competitive tasks; reported metrics include Kendall’s τ, Spearman correlation, RMSEc, and MCC.
Limitations
- The paper states that docking accuracy remains a bottleneck for affinity prediction, that none of the tried docking protocols showed a dominant role in binding affinity accuracy, and that excluding pose prediction error improved Kendall’s τ from 0.21 to 0.54 on Cathepsin S affinity ranking.
- The paper also states that machine learning-based scoring function performance depends crucially on training data quality and statistical distribution, and on selected features that may not accurately or completely describe protein–ligand binding interactions.
- Evident from the reported results: the models did not perform well on GC3 Subchallenge 2, with the best result being second place on VEGFR2 active/inactive classification (MCC = 0.48), and affinity ranking in Subchallenge 3 was described as unremarkable; GC2 pose ranking power was also described as not impressive.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
18 Own result · 14 Not checked yet · 5 Own interpretation · 5 No basis given
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our submissions were ranked 1st in 10 of these 26 tasks as shown in Table 1 for additional information.”
- Also stated in: § Conclusion · plain
“In GC3, our submissions were ranked 1st in 10 out of 26 official evaluation tasks.”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Results and discussion > Grand Challenge 3
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § Conclusion · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In stage 2, our models improved the accuracy of the energy prediction of compounds in the aforementioned free energy set.”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Results and discussion > Grand Challenge 2
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We have tried a variety of docking protocols, namely align-close, align-target, close-dock, cross-dock, constraint-IFD, and free-IFD, for pose selection in GC3. However, none of them showed a dominant role in binding affinity accuracy.”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Conclusion
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Specifically, on Set 1, our predictor with receipt ID vwbp8 was ranked the first place with MCC = 1.0.”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Results and discussion > Grand Challenge 3
plainSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our predictions were ranked 1st in 10 out of these 26 tasks.”
- Also stated in: § Introduction · plain
“we obtained the first place in 10 out of a total of 26 predictive tasks.”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § Introduction · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In addition, when one excludes the pose prediction error, Kendall’s tau of our model improves from 0.21 to 0.54 on the affinity ranking of compounds in Cathepsin S subchallenge.”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Conclusion
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In fact, these additional docking features did not improve our available models.”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Results and discussion > Grand Challenge 3
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Our models achieved the top place in affinity ranking for the free energy set 1 in stage 2.”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Introduction
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We obtained the first place on the binding energy prediction with the centered RMSE as low as RMSEc = 1.06 kcal/mol (receipt ID 4u5ey).”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Results and discussion > Grand Challenge 3
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“On Set 2, our model with receipt ID 5g8ed attained the RMSEc = 1.02 kcal/mol which is the lowest among all submissions.”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Results and discussion > Grand Challenge 3
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- It may state two separate claims as one. 9
- Probably not a substantial claim. 8
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“That explains why our predictors performed decently for scoring task in stage 1 with the best Kendall’s τ = 0.23, but they achieved a state-of-the-art result for the same task in stage 2 with the best Kendall’s τ = 0.54 (receipt ID 6jekk).”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Results and discussion > Grand Challenge 3
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In fact, we obtained the first place in term of Kendall’s tau value (τ = 0.41) with receipt ID 4rbjk. That was also the highest Kendall’s tau value among all submissions in two stages for the free energy set 1.”
