Calculation of Thermodynamic Properties of Bound Water Molecules

Yang, Ying; Abdallah, Amr H. A.; Lill, Markus A.

doi:10.1007/978-1-4939-7756-7_19

Cited by 7 publications

(9 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While vScreenML does incorporate a broad and distinct set of features, these have been largely collected from other approaches: There is nothing particularly unique or special about the features it includes. There are also numerous potential contributions to protein-ligand interactions that are not captured in this collection of features, ranging from inclusion of tightly bound interfacial waters (16,87,88) to explicit polarizability and quantum effects (89,90). In this vein, ongoing research in ligand-based screening has led to new approaches that learn optimal molecular descriptors (and thus the representation that directly leads to the features themselves) at the same time as the model itself is trained (91,92): These might similarly be used as a means to improve the descriptors used in structure-based screening as well.…”

Section: Discussionmentioning

confidence: 99%

Machine learning classification can reduce false positives in structure-based virtual screening

Adeshina

Deeds

Karanicolas

2020

Proc. Natl. Acad. Sci. U.S.A.

143

120

View full text Add to dashboard Cite

With the recent explosion in the size of libraries available for screening, virtual screening is positioned to assume a more prominent role in early drug discovery’s search for active chemical matter. In typical virtual screens, however, only about 12% of the top-scoring compounds actually show activity when tested in biochemical assays. We argue that most scoring functions used for this task have been developed with insufficient thoughtfulness into the datasets on which they are trained and tested, leading to overly simplistic models and/or overtraining. These problems are compounded in the literature because studies reporting new scoring methods have not validated their models prospectively within the same study. Here, we report a strategy for building a training dataset (D-COID) that aims to generate highly compelling decoy complexes that are individually matched to available active complexes. Using this dataset, we train a general-purpose classifier for virtual screening (vScreenML) that is built on the XGBoost framework. In retrospective benchmarks, our classifier shows outstanding performance relative to other scoring functions. In a prospective context, nearly all candidate inhibitors from a screen against acetylcholinesterase show detectable activity; beyond this, 10 of 23 compounds have IC50 better than 50 μM. Without any medicinal chemistry optimization, the most potent hit has IC50 280 nM, corresponding to Ki of 173 nM. These results support using the D-COID strategy for training classifiers in other computational biology tasks, and for vScreenML in virtual screening campaigns against other protein targets. Both D-COID and vScreenML are freely distributed to facilitate such efforts.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine learning classification can reduce false positives in structure-based virtual screening

Adeshina

Deeds

Karanicolas

2020

Proc. Natl. Acad. Sci. U.S.A.

143

120

View full text Add to dashboard Cite

show abstract

“…MD simulations were performed using the modified GPU-accelerated OpenMM-WATsite package with the AMBER14SB force field and SPC/E water model. , The SHAKE algorithm was applied to constrain bonds including hydrogen atoms to their equilibrium lengths and to maintain rigid water geometries. Long-range electrostatic interactions were treated with the Particle Mesh Ewald method with a cutoff of 10 Å for the direct interactions.…”

Section: Methodsmentioning

confidence: 99%

“…MD simulations were performed using the modified GPU-accelerated OpenMM-WATsite package 17 with the AMBER14SB force field 18 and SPC/E water model. 19,20 The SHAKE algorithm 21 was applied to constrain bonds including hydrogen atoms to their equilibrium lengths and to maintain rigid water geometries.…”

Section: ■ Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Efficient and Accurate Hydration Site Profiling for Enclosed Binding Sites

Masters

Mahmoud

Yang

et al. 2018

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

Molecular dynamics (MD) simulations allow for accurate prediction of the thermodynamic profile of binding-site water molecules critical for protein–ligand association. Whereas this hydration-site profiling converges rapidly for solvent-exposed sites independent of the initial water placement, an accurate and reliable placement is required for water molecules in occluded binding sites. Here, we present an accurate and efficient hydration-site prediction method for occluded binding sites combining water placement based on 3D-RISM and MD simulations using WATsite.

show abstract

“…While vScreenML does incorporate a broad and distinct set of features, these have been largely collected from other approaches: there is nothing particularly unique or special about the features it includes. There are also numerous potential contributions to protein-ligand interactions that are not captured in this collection of features, ranging from inclusion of tightly-bound interfacial waters [16,89,90] to explicit polarizability and quantum effects [91,92]. In this vein, ongoing research in ligandbased screening has led to new approaches that learn optimal molecular descriptors (and thus the representation that directly leads to the features themselves) at the same time as the model itself is trained [93,94]: these might similarly be used as a means to improve the descriptors used in structure-based screening as well.…”

Section: Compound Identified As a Top-scoring Hitmentioning

confidence: 99%

Machine learning classification can reduce false positives in structure-based virtual screening

Adeshina

Deeds

Karanicolas

2020

Preprint

View full text Add to dashboard Cite

With the recent explosion in the size of libraries available for screening, virtual screening is positioned to assume a more prominent role in early drug discovery's search for active chemical matter.Modern virtual screening methods are still, however, plagued with high false positive rates: typically, only about 12% of the top-scoring compounds actually show activity when tested in biochemical assays.We argue that most scoring functions used for this task have been developed with insufficient thoughtfulness into the datasets on which they are trained and tested, leading to overly simplistic models and/or overtraining. These problems are compounded in the literature because none of the studies reporting new scoring methods have validated their model prospectively within the same study. Here, we report a new strategy for building a training dataset (D-COID) that aims to generate highly-compelling decoy complexes that are individually matched to available active complexes. Using this dataset, we train a general-purpose classifier for virtual screening (vScreenML) that is built on the XGBoost framework of gradient-boosted decision trees. In retrospective benchmarks, our new classifier shows outstanding performance relative to other scoring functions. We additionally evaluate the classifier in a prospective context, by screening for new acetylcholinesterase inhibitors. Remarkably, we find that nearly all compounds selected by vScreenML show detectable activity at 50 µM, with 10 of 23 providing greater than 50% inhibition at this concentration. Without any medicinal chemistry optimization, the most potent hit from this initial screen has an IC50 of 280 nM, corresponding to a Ki value of 173 nM. These results support using the D-COID strategy for training classifiers in other computational biology tasks, and for vScreenML in virtual screening campaigns against other protein targets. Both D-COID and vScreenML are freely distributed to facilitate such efforts.

show abstract

Calculation of Thermodynamic Properties of Bound Water Molecules

Cited by 7 publications

References 30 publications

Machine learning classification can reduce false positives in structure-based virtual screening

Machine learning classification can reduce false positives in structure-based virtual screening

Efficient and Accurate Hydration Site Profiling for Enclosed Binding Sites

Machine learning classification can reduce false positives in structure-based virtual screening

Contact Info

Product

Resources

About