Persistent spectral based machine learning (PerSpect ML) for drug design

Meng, Zhenyu; Xia, Kelin

doi:10.48550/arxiv.2002.00582

Cited by 3 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Motivated by the persistent (co)homology in dealing with the given initial data by constructing a family of simplicial complexes to track their topological invariants, and the multiscale graphs by creating a set of spectral graphs aiming to extract rich geometric information, we proposed persistent spectral graph (PSG) theory as a unified multiscale paradigm for simultaneous geometric and topological analysis [37]. PSG theory has stimulated mathematical analysis and algorithm development [26], as well as applications to drug discovery [28], and protein flexibility analysis [38].…”

Section: Discussionmentioning

confidence: 99%

“…Moreover, the additional geometric shape information of the data will be unveiled in the non-harmonic spectra. Recently, the theoretical properties and algorithms of PSGs have been further studied [26] and the application of PSG methods to drug discovery has been reported [28] . The de Rham-Hodge theory counterpart, called evolutionary de Rham-Hodge theory, has also been formulated [12].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Persistent spectral graph

Wang

Nguyen

Wei

2020

Numer Methods Biomed Eng

106

View full text Add to dashboard Cite

Persistent homology is constrained to purely topological persistence, while multiscale graphs account only for geometric information. This work introduces persistent spectral theory to create a unified low‐dimensional multiscale paradigm for revealing topological persistence and extracting geometric shapes from high‐dimensional datasets. For a point‐cloud dataset, a filtration procedure is used to generate a sequence of chain complexes and associated families of simplicial complexes and chains, from which we construct persistent combinatorial Laplacian matrices. We show that a full set of topological persistence can be completely recovered from the harmonic persistent spectra, that is, the spectra that have zero eigenvalues, of the persistent combinatorial Laplacian matrices. However, non‐harmonic spectra of the Laplacian matrices induced by the filtration offer another powerful tool for data analysis, modeling, and prediction. In this work, fullerene stability is predicted by using both harmonic spectra and non‐harmonic persistent spectra, while the latter spectra are successfully devised to analyze the structure of fullerenes and model protein flexibility, which cannot be straightforwardly extracted from the current persistent homology. The proposed method is found to provide excellent predictions of the protein B‐factors for which current popular biophysical models break down.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Persistent spectral graph

Wang

Nguyen

Wei

2020

Numer Methods Biomed Eng

106

View full text Add to dashboard Cite

show abstract

“…Therefore, a multiscale representation is key to the characterization of biomolecular structures and interactions. Here, we use the filtration process, which is a key component of persistent models, including persistent homology/cohomology, 55−57 persistent spectral, 58,59 and persistent function, 60 to generate a series of the nested biomolecular graphs at different scales. A simple way to generate a filtration process is to set the edge weight as a filtration parameter.…”

Section: ■ Resultsmentioning

confidence: 99%

Ollivier Persistent Ricci Curvature-Based Machine Learning for the Protein–Ligand Binding Affinity Prediction

Wee

Xia

2021

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

Efficient molecular featurization is one of the major issues for machine learning models in drug design. Here, we propose a persistent Ricci curvature (PRC), in particular, Ollivier PRC (OPRC), for the molecular featurization and feature engineering, for the first time. The filtration process proposed in the persistent homology is employed to generate a series of nested molecular graphs. Persistence and variation of Ollivier Ricci curvatures on these nested graphs are defined as OPRC. Moreover, persistent attributes, which are statistical and combinatorial properties of OPRCs during the filtration process, are used as molecular descriptors and further combined with machine learning models, in particular, gradient boosting tree (GBT). Our OPRC-GBT model is used in the prediction of the protein−ligand binding affinity, which is one of the key steps in drug design. Based on three of the most commonly used data sets from the well-established protein−ligand binding databank, that is, PDBbind, we intensively test our model and compare with existing models. It has been found that our model can achieve the state-of-the-art results and has advantages over traditional molecular descriptors.

show abstract

“…Therefore, a multiscale representation is key to the characterization of biomolecular structures and interactions. Here, we use the filtration process, which is key component of persistent models, including persistent homology/cohomology [35,36,37], persistent spectral [38,39] and persistent function [40], to generate a series of nested biomolecular graphs at different scales. A simple way to generate a filtration process is to set edge weight as a filtration parameter.…”

Section: Persistent Ricci Curvaturementioning

confidence: 99%

Ollivier persistent Ricci curvature (OPRC) based molecular representation for drug design

Wee,

Xia

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Efficient molecular featurization is one of the major issues for machine learning models in drug design. Here we propose persistent Ricci curvature (PRC), in particular Ollivier persistent Ricci curvature (OPRC), for the molecular featurization and feature engineering, for the first time. Filtration process proposed in persistent homology is employed to generate a series of nested molecular graphs. Persistence and variation of Ollivier Ricci curvatures on these nested graphs are defined as Ollivier persistent Ricci curvature. Moreover, persistent attributes, which are statistical and combinatorial properties of OPRCs during the filtration process, are used as molecular descriptors, and further combined with machine learning models, in particular, gradient boosting tree (GBT). Our OPRC-GBT model is used in the prediction of proteinligand binding affinity, which is one of key steps in drug design. Based on three most-commonly used datasets from the well-established protein-ligand binding databank, i.e., PDBbind, we intensively test our model and compare with existing models. It has been found that our model are better than all machine learning models with traditional molecular descriptors.

show abstract

Persistent spectral based machine learning (PerSpect ML) for drug design

Cited by 3 publications

References 42 publications

Persistent spectral graph

Persistent spectral graph

Ollivier Persistent Ricci Curvature-Based Machine Learning for the Protein–Ligand Binding Affinity Prediction

Ollivier persistent Ricci curvature (OPRC) based molecular representation for drug design

Contact Info

Product

Resources

About