- Also stated in: § Conclusion · plain
“Overall, in GC2, our predictive models achieved the top place in free energy prediction for free energy set 1 in stage 2.”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Results and discussion > Grand Challenge 2
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Also stated in: § Conclusion · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Particularly, in stage 1, our prediction with receipt ID fomca obtained RMSEc = 0.33 kcal/mol. In stage 2, we accomplished RMSEc = 0.29 kcal/mol with receipt ID v4jv4.”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Results and discussion > Grand Challenge 3
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our best result is the second place on the active/inactive classification of VERGFR2 set. Our best Matthews correlation coefficient (MCC) on such task is reported to be 0.48 from receipt ID rtv8m.”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Results and discussion > Grand Challenge 3
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“With this setting, our models attained the first places for the following tasks: free energy set in stage 1, scoring and free energy set in stage 2.”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Results and discussion > Grand Challenge 3
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“The statistics of element specific persistent homology barcodes can also be used for featurization [23].”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Methods > Algebraic topology based molecular signature
What the sources say
- Not checked yetcites [23] Cang ZX, Mu L, Wei GW (2018) Representability of algebraic topology for biomolecules in machine learning based scoring and virtual screening. PLoS Comput Biol 14(1):e1005929. https://doi.org/10.1371/journal.pcbi.1005929 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Both our graph theory based models [20, 62] and algebraic topology based models [21, 23] achieve top-class performance with the ensemble of trees methods.”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Methods > Machine learning algorithms
What the sources say
- Not checked yetcites [20] Nguyen DD, Xiao T, Wang ML, Wei GW (2017) Rigidity strengthening: a mechanism for protein–ligand binding. J Chem Inform Model 57:1715–1721 source
- Not checked yetcites [62] Nguyen DD, Wei GW (2018) Multiscale weighted colored algebraic graphs for biomolecules (to be submitted)
- Not checked yetcites [21] Cang ZX, Wei, GW (2018) “Integration of element specific persistent homology and machine learning for protein–ligand binding affinity prediction. Int J Numer Methods Biomed Eng. https://doi.org/10.1002/cnm.2914 source
- Not checked yetcites [23] Cang ZX, Mu L, Wei GW (2018) Representability of algebraic topology for biomolecules in machine learning based scoring and virtual screening. PLoS Comput Biol 14(1):e1005929. https://doi.org/10.1371/journal.pcbi.1005929 source
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Therefore, a higher level bagging of models of different kinds can further improve the performance.”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Methods > Machine learning algorithms
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Rests on an assumption: Random forest is better at lowering bias and gradient boosting trees focus more on reducing variance.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The topological analysis provides us a description of the molecular system that captures a collection of key aspects of the system including the multiscale description of geometry, the characterization of interaction network in an arbitrary dimension, and the important physical and chemical information, which ensures the success of the downstream machine learning modeling.”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Methods > Algebraic topology based molecular signature
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
- The authors state this as an assumption: The intrinsic physics of interest of complex biomolecules and interactions lies on low-dimensional manifolds or subspaces embedded in a high-dimensional data space.
None of the sources cited for this claim have been checked yet.
In the paper
“The barcodes can also be transformed to representations similar to images and used in a 1-dimensional or a 2-dimensional convolutional neural networks [22, 23].”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Methods > Algebraic topology based molecular signature
What the sources say
- Not checked yetcites [22] Cang ZX, Wei GW (2017) TopologyNet: topology based deep convolutional and multi-task neural networks for biomolecular property predictions. PLoS Comput Biol 13(7):e1005690. https://doi.org/10.1371/journal.pcbi.1005690 source
- Not checked yetcites [23] Cang ZX, Mu L, Wei GW (2018) Representability of algebraic topology for biomolecules in machine learning based scoring and virtual screening. PLoS Comput Biol 14(1):e1005929. https://doi.org/10.1371/journal.pcbi.1005929 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“specific persistent homology computation on the collection of all carbon atoms describes the hydrophobic network or the structural basis of the molecule while computation on the nitrogen and oxygen atoms characterizes the hydrophilic networks [21].”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Methods > Algebraic topology based molecular signature
What the sources say
- Not checked yetcites [21] Cang ZX, Wei, GW (2018) “Integration of element specific persistent homology and machine learning for protein–ligand binding affinity prediction. Int J Numer Methods Biomed Eng. https://doi.org/10.1002/cnm.2914 source
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“The MWCG approach has been shown to be over 40% more accurate than the Gaussian network model on a set of 364 proteins [24].”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Introduction
What the sources say
- Not checked yetcites [24] Bramer D, Wei G-W (2018) Multiscale weighted colored graphs for protein flexibility and rigidity analysis. J Chem Phys 148(5):054103 source
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- The authors state this as an assumption: The intrinsic physics of interest of complex biomolecules and interactions lies on low-dimensional manifolds or subspaces embedded in a high-dimensional data space.
