Sunsetting Binding MOAD with its last data update and the addition of 3D-ligand polypharmacology tools

Wagle, Swapnil; Smith, Richard; Dominic, Anthony J; DasGupta, Debarati; Tripathi, Sunil Kumar; Carlson, Heather A.

doi:10.1038/s41598-023-29996-w

Cited by 7 publications

(13 citation statements)

References 85 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PATH was trained on the PDBBind v2020 refined set and generalized to the Binding MOAD [92] and BindingDB [35] datasets. The performance of PATH on these datasets is comparable to its performance on the PDBBind v2020 refined set.…”

Section: Resultsmentioning

confidence: 99%

“…Computation of persistence fingerprint using the pruning method described in previous sections was tested by calculating persistence fingerprint of protein-ligand complexes in the BioLiP dataset [103], which consists of entries from PDBBind [96], Binding MOAD [92], and Binding DB [35]. For this test, the pruning radius r is arbitrarily set to be 15 Angstroms.…”

Section: Definition Of Persistent Homologymentioning

confidence: 99%

“…Next, we measured the generalizability of persistence fingerprint and PATH beyond the training dataset (see figure 4). We curated subsets of two protein-ligand binding affinity datasets from the BioLiP database [105, 103], namely Binding MOAD [41, 3, 88, 92] and Bind-ingDB [35, 56], which consist of protein-ligand complexes with binding affinity (ΔG) in the range −2.7 to −16.3 kcal/mol, and has ligands with fewer than 1000 atoms due to runtime constraints (details of curation of FastBind are in Appendix Section C.5 for the interested referee). We call the resulting curated datasets FastBind-MOAD and FastBind-BindingDB .…”

Section: Computational Experimentsmentioning

confidence: 99%

“…Therefore, the protein-ligand complexes from Binding MOAD [92] and BindingDB [35] with fewer than 1000 ligand atoms were selected to be the FastBind-MOAD and FastBind-BindingDB.…”

Section: Definition Of Persistent Homologymentioning

confidence: 99%

See 3 more Smart Citations

Predicting Affinity Through Homology (PATH): Interpretable Binding Affinity Prediction with Persistent Homology

Long,

Donald

2023

Preprint

View full text Add to dashboard Cite

Accurate binding affinity prediction is crucial to structure-based drug design. Recent work used computational topology to obtain an effective representation of protein-ligand interactions. Although persistent homology encodes geometric features, previous works on binding affinity prediction using persistent homology employed uninterpretable machine learning models and failed to explain the underlying geometric and topological features that drive accurate binding affinity prediction.In this work, we propose a novel, interpretable algorithm for protein-ligand binding affinity prediction. Our algorithm achieves interpretability through an effective embedding of distances across bipartite matchings of the protein and ligand atoms into real-valued functions by summing Gaussians centered at features constructed by persistent homology. We name these functionsinternuclear persistent contours (IPCs). Next, we introducepersistence fingerprints, a vector with 10 components that sketches the distances of different bipartite matching between protein and ligand atoms, refined from IPCs. Let the number of protein atoms in the protein-ligand complex ben, number of ligand atoms bem, andω≈ 2.4 be the matrix multiplication exponent. We show that for any 0 <ε< 1, after an 𝒪 (mnlog(mn)) preprocessing procedure, we can compute anε-accurate approximation to the persistence fingerprint in 𝒪 (mlog6ω(m/”)) time, independent of protein size. This is an improvement in time complexity by a factor of 𝒪 ((m+n)3) over any previous binding affinity prediction that uses persistent homology. We show that the representational power of persistence fingerprint generalizes to protein-ligand binding datasets beyond the training dataset. Then, we introducePATH, Predicting Affinity Through Homology, an interpretable, small ensemble of shallow regression trees for binding affinity prediction from persistence fingerprints. We show that despite using 1,400-fold fewer features, PATH has comparable performance to a previous state-of-the-art binding affinity prediction algorithm that uses persistent homology features. Moreover, PATH has the advantage of being interpretable. Finally, we visualize the features captured by persistence fingerprint for variant HIV-1 protease complexes and show that persistence fingerprint captures binding-relevant structural mutations. The source code for PATH is released open-source as part of the osprey protein design software package.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Definition Of Persistent Homologymentioning

confidence: 99%

Section: Computational Experimentsmentioning

confidence: 99%

“…Therefore, the protein-ligand complexes from Binding MOAD [92] and BindingDB [35] with fewer than 1000 ligand atoms were selected to be the FastBind-MOAD and FastBind-BindingDB.…”

Section: Definition Of Persistent Homologymentioning

confidence: 99%

See 2 more Smart Citations

Predicting Affinity Through Homology (PATH): Interpretable Binding Affinity Prediction with Persistent Homology

Long,

Donald

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Binding MOAD contains 41,409 complexes. Note that as of 2024, the structural data will be integrated in RCSB PDB . A more detailed overview of available datasets beyond structural data and related common methods in the context of DL-based virtual screening is given by Kimber et al…”

Section: Introductionmentioning

confidence: 99%

Guided Docking as a Data Generation Approach Facilitates Structure-Based Machine Learning on Kinases

Backenköhler,

Groß,

Wolf

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Drug discovery pipelines nowadays rely on machine learning models to explore and evaluate large chemical spaces. While including 3D structural information is considered beneficial, structural models are hindered by the availability of protein− ligand complex structures. Exemplified for kinase drug discovery, we address this issue by generating kinase-ligand complex data using template docking for the kinase compound subset of available ChEMBL assay data. To evaluate the benefit of the created complex data, we use it to train a structure-based E(3)-invariant graph neural network. Our evaluation shows that binding affinities can be predicted with significantly higher precision by models that take synthetic binding poses into account compared to ligand-or drug-target interaction models alone.

show abstract

Modern machine‐learning for binding affinity estimation of protein–ligand complexes: Progress, opportunities, and challenges

Harren,

Gutermuth,

Grebner

et al. 2024

WIREs Comput Mol Sci

View full text Add to dashboard Cite

Structure‐based drug design is a widely applied approach in the discovery of new lead compounds for known therapeutic targets. In most structure‐based drug design applications, the docking procedure is considered the crucial step. Here, a potential ligand is fitted into the binding site, and a scoring function assesses its binding capability. With the rise of modern machine‐learning in drug discovery, novel scoring functions using machine‐learning techniques achieved significant performance gains in virtual screening and ligand optimization tasks on retrospective data. However, real‐world applications of these methods are still limited. Missing success stories in prospective applications are one reason for this. Additionally, the fast‐evolving nature of the field makes it challenging to assess the advantages of each individual method. This review will highlight recent strides toward improved real world applicability of machine‐learning based scoring, enabling a better understanding of the potential benefits and pitfalls of these functions on a project. Furthermore, a systematic way of classifying machine‐learning based scoring that facilitates comparisons will be presented.This article is categorized under: Data Science > Chemoinformatics Data Science > Artificial Intelligence/Machine Learning Software > Molecular Modeling

show abstract

Sunsetting Binding MOAD with its last data update and the addition of 3D-ligand polypharmacology tools

Cited by 7 publications

References 85 publications

Predicting Affinity Through Homology (PATH): Interpretable Binding Affinity Prediction with Persistent Homology

Predicting Affinity Through Homology (PATH): Interpretable Binding Affinity Prediction with Persistent Homology

Guided Docking as a Data Generation Approach Facilitates Structure-Based Machine Learning on Kinases

Modern machine‐learning for binding affinity estimation of protein–ligand complexes: Progress, opportunities, and challenges

Contact Info

Product

Resources

About