In the paper
“For example, Wasserstein metric can be applied to measure similarities among the barcodes of different proteins, which can be used with methods such as nearest neighbors and manifold learning [23].”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Methods > Algebraic topology based molecular signature
What the sources say
- Not checked yetcites [23] Cang ZX, Mu L, Wei GW (2018) Representability of algebraic topology for biomolecules in machine learning based scoring and virtual screening. PLoS Comput Biol 14(1):e1005929. https://doi.org/10.1371/journal.pcbi.1005929 source
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Topological descriptors were further integrated with a variety of deep learning algorithms to achieve state-of-the-art analysis and prediction of protein folding stability change upon mutation [38], drug toxicity [39], aqueous solubility [40], partition coefficient [40], binding affinity [21, 22], and the virtual screening of active ligands and decoys [23].”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Introduction
What the sources say
- Not checked yetcites [23] Cang ZX, Mu L, Wei GW (2018) Representability of algebraic topology for biomolecules in machine learning based scoring and virtual screening. PLoS Comput Biol 14(1):e1005929. https://doi.org/10.1371/journal.pcbi.1005929 source
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- The authors state this as an assumption: The intrinsic physics of interest of complex biomolecules and interactions lies on low-dimensional manifolds or subspaces embedded in a high-dimensional data space.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“These results confirm the predictive power and practical usage of our mathematical deep learning models in drug design and discovery.”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Conclusion
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“By using advanced machine learning algorithms, such as random forest (RF) and deep convolutional neural network, the machine learning-based SFs can characterize the non-additive contributions of functional groups in protein–ligand binding interactions [18].”
§ Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges > Introduction
What the sources say
- Not checked yetcites [18] Baum B, Muley L, Smolinski M, Heine A, Hangauer D, Klebe G (2010) Non-additivity of functional group contributions in protein–ligand binding: a comprehensive study by crystallography and isothermal titration calorimetry. J Mol Biol 397(4):1042–1054 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Rests on an assumption: The performance of machine learning-based scoring functions depends crucially on the quality and statistical distribution of training data and on selected features that may or may not accurately and completely describe protein–ligand binding interactions.
The authors state this as an assumption.
The intrinsic physics of interest of complex biomolecules and interactions lies on low-dimensional manifolds or subspaces embedded in a high-dimensional data space.
“We assume that the intrinsic physics of interest of complex biomolecules and interactions lies on low-dimensional manifolds or subspaces embedded in a high-dimensional data space.”
The paper relies on this without support.
The performance of machine learning-based scoring functions depends crucially on the quality and statistical distribution of training data and on selected features that may or may not accurately and completely describe protein–ligand binding interactions.
“However, the performance of machine learning-based SFs depends crucially on the training data quality and statistic distribution. Additionally, it also depends on selected features that might or might not accurately and completely describe the protein–ligand binding interactions.”
The authors state this as an assumption.
Grouping weak learners can improve learning capability.
“Ensemble of trees methods build models consisting of a collection of decision trees with the assumption that grouping the weak learners can improve the learning capability.”
The paper relies on this without support.
Random forest is better at lowering bias and gradient boosting trees focus more on reducing variance.
“As these two models attempt to reduce error in two different ways, they behave differently in the bias-variance trade-off where the random forest is better at lowering bias and gradient boosting trees focus more on reducing variance.”
The paper relies on this without support.
Ensemble learning methods are robust and overfitting can be reduced by learning partial problems.
“The ensemble learning methods are also robust and overfitting can be reduced by learning partial problems.”
The paper relies on this without support.
When the feature is complex or has an underlying dimension in feature space, deep learning models can further improve predictor performance.
“When the feature is complex or there is some underlying dimension in the feature space, deep learning models can further imporve the performance of the predictor.”
The paper relies on this without support.
A spatial dimension associated to the filtration parameter lies in the persistent homology representation of protein–ligand systems.
“For example, a spatial dimension associated to the filtration parameter lies in the persistent homology representation of protein–ligand systems.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“It has been devised to win worldwide competitions in computer-aided drug design36.”
From A topology-based network tree for the prediction of protein–protein binding affinity changes following mutation (2020) · cites this paper as [36]
Citations
Cites
Berman, H. M. (2000) · Nucleic Acids Research · doi:10.1093/nar/28.1.235 · Cited by 40,196
Trott, O., & Olson, A. J. (2010) · Journal of Computational Chemistry · doi:10.1002/jcc.21334 · Cited by 38,412
AutoDock4 and AutoDockTools4: Automated docking with selective receptor flexibility
Morris, G. M., Huey, R., Lindstrom, W., Sanner, M. F., Belew, R. K., Goodsell, D. S., & Olson, A. J. (2009) · Journal of Computational Chemistry · doi:10.1002/jcc.21256 · Cited by 26,294
Centrality in social networks conceptual clarification
Freeman, L. C. (1978) · Social Networks · doi:10.1016/0378-8733(78)90021-7 · Cited by 17,062
Open Babel: An open chemical toolbox
O'Boyle, N. M., Banck, M. S., James, C. A. J., Morley, C., Vandermeersch, T., & Hutchison, G. R. (2011) · Journal of Cheminformatics · doi:10.1186/1758-2946-3-33 · Cited by 10,745
Friesner, R. A., Banks, J. L., Murphy, R. B., Halgren, T. A., Klicic, J. J., Mainz, D. T., Repasky, M. P., Knoll, E. H., Shelley, M., Perry, J. K., et al. (2004) · Journal of Medicinal Chemistry · doi:10.1021/jm0306430 · Cited by 10,057
Development and validation of a genetic algorithm for flexible docking 1 1Edited by F. E. Cohen
Jones, G., Willett, P., Glen, R. C., Leach, A. R., & Taylor, R. (1997) · Journal of Molecular Biology · doi:10.1006/jmbi.1996.0897 · Cited by 6,763
Sastry, G. M., Adzhigirey, M., Day, T., Annabhimoju, R., & Sherman, W. (2013) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-013-9644-8 · Cited by 6,207
Borgatti, S. P. (2005) · Social Networks · doi:10.1016/j.socnet.2004.11.008 · Cited by 3,191
A hierarchical approach to all‐atom protein loop prediction
Jacobson, M. P., Pincus, D. L., Rapp, C. S., Day, T., Honig, B. H., Shaw, D. E., & Friesner, R. A. (2004) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.10613 · Cited by 2,541
Novel Procedure for Modeling Ligand/Receptor Induced Fit Effects
Sherman, W., Day, T., Jacobson, M. P., Friesner, R. A., & Farid, R. (2005) · Journal of Medicinal Chemistry · doi:10.1021/jm050540c · Cited by 2,089
Communication Patterns in Task-Oriented Groups
Bavelas, A. (1950) · The Journal of the Acoustical Society of America · doi:10.1121/1.1906679 · Cited by 2,059
Topological Persistence and Simplification
Edelsbrunner, Letscher, & Zomorodian (2002) · Discrete & Computational Geometry · doi:10.1007/s00454-002-2885-2 · Cited by 1,779
Borgatti, S. P. (2005) · Cited by 1,734
Eldridge, M., Murray, C. W., Auton, T. R., Paolini, G. V., & Mee, R. P. (1997) · Journal of Computer-Aided Molecular Design · doi:10.1023/a:1007996124545 · Cited by 1,692
Zomorodian, A., & Carlsson, G. (2005) · Discrete & Computational Geometry · doi:10.1007/s00454-004-1146-y · Cited by 1,591
On the Role of the Crystal Environment in Determining Protein Side-chain Conformations
Jacobson, M. P., Friesner, R. A., Xiang, Z., & Honig, B. H. (2002) · Journal of Molecular Biology · doi:10.1016/s0022-2836(02)00470-9 · Cited by 1,289
Dixon, S. L., Smondyrev, A. M., Knoll, E. H., Rao, S. N., Shaw, D. E., & Friesner, R. A. (2006) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-006-9087-6 · Cited by 1,207
Wang, R., Lai, L., & Wang, S. (2002) · Journal of Computer-Aided Molecular Design · doi:10.1023/a:1016357811882 · Cited by 1,185
A General and Fast Scoring Function for Protein−Ligand Interactions: A Simplified Potential Approach
Muegge, I., & Martin, Y. C. (1999) · Journal of Medicinal Chemistry · doi:10.1021/jm980536j · Cited by 1,008
Comparative evaluation of 11 scoring functions for molecular docking.
Wang, R., Lu, Y., & Wang, S. (2003) · Journal of Medicinal Chemistry · doi:10.1021/jm0203783 · Cited by 849
Use of an Induced Fit Receptor Structure in Virtual Screening
Sherman, W., Beard, H. S., & Farid, R. (2005) · Chemical Biology & Drug Design · doi:10.1111/j.1747-0285.2005.00327.x · Cited by 716
PHASE: A Novel Approach to Pharmacophore Modeling and 3D Database Searching
Dixon, S. L., Smondyrev, A. M., & Rao, S. N. (2006) · Chemical Biology & Drug Design · doi:10.1111/j.1747-0285.2006.00384.x · Cited by 676
Prediction of Protein−Ligand Interactions. Docking and Scoring: Successes and Gaps
Leach, A. R., Shoichet, B. K., & Peishoff, C. E. (2006) · Journal of Medicinal Chemistry · doi:10.1021/jm060999m · Cited by 648
Identifying miRNAs, targets and functions
Liu, B., Li, J., & Cairns, M. J. (2014) · Briefings in Bioinformatics · doi:10.1093/bib/bbs075 · Cited by 563
Farid, R., Day, T., Friesner, R. A., & Pearlstein, R. A. (2006) · Bioorganic & Medicinal Chemistry · doi:10.1016/j.bmc.2005.12.032 · Cited by 511
Forging the basis for developing protein-ligand interaction scoring functions.
Liu, Z., Su, M., Han, L., Liu, J., Yang, Q., Li, Y., & Wang, R. (2017) · Accounts of Chemical Research · doi:10.1021/acs.accounts.6b00491 · Cited by 493
Drefahl, A. (2011) · Journal of Cheminformatics · doi:10.1186/1758-2946-3-1 · Cited by 415
Kaczyński, T., Mischaikow, K., & Mrożek, M. (2004) · Applied mathematical sciences · doi:10.1007/b97315 · Cited by 403
Velec, H. F. G., Gohlke, H., & Klebe, G. (2005) · Journal of Medicinal Chemistry · doi:10.1021/jm050436v · Cited by 347
Structure-Based Drug Design: Docking and Scoring
Kroemer, R. T. (2007) · Current Protein and Peptide Science · doi:10.2174/138920307781369382 · Cited by 342
Cang, Z., & Wei, G.-W. (2017) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1005690 · Cited by 330
Self-citationClassification of Current Scoring Functions
Liu, J., & Wang, R. (2015) · Journal of Chemical Information and Modeling · doi:10.1021/ci500731a · Cited by 311
Prediction of Drug Binding Affinities by Comparative Binding Energy Analysis
Ortíz, Á. R., Pisabarro, M. T., Gago, F., & Wade, R. C. (1995) · Journal of Medicinal Chemistry · doi:10.1021/jm00014a020 · Cited by 267
Cang, Z., Mu, L., & Wei, G.-W. (2018) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1005929 · Cited by 257
Self-citationPersistent homology analysis of protein structure, flexibility, and folding
Xia, K., & Wei, G. (2014) · International Journal for Numerical Methods in Biomedical Engineering · doi:10.1002/cnm.2655 · Cited by 254
Self-citationHuang, S., & Zou, X. (2006) · Journal of Computational Chemistry · doi:10.1002/jcc.20504 · Cited by 215
MedusaScore: An Accurate Force Field-Based Scoring Function for Virtual Drug Screening
Yin, S., Biedermannová, L., Vondrášek, J., & Dokholyan, N. V. (2008) · Journal of Chemical Information and Modeling · doi:10.1021/ci8001167 · Cited by 212
A Topological Paradigm for Hippocampal Spatial Map Formation Using Persistent Homology
Dabaghian, Y. A., Mémoli, F., Frank, L. M., & Carlsson, G. (2012) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1002581 · Cited by 187
De novodesign of molecular wires with optimal properties for solar energy conversion
O’Boyle, N. M., Campbell, C. M., & Hutchison, G. (2011) · Journal of Cheminformatics · doi:10.1186/1758-2946-3-s1-o14 · Cited by 183
Cang, Z., & Wei, G. (2018) · International Journal for Numerical Methods in Biomedical Engineering · doi:10.1002/cnm.2914 · Cited by 172
Self-citationVerkhivker, G. M., Appelt, K., Freer, S. T., & Villafranca, J. E. (1995) · Protein Engineering Design and Selection · doi:10.1093/protein/8.7.677 · Cited by 161
Quantitative Toxicity Prediction Using Topology Based Multitask Deep Neural Networks
Wu, K., & Wei, G.-W. (2018) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.7b00558 · Cited by 160
Self-citationBaum, B., Muley, L., Smolinski, M., Heine, A., Hangauer, D., & Klebe, G. (2010) · Journal of Molecular Biology · doi:10.1016/j.jmb.2010.02.007 · Cited by 157
Size theory as a topological tool for computer vision
Frosini, P., & Landi, C. (1999) · Cited by 137
Are 2D fingerprints still valuable for drug discovery?
Gao, K., Nguyen, D. D., Sresht, V., Mathiowetz, A. M., Tu, M., & Wei, G. (2020) · Physical Chemistry Chemical Physics · doi:10.1039/d0cp00305k · Cited by 136
Self-citationRigidity Strengthening: A Mechanism for Protein–Ligand Binding
Nguyen, D. D., Xiao, T., Wang, M., & Wei, G.-W. (2017) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.7b00226 · Cited by 105
Self-citationRecent improvements to Binding MOAD: a resource for protein–ligand binding affinities and structures
Ahmed, A., Smith, R. D., Clark, J. J., Dunbar, J. B., & Carlson, H. A. (2014) · Nucleic Acids Research · doi:10.1093/nar/gku1088 · Cited by 103
Wu, K., Zhao, Z., Wang, R., & Wei, G. (2018) · Journal of Computational Chemistry · doi:10.1002/jcc.25213 · Cited by 101
Self-citationA review of mathematical representations of biomolecular data
Nguyen, D. D., Cang, Z., & Wei, G. (2020) · Physical Chemistry Chemical Physics · doi:10.1039/c9cp06554g · Cited by 101
Self-citationPrimeX and the Schrödinger computational chemistry suite of programs
Bell, J. A., Cao, Y., Gunn, J. R., Day, T., Gallicchio, E., Zhou, Z., Levy, R. M., & Farid, R. (2012) · International Tables for Crystallography · doi:10.1107/97809553602060000864 · Cited by 98
Self-citationPersistent homology for the quantitative prediction of fullerene stability
Xia, K., Feng, X., Tong, Y., & Wei, G. W. (2014) · Journal of Computational Chemistry · doi:10.1002/jcc.23816 · Cited by 96
Self-citationCang, Z., & Wei, G. (2017) · Computer applications in the biosciences · doi:10.1093/bioinformatics/btx460 · Cited by 95
Self-citationA topological approach for protein classification
Cang, Z., Mu, L., Wu, K., Opron, K., Xia, K., & Wei, G.-W. (2015) · Computational and Mathematical Biophysics · doi:10.1515/mlbmb-2015-0009 · Cited by 93
Self-citationLi, H., Leung, K., Wong, M., & Ballester, P. J. (2014) · BMC Bioinformatics · doi:10.1186/1471-2105-15-291 · Cited by 92
DeltaDelta neural networks for lead optimization of small molecule potency
Jiménez-Luna, J., Pérez‐Benito, L., Martínez-Rosell, G., Sciabola, S., Torella, R., Tresadern, G., & Fabritiis, G. D. (2019) · Chemical Science · doi:10.1039/c9sc04606b · Cited by 73
Conceptual Distance in Social Network Analysis.
Dekker, A. H. (2005) · Journal of Social Structure · Cited by 72
Machine intelligence design of 2019-nCoV drugsPreprint
Gao, K., Nguyen, D. D., Wang, R., & Wei, G. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.01.30.927889 · Cited by 56
Self-citationPersistent voids: a new structural metric for membrane fusion
Kasson, P. M., Zomorodian, A. J., Park, S., Singhal, N., Guibas, L. J., & Pande, V. S. (2007) · Bioinformatics · doi:10.1093/bioinformatics/btm250 · Cited by 53
Object-oriented persistent homology
Wang, B., & Wei, G. (2015) · Journal of Computational Physics · doi:10.1016/j.jcp.2015.10.036 · Cited by 50
Self-citationMultiscale weighted colored graphs for protein flexibility and rigidity analysis
Bramer, D., & Wei, G. (2018) · The Journal of Chemical Physics · doi:10.1063/1.5016562 · Cited by 50
Self-citationAnand, D. V., Meng, Z., Xia, K., & Mu, Y. (2020) · Scientific Reports · doi:10.1038/s41598-020-66710-6 · Cited by 41
Persistent topology for cryo‐EM data analysis
Xia, K., & Wei, G. (2015) · International Journal for Numerical Methods in Biomedical Engineering · doi:10.1002/cnm.2719 · Cited by 36
Self-citationNovikov, F. N., Zeifman, A. A., Stroganov, O. V., Stroylov, V. S., Kulkov, V., & Chilov, G. G. (2011) · Journal of Chemical Information and Modeling · doi:10.1021/ci200034y · Cited by 32
Topological Measurement of Protein Compressibility via Persistence DiagramsPreprint
Gameiro, M., ガメイロ, マ., Hiraoka, Y., 平岡, 裕., ヒラオカ, ヤ., Izumi, S., 泉, 俊., イズミ, シ., Kramár, M., クラマー, ミ., et al. (2012) · Kyushu University Institutional Repository (QIR) (Kyushu University) · Cited by 30
ESES: Software for E ulerian solvent excluded surface
Liu, B., Wang, B., Zhao, R., Tong, Y., & Wei, G. (2017) · Journal of Computational Chemistry · doi:10.1002/jcc.24682 · Cited by 30
Self-citationLiu, C., Lu, L., Kong, Q., Li, Y., Wu, H., Yang, W. E., Shan-dan, X., Yang, X., Song, X., Yang, J. Y., et al. (2014) · BMC Bioinformatics · doi:10.1186/1471-2105-15-s17-s5 · Cited by 22
Ye, Z., Baumgartner, M. P., Wingert, B. M., & Camacho, C. J. (2016) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-016-9941-0 · Cited by 22
KECSA-Movable Type Implicit Solvation Model (KMTISM)
Zheng, Z., Wang, T., Li, P., & Merz, K. M. (2014) · Journal of Chemical Theory and Computation · doi:10.1021/ct5007828 · Cited by 20
Wu, K., Zhao, Z., Wang, R., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.01558 · Cited by 5
Self-citation
Research works printed but not linked: 2
- Schrödinger LLC (2017) Schrödinger release 2017-4. Schrödinger LLC, New York
- Edelsbrunner H (1992) Weighted alpha shapes. Technical report. University of Illinois, Champaign
Cited by
Sorted by citations
Key Topics in Molecular Docking for Drug Design
Torres, P. H. M., Sodero, A. C. R., Jofily, P., & Silva, F. P. (2019) · International Journal of Molecular Sciences · doi:10.3390/ijms20184574 · Cited by 703
Guedes, I. A., Pereira, F. S. S., & Dardenne, L. E. (2018) · Frontiers in Pharmacology · doi:10.3389/fphar.2018.01089 · Cited by 331
Deep learning methods for molecular representation and property prediction
Li, Z., Jiang, M., Wang, S., & Zhang, S. (2022) · Drug Discovery Today · doi:10.1016/j.drudis.2022.103373 · Cited by 289
Machine and deep learning approaches for cancer drug repurposing
Issa, N. T., Stathias, V., Schürer, S. C., & Dakshanamurthy, S. (2020) · Seminars in Cancer Biology · doi:10.1016/j.semcancer.2019.12.011 · Cited by 292
Dhakal, A., McKay, C., Tanner, J. J., & Cheng, J. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbab476 · Cited by 269
Metadata
- Authors
- Nguyen, D. D., Cang, Z., Wu, K., Wang, M., Cao, Y., & Wei, G.-W.
- Affiliations
- Michigan State University (US)
- Corresponding author
- Wei, Guo-Wei
- Venue
- Journal of Computer-Aided Molecular Design
- Published
- 2018-08-16
- Volume
- 33
- Issue
- 1
- Pages
- 71-82
- ISSN
- 0920-654X (ISSN-L)
- 1573-4951
- PMC
- PMC7163798
- OpenAlex
- W2963883198
- Semantic Scholar
- 2ca793d6b2ce88d315b20441f9aa4189965d429a
- Cited by
- 155
- References
- 70
- Citations by year
- 2026: 8 · 2025: 25 · 2024: 19 · 2023: 18 · 2022: 20 · 2021: 27 · 2020: 21 · 2019: 15 · 2018: 2
- FWCI
- 12.13
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Journal of Computer-Aided Molecular Design (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1160352, 1302285, 1761320)
- National Institute of General Medical Sciences (R01GM126189)
- Topics
- Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Degradation and Inhibitors
- Keywords
- binding affinity ranking, free energy prediction, persistent homology, cathepsin S, kinase inhibitors, VEGFR2, JAK2, Tie2, c-Abl
- MeSH terms
- Deep Learning, Receptor, Farnesoid X-Activated, Binding Sites, Cathepsins, Ligands, Protein Binding, Protein Conformation, Protein Kinases, Thermodynamics, Drug Design, Computer-Aided Design, Receptors, Cytoplasmic and Nuclear, Crystallography, X-Ray, Databases, Protein, Molecular Docking Simulation
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.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